​Artificial intelligence is being implemented within nearly every aspect of our lives and is slowly changing the face of manufacturing. We only need to look at Industry 4.0 to see its vital part within a manufacturer’s roadmap. Technological advancement is a prime candidate to optimise manufacturing processes, automate complex tasks and identify unknown patterns in workflows.
 
The manufacturing industry is leveraging this game-changing technology with a 60% adoption rate in 2020 (using in at least one business function). This means manufacturers are starting to realise the huge potential of utilising AI to increase their commercial advantage.
 
What is Holding Manufacturers Back?
 
AI is revolutionising almost all sectors, giving empowerment to companies across the globe to gain immense value from their data. Utilising AI can help manufacturers increase operational efficiency, reduce downtime, and deliver high-quality products. If this sophisticated technology is the epitome of Industry 4.0, why is the install rate relatively small?
 
Outdated Technological Infrastructure
 
Manufacturers often use a wide variety of machines, tools and systems that use different and competing technologies. Some of these may be outdated and not compatible with their other technological infrastructure. This combined with a lack of digitalisation is preventing manufacturers from capitalising on the potential.
 
Confidence, Uncertainty and Trust
 
A significant barrier to AI adoption is the trust and confidence in the capabilities of abstract algorithms. Personnel within manufacturing who don’t hold a data science background struggle to validate how predictive modelling and data science work together.
 
JetSoft’s Use of AI in Manufacturing
 
JetSoft employs AI techniques to automatically analyse inspection and manufacturing data, to detect anomalies in product output and associate them with the upstream processes that created them. Manufacturers gain deep insights to understand the correlations in inspection failures and deploy targeted process improvements, to reduce the likelihood of that anomaly occurring again.
 
Our OverSeer solution automatically manages inspection data and techniques from different sources. OverSeer reads and places the data automatically into a central database to perform thorough assessments. Data from new inspections can be tracked as it passes through each module that has an output. Working on legacy formats means our cutting-edge AI technology is able to analyse historic data from manufacturers to instantly spot anomalies and defects.
 
 
JetSoft deploys AI technology into a customer's site, which analyses images and inspection data to automatically detect anomalies and patterns within the data. The AI functionality pinpoints which processes have created the specific anomaly without having to stop the entire production to detect and fix the problem. Manufacturing personnel are then able to analyse the anomaly against a defect specification to gain a deeper insight into if the anomaly has become a defect.
 
Benefits of AI in Manufacturing
 
The applications of using AI are widespread and revolutionising, offering actionable insights into reducing waste and scrap. So, what are the overall benefits of using AI in manufacturing?
 
Predictive Analytics for Increased Production Output
 
AI systems are able to learn from machine learning algorithms and make use of predictive analytics. The manufacturing industry holds a large volume of data, which predictive analytics is powered from. Manufacturers can easily pinpoint anomalies without disrupting the production process.
 
Improved Process Quality
 
AI technology creates an efficient production process, resulting in higher product quality. The software ensures that products going through the inspection stage don’t just meet quality standards but are of higher quality and closer to nominal. 
 
Reduction of Scrap and Waste
 
Early detection of anomalies using AI techniques allows manufacturers to make quick industry-related decisions that won’t further impact production and create more waste. Reducing waste and scrap has a direct correlation with profit generation and the bottom line. When high-quality products are always created, manufacturers are maximising their output without having to scrap any materials. Utilising assets more effectively creates a reduction in the variable cost of each component, meaning lower prices can be introduced to become more competitive. Minimising component costs ultimately creates a more profitable company.
 
Implementing our solutions has allowed established clients to benefit from huge commercial gains. One JetSoft customer who using our solutions has reduced their scrap rates by over 60%, resulting in savings in excess of $2m a year.
 
AI solutions allow manufacturers to utilise their assets more effectively and take advantage of commercial gains. If you want to know more about how JetSoft can help you, get in touch.

The manufacturing sector is in the midst of a digital revolution, embracing the likes of IoT, robotics and AI, so why is it that so many paper-based processes remain? According to a recent study, roughly 62% of manufacturers still utilise some form of paper-based system, yet those same respondents were aware that is where the greatest productivity improvement could be derived. Enter digitisation.
 
