Blog

BMW chooses Inspekto to bring AI to the factory floor

October 19, 2020

The BMW plant in Steyr, Austria, is the BMW Group’s largest engine plant worldwide and is the only one to host a Diesel Engine Development Centre. At the facility, the top priorities are quality, efficiency and the transformation to Industry 4.0 through the implementation of digital technologies at shop floor level. To improve all three, plant managers embraced Autonomous Machine Vision, a new category of machine vision for quality inspection developed by German-Israeli company Inspekto.

We talked to David Bricher, PhD candidate at BMW Steyr and expert in innovation and digitalisation, to delve into the details of this successful partnership.

The iconic white and blue badge on the front of every BMW vehicle is recognised worldwide as a symbol of quality, reliability and luxury. To remain at the cutting edge of its industry, the German automotive giant is constantly improving its manufacturing standards by implementing the latest digital technologies.

In this context, quality assurance (QA) plays a central role. In line with BMW’s mission to improve production processes using digitalisation, the Steyr plant has several state-of-the-art machine vision solutions in place to inspect the quality of its engines and make sure that each process and component respects the company’s rigid standards.

However, even the most sophisticated traditional machine vision solutions suffer from pseudo-errors, where the solution indicates the presence of a defect in components that were actually made to specification. Moreover, the complexity of the solutions means that they can only be implemented with the assistance of a machine vision expert.

A challenging scenario

“We have lots of different techniques in place to validate the quality of components,” explained David Bricher, PhD candidate and expert in innovation and digitalisation at BMW. “In many cases, they perform adequately, but it is our main aim to further enhance process excellence in all aspects of our production chain. This also means that we want to keep the pseudo-defect rates as low as possible.”

Pseudo-defects are a common problem with state-of-the-art machine vision solutions, which tend to pick up small permitted variations and classify them as defects. This creates an extra and unnecessary loop in production, since flagged items need be conveyed to a repair station, where an employee rechecks them manually.

“The most problematic issue,” continues Bricher, “is that with increasing pseudo-defect rates, employees at the repair station could let their guard down and assume that an actually defected item is good. BMW is not willing to compromise on quality, and we want to prevent this scenario at all costs.”

Democratising quality

BMW is a strong believer in bringing AI-based technologies to the shop floor, so plant managers were on the lookout for a more intuitive quality assurance technology — an out-of-the-box product that could be easily installed and used by any employee on the production line. Enter Inspekto, the leader of Autonomous Machine Vision.

“The BMW Start-Up Garage helps us find new companies with ground-breaking ideas to improve our processes with digitalisation,” said Bricher. “The team researched several companies with innovative machine vision solutions, but only Inspekto offered exactly what we were looking for — a system that is out-of-the-box, and so intuitive that any employee can set it up in minutes.”

Inspekto then introduced BMW to the world’s first Autonomous Machine Vision system, the INSPEKTO S70.

“As opposed to traditional solutions, made up of several components that are selected and assembled by a systems integrator on a project base, the INSPEKTO S70 is a self-contained product,” explained Harel Boren, CEO and co-founder of Inspekto. “It is self-learning, self-setting and self-adjusting — in other words, fully autonomous. This eliminates the lengthy and complex integration phases that characterise traditional machine vision projects, and puts the potential of industrial inspection right where it belongs: in the hands of the QA manager.”

Convinced by the capabilities of the INSPEKTO S70, BMW Group Plant Steyr purchased four systems and started a pilot phase to check their suitability for complex applications. Following its success, the systems are now already operationally used in two different use cases — a tricky connector with many small, hardly visible components and a fuel pipe. In both cases, the plant has noticed an improvement in quality and a noticeable reduction of false detection instances.

The Plug & Inspect® experience

“For me, one of the most interesting characteristics of the INSPEKTO S70 is its ease of installation. The system is very intuitive to set up, it really is out-of-the-box,” confirmed Bricher.

“At BMW one of our main targets is to bring the potential of AI closer to the production field. We want to make AI easy to understand so that it can really serve our people. We have to get rid of the mystique that surrounds the technology — people have to be able to say: I work with AI.”

This philosophy perfectly mirrors Inspekto’s mission to democratise machine vision, by putting a vision inspection product directly into the hands of the people on the shop floor, with no need for a systems integrator or machine vision expert.

Thanks to the patented Plug & Inspect® technology that powers the INSPEKTO S70, the user simply switches on the controller and ensures that the field of view (FOV) covers the location to be inspected. The user then presents an average of 20 to 30 good items only to the system, which will automatically learn their characteristics.

Much like a human being, the INSPEKTO S70 knows when it has enough information about a product and informs the user that inspection can start. Anything that is different from the characteristics of a good part, that the system has ‘memorised’, will be flagged as an anomaly.

“Typically, machine vision solutions require a long training process, during which they are exposed to hundreds of defective parts. But in a manufacturing environment dedicated to the highest levels of quality, we don’t have that many defective parts readily available, so we would have to produce them explicitly for training purposes,” explains Bricher. “The INSPEKTO S70 only needs good parts, which is a huge advantage. We produce good parts all the time!”

