How explainable AI is changing manufacturing jobs for better World Economic Forum

PINC, meanwhile, combines their drones with computer vision systems, cloud computing, RFIC sensors and AI to track and monitor their warehouse assets. To construct the system, researchers amassed a huge dataset of 90+ videos using cameras installed onsite, before annotating the data and training an object detection model. The main problem here is that it’s almost impossible for a company to monitor their workers all day long for the use of PPE. Managers are also informed each time there’s a malfunction or other type of problem that needs to be rectified ASAP.

In our survey, nearly half of semiconductor-device makers stated that lack of integration was the second-biggest problem in scaling AI/ML use cases. If organizations form tight links between the AI/ML function and the business side, it will be significantly easier to take the user’s perspective when initially designing the use case. Industry-wide, manufacturing will accrue the most value from AI/ML (Exhibit 4). This is not a surprise, given the capital expenditures, operating expenditures, and material costs involved in semiconductor fabrication. The greatest relative spend reduction will occur in research and design, primarily resulting from the automation of chip design and verification. AI is still in relatively early stages of development, and it is poised to grow rapidly and disrupt traditional problem-solving approaches in industrial companies.

Equipment Predictive Maintenance

The COVID-19 pandemic also increased the interest of manufacturers in AI applications. As seen on Google Trends graph below, the panic due to lockdowns may have forced manufacturers to shift their focus to artificial intelligence. The industrial manufacturing industry is the top adopter of artificial intelligence, with 93 percent of leaders stating their organizations are at least moderately using AI.

Robotic employees are used by the Japanese automation manufacturer Fanuc to run its operations around the clock. The robots can manufacture crucial parts for CNCs and motors, continuously run all factory floor equipment, and enable continuous operation monitoring. Supply chain and inventory management can better prepare for future component needs by forecasting yield.

Shop floor performance improvement

The company is going to expand POSS with a forecasting tool to predict impending failures and such application of AI-based predictive maintenance can be suitable not only for the Dutch railway, but others as well. Factories without any human labor are called dark factories since light may not be necessary for robots to function. This is a relatively new concept with only a few experimental 100% dark factories currently operating.

• Image recognition and analysis can find even small flaws in your product, which can improve the overall quality of your product.
• On the factory floor and in any building or processing setting, errors and accidents do happen, but AI and robotic aid can all but eliminate this propensity.
• They store your data pretty cheaply, but when you start using computing resources, it becomes a lot more expensive.
• These robots can move accurately in a variety of work environments, eliminate or reduce human error, and enable reliable production.

This IoT platform helps create a digital representation of manufacturing – and not only – processes and enables the optimization of costs and operations. Azure Digital Twins can help you as a manufacturer define your business environment by defining the custom twin types (usually referred to as models). Industrial robots, also referred to as manufacturing robots, automate repetitive tasks, prevent or reduce human error to a negligible rate, and shift human workers’ focus to more productive areas of the operation. Applications include assembly, welding, painting, product inspection, picking and placing, die casting, drilling, glass making, and grinding.

Supply Chains Are Still in Shock from COVID-19

Some of the most difficult challenges for industrial companies are scheduling complex manufacturing lines, maximizing throughput while minimizing changeover costs, and ensuring on-time delivery of products to customers. AI can help through its ability to consider a multitude of variables at once to identify the optimal solution. For example, in one metals manufacturing plant, an AI scheduling agent was able to reduce yield losses by 20 to 40 percent while significantly AI in Manufacturing improving on-time delivery for customers. Manufacturers can use knowledge gained from the data analysis to reduce the time it takes to create pharmaceuticals, lower costs and streamline replication methods. Manufacturers can use automated visual inspection tools to search for defects on production lines. Visual inspection equipment — such as machine vision cameras — is able to detect faults in real time, often more quickly and accurately than the human eye.

Due to the shift toward personalization in consumer demand, manufacturers can leverage digital twins to design various permutations of the product. This allows customers to purchase the product based on performance metrics rather than its design. The enemy of all manufacturing operations is a breakdown (or “unexpected downtime” as it’s referred to in heavy industry). In so many words, breakdown means unplanned downtime, either from broken machines, late supplies, personnel issues, or any manner of factory-related issues. We’ll come back to the concept again when we discuss maximizing uptime. Data points are time stamped and help to provide an arsenal of machine performance metrics.

Generative AI ERP Systems: 10 Use Cases & Benefits

The company set up a camera that uninterruptedly monitored fibers as they left a bushing. Afterwards, the machine learning network analyzed the received data and predicted the moment of a break. Three-year data was collected and analyzed from channels inside the furnace and close to the panels. Predictive maintenance is a strategy that entails continuous monitoring of equipment’s state under normal working conditions and predicting remaining useful life. While reactive and preventive maintenance help decrease or just prevent failures, predictive maintenance uses models to forecast when a specific asset is about to have a component fail. A digital twin can be used to monitor and analyze the production process to identify where quality issues may occur or where the performance of the product is lower than intended.

Generative models can simulate multiple scenarios considering variables like demand fluctuations, resource availability, and supply chain factors. This aids in proactive decision-making and in reducing costs linked to overproduction or stockouts. The use of artificial intelligence in supply chain management is rapidly increasing. From inventory management and material loading and delivery, AI applications with the help of IoT sensors are helping manufacturers in organizing entire supply-chain operations in a more organized way. Predictive maintenance of devices allows the manufacturer to cut device repair or maintenance costs. Using ML-powered predictive solutions, AI tools for manufacturing can predict when machinery requires maintenance services.

Predictive maintenance

According to Strukton Rail, predictive maintenance as a solution to this problem leads to higher rail availability at lower costs. Machine learning solutions can promote inventory planning activities as they are good at dealing with demand forecasting and supply planning. AI-powered demand forecasting tools provide more accurate results than traditional demand forecasting methods (ARIMA, exponential smoothing, etc) engineers use in manufacturing facilities.

Manufacturing companies are deploying AI t get information of equipment damages for ensuring excellent performance. By using shift end time as a trigger, relevant data from the last shift can be extracted from SAP Digital Manufacturing via public APIs (see available public APIs at Business Accelerator Hub). This includes last shift highlights such as production details, stock levels, defect and downtime information, OEE KPIs, and more. Some examples of this in practice include Pepsi and Colgate, which both use technology designed by AI startup Augury to detect problems with manufacturing machinery before they cause breakdowns. Industrial Revolution 4.0 is altering and redefining the manufacturing sector thanks to artificial intelligence (AI). AI has significantly aided the advancement of the manufacturing industry’s growth.

Robotic Process Automation to Streamline Paperwork

Defect detection, predictive maintenance, liquid level analysis, asset inspection are all being shaped by AI solutions based on computer vision and machine learning. An agile approach, which is central to software development, can help semiconductor companies attain this focus. Although AI/ML development involves intense discovery and exploration, semiconductor companies should receive continuous feedback from people who use insights from their models.