 
Shifting to digitised processes
 
Whilst many manufacturers haven’t dropped their pen and paper just yet, more and more manufacturers are considering digitising their processes to transition to the digital age effectively.
 
The past couple of years have only amplified this, with proportions of the workforce working remotely, there was a greater need for employees to be able to access relevant information remotely and with paper records, this just isn’t possible. Digitising paper processes is the first step on the digital road, there is no point in having a manufacturing facility with IoT sensors connected to assets to conduct predictive maintenance if that same maintenance procedure is being documented on paper. You have to digitise before you digitalise.
 

The potential of digitising
 
The manufacturing sector is evolving and paper-based processes are holding manufacturers back from their true productivity potential. So, what exactly can be gained from digitising these processes?
 
1. Time 
If we take inspections as an example, a record of every inspection has to be collected, however filling in paper-based forms is an arduous task and often leads to a lot of unnecessary repeats and the information sometimes has to be manually inputted into a central system. Digitising this process means inspections can be logged digitally and automatically stored in a central location. Also, pre-generated forms can be developed with certain aspects automatically filled-in to reduce unnecessary repetitions. IDC research states the manufacturers could gain a 50% increase in productivity by going paperless.
 
 
2. Minimising Errors 
Everybody makes mistakes, we’re human at the end of the day. However, paper-based systems only increase the probability of mistakes appearing in records. It gives way to incorrect entries or inconsistent records, leading to a lack of data integrity. The ability to replicate forms means less data entry is required, and less chance of an incorrect data entry.  
 
3. Actioning Data 
As paper-based systems are more time intensive, the route to action is longer. For example, when workers are registering deviations or maintenance issues these are done so on paper, which then must be manually inputted and flagged with relevant members via email or in-person, which could be days later. Whereas a digital platform can instantly highlight any recorded deviations on a shared interactive dashboard, so issues are resolved faster.
 
4. Sourcing Data 
Due to the compliance nature of the manufacturing industry, records are constantly being kept throughout the production processes but once they are done, they are simply stored away and never seen again until an audit, where there’s often a scramble to source critical information. Digitising these documents will mean each record, in various formats can be stored in one location, where it will be accessible for other applicable colleagues. Utilising software means the required information is easier to source through filters and refined searches, reaching records in a few simple clicks. Valuable data is now made accessible.
 
5. Conduct Analysis 
Not only is filling in paper documentation time-consuming, it also loses any opportunity to derive value from the results and data is the new oil! Documents are being filled in purely from a compliance perspective, whereas digitising could allow the stored data to be analysed to give greater insight into operational performance. Data becomes more centralised when the processes are digitised, meaning production, inspection and financial data could be stored in one central location. And when utilising a digital platform that incorporates business intelligence the data can be analysed to detect trends and patterns that can drive more valuable decisions and continuous improvement. For example, the analysis may show that one particular component is failing inspections at a higher rate, which could indicate a design flaw or a problem on the production line.
 
6. Sustainability  
Many manufacturers have set sustainability agendas for their businesses to reduce their environmental impact and printing thousands of sheets of paper won’t help achieve a carbon neutral goal. In addition, the potential for analysis means failed inspections and wastage figures can be analysed and detect areas for concern, so that production waste can be limited in the future.
 
Digitisation is the next step for manufacturers, the move can deliver end-to-end data visibility for continuous improvement and elevated quality control.
 
 
Introducing DigiOps
 
As much as the benefits of digitising processes are clear to see, transitioning to an electronic format is no small feat. Our DigiOps solution is designed to replicate and replace paper and spreadsheet systems, with smooth integration in mind and tailored to your specific needs.
 
Built on our OverSeer framework, DigiOps has the capacity to create digital replicas of your paper forms and the ability to create and revise form templates to be distributed to shop floor team members. These forms from then can be completed digitally from several devices and be shareable with other colleagues. DigiOps comes with business intelligence built in, so data is easily viewable via interactive visualisations and simple filtering systems, and data analysis to develop key insight, delivering actionable information.
 
 
Futureproof your data management with DigiOps. Speak to our experts to find out more.  