“The INSPEKTO S70 learns extraordinarily fast,” added Bricher. Using only 20 to 30 items, the system can memorise the characteristics of a rather complex product in about half an hour. Also, after initial set up, the system keeps learning. If there are more variations to the product, they can be easily introduced in the same fast, intuitive way. Another reason pseudo-defects are so low is that the operator can flag a pseudo-defect, and the system will never mark it as defective again.”

The more the merrier

The BMW Group Plant Steyr needs to inspect many different kinds of engines and parts, often on the same production line, so traditional machine vision solutions are limiting because they are developed ad hoc to inspect only one item. The INSPEKTO S70, on the contrary, can inspect an array of different products on the same production line.

Just like a smartphone, the INSPEKTO S70 can be personalised and adapted to the needs of the end user thanks to a large array of apps. One of those apps is INSPEKTO TYPES™, which allows the system to learn the characteristics of different types of products and easily switch from one to the other, providing maximum flexibility.

The benefits of Autonomous Machine Vision are already visible at BMW Steyr. “Quality is a top priority at BMW — the most important thing for us it to ship perfect engines. In this sense, the INSPEKTO S70 has already proved to be a valuable tool,” added Bricher. “The other priority is efficiency. By eliminating pseudo-defects, the system allows us to avoid the extra loop of manual double-checks.

“This also means that we will reduce costs in the long run, because employees will not waste their time rechecking components, they can instead be assigned to more productive tasks. But the more important thing for me is that with the INSPEKTO S70 we have brought AI closer to our production employees. BMW and Inspekto have a shared vision, and the future looks bright.”

Read More

Three ways Autonomous Machine Vision (AMV) benefits plastic injection moulding

October 19, 2020

Traditionally, plastic injection moulding is a difficult application for machine vision. The highly reflective surface of plastics is hard to illuminate correctly, and the fact that the same production line can create items of different colours and shapes is problematic for traditional solutions, only capable of inspecting one product at a time. Zohar Kantor, VP Sales of Inspekto, explains how Autonomous Machine Vision (AMV) has overcome these challenges.

Autonomous Machine Vision is a new approach to quality assurance (QA) developed by Inspekto, a German company with Israeli DNA. As the name suggests, this technology is conceived to be autonomous in every way, from determining the ideal number of samples the system needs to learn the characteristics of the item, to self-adjusting the camera settings to obtain the best image possible of the item to be inspected. This allows production line engineers with no previous knowledge of machine vision or artificial intelligence, to set up the system to work in hours, rather than weeks and months with the aid of a systems integrator.  

Thanks to its self-adjusting and self-learning capabilities, the INSPEKTO S70, the first QA system in the AMV category, can successfully overcome the challenges that make traditional QA solutions inadequate for plastics injection moulding. Here are three examples of how AMV can benefit this industry.  

Multi-product inspection

Traditional machine vision solutions are designed to inspect only one item at a specific point on the production line. This makes them unpractical for a sector such as plastic injection moulding, where the same production line can potentially make various products that come in varying shapes and forms.

However, Inspekto TYPES™, one of the many apps that can be installed on the S70, allows plastics manufacturers to overcome this issue. While traditional machine vision solutions can only monitor one product at any given location on the production line, an S70 system installed with TYPES™ is able to inspect any number of products — even tens or hundreds of different products — at that same location on the line.

Emerging from the traditional constraints of one-product-per-solution, AMV allows manufacturers to inspect a variety of items with one single system, something that was unthinkable until recently.

Self-adjusting camera parameters

Another typical problem in this sector is achieving the correct lighting of the parts to be inspected. Typically, injection moulds have smooth, highly reflective surfaces that resemble mirrors. Additionally, moulds can be the same colour of the plastic polymer, or can appear that way because of a lack of contrast due to insufficient illumination of the inside of the mould.

Finally, moulding machines are built to be as compact as possible, so that they will open just enough to eject the part, but not enough to guarantee adequate illumination for visual QA.

All these challenges make inspection hard for traditional QA solutions, but not for AMV systems, which are designed to self-adjust their camera parameters to obtain perfect lighting, focus and contrast. In this way, the plastic parts can be illuminated in a way that clearly differentiates one from the other, allowing the system to perform effective visual QA in total autonomy.

Total QA

Traditional QA solutions require several months to be designed, built and tested, and the whole process costs often reach even hundreds of thousands of euros. On the other hand, the INSPEKTO S70 can be installed in by the plant’s own line engineers, without any external intervention, and costs a fraction of a traditional solution.

The cost-effectiveness and rapidity of installation of the S70 mean that plant managers can have a QA station at every junction on the production line, instead of just at the end – reaching far higher productivity, profitability and yield. Alternatively, QA managers can decide to move their S70 from one junction to the other when needed, by just repeating the quick and easy installation process.

In this way, manufacturers can achieve what Inspekto calls Total QA – quality assurance at every step of production.

