Gearbox oil temperature is one of the important indicators for gearbox condition monitoring and faults early warning. Accurately predicting the gearbox oil temperature change trend can maintain the gearbox in advance and ensure the safety and reliability of the wind turbine gearbox. The purpose of this article is to analyze the supervisory control and data acquisition (SCADA) data in wind turbines. A method based on multi-input improved ant lion optimization and support vector regression (M-IALO-SVR) proposed, which can accurately predict the gearbox oil temperature. The prediction method is compared with back propagation neural network (BPNN) and ALO-SVR methods to verify the effectiveness of the M-IALO-SVR method. To further analyze the prediction results, the 95% confidence interval processing is performed on the residuals of the prediction model, and then the trends of the mean and standard deviation of the moving window residuals are calculated. Testing SCADA data from a wind farm in northeast China, the test results show that when the gearbox is operating normally, the predicted value of the gearbox oil temperature follows the measured value very well. When the gearbox operates abnormally, its temperature deviates from the normal range, and the statistical characteristics of the residuals also change. According to the trend of the residuals statistical characteristics, the abnormal state of the gearbox can be found in time.

中文翻译：

---

基于多输入支持向量回归和改进蚁狮优化的风电齿轮箱故障预警

变速箱油温是变速箱状态监测和故障预警的重要指标之一。准确预测齿轮箱油温变化趋势，可以提前维护齿轮箱，确保风电齿轮箱安全可靠。本文的目的是分析风力涡轮机中的监控和数据采集 (SCADA) 数据。提出了一种基于多输入改进蚁狮优化和支持向量回归的方法（M-IALO-SVR），可以准确预测变速箱油温。将预测方法与反向传播神经网络（BPNN）和ALO-SVR方法进行对比，验证M-IALO-SVR方法的有效性。为了进一步分析预测结果，对预测模型的残差进行95%置信区间处理，然后计算移动窗口残差的均值和标准差的趋势。对东北某风电场的SCADA数据进行测试，测试结果表明，在齿轮箱正常运行时，齿轮箱油温预测值与实测值吻合较好。当齿轮箱运行异常时，其温度偏离正常范围，残差的统计特性也发生变化。根据残差统计特征的趋势，可以及时发现齿轮箱的异常状态。测试结果表明，在齿轮箱正常运行时，齿轮箱油温预测值与实测值吻合较好。当齿轮箱运行异常时，其温度偏离正常范围，残差的统计特性也发生变化。根据残差统计特征的趋势，可以及时发现齿轮箱的异常状态。测试结果表明，在变速箱正常运行时，变速箱油温预测值与实测值吻合较好。当齿轮箱运行异常时，其温度偏离正常范围，残差的统计特性也发生变化。根据残差统计特征的趋势，可以及时发现齿轮箱的异常状态。