​This month (August 2020) marks the second anniversary of our first AI, Automatic Defect Recognition (ADR) system being installed in a production environment.
​
To date we haven’t promoted our ADR system publicly, deciding to concentrate on working with select companies and individuals to fully develop it. However it has formed a natural addition to OverSeer’s framework. OverSeer collects inspection data and performs validation and calculations upon it, notifying stakeholders of results and storing data for further analysis. ADR is just another calculation.

​
This flagship installation at an aerospace metal production facility was installed in August 2018 and utilises many of JetSoft’s software features. We are gathering positive feedback from the site about the quality and productivity benefits it is delivering, including:
​

• Automatic defect and characteristic recognition
• Combining factory wide data with inspection information
• Driving process change
• Generating new insight and enabling predictive maintenance
• Reducing the requirements on downstream processes

In a series of upcoming posts, I will discuss these areas in more detail to explain how our processes deliver these benefits, starting with an insight into our ADR software.
 

A note on ADR
Firstly, this article uses the term ADR, which is an industrial term to mean the automatic detection of a problem within a component. ADR isn’t clearly defined yet within the industry, as explained in the previous post ADR - what’s expected? 

​The installation discussed in this article is an Automatic Indication Detection (AID) system, where inspections are still signed off by a qualified human operator.
 

How it works
JetSoft’s core mission is to provide systems that automatically aggregate and catalogue inspection data into a single database. We understand inspection data, and we gather it into a convenient format to take advantage of it. Our solutions combine quality control information with data from other manufacturing systems. These include details about the processing conditions that the part has gone through, details of the component structure and the customer specifications. Combining this information, and making it available for all, has the huge benefit of keeping quality at the forefront of everyone’s mind. I will talk about this in more detail in a future article.

This collated data is passed through an extensible list of models which are trained to look for particular faults or certain characteristics. Each model outputs a confidence level based on the likelihood that the inspection contains a positive match. Any disagreement between the system and inspector is highlighted to the responsible level 3 or automatically sent for a second opinion. This drastically minimises the potential for misdiagnosis. Additionally, the output of these models is stored in the system and is made available for analysis. 

​ 
Thresholding of output confidence enables the user to select the desired level of Probability of Detection (POD).

Model training is in depth and employs a hybrid approach using a combination of pre-processing, AI machine learning techniques using historic data and deterministic algorithms.

One of the key advantages of this system is its ability to subcategorise defects. For example, this system can differentiate between a lamination crack caused by rolling and a quench crack caused by heat treatment. Detecting this distinction is non-trivial for a human inspector, requiring further analysis

​Similar defects which are caused by different process may look very similar to inspectors, but it is important to differentiate them to target improvements towards the appropriate processes. For inspectors to make this distinction may require additional training and further analysis, whereas the systematic solution is automatic, quick and consistent.

​I mentioned earlier that the system can be configured to identify any characteristics, not just defects. This is important as there are many things we may want to observe and track that could indicate future problems which in time could lead to defects, or just a general reduction in quality. The time and cost investment of training inspectors to manually identify such trends or patterns would not be justified, however by recognising these warning signs early, there is time for mitigating action to be taken to reduce scrap rates in the long run.

 
Key benefits summary
An independent assessment – this system provides an independent assessment alongside the inspector. If there is any difference between the system and the inspector, the responsible level 3 can be alerted or it can be automatically sent for a second opinion. This improves quality and reduces the chance of mistakes or misdiagnosis, without increasing operating costs.

Sub categorisation of defects – this is the big commercial driver behind the software. It is the application of this feature that has seen scrap rates plummet. An inspector’s job is not necessarily to interpret the cause of a defect, but to highlight its existence. By training models to examine for defects with a known cause, we can target our time and efforts on improving process where we will see the most commercial benefit. This creates a feedback loop of high-quality, useful, data from inspection to all other departments.
 
Next time
Quality should be everyone’s responsibility, but this is only achievable if everyone has a clear vision of quality, and their impact upon it. JetSoft is providing the tools that deliver real time statistics which demonstrate and communicate quality to all.

​Next time we’ll look in more detail at how we’re achieving this and how JetSoft’s is helping everyone to take ownership of quality.