Read More

It’s time to democratise quality assurance

October 19, 2020

Quality assurance is mandatory in all industries, tiers and geographies. But existing machine vision solutions are often so complex, that end-customers have no choice but to rely on machine vision experts and systems integrators to commission expensive, slow to deploy and highly tailored solutions. But quality shouldn’t be a luxury. Here Harel Boren, CEO and co-founder of Inspekto, the company that developed Autonomous Machine Vision (AMV), explains why it’s time to democratise industrial quality assurance.

The emergence of fully autonomous – rather than simply automated – technology is one of the major global upcoming trends in robotics and manufacturing. Thanks to the newest advances in deep learning, AI and electrooptic components, autonomous technology that truly acts and learns like humans is the ultimate goal in many areas of manufacturing. The accomplishment of this goal in the next two to three decades is destined to add tremendous value to production, significantly adding to yield, productivity and profitability, with manageable upfront investments.

However, a key barrier that producers are facing, without much success to date, is simplicity, achieved at lower costs and in tighter timeframes. You can have all the technology you want, but if you have no control over it, you will be forced to rely on an external expert. Currently, this is the situation of machine vision technology for industrial quality inspection.

Typically, a systems integrator will choose all the necessary hardware and software on behalf of the client, and assemble a tailor-made solution. The process of developing, integrating and training such a solution might take weeks or even months, is highly complex and very expensive. The resulting solution might or might not work for all the changing scenarios it has to inspect. And each time a problem arises, the manufacturer has no choice but to call the expert back, and the whole process begins all over again.

The manufacturer is held captive to the machine vision solution installed. Shopfloor personnel has long realised that these sophisticated and expensive solutions are actually expensive and sophisticated headaches. In fact, many feel they’ve been turned into ‘profit centres’ whose difficulties continually feed experts and component manufacturers with more and more work – burning more and more budget.

Yonatan Hyatt and I founded Inspekto with the goal of changing this status quo. We wanted to develop a self-contained product, simple to install, that served the end-customer directly. To serve the people on the shop floor, autonomous technology must be simple and quick to install, at least as effective as traditional solutions, and – why not? – even fun to set up and use. That’s how we developed the INSPEKTO S70, the first Autonomous Machine Vision product.

Autonomous Machine Vision (AMV) is a new category of machine vision for visual inspection and the INSPEKTO S70, is the only universal industrial inspection product on the market. It was designed to be set up by the employees themselves, without any external assistance, in hours, not weeks. It learns the gold standard of any item by viewing only 20 good samples, as they run by on the manufacturing line – without interfering with the manufacturing process. It’s ready to be connected to any PLC, right out of the box, like your smartphone or laptop would connect to any network.

Our motto is “just plug & inspect”, which we’ve also registered as the name of the patented technology that powers the S70. The expert-free setup process allows QA managers to do everything themselves, without relying on machine vision experts nor systems integrators, and costs are typically 1/10th than previous tailored solutions would have sold for. We fiercely believe that in industry 4.0, quality can’t any longer be a luxury, but a baseline accessible to all, and that technology should be used to democratise quality.

Read More
See the Inspekto S70 in person

Bosch Waiblingen plant utilises Autonomous Machine Vision

July 30, 2020

~ The company tested the world’s first autonomous visual inspection product ~

In its plant in Waiblingen, Germany, Bosch produces plastic moulded connectors for the automotive sector. Plastic injection moulding is traditionally a difficult application for standard machine vision because of the lack of contrast between the background and the part being inspected – the “black-on-black” nemesis. To solve this problem, Bosch turned to Inspekto, founder of the Autonomous Machine Vision (AMV) category.

The automotive industry’s quality standards place high demands on production. Global competition and market expectations put growing pressures on automotive vendors to enhance their QA procedures, moving away from manual to automated inspection. The challenge is to find and implement cutting-edge machine vision methods.

The problem with injection moulding

“Plastic injection moulding poses a lot of problems for traditional machine vision systems,” explains Zohar Kantor, VP of Sales & Project Management at Inspekto. “The highly reflective surface of plastic is hard to illuminate correctly. In addition, if the background material, the mould and the plastic polymer are a similar colour, and the available illumination is anything but ideal, a lack of contrast can make it very difficult for the machine vision system to work.”

“Combine this with the fact that traditional systems can only inspect one type of product at a time — and manufacturers need to create product lines in different colours and sizes — it’s easy to see why a fundamental change in machine vision is needed.”

This is exactly the problem that Bosch was facing. In Waiblingen, the company produces plastic moulded connectors for vehicles, specialising in motor plugs, device connectors and sensor connectors. The plant has various production lines and injection moulding machines.

“The plant uses conventional state-of-the-art machine vision solutions, some developed internally, some created and integrated by external machine vision experts,” explains one of the development engineers for optical inspection systems at Bosch in Waiblingen.

“However, these solutions are not suitable for some of our applications, where the item that we need to inspect consists of a black polymer on a black background. In these conditions, it is virtually impossible to set the parameters for the QA solution to recognise defects.”

The plant had to check the connectors manually. As this is a tedious, repetitive job, inspectors might easily become tired and unfocused and fail to recognise defects. Moreover, the cost for personnel is significant.

