Data analytics has been an integral part of manufacturing management for most of its history. However, analytics has undergone both evolutionary and revolutionary changes over the decades with the advent of information technology and digital data gathering and analysis. Part One of this series takes a look at the evolution behind data analytics and new data sources behind its growth. Part Two will provide practical applications of data within the manufacturing environment.
Part One: Data Analytics in Manufacturing
The most recent revolution in this space has been the availability of an extremely large amount of data, collected in real time, from multiple sources across the manufacturing operations, often referred to as “Big Data.” Sources of this data are:
- Various sensors and measuring devices that are part of the manufacturing line
- Material input-output transaction processing at each manufacturing stage
- Location-based data for material and equipment in a manufacturing plant
- Quality inspection data from online checks
- Usage based data for equipment
Analysis of all this big data can provide deep insights into the manufacturing planning and operations processes and aid in optimized decision making.
Production and Distribution Planning
A large amount of data is available from current Enterprise Resource Planning (ERP) and Manufacturing Execution Systems (MES) that lends itself to analysis, providing insights into the performance of the manufacturing operations. When large amounts of data from the Programmable Logic Controllers (PLCs)-sensors and machines are included – the analysis yields results at low levels of granularity (both time and equipment). This kind of analysis can help with the end-to-end supply chain planning processes, including capacity planning, order allocation, production scheduling, inventory planning and can even be made to extend to suppliers, customers and logistics partners.
Process parameter optimization
In cases of complex manufacturing operations, especially where a number of process parameters affect productivity, manufacturers can use real-time data from the plant floor to optimize such parameters to improve yield, quality and operational efficiency. These solutions are common in the chemical process as well as semiconductor manufacturing industries, but lend themselves to use in other industries that incorporate process parameter controls.
Condition monitoring and predictive maintenance
While most organizations focus on minimizing unplanned downtime by implementing planned preventive maintenance schedules, these are expensive and time consuming, not to mention the risk of failures and unplanned downtime due to reliability issues in the hundreds of machine parts involved. Leading manufacturing organizations have implemented condition monitoring and predictive maintenance solutions to overcome such issues. With the availability of huge amounts of data from PLCs, sensors and machines directly, it is now possible to analyze this data and predict failure to a level of accuracy that allows predictive maintenance to be completely automated with minimal human intervention in decision making. These have resulted in improved equipment efficiencies and lower quality costs.
Material flow analysis (identification of bottlenecks, non-value added flows)
Most plant floors and warehouses deal with millions of pallets of raw materials, work-in-process and finished goods that are moved around the plant floor and warehouses using material handling equipment. Such movement often leads to bottlenecks that can result in downtimes due to machines being starved of inputs. In many cases, such movement is not really necessary for the operation and adds no value to the product. Location based data from these pallets as well as material handling equipment can be analyzed to find bottlenecks, which can then be targeted to improve operational efficiencies on the plant floor
Lean / six sigma initiatives
Most manufacturers now have an extreme focus on operating costs, yields and quality and have implemented lead / six sigma initiatives to identify and eliminate waste in any form from the plant floor. Such initiatives rely heavily on data based analysis and decision making to identify improvement actions. Data from the plant floor, whether it is from the stationary sources (machines, PLCs, sensors) or mobile sources (materials, material handling equipment, people), is key to support these initiatives.
How can Cisco help your manufacturing organization improve efficiencies and gain valuable insight through data? Visit our solutions page to find out more and share your thoughts with us in the comments section below. Stayed tuned for Part Two of this series where I’ll detail practical applications of data within the manufacturing environment.