One of the areas Castrip has been working on for the last two years is increasing the use of machine intelligence to increase process efficiency in throughput. “This is highly influenced by the skill of the operator who sets the points for automation, so we use reinforcement learning-based neural networks to increase the precision of this setting to build a self-driving casting machine. This will certainly create more energy efficiency gains – not like the previous big step changes, but still measurable.
Reuse, recycling, remanufacturing: design for circular production
The increase in the use of digital technologies (often referred to as Industry 4.0) to automate machines and monitor and analyze production processes is driven primarily by the need to increase efficiency and reduce waste. Firms are expanding the productive capabilities of tools and machines in their manufacturing processes through the use of monitoring and management technologies that can evaluate performance and proactively predict optimal repair and reconditioning cycles. This type of operational strategy, known as case-based maintenance, can extend the life of production assets and reduce downtime and downtime; all this not only results in higher operational efficiency, but also directly improves energy efficiency and optimizes material use, thereby reducing the carbon footprint of the manufacturing plant.
The use of such tools can also identify a firm in the first steps of its journey towards a business defined by the principles of the “circular economy”; whereby a firm not only produces goods in a carbon-neutral fashion, but also relies on recycled or recycled inputs. produce them. Circularity is a progressive journey of many steps. Each step requires a long-term viable business plan for materials and energy management in the short term, and future “design for sustainability” production.
IoT monitoring and measurement sensors deployed on manufacturing assets and on production and assembly lines represent a critical element of a firm’s efforts to implement circularity. Through situational maintenance initiatives, a company can reduce energy expenditure and increase the life and efficiency of its machines and other manufacturing assets. “Performance and status data collected by IoT sensors and analyzed by management systems provides the ‘next level’ of real-time, factory-based insight that allows for much greater precision in maintenance assessments and condition-refresh schedules,” notes Pierre Sagrafena. , circularity Schneider Electric’s program leader in the energy management business.
Global food manufacturer Nestle is undergoing digital transformation through its Connected Worker initiative, which focuses on improving operations by increasing the flow of paperless information to facilitate better decision making. José Luis Buela Salazar, Nestle’s Eurozone maintenance manager, oversees efforts to improve the process control capabilities and maintenance performance of the company’s 120 plants in Europe.
“Condition monitoring is a long journey,” he says. “We used to rely on a long ‘First Level’ process: information specialists in the shop would review performance and write reports to create alarm system settings and maintenance schedules. We now come to a ‘4.0’ process where data sensors are online and our maintenance planning processes are predictive, using artificial intelligence to predict failures, often based on historical data collected from hundreds of sensors hourly.” About 80% of Nestle’s global facilities use advanced condition and process parameter monitoring, which Buela Salazar estimates reduces maintenance costs by 5% and improves equipment performance by 5% to 7%.
Buela Salazar says much of this improvement is due to an increasingly dense array of IoT-based sensors (between 150 and 300 per factory); We have more time to react and less need for external maintenance solutions.” Currently, Buela Salazar explains that the carbon reduction benefits of situational care are implicit, but that is changing rapidly.
“We have a major energy-intensive equipment initiative to install IoT sensors for all such machines at 500 sites around the world to monitor water, gas and energy consumption for each and make correlations with relevant process performance data,” he says. This will help Nestle reduce its production energy consumption by 5% in 2023. In the future, this type of correlation analysis will help Nestle conduct “big data analysis for carbon optimization of production line configurations at an integrated level” by combining insights into material usage metrics, energy efficiency of machinery, rotation programs for motors and gearboxes, and the performance of a complex food manufacturing facility. About 100 other parameters add Buela Salazar. “Integrating all this data with IoT and machine learning will allow us to see what we haven’t seen before.”