After reading about Autonomous Machine Vision in an industrial report, Bosch decided to approach Inspekto to see if the company could provide a solution for Bosch’s machine vision challenges.

Plug & Inspect ® technology

Autonomous Machine Vision (AMV) is a new category of machine vision for quality assurance invented by Inspekto, a German company with Israeli DNA. In 2018, the company launched its first AMV system, the INSPEKTO S70, establishing a ground-breaking approach to QA.

“The INSPEKTO S70 is the first standalone product for visual QA, gating and sorting,” says Kantor. “It is self-setting, self-learning and self-adjusting and can be used to inspect any item, in any industry, produced with any handling method.”

“The product comes out of the box with everything the user needs to start inspecting products right away. The installation process is designed to be quick and easy. The plant’s own staff can set up and train the system without using an external systems integrator. Most importantly, the S70 only requires an average of 20 to 30 good samples to learn the characteristics of a perfect product. Therefore, there’s no need to set up parameters to train the system to recognise mistakes, like with traditional solutions.”

Because of these advantages, Bosch decided to run a pilot project in Waiblingen and see if it would help where traditional solutions had failed. Inspekto and Bosch started an application partnership and after a few weeks, the first system was ready for use in series production.

“In our area of the business, we are experts in machine vision, so it wasn’t difficult to integrate the system. So, I’m confident that our colleagues in other Bosch plants also would have no difficulty in using Inspekto’s AMV system,” reports one of the development engineers at Bosch. “The initial installation of the pilot system took about an hour, and less than a day if you factor in the small adjustments that we made to optimise the speed of the process. It took another 20 minutes to learn the software programme, and then we just had to plug in the camera and begin inspecting.”

Cost reduction and quality improvement

During installation, the production line kept running as normal and the plant didn’t experience any downtime. “Because the INSPEKTO S70 can run without any input from the control system, it can be installed without affecting production,” says one of the development engineers. “Initially, we had the S70 running in parallel with the production line, where we integrated it mechanically but without connecting it to the machine. The system then learned the characteristics of the product quickly. All of this was done without any impact on production.”

“The cost of the initial system was amortised in under a month and we could immediately see further savings and an improvement in quality. Because the pilot system worked so well, we ordered another one for our subsidiaries overseas, then another one to be installed in an older application here in Waiblingen.”

Read More
Inspekto S70 | Autonomous Machine Vision

How Autonomous Machine Vision can help ward off the looming recession

June 24, 2020

The Great Depression that hit the US in the 1930s was probably the worst economic recession ever registered. To guide the country out of it, President Roosevelt launched a series of programmes, public work projects and financial reforms known as the New Deal. While the economic implications of COVID-19 threaten to shadow the Great Depression, Harel Boren, CEO and co-founder of Inspekto, explains why Autonomous Machine Vision (AMV) could bethe new New Deal.

Today, we are facing a risk of a major global recession as the result of the COVID-19 pandemic. As manufacturers are planning the resumption of work after the shutdown period, experts predict that a major global recession might be inevitable.

To ward off its negative impact, ‘affordable flexibility’ is key, and manufacturers need the ability to adapt, adjust and modify their production lines, cost effectively, to meet changing needs in a dynamic and competitive environment. Most importantly, plant managers need ready-to-use, out-of-the-box technology that delivers added value right away, and that they can manage on their own without any help from external experts.

For industrial inspection, a key element to deliver high quality products, Autonomous Machine Vision (AMV), a new category in machine vision for visual quality assurance (QA), offers this and much more.

It’s good to be autonomous (it’s cheaper, too)

The INSPEKTO S70, the first Autonomous Machine Vision product, is autonomous in every way, releasing plant managers from lengthy and expensive contracts with external third parties, such as systems integrators. It is highly versatile in that it can be used to inspect any product, in any industry, produced with every manufacturing techniques.

The installation is quick, easy and fun. Thanks to Inspekto’s Plug & Inspect® technology, the plant’s own personnel can install an AMV system in just 30 to 45 minutes, with no external intervention. The user simply presents an average of 20 to 30 good samples to the system, which will automatically learn what a gold-standard product should look like.

Much like a human being, the INSPEKTO S70 knows when it has enough information about a part to start inspecting it. After inspection begins, the system will alert the user to every deviation from the defined standards.

Minimal investment, maximal result

In times of financial instability, the first thing plant managers do is keep their budgets under control. The INSPEKTO S70 requires minimal initial investment, because it can be purchased for less than one tenth of the cost of traditional QA solutions. In addition, it can be installed while the production line is running, causing zero downtime.

This out-of-the-box, ready-to-go system comes with everything QA managers need to perform accurate and effective visual QA right away. Also, with the INSPEKTO S70 there’s no need to invest in training. Thanks to its self-adapting and self-learning capabilities, the product operates in complete autonomy, communicating directly with the programmable logic controller (PLC) without any intervention from the plant’s personnel.

Less scrap equals more profit

If the country hits a phase of economic recession, cutting costs is not enough. Manufacturers should also enhance profitability by reducing scrap and waste, identifying defective items as soon as possible and optimising their production lines so that the same defect doesn’t keep happening.

