Description
IS200VRTDH1DAC GE Steam Turbine System
Germany”s “Industry 4.0″ and the United States” “Industrial Internet” will
restructure the world”s industrial layout and economic structure, bringing different challenges and
opportunities to countries around the world. The State Council of China issued “Made in China 2025” as an action plan
for the first ten years of implementing the strategy of manufacturing a strong country, which will accelerate the integrated
development of IoT technology and manufacturing technology [1]. IoT collects data on machine operations, material usage
, facility logistics, etc., bringing transparency to operators. This transparency is brought about by the application of data analytics,
which refers to the use of statistical and machine learning methods to discover different data characteristics and patterns. Machine
learning technology is increasingly used in various manufacturing applications, such as predictive maintenance, test time reduction,
supply chain optimization, and process optimization, etc. [2-4]. The manufacturing process of enterprises has gradually developed from
the traditional “black box” model to the “multi-dimensional, transparent and ubiquitous perception” model [5].
1 Challenges facing manufacturing analysis
The goal of manufacturing analytics is to increase productivity by reducing costs without compromising quality:
(1) Reduce test time and calibration, including predicting test results and calibration parameters;
(2) Improve quality and reduce the cost of producing scrap (bad parts) by identifying the root causes of scrap and optimizing
the production line on its own;
(3) Reduce warranty costs, use quality testing and process data to predict field failures, and cross-value stream analysis;
(4) Increase throughput, benchmark across production lines and plants, improve first-pass rates, improve first-pass throughput,
and identify the cause of performance bottlenecks such as overall equipment effectiveness (OEE) or cycle time;
Reviews
There are no reviews yet.