This latest revolution in quality is supported by increasing levels of automation along with big data, improved analytics and sophisticated software. As an example of what these technologies can do, consider Yokogawa Electric Corporation’s Process Data Analytics, an application program that can detect a decline in quality or productivity at an early stage of the manufacturing process by analyzing process data, facility status information, operation history and other data.
Developing Process Data Analytics
Manufacturers face a growing need to stabilize the quality of the products coming off their production lines. Product quality is affected by factors such as fluctuations in the quality of raw materials and the aging of manufacturing facilities. Even when the raw materials supplied by different contractors vary in composition, the need to ensure high quality in the final product remains unchanged.
To improve quality in each production process and thereby improve the quality of their final products, manufacturers must analyze various types of data. The effectiveness of such analysis has largely depended on the knowledge and expertise of the workers at each production site.
As a solution to such challenges, Yokogawa began offering a process data analytical service to its customers in 2008. Based on the insights that Yokogawa engineers gained by providing this service to their customers, the company developed an analytical tool to improve its efficacy and thereby help its customers maintain and improve product quality.
This software makes use of the Mahalanobis Taguchi (MT) method, a pattern-recognition technique that is employed in multivariate analysis. The MT method is named after Dr. P.C. Mahalanobis, who introduced the Mahalanobis distance (a multivariate measurement scale based on the correlation among variables), and Dr. Genichi Taguchi, a key figure in the development of quality engineering.
Based on the distance between reference data and sample data, this method can quantitatively determine the deviation from the target data.
Features of Process Data Analytics
According to Yokogawa, Process Data Analytics will run on Windows PCs to analyze production operations using temperature, pressure, flow rate, liquid level and other process data as well as data on facility operations and equipment maintenance collected by a plant information management system (PIMS), DCS, or PLC.
While data from such systems must normally be converted to CSV format for use in another program, data from Yokogawa’s Exaquantum plant information management system can be used as is, without the need for file conversion.
Process Data Analytics will use the MT method for the analysis of multiple statistical variables. This will compare the collected data and accurately detect deviations from normal conditions. Any deviation will trigger a warning that quality may have deteriorated.
Key features of the software include:
- Early detection of abnormalities in production processes:
- By detecting changes in production process data, this software can spot quality and productivity issues at an early stage of the manufacturing process. Based on this information, measures can then be taken to bring production operations back to a normal condition and recover quality.
- Fail-proof quality inspection:
- By detecting changes in the data from production processes, this software can detect signs of deteriorating quality and thereby catch faults that might be overlooked in a conventional pre-shipment inspection.
- Extensible via integration with MATLAB (requires license):
- This software supports MATLAB, the widely used numerical analysis tool from MathWorks. Custom MATLAB calculations can be integrated within the Process Data Analytics software.
- AngleTry Associates’ proprietary technology
- A pattern-recognition technology licensed from AngleTry Associates makes this technology useful for consulting and systems construction.
The software is designed to facilitate production quality control in the oil, petrochemical, chemical, pulp and paper, iron and steel, pharmaceutical, food, automobile, glass, rubber, electronics and other industries. The software will be released for sale in March 2017.
For more information, visit the Yokogawa website.