Lean Manufacturing

whitePaper | October 23, 2021

Artificial Intelligence (AI) will increase the level of intelligence in the manufacturing industry by promoting, inter alia, the matching of production and demand, improving quality inspection, increasing product yield, reducing product failure rates, and improving production efficiency.1 While the last decade of Industry 4.0 was determined by technology-driven innovation, the coming years will focus on data- and intelligence-driven innovation. In this perspective, AI is an enabler for the transition from smart factories towards intelligent factories with self-optimising and self-healing characteristics. While smart factories are capable of applying previously acquired knowledge, intelligent factories will be able to autonomously acquire new knowledge and apply it for self-optimisation purposes.

whitePaper | July 30, 2020

After the COVID-19 pandemic abruptly ground the world to a halt in the first few months of 2020, it created both new challenges for the manufacturing industry and exacerbated those that had existed for some time. According to an article by McKinsey & Company analysts,1 the future we expected by 2020 hasn’t quite come to pass. Rather than a significant shift towards more automation and a smaller workforce, the opposite is true, due in part to the pandemic.

whitePaper | July 7, 2022

Production scheduling primarily deals with arranging different jobs in various machines based on the timelines for each job. There can be numerous combinations of schedules possible. Production schedules can be designed to maximize the capacity utilization, minimize idle time of the machine, earliness, overall costs etc. Manual design of a schedule can be a tedious and time consuming task. There are a lot of dependencies which the scheduler needs to tweak based on a single change. Generating a production schedule targeting a specific objective function can be done using mathematical models. Mathematical models involve formulating the production scheduling problem as an optimization model wherein there is a certain objective function which needs to be optimized based on a set of constraints. Mathematical models generally outperform manually designed schedules which involve a lot of inter-dependencies among the jobs. Due to improvement in computational power, developing a production schedule using mathematical models is relatively quick and efficient.

whitePaper | March 22, 2020

Manufacturers are beginning to adopt AI technology themselves, marrying this new technology with the automation systems they already widely use with the advent of the programmable logic controller, manufacturers have been able to increase their productivity while employing fewer people. Here are three major AI ethical problems that manufacturing executive are facing.

whitePaper | July 25, 2022

Manufacturers are demanding ever-greater precision, accuracy, and reliability from industrial automation. Fortunately, sensors, robot arms, grippers, and the software to connect and guide them have become increasingly capable. In response to the labor and supply chain challenges of the past few years, as well as the demands for personalization and rapid fulfillment, many factories and other facilities are looking to adopt robots or add them to their operations. In this Special Focus Issue, we look at how AI and machine learning are enabling more precise picking, among other applications.

whitePaper | February 29, 2020

Ideal Boilers in Hull, UK started manufacturing boilers back in 1906. Since autumn 2018, the boiler chassis for the domestic range of boilers have been manufactured in a fully automated and highly efficient process designed by AP&T. Over 400,000 boilers leave the factory in Hull every year for households and commercial properties all over the UK. In order to meet the growing demand for the company’s products, Ideal Boilers decided in 2016 to investigate the possibilities for increased automation and streamlined production.