Manufacturing companies have faced many challenges in the past few years, from an aging workforce to a rapidly changing technology landscape. Despite these challenges, manufacturing is on the edge of a new innovation period thanks to shifting business models and new technologies. This promises a significant increase in productivity and potential lower costs with higher rewards for businesses.
Future successes in manufacturing require consideration of new levels of automation and coordination within production facilities as well as greater integration of the supply chain into production. The technology itself is exciting – robots, artificial intelligence (AI), end-to-end security – and the benefits are immense: scalability, flexibility, and strength to meet market needs, foster new partnerships, satisfy customers, and drive workforce growth.
Digital technology is accelerating at incredible speed, and the changes in areas like machine learning, autonomous production, and the industrial internet of things (IIoT) promise to be even more disruptive and drive further change than what the manufacturing industry has experienced in the past two decades. It is not far-fetched to suggest that any plant manager who does not embrace this next-generation technology – and therefore enable smart manufacturing – will be left behind. Not even a current dominant position in an industry safeguards a business from the effects of delaying digital transformation.
Some existing automation technologies, such as MES, SCADA software, and smart sensors, promise to make factories more efficient and safer for operators than ever before. New developments in the manufacturing process as well as the emergence of new products and technologies are designed to make manufacturing more efficient, more competitive, and in line with modern industrial needs.
Use what you've got
Companies can begin with the software that they already have on hand – MES and SCADA applications that help control the process and plant. These applications will make it easier to learn more about a plant’s systems and how to keep them running at peak performance, avoiding the pitfalls of unexpected downtime with preventive maintenance procedures.
These applications can also be used to collect and organize data to do more analytics by leveraging a common data model and data storage. By utilizing this on-premises software, you can structure information so that it is easier for IT personnel and data experts to correlate across multiple plants by ultimately moving data to the cloud.
For example, in GE Transportation’s manufacturing facility in Grove City, PA, by equipping machines with sensors, coupled with MES applications, maintenance happens based on operating conditions. This team has realized 10%–20% reduced unplanned downtime, 20% reduction in inventory, and an increase of 20% in recovered capacity.
Modern industrial equipment is instrumental in measuring and assessing everything from inventory levels to temperature discrepancies in plants and along the supply chain. Central monitoring and resulting actions to correct any anomalies in the plant can have a direct impact on the cost-effectiveness and bottom line of the business.
In another example, one tire manufacturer uses real-time visualization through its SCADA systems to ensure precision during manufacturing, filling, and storing cooling lubricant. The company, which runs its 19 plants 24/7, has lowered its energy costs by 45% and has seen a 40% increase in the speed at which it can troubleshoot system anomalies.
Collecting data from sensors
Sensor data will also enable condition-based maintenance with accurate precision, resulting in an estimated reduction of 10%–30% in maintenance costs. The very nature of sensor data collection is that it happens in the background of other central system applications, allowing for constant collection and assessment of data without disrupting operations.
And, because data collection happens automatically, eliminating human error, it creates a comprehensive, accurate data set. These cloud-based analytics detect subtle variations in equipment operations and use the signals as a predictive indicator of future issues and downtime.