Method and apparatus for configuring processing parameters of production equipment, and computer-readable medium

A workpiece data processing apparatus, comprising:

• at least one memory to store computer readable code;
• and
• at least one processor to execute the computer readable code stored in the at least one memory to perform at least:
• acquiring processing condition data, a quality attribute value and quality inspection result data of each workpiece of multiple workpieces processed by production equipment, the processing condition data of one workpiece including a processing parameter used by the production equipment when processing the workpiece and ambient condition data of the production equipment when processing the workpiece;
• determining a first relationship between the quality attribute value of the workpiece processed by the production equipment and the ambient condition data of the production equipment when processing the workpiece and the processing parameter of the production equipment, based on the processing condition data and the quality attribute value of each workpiece of the multiple workpieces;
• and
• determining a second relationship between the quality inspection result data and quality attribute value of the workpiece processed by the production equipment, based on the quality attribute value and the quality inspection result data of each workpiece of the multiple workpieces, wherein the at least one processor is further configured to execute the computer readable code stored in the at least one memory to perform:
• randomly generating a set of processing parameters of the production equipment for the ambient condition data;
• determining, for each element in the set and based on the given ambient condition data, the element and the first relationship, a quality attribute value of each second simulated workpiece of multiple second simulated workpieces processed based upon the processing parameter represented by the element;
• determining, for each element in the set and for each second simulated workpiece of the multiple second simulated workpieces and based on the second relationship and the quality attribute value of the second simulated workpiece determined, quality inspection result data of the second simulated workpiece;
• compiling, for each element in the set, statistics of a quality inspection pass rate according to the quality inspection result data of each of the multiple second simulated workpieces determined;
• repeating a process until a condition is met, the condition including a number of iterations reaching a maximum number of iterations or a calculated quality inspection pass rate of the workpiece processed by the production equipment reaching a pass rate threshold, the process including:
• adding a new element to the set, so that an expected value of the quality inspection pass rate obtained statistically based upon the new element has a relatively largest increase compared with the maximum value of the quality inspection pass rate statistically obtained previously,
• determining, for the new element added to the set and based on the ambient condition data, the new element and the first relationship, a quality attribute value of each third simulated workpiece of multiple third simulated workpieces processed based upon the processing parameter represented by the new element,
• determining, for the new element added to the set and for each third simulated workpiece of the multiple third simulated workpieces and based on the second relationship and the quality attribute values of the multiple third simulated workpieces determined, quality inspection result data of each third simulated workpiece of the multiple third simulated workpieces, and
• compiling, for the new element added to the set, statistics of the quality inspection pass rate according to the quality inspection result data determined of each third simulated workpiece of the multiple third simulated workpieces;
• and
• determining the element corresponding to a maximum value of all quality inspection pass rates obtained statistically as the optimal value of the processing parameter of the production equipment for the ambient condition data, wherein when determining the first relationship, the at least one processor is configured to execute the computer readable code stored in the at least one memory to perform:
• using the processing condition data of each workpiece of the multiple workpieces as an input vector of a generator in a Conditional Generative Adversarial Net (CGAN) model;
• using the processing condition data of each workpiece of the multiple workpieces as an input vector of a discriminator of the CGAN model;
• using the quality attribute value of each workpiece of the multiple workpieces or an output vector of the generator of the CGAN model as another input vector of the discriminator in the CGAN model;
• and
• training the CGAN model, and use the generator of the CGAN model obtained by training as the first relationship.

A processing parameter setting method, comprising:

• generating, for ambient condition data, a set of processing parameters of production equipment;
• determining, for each element in the set and based on the ambient condition data, an element and a first relationship, a quality attribute value of each second simulated workpiece of multiple second simulated workpieces processed based upon a processing parameter, of the set of processing parameters, represented by the element, wherein the first relationship is a relationship between the quality attribute value of a workpiece processed by the production equipment and the ambient condition data of the production equipment when processing the workpiece and the processing parameter of the production equipment;
• determining, for each element in the set, for each second simulated workpiece of the multiple second simulated workpieces and based on a second relationship and the quality attribute value of the second simulated workpiece determined, quality inspection result data of the second simulated workpiece, wherein the second relationship is a relationship between the quality inspection result data and quality attribute value of the workpiece processed by the production equipment;
• compiling, for each element in the set, statistics of a quality inspection pass rate according to the quality inspection result data determined of each second simulated workpiece of the multiple second simulated workpieces;
• repeating a process until a preset condition is met, the preset condition including a number of iterations reaching a maximum number of iterations or a calculated quality inspection pass rate of the workpiece processed by the production equipment reaching a pass rate threshold, the process including:
• adding a new element to the set, so that an expected value of the quality inspection pass rate obtained statistically based upon the new element has the largest increase compared with a maximum value of the quality inspection pass rate statistically obtained previously,
• determining, for the new element added to the set and based on the ambient condition data, the new element and the first relationship, a quality attribute value of each third simulated workpiece of multiple third simulated workpieces processed based upon the processing parameter represented by the new element,
• determining for the new element added to the set, for each third simulated workpiece of the multiple third simulated workpieces, and based on the second relationship and the quality attribute values of the multiple third simulated workpieces determined, quality inspection result data of each third simulated workpiece of the multiple third simulated workpieces,
• compiling for the new element added to the set, statistics of a quality inspection pass rate according to the quality inspection result data determined of each third simulated workpiece of the multiple third simulated workpieces;
• and
• determining the element corresponding to a maximum value of all quality inspection pass rates obtained statistically as an optimal value of the processing parameter of the production equipment for the ambient condition data, wherein the determining of the first relationship comprises:
• using the processing condition data of each second simulated workpiece of the multiple second simulated workpieces as an input vector of a generator in a Conditional Generative Adversarial Net (CGAN) model;
• using the processing condition data of each second simulated workpiece of the multiple second simulated workpieces as an input vector of a discriminator of the CGAN model;
• using the quality attribute value of each second simulated workpiece of the multiple second simulated workpieces or an output vector of the generator of the CGAN model as another input vector of the discriminator in the CGAN model;
• and
• training the CGAN model, and using the generator of the CGAN model obtained by training as the first relationship.