Because AMV products are cost-effective and extremely quick and easy to set up, plant managers can position a QA station at every junction on the production line, instead of just at the end, realising what Inspekto calls Total QA. This minimises scrap, because resources will not be wasted on items that are destined to be defective from the very beginning.

Over time, Total QA allows manufacturers to see where defects are more likely to occur, so that they intervene in the most appropriate way. In times of financial instability, it is paramount that plant managers identify every opportunity to improve their production processes, working at full potential to outrun the competition. 

Investing in your people

AMV allows manufacturers to free personnel from tedious QA procedures, whether these are manual inspection tasks, or the maintenance of complex machine vision solutions.

Manual visual inspection carries an error rate of up to 25 per cent and keeps employees busy on a task that does not add value to the business. Consider this example from the automotive engineering sector. In the UK, the average value added by each employee in this sector is £100,000 a year, so manufacturers lose millions by assigning several shifts of employees to tedious inspection tasks.

By investing in an Autonomous Machine Vision system, manufacturers can move those employees into productive roles that create value for the business. A small investment in an INSPEKTO S70 can therefore save a plant hundreds of thousands per year.

It’s clear that automotive manufacturers in particular, but also industry overall could save millions by reducing the number of detectable faults in their products. The New Deal that AMV provides could certainly be the boost that the economy requires.

Read More
Inspekto S70 | Autonomous Machine Vision

Camera specs – not the frontier in the era of AI

September 26, 2019

~ Autonomous Machine Vision (AMV) offers a new approach to visual QA ~

If humans had the eyesight of an eagle, we could spot an ant from the top of a ten-story building. But do we actually need to? Probably not, which is why our eyesight did not evolve in this direction. Similarly, machine vision engineers are pushing the frontiers of camera specifications to offer solutions with incredible resolution. But do manufacturers need this level of sophistication? Yonatan Hyatt, CTO and co-founder of Inspekto, explains why  Autonomous Machine Vision (AMV) is pushing the boundaries of artificial intelligence, not camera specifications.

Birds of prey can see up to five times further than a human being with perfect vision. Their eyesight evolved to allow them to swoop down on their prey with incredible accuracy, making them terrific hunters. In nature as well as in industry, the ability to adapt to environmental demands, coming up with the simplest and most efficient solution, is what characterises successful evolution.

In machine vision, the evolution of the field has been dominated by attempts to achieve the best image possible of the product to be inspected. The marketing of ultra-high-resolution digital cameras — offering thirty megapixels and higher — is just one of the ways that machine vision suppliers are trying to meet their clients’ expectations.

These solutions, however, do not tackle the biggest shortcomings of the industry. The hardware, software and algorithms of traditional solutions for visual quality assurance (QA) are tailor-made by a systems integrator to inspect only one product at a specific junction in the production line, and the process of designing, creating, installing and validating them is time-consuming and very expensive. Moreover, all phases often require numerous iterations after the validation stage.

Sophisticated cameras and illumination settings were developed to increase the detail level and the signal-to-noise-ratio to much higher levels than would be required by a human inspector. Such technology makes things easier for the systems integrator when setting an algorithm, but these highly sophisticated cameras and their accessories make up a big chunk of the final cost — lenses and filters alone can cost a small fortune.

Evolution or revolution

Autonomous Machine Vision (AMV), a new category of machine vision, is not the next evolutionary step in the existing ecosystem, but the start of a new era in machine vision. The INSPEKTO S70, the first AMV system, offered by German-Israeli start-up Inspekto, takes a different technological approach. Building on recent academic and industrial achievements in AI, Inspekto’s team pushed the frontier of autonomous systems to offer better decision-making and hardware-tuning. Because of this, the system can reach excellent inspection results in a fraction of the set-up time and greatly reduce the costs associated with traditional solutions for visual quality assurance (QA).

The INSPEKTO S70 is designed to be flexible and user-friendly, so that any employee can install it in 30 to 45 minutes. The system integrates a Video-Sensor-Optimisation AI engine that automatically adjusts the illumination and camera parameters to the reflective properties of the product and the environmental conditions. Changes in lighting, the nightmare of traditional QA solutions, are not a problem thanks to the system’s self-adjusting capabilities.  

Additionally, a Detection & Alignment AI engine can autonomously locate the product in a 3D space using just one image. This means that during the set-up phase, the user can add sample items in any orientation, since the INSPEKTO S70’s algorithms will detect and localise them even under heavy transformation and rotation.

During installation, the user simply traces the field of view (FOV) and presents an average of 20 good sample items to the system, which will automatically learn what a perfect item should look like. The benchmark for inspection is therefore established using a limited number of good products instead of hundreds or thousands of defective ones. This simplifies the set-up process and makes it more accurate, since manufacturers usually don’t have a sample item for every possible abnormality.

After the system has learnt the item’s characteristics, inspection can begin. The S70 will alert the user automatically if it detects a product outside the parameters of the collected good samples set. However, if the QA manager deems that the item is not defective, the Defect Detection AI engine will process the new sample as a good product and the same issue will not be flagged up again.

