6 March 2024 in IEEE Transactions on Power Electronics
This study improves the accuracy of junction temperature prediction, as the insulated gate bipolar transistor (IGBT) reliability is important for the safe operation of its working system due to junction temperature is limited in its actual performance and reliability. A model based on an improved sailfish optimization algorithm to optimize support vector machine (ISFO-SVM) is proposed to solve the problem that the junction temperature prediction accuracy is not high enough. The proposed algorithm is improved by adaptive nonlinear iterative factor, Le'vy flight and differential mutation strategy to optimize the support vector machine (SVM) internal parameters to predict junction temperature. The results indicate that ISFO-SVM performs better under the same evaluation indexes. The root mean squared error average value decreased by 67.189%, and the mean absolute percentage error average value decreased by 63.189%, compared with the sailfish optimization algorithm to optimize the SVM. The prediction error of ISFO-SVM is smaller and the error value is in the [−5 °C, 5 °C] range accounting for 98.270% of the total test samples. ISFO-SVM has a higher fitting degree than the actual junction temperature and the R2 has reached 99.660%. The model predicts the junction temperature of IGBT modules and provides scientific guidance for system reliability evaluation to maintain safe and stable operation effectively.
9 December 2022 in IEEE Transactions on Device and Materials Reliability
The insulated gate bipolar transformer (IGBT) is widely used in industry, aerospace, renewable energy and other fields, which requires high reliability. However, in the research field of IGBT health evaluation, there are still problems that the accuracy is not high enough and the reliability manager of IGBT cannot accurately grasp. In this study, an IGBT health status evaluation model based on improved krill herd optimized extreme learning machine (IKH-ELM) is proposed to accurately evaluate the health status of IGBT, provide guidance for timely replacement of components, thus reducing the failure probability and maintenance cost, and improving the system reliability. Firstly, the power cycle accelerated aging test, short pulse-high amplitude current test and thermal resistance measurement test are carried out to obtain the failure predictor parameters data of IGBT. Then, an IGBT health status classification method based on cloud model is proposed to make the health status assessment results more scientific. In addition, since the random selection of weights and thresholds of ELM affects the performance of the model, the krill herd algorithm is improved to optimize ELM for obtaining better prediction ability. Based on this, a prediction model based on IKH-ELM is established. Finally, the proposed model is proved to be more accurate and effective under the same experimental environment and the same index.
1 January 2024 in Journal of Renewable and Sustainable Energy
The reliability and safety of power systems heavily depend on accurate forecasting of new energy generation. However, the non-stationarity and randomness of new energy generation power increase forecasting difficulty. This paper aims to propose a short-term wind power forecasting method with strong characterization ability to accurately understand future new energy generation conditions so as to ensure power systems' reliability and safety. The required input variables for wind power forecasting are determined by the gray relational analysis method. An advanced marine predators algorithm is proposed by improving the marine predators algorithm to enhance convergence ability and probability of escaping local optimal solutions. The advanced marine predators algorithm optimizes support vector regression machine to address the issue of insufficient utilization of its forecasting performance due to the selection of parameter values based on personal experience in traditional methods. Finally, different wind power generation scenarios verify its effectiveness and universality. This study promotes the application of artificial intelligence technology for improving short-term wind power forecasting accuracy, thereby enhancing the reliability and safety level of power systems.
26 October 2023 in Measurement Science and Technology
As the use of renewable energy generation continues to grow, improving power conversion efficiency has become an urgent task. This study aims to propose a high-precision power module loss estimation method, with a focus on predicting the switching losses of insulated gate bipolar transistor (IGBT) modules, which is crucial for the reliability assessment of IGBT modules. The main objective of this study is to establish a high-precision predictive model for IGBT module switching losses to enhance the reliability and efficiency of these devices. Firstly, a dynamic characteristic test platform was established to acquire relevant data for in-depth analysis of IGBT behavior. Secondly, given the excellent performance of support vector machine (SVM) in handling both strong and small-sized datasets, SVM was chosen as the foundational model for high-precision switching loss estimation. Subsequently, an enhanced marine predatory algorithm (EMPA), known for its superior convergence precision and speed, was introduced to optimize the random parameters of SVM. Finally, a method based on the optimized EMPA-SVM was constructed for predicting IGBT switching power losses. The proposed approach was validated using dynamic characteristic test data. And it indicated that the predictive model achieved the value of R 2 exceeding 99.8% for switching losses. Additionally, the mean absolute error and root mean square error metrics of EMPA-SVM model outperformed other models. Therefore, the research results unambiguously demonstrate the significant benefits of accurately predicting IGBT switching losses in enhancing device performance.