Open standards, more powerful desktop computers and lower-cost software make design, modeling and automatic code generation for PLCs and PACs practical for improving automation. Other technologies go beyond problem-solving to achieve productivity and performance enhancements. Here’s a look at advances in 18 technology areas that are worth paying attention to:
AI, ML and expert systems
The commercial use of artificial intelligence is accelerating at all levels with the wide commercial application of AI, natural language processing, machine learning and other expert systems. Increased processing power at lower cost is accelerating the technology. It is tempting to apply new technology immediately but as with any technology, these are new tools that need to be understood and applied properly; they are not instant “silver bullets” to solve all problems and increase operations efficiencies. The quality and value of AI applications depend directly on internal algorithms and data sources.
In the context of industrial automation and controls, poorly applied AI can have negative outcomes impacting performance, personnel and plant safety. The European Commission AI ACT Legal Framework notes: “What does ‘reliable’ mean in the AI context? We speak of a ‘reliable’ AI application if it is built in compliance with data protection, makes unbiased and comprehensible decisions, and can be controlled by humans.”
The AI ACT Regulatory Framework defines four levels of risk for AI systems: unacceptable risk, high risk, limited risk and minimal risk. Mission-critical industrial control and automation applications are within the AI ACT high-risk category. AI systems identified as high-risk include AI technology used in:
Properly applied AI, ML and expert systems offer industrial companies enormous potential to significantly cut operating expenses and improve staff efficiencies, quality, productivity, operations and reduce maintenance and repair costs. AI technologies help achieve the goals of all industrial automation to increase productivity and efficiency. AI industrial applications properly designed with the right data can more effectively handle unforeseen scenarios in complex and rapidly changing environments based on patterns and trends in the data without being explicitly programmed for every possible scenario with little to no human interaction.
The goals of AI applications should be in line with the company’s overall strategy and then define potential AI use cases for evaluation and prioritization for projects.
There are an increasing number of no-code, self-serve software tools simplifying the application of these technologies by industrial subject matter experts rather than data scientists. Industrial automation and control systems have a wealth of data that can be used more effectively with these technologies.
In addition, AI processor chips enable high-performance applications to run within controllers and edge computers for demanding applications. Server and cloud AI/ML/expert system solutions are suitable for a wide range of applications, but network communication speed and latency factors pose limitations for many real-time industrial and process applications that are overcome with AI chips embedded in industrial edge devices and sensors.
There are offerings from offerings in the market including Nvidia, Intel Myriad-X, Google Edge TPU and Hailo. These new technologies are proven in other areas including video analytics with image recognition and related applications. These chips can be applied using plugin add-on board modules that are aggressively priced, conforming to the popular M.2 and mPCIe connector standards found in many computers including embedded industrial PCs, adding high-performance AI processing without degrading other applications in the computer.
This is analogous to early PC coprocessor add-ons to achieve high-performance floating-point mathematical calculation performance and video display coprocessors to achieve high-resolution/performance graphics. For example, the original IBM PC included a socket for the Intel 8087 floating-point coprocessor (aka FPU), which was a popular option for people using the PC for computer-aided design or mathematics-intensive calculations, or system architecture encompassing cloud, enterprise and embedded applications. AI chips for embedded edge applications are particularly valuable for real-time industrial automation and control effectiveness. READ MORE
By Bill Lydon
Source: autiomation.com
Mondi has co-founded a Spanish alliance to improve used paper bag circularity in the construction industry. The alliance, Paper Sacks Go Circular Spain, comprises 12 European companies from the full value chain, including Mondi. The initiative follows Mondi’s summer launch of a dissolvable cement bag to the Spanish building industry.
Twellium Industrial Company, a manufacturer of non-alcoholic beverages in West Africa, has announced a partnership with Sidel to establish a state-of-the-art packaging hub in Kumasi, Ghana. This new facility will feature two complete PET packaging lines designed for both still and carbonated beverages, marking a significant expansion for Twellium in the region.
Konecranes is adjusting its operating model to support its strategy deployment and growth ambitions. As of January 1, 2025, the company will have three Business Areas: Industrial Service, Industrial Equipment and Port Solutions, instead of the current two, Industrial Service and Equipment, and Port Solutions.