The simple and quick set up process means that the system can be moved from one point to the other of a production line when needed, offering unprecedented flexibility. Additionally, since the whole system costs less than one tenth of traditional solutions, plant managers can have an S70 at every junction of the production line instead of just at the end, achieving what we call Total QA — quality assurance at every step of production.

Autonomous Machine Vision focuses on pushing the boundaries of AI, not of camera specifications. Because of the benefits offered by several AI engines working in tandem, the S70 can self-adjust its sensing equipment to provide a clearer image and consequently a more reliable inspection than traditional solutions with state-of-the-art cameras, which add to the final cost without offering the flexibility and simplicity of use that manufacturers are asking for.

Eagles need incredible visual acuity, but manufacturers don’t. Instead of developing increasingly sophisticated and therefore expensive cameras, Autonomous Machine Vision offers a flexible, user-friendly and cost-effective answer to plant managers’ QA needs.

Read More
Inspekto S70 | Autonomous Machine Vision

Tracing QA through tiers

September 16, 2019

~ Improving quality in the automotive supply chain ~

Each year, approximately a million vehicles are recalled in the UK for safety repairs. In the USA, 23 per cent of all the cars in service have been called back over the past three years. These figures don’t include cars that just malfunction and need repair. Whether the problem is engines, HVAC systems, gear components, tyres, software, airbags or steering wheels, faults in vehicles pose a serious safety risk. Here Harel Boren, CEO of Inspekto, the founder of Autonomous Machine Vision, discusses what can be done to improve quality and reduce costs in the automotive supply chain.

The automotive supply chain is incredibly complex — structured in tiers from raw materials to larger structures, to the original equipment manufacturer (OEM) building the final product. The average vehicle has around 30,000 individual parts, sourced from a range of suppliers, which will be transported between tiers — sometimes halfway around the globe.All this means thatassuring andmonitoring quality across this vast supply chain has historically been a tricky process.

In addition, Automotive OEMs continuously manage the quality of products their suppliers, and their supplier’s suppliers, provide. During production and just before shipping, manufacturers perform visual quality assurance (QA) so that any defective products are not sent on to the next tier. As the dire statistics show, these huge efforts generate sub-optimal results for OEMs across the globe.

The factory has eyes

However, the traditional visual quality assurance ecosystem is not fit for this purpose. Random checks deliver little more than nothing. The next best thing is human inspection – which fails to recognize defects in 25 per cent of products inspected, not to mention the tedious work and the cost of labour that is taken away from actual production.

The last resort would be machine vision inspection. However, because machine vision inspection solutions are so expensive, a minimum of £70,000 and sometimes in excess of £150,000 for each project deployed at one point on a single line, automotive manufacturers are installing them only at major junctions. Even so, these solutions are prone to fail with any change to the production line. Whether it is lighting, handling or the product itself, any change will require costly adaptation of the machine vision solution, along with a long and nerve wrecking wait.

In addition, because machine vision inspection traditionally relied on a systems integrator to hard-engineer a solution onto the line, there are significant wait times in proof of concepts, commissioning and delivery of components. Once it is installed, a lengthy training process is required to teach the system all possible defects that could occur, followed by iterative optimization, validation and commissioning. This too, deters manufacturers from using machine vision.

Autonomous is the answer

As of November 2018, this no longer applies. The launch of Autonomous Machine Vision as a new category in machine vision, introduced affordable inspection systems that can be readily installed by the company’s own personnel. This means that automotive manufacturers can install visual QA at any point they want to address on the production line and do so as soon as the need comes up.  

Installing visual QA at every required point on the line means that any quality issues that occur in between major junctions are identified and defective products can be removed from the line. This reduces wasted energy and labour spent on a product, which will inevitably be scrapped. On top of that — if your buyer, the next tier manufacturer, claims that your business sent them a faulty product, you will be able to prove that it left your premises undamaged.

In addition, AMV enables plant optimisation. Using TRACKS, the archiving and traceability application that can be installed on every INSPEKTO S70, manufacturers can trace exactly where a defect was introduced and what machine caused it, so that they can optimise their process to reduce the risk of defects being introduced in the future.

It feels as though every day, another vehicle is being recalled. However, with the introduction of Autonomous Machine Vision, recalls will decline. To find out why no manufacturing plant that has received a demo of the Inspekto S70 has ever failed to place an order, visit https://inspekto.com.

Read More
Flexible machine vision system | Quality assurance

Bend, don’t break

June 26, 2019

~ Flexible machine vision systems improve manufacturing productivity ~

In metalworking, tensile tests are conducted to test the ductility of a material, often to determine the most suitable metalworking process. While we have tests in place to assess the flexibility of a material, there is no such test for a machine vision solution. Why? Because they simply aren’t flexible — until now. Here Harel Boren, CEO and co-founder of Inspekto, the founder of Autonomous Machine Vision, explains why flexible visual quality assurance (QA) systems are needed for the industry to progress.

