A precision-grinding process could save U.S. companies $1 billion annually in manufacturing costs
, say researchers at Purdue University. “Precision grinding is an art that relies heavily on the experience and knowledge of employees who have been in the business for years,” says Yung Shin, a Purdue mechanical engineering professor. “The problem is that many factories don't have enough of these experienced people, so many grinding processes run under sub-optimal conditions,” he adds.
The intelligent system uses data collected by various sensors as a part is being ground. Advanced software implementing control techniques such as neural networks and genetic algorithms will operate CNC grinding machines. The sensors collect information about details such as forces on bearings, speed, vibration, and temperatures during various parts of the process. “We capture that information in the software to establish a database that will set the machine to optimal operating conditions,” says Shin. He adds that it will be a challenge to transfer the method from the lab to large-scale industrial settings.
Purdue University is teaming up with industrial partners to develop the grinding process. TechSolve Inc., Cincinnati, is leading the team of industrial partners in a three-year, $6 million project funded through the National Institute of Standards and Technology's Advanced Technology Program.