Workpiece quality prediction model construction method and prediction method based on machine learning
A machine learning and quality prediction technology, applied in machine learning, forecasting, calculation models, etc., to achieve the effect of eliminating the need for data preprocessing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0042] A method for building a machine learning-based workpiece quality prediction model of the present invention comprises the following steps:
[0043] S100. Collect features of manufactured workpieces as training data, and preprocess the training data;
[0044] S200. Construct at least one polynomial feature based on the above collected features, and for each polynomial feature, calculate the distribution of the polynomial feature among different tags, and select a polynomial feature with obvious distribution difference;
[0045] S300. Composing training samples through the collected features and selected polynomial features, using the training samples as input, optimize the parameters of the constructed prediction model to obtain a trained prediction model, the prediction model is a machine learning decision tree model.
[0046] Among them, in step S100, features such as length and width of manufactured workpieces corresponding to different manufacturing times are collecte...
Embodiment 2
[0054] A kind of workpiece quality prediction method based on machine learning of the present invention comprises the following steps:
[0055] S100. Construct a prediction model through a method for constructing a workpiece quality prediction model based on machine learning as disclosed in Embodiment 1, and obtain a trained prediction model;
[0056] S200. Collect the characteristics of the workpiece to be tested as test data, and preprocess the test data;
[0057] S300. Construct at least one polynomial feature based on the above collected features, and for each polynomial feature, calculate the distribution of the polynomial feature among different tags, and select a polynomial feature with obvious distribution difference;
[0058] S400. Composing a test sample by using the collected features and the selected polynomial features, and inputting the test sample into the trained prediction model to obtain the probability corresponding to each label;
[0059] S500. Composing p...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More