For businesses in Central Europe, product quality is a key factor in ensuring international competitiveness. But the price for this advantage is often laborious – and expensive – quality control. Automation can help to some extent, but the trend towards batch sizes of 1 seriously ramps up complexity. Now a new approach promises to square this circle – and offers the prospect of new methods of human-machine collaboration in quality assurance.
Faced with increasing global competition, industrial manufacturers are having to contend with both ever increasing price pressure and the need to meet ever more demanding quality standards. As a result the efficacy and, above all, the efficiency of the quality assurance process are becoming key success factors. Automated systems are already used extensively to support time-consuming manual quality control processes. These systems are taught to distinguish between good and unacceptable quality using training data. One downside is that they are often laserbased, making them expensive. Consequently, the focus is increasingly switching to combining cheaper camera systems with AI. Training this AI generally involves the use of ‘supervised learning’.
The problem with this approach is that the training material for supervised learning needs to consist of labelled sample data which includes items of both good and unacceptable quality. Labelled in this context means that, in addition to the actual data, it also needs to indicate whether the product is acceptable or faulty. Separate training materials and training processes are required for each individual component or component variant. For Industry 4.0 this presents a major problem, since increased customisation and ever greater specialisation mean greater product variety and much more frequent product changes. Faced with this increased variability, the shortcomings of the current generation of intelligent quality control assistant systems quickly become apparent. For small production runs in particular, costs can quickly escalate.
Supervised learning needs lots of image material
Imagine that, for quality assurance purposes, we want to distinguish between visually acceptable and visibly faulty car body components moving along a conveyor belt. For a machine to be able to perform this task automatically following supervised learning, we need to provide the machine with lots of images of acceptable car body components as well as lots of images of potentially faulty components. For a simple component with a small number of characteristic fault types, this might be commercially viable. But what about product innovations from R&D, customisations or previously unrecognised fault types?
In cases like this, the QA department will need to determine whether there is a need for further training and, where necessary, produce new training materials. This requires close coordination between the R&D and production departments. In addition to providing the training materials, this entails substantial extra work. If the product comes in lots of variants or changes are made too frequently, investing the time and capacity involved in performing this work may simply not be worthwhile.
This is where ‘unsupervised learning’ comes in. Unsupervised learning means that training materials no longer need to be labelled by a human. For quality assurance departments, the potential benefits are huge, since unsupervised learning significantly reduces both the labelling workload and the level of coordination required.
Unsupervised learning – the next stage in quality assurance evolution
Unsupervised learning has been around for a while already and, after supervised learning, represents nothing less than the next evolutionary step towards autonomous machine learning. The use of the term unsupervised learning is not limited to quality assurance – it’s used to refer to any kind of machine learning which doesn’t need labelled data. A good example for illustrating the advantages of this approach is visual inspection of a car body component. The training materi-al consists solely of images of fault-free body components. This means that no manual labelling is required, as all images are automatically labelled as acceptable.
So why aren’t we making more use of this technology? Autonomous learning requires specific algorithms. In the field of machine learning, these algorithms are not derived mathematically, but are arrived at by trial and error. There are lots of supervised learning quality control algorithms around which have already proven their utility in real world use. For unsupervised learning algorithms that’s not yet the case.
Unsupervised learning a hot field for research
With demand for unsupervised learning algorithms increasing, the last few years have seen a lot of research in this field, resulting in a number of potentially useful algorithms. We have tested a few using sample data and verified their utility in a manufacturing context, with some very positive results. We were, for example, able to identify anomalies on steel surfaces with no manual image labelling.
This work used a very clean data set intended solely for research purposes. So we decided to go one step further. Using low-cost webcams, we created a more realistic dataset of simple wood panels inhouse. Even in these low quality images, the machine was able to autonomously identify anomalies with no human intervention.
This offers the prospect of new, low-cost options for human-machine collaboration in quality assurance. One possibility is that machines could significantly reduce the number of cases requiring human evaluation. Taking our car body component example, this might mean that the machine marks components suspected of being faulty for subsequent human inspection. All other parts can be verified with no human intervention or using samples selected using a statistical sampling method. This would reduce the human workload and allow staff to focus on the small number of potentially faulty units.
Unsupervised learning – quality assurance and beyond
One thing is clear – demand for new quality control solutions is ever increasing. Unsupervised learning is not just the latest buzzword – it promises to deliver big increases in automation. Businesses have an opportunity to become pioneers in this field. This could provide them with a valuable competitive advantage, with potential multiplier effects. That’s because unsupervised learning could also offer utility in many other areas, such as automatic detection of anomalies in time series data (e.g. IoT sensor data).
It’s time to unleash the power of algorithms!
You are interested in Data Science and unsupervised learning. Please contact us!