Ashland firm predicts machine failures using web data
Companies who use Internet of things data to predict machine failures can cut costs by reducing inventory stock and improving their ability to meet service levels, according to the results of a research project between Ashland-based OnProcess Technology and the Massachusetts Institute of Technology.
The project, announced Tuesday, found a proactive use of machine data can lead to better inventory planning and result in higher service levels. OnProcess Technology teamed up with MIT’s Supply Chain Management Program to carry out the research -- the first to analyze how connected machine data affects inventory planning and parts forecasting.
“Companies tend to overstock inventory so that when customers’ products break down, they have replacement parts readily available. But purchasing and storing all that extra safety stock is very costly,” said Mike Wooden, CEO of OnProcess Technology, in a press release. “With the proliferation of connected products, we saw an opportunity to analyze each product’s machine signals to predict when components may fail and, thus, develop a more sophisticated forecasting model.”
Working off the traditional mathematical model used in supply chain, MIT students and staff developed a model that incorporates failure predictability, and found that even machine-failure predictability tests that seem poor can reduce inventory levels significantly. Tests can also be used to signify part demands, leading to improved service levels.
The machine-failure analysis is one part of the joint research effort between OnProcess and MIT. The hope is that the joint Internet of things research could lead to a number of solutions, including shortened time to fix customer issues, proactive placement of inventory, and product improvements.
WBJ Web Partners
Most Recent
Most Recent
0 Comments