本页翻译不是最新的。点击此处可查看最新英文版本。

Simulink 中的机器学习

使用 Simulink 扩展机器学习工作流

通过使用 Statistics and Machine Learning Toolbox™ 中包含的 Statistics and Machine Learning 模块库中的模块，在 Simulink® 模型中实现机器学习功能。此工具箱提供执行以下工作流的模块：

  • 使用分类预测或回归预测模块将经过训练的分类或回归模型对象导入 Simulink 中。

  • 在分类学习器或回归学习器中训练机器学习模型，并将模型导出到 Simulink。

  • 在 Simulink 中使用增量学习模块实时持续更新和监控机器学习模型中的漂移。

  • 在 Simulink 中使用 KNN Search 模块查找数据中的最近邻点以查询点并执行聚类分析。

  • 在 Simulink 中使用 Python 协同执行模块协同执行经过训练的 Python® 机器学习模型。

模块

全部展开

ClassificationECOC PredictClassify observations using error-correcting output codes (ECOC) classification model (自 R2023a 起)
ClassificationEnsemble PredictClassify observations using ensemble of decision trees (自 R2021a 起)
ClassificationKNN PredictClassify observations using nearest neighbor classification model (自 R2022b 起)
ClassificationLinear PredictClassify observations using linear classification model (自 R2023a 起)
ClassificationNaiveBayes PredictClassify observations using naive Bayes model (自 R2023b 起)
ClassificationNeuralNetwork PredictClassify observations using neural network classification model (自 R2021b 起)
ClassificationSVM PredictClassify observations using support vector machine (SVM) classifier for one-class and binary classification
ClassificationTree PredictClassify observations using decision tree classifier (自 R2021a 起)
ClassificationDiscriminant PredictClassify observations using discriminant analysis model (自 R2024a 起)
ClassificationKernel PredictClassify observations using Gaussian kernel classifier for binary classification (自 R2024b 起)
RegressionEnsemble PredictPredict responses using ensemble of decision trees for regression (自 R2021a 起)
RegressionGP PredictPredict responses using Gaussian process (GP) regression model (自 R2022a 起)
RegressionLinear Predict使用线性回归模型预测响应 (自 R2023a 起)
RegressionNeuralNetwork PredictPredict responses using neural network regression model (自 R2021b 起)
RegressionSVM Predict使用支持向量机 (SVM) 回归模型预测响应
RegressionTree Predict使用回归树模型预测响应 (自 R2021a 起)
RegressionKernel Predict Predict responses using Gaussian kernel regression model (自 R2024b 起)
IncrementalClassificationLinear PredictClassify observations using incremental linear classification model (自 R2023b 起)
IncrementalClassificationLinear FitFit incremental linear binary classification model (自 R2023b 起)
IncrementalRegressionLinear PredictPredict responses using incremental linear regression model (自 R2023b 起)
IncrementalRegressionLinear FitFit incremental linear regression model (自 R2023b 起)
IncrementalClassificationECOC FitFit incremental ECOC classification model (自 R2024a 起)
IncrementalClassificationECOC PredictClassify observations using incremental ECOC classification model (自 R2024a 起)
IncrementalClassificationKernel FitFit incremental kernel classification model (自 R2024b 起)
IncrementalClassificationKernel PredictClassify observations using incremental kernel classification model (自 R2024b 起)
IncrementalRegressionKernel FitFit incremental kernel regression model (自 R2024b 起)
IncrementalRegressionKernel PredictPredict responses using incremental kernel regression model (自 R2024b 起)
IncrementalClassificationNaiveBayes FitFit incremental naive Bayes classification model (自 R2025a 起)
IncrementalClassificationNaiveBayes PredictClassify observations using incremental naive Bayes classification model (自 R2025a 起)
Detect DriftUpdate drift detector states and drift status with new data (自 R2024b 起)
Per Observation LossPer observation regression or classification error of incremental model (自 R2025a 起)
Update MetricsUpdate performance metrics in incremental learning model given new data (自 R2023b 起)
KNN Search使用搜索器对象查找 k 最近邻 (自 R2023b 起)
Scikit-learn Model PredictPredict responses using pretrained Python scikit-learn model (自 R2024a 起)
Custom Python Model PredictPredict responses using pretrained custom Python model (自 R2024a 起)

主题

分类

回归

增量学习

增量学习模板

聚类分析和建立分类模型检测

Python 协同执行

将使用学习器 App 训练的模型导出到 Simulink

代码生成

相关信息

精选示例

Human Activity Recognition Simulink Model for Fixed-Point Deployment

Human Activity Recognition Simulink Model for Fixed-Point Deployment

Generate code from a classification Simulink model prepared for fixed-point deployment.

Human Activity Recognition Simulink Model for Smartphone Deployment

Human Activity Recognition Simulink Model for Smartphone Deployment

Generate code from a classification Simulink model prepared for deployment to a smartphone.

Identify Punch and Flex Hand Gestures Using Machine Learning Algorithm on Arduino Hardware

Identify Punch and Flex Hand Gestures Using Machine Learning Algorithm on Arduino Hardware

Use the Simulink® Support Package for Arduino® Hardware to identify punch and flex hand gestures using a machine learning algorithm. The example is deployed on an Arduino Nano 33 IoT hardware board that uses an onboard LSM6DS3 6DOF IMU sensor to identify the hand gestures. The output from the machine learning algorithm, after identifying whether a hand gesture is a punch or a flex, is transmitted to the serial port where 0 represents a punch and 1 represents a flex.

(Simulink)

Compress Machine Learning Model for Memory-Limited Hardware

Compress Machine Learning Model for Memory-Limited Hardware

Reduce model size by feature selection, constrained Bayesian optimization, and parameter quantization.