Historically, for a manufacturer to implement a machine vision solution they are tied into an outdated ecosystem. They must arrange for a vision systems integrator to build a custom solution, pay the high associated costs and either pause production or turn to manual QA during the long wait time. At the end of this process, they are lumped with a solution that can operate at only one point on the line, to inspect one product. A solution with no flexibility at all — any minor change to the environment or on the line requires the return of the vision systems integrator to make expensive and time-consuming alterations or, in many cases, declare the original solution obsolete and start again from scratch.

According to Market Insider, “factors that are restraining the growth of the industrial machine vision market include the … lack of flexible machine vision solutions.” But the success of the manufacturing industry is hinged on product quality, making visual QA essential. The flexibility conundrum is holding back the industry from realising its potential.

Introducing a flexible option

For visual QA to be flexible, it must be easy-to-use by non-machine vision experts who must be able to independently and quickly alter the function of their system.  Autonomous Machine Vision products do just that. The INSPEKTO S70, for example, can be set up in 30 to 45 minutes by the plant’s own personnel. During set up, employees only have to show the system 20 to 30 good samples — no defective samples are even necessary — and the system will learn the surface variations of a gold standard product. The operator uses just a mouse to define a polygon around their object of interest and they are ready to go.

Autonomous Machine Vision systems can be applied to any product, made from any material, using any handling method. Unlike a traditional solution which requires a vision integrator to manually make any changes, using its artificial intelligence engines (AI) it can self-adapt and self-adjust to any environmental changes, such as new lighting conditions. This flexibility extends so far that a system could be moved from one point on the line to another and set up again in minutes by any member of staff.

Applications provide customisation

Manufacturers can add significant layers of value to an Autonomous Machine Vision system, due to the flexibility and customisation options available. For example, Inspekto has launched a suite of applications for the INSPEKTO S70, which means that on top of its standard visual QA capabilities, sit a myriad of capabilities that manufacturers can choose to make use of. For example, Inspekto TRACKSTM, for archiving and traceability as the product travels down a production line. This app means that manufacturers can null a void claim about product quality and can also perform root-cause analysis to identify the source of an issue should something go wrong.

Autonomous Machine Vision systems can even inspect product as part of a multi-product range from one single location, unlike traditional solutions that can inspect just one. Inspekto TYPESTM for example, is a powerful application that means any number of models can be inspected at one point. Manufacturers using plastic injection moulding machines will be relieved to hear there is now one system able to inspect every product manufactured by the moulding heads of their machines.

Flexibility has held the market back for too long. We are now at the beginning of an Autonomous Machine Vision revolution, which means that, finally, manufacturers can opt for a flexible system that meets more than just their QA needs.

Read More
Autonomous machine vision | Inspekto

Is the machine the expert?

June 9, 2019

A recent study by the University of Michigan found that multi-tasking has a negative impact on productivity. When you think about it, it makes sense. How many times have you had so many tasks to complete, you don’t know where to start? Luckily, we now have technology that can help us. Here Zohar Kantor, Vice President of Sales of Autonomous Machine Vision expert Inspekto, explains how this new technology can be used as an engine for economic growth.

While this study suggests that humans shouldn’t attempt to multi-task, machines are capable of carrying out several tasks at once, if they have the right intelligence. One example of this is Autonomous Machine Vision. But, before we take a deeper look at the capabilities of this ground-breaking technology, let’s consider its predecessor.  

Price versus value

When the price of a product outweighs its value, the manufacturer will start to lose business. This is the case with traditional machine vision solutions — they cost upwards of $20,000 and sometimes in the region of $150,000 or more — but fail to give the manufacturer any control over their own quality assurance (QA).  

This is because there is no traditional machine vision solution that can be installed and controlled by the manufacturer’s own personnel. Instead, QA managers must rely on a vision systems integrator to create Proof of Concepts, develop a possible solution from many hundreds of good and bad annotated samples, test it, optimize it, and eventually build an installation on the line. Next, they must go through a tedious, expert-dependent software set up stage. The integrator must purchase the necessary components at expense to the manufacturer, including cameras, lenses, lighting, housing and communication and more.

Unfortunately, this is just the beginning of the problem. On top of the capital expenditure, there are operational costs associated with installing a traditional solution. There’s the wait time while the solution is being built and the downtime while it is installed, tested and commissioned. In addition, if there is an environmental change in the plant or the manufacturing line is modified, the manufacturer will have to call on the systems integrator to adjust or redesign the solution.

The future is autonomous

Autonomous Machine Vision was introduced to the industry in November 2018 at VISION, Stuttgart. Now, QA managers can finally take control over their QA processes. Autonomous Machine Vision requires little cost, effort and time to install and run. This means that the manufacturer doesn’t have to rely on a vision systems integrator to design and build a custom solution for a particular point on the production line — they can install an off-the-shelf product in-house.

In the case of Inspekto’s product, the INSPEKTO S70, the system can be installed and begin assessing the quality of products on a production line in under an hour. The system’s artificial intelligence (AI) engines will optimize the camera and illumination settings for the object and environment and then detect and locate the object without any input from the operator. Finally, all that’s needed to set it up for operation is just 20 to 30 good references — no bad samples at all.

