Automatic evaluation device, automatic evaluation method and computer program

An automatic evaluation method for a trained model modifying an operating condition of an industrial machine, comprising:

• receiving an upper limit, a lower limit and a dividing number for each of a plurality of defect inducing conditions inducing a defective product occurrence behavior;
• generating a plurality of defective conditions by combining values for each of the defect inducing conditions, the values being obtained based on an upper limit, a lower limit and a dividing number of each of the plurality of defect inducing conditions received, by dividing a numerical range between the upper limit and the lower limit by the dividing number;
• setting the generated defective conditions to the industrial machine;
• acquiring an operation result when the operating condition is modified by the trained model in a case where the industrial machine to which the defective conditions are set is operated;
• and
• generating an evaluation report of the trained model based on operation results obtained by setting each of the plurality of defective conditions to the industrial machine and operating the industrial machine a plurality of times for each of the defective conditions.

A non-transitory computer readable recording medium storing a computer program causing a computer to evaluate a trained model modifying an operating condition of an industrial machine, comprising:

• receiving an upper limit, a lower limit and a dividing number for each of a plurality of defect inducing conditions inducing a defective product occurrence behavior;
• generating a plurality of defective conditions by combining values for each of the defect inducing conditions, the values being obtained based on an upper limit, a lower limit and a dividing number of each of the plurality of defect inducing conditions received, by dividing a numerical range between the upper limit and the lower limit by the dividing number;
• setting the generated defective conditions to the industrial machine;
• acquiring an operation result when the operating condition is modified by the trained model in a case where the industrial machine to which the defective conditions are set is operated;
• and
• generating an evaluation report of the trained model based on operation results obtained by setting each of the plurality of defective conditions to the industrial machine and operating the industrial machine a plurality of times for each of the defective conditions.