The system is ready to go, straight out of the box ─ the QA manager simply has to use a mouse to draw a polygon to mark their areas of interest on the object to be inspected. Once in operation, the system will compare each image with the gold standard, verifying both the shape tolerances and surface variations to identify any defects.

An engine for economic growth

On top of its standard quality assurance capabilities, an Autonomous Machine Vision system will offer a variety of apps priced so they are compliant with the actual value they bring to the manufacturer. This drastically enhances the overall profitability of the line.

Inspekto’s applications further enable archiving of the images and data gathered during inspection. Manufacturers can use this archive to find exactly where the defect was caused and identify the culprit. They can then address the issue before more parts are passed through the same manufacturing process and prevent producing further products that are destined to become scrap.

Many traditional machine vision solutions offer some archiving capabilities, but they are usually only installed at major junctions on the line, due to the high costs, long wait times and downtime required for an integrator to finalize the solution. This means that manufacturers using traditional solutions have no way of easily locating the source of a defect.

Manufacturers will also be able to use Inspekto’s archiving and traceability apps to counteract claims that a defective product has left their premises, when in fact the damage happened during shipment or in further stages of production.

Inspekto also offers a multi-product app for lines where different products need to be inspected on the same location — as is the case on many plastic injection moulding lines. This adds value to the production line in that a single system can adapt itself to inspect a variety of items, something that was unthinkable until the advent of Autonomous Machine Vision. There are also apps to allow products to be counted before they are boxed and apps for gating or sorting. Each app can be set up in minutes by the plant’s own personnel, without any expert assistance whatsoever.

If workers in a manufacturing plant are to focus on just one task at a time, this should be one that brings genuine value to the business and certainly not one that a machine can do even better. Autonomous Machine Vision was brought to market by a team of experts to improve profitability per line for a growing customer base. With increased control over their own quality assurance, QA managers are now free to love their jobs.

Read More
Inspekto S70 | Autonomous Machine Vision

Applications for productivity enhancement

May 29, 2019

~ Implement Total QA with a variety of useful applications~

Autonomous Machine Vision systems are revolutionizing the manufacturing industry all over Europe. Safe, inexpensive, quick and easy to install, they save manufacturers the time and troubles that traditional solutions carry. But did you know that they also come with a variety of useful applications, each of which can add value to your production line? Here Harel Boren, CEO, and Yonatan Hyatt, CTO, co-founders of Inspekto, the world’s first Autonomous Machine Vision systems vendor, explain more about what they do.

Machine vision solutions of the past helped speed up manual visual QA but came with a variety of problems including high costs, downtime when installed, long wait times and total reliance upon vision systems integrators. Luckily, this is now a thing of the past thanks to Autonomous Machine Vision (AMV). Using AMV systems, which are immediate to install and highly affordable, manufacturers can now make their production lines far more profitable and efficient.

Because the manufacturer can now quickly install an Autonomous Machine Vision system at every point it’s needed, it eliminates the need for manual visual QA and frees employees to focus on far more productive tasks. While factories used to have several employees just for visual QA and install machine vision systems only at select locations, for €10,000 they can now install an Inspekto S70 at any location in their facility in minutes. The S70, which can be set up using only good samples, can save a company hundreds of thousands of euros over the course of a single year.

Adding value to value

Besides the obvious impacts on productivity and profitability, INSPEKTO S70 systems can benefit manufacturing establishments in a variety of ways. Each S70 can make use of a range of powerful apps that can be installed to fulfil the specific QA needs of a line. Flexibility is the key word here, because customers can install the apps they need for their specific production line.

One of these apps archives and traces all product images and data gathered during inspection. In this way, manufacturers hold a live archive that they can use to counteract claims that a defective product has left their premises, when in fact the damage happened during shipment or in further stages of production. If a faulty product did leave their plant, they can retrace the production history of that particular item to understand exactly where it was made defective. Over time, this allows manufacturers to improve critical areas of the production line where damage happens more often.

Another useful app enables each S70 to be applied to any number of inspected products on the line. While traditional machine vision solutions allowed you to monitor only one product at any given location on the production line, the app enables the S70 system to inspect any number of products — even tens or hundreds of different products — at that same location on the line. Emerging from the traditional constraints of one-product-per-solution, Inspekto allows manufacturers to inspect a variety of items by one single system, something that was unthinkable until recently.

Other apps enable products to be counted before they are boxed to leave the plant or sorted and gated towards the next designated stages of production lines. These applications can be combined in a variety of ways to give every plant the flexibility it needs to take Autonomous Machine Vision to the next level, adding the advantage of an adaptable, open system to those of state-of-the-art Total QA.

If you want to know more about the Inspekto S70 applications that can help you enhance your productivity, visit www.inspekto.com.

Inspekto S70 | Autonomous Machine Vision
Read More

Subscribe to Inspekto's Newsletter

Get industry insider updates delivered to your inbox

Newsletter Signup

  • This field is for validation purposes and should be left unchanged.