A Study on Extreme Learning Machine for Gasoline Engine Torque Prediction

Abstract

This research presents an extreme learning machine (ELM) based neural network modeling technique for gasoline engine torque prediction. The technique adopts a single-hidden layer feedforward neural network (SLFN) structure which has the potential to approximate any continuous function with high accuracy. To verify the robustness of this technique, over 3300 data points collected from a real-world gasoline engine are used to train, validate, and test the model. These data points cover a wide spectrum of normal engine operating conditions, with the engine speed from 1000 rpm to 4500 rpm, and the engine torque from idle to full load. The experiment results demonstrate that the model can predict the gasoline engine torque with high accuracy. Moreover, this research proposes a weight factor approach to further improve the prediction accuracy of the model in the desired data regions without modifying the input data set. The evaluation shows that the weight factor approach can reduce the overall prediction errors in the regions significantly. This feature is particularly useful in tuning the performance of the model when the significance of the individual data points varies, or when the distribution of the data points is imbalanced. In practice, the modeling approaches presented in this research will help reduce the engine test and verification time.

Multi-step prediction of automobile rear axle assembly torque based on adaptive time series data decomposition hybrid deep learning model

“…The model can run immediately on embedded hardware and realize stable torque control in electric bus applications. Weiying Zeng et al [25] proposed an engine torque prediction modeling technology based on extreme learning machine (ELM). This method performs regression fitting on more than 3300 torque data points collected.…”

Digital Twin-Driven Rear Axle Assembly Torque Prediction and Online Control

“…Mahdi Bagheripoor [ 19 ] used finite element simulation method to obtain process parameters, and used artificial intelligence methods to forecast the rolling force and torque of a hot rolling mill. Weiying Zeng [ 20 ] proposed a neural network engine torque method, by using a single hidden-layer neural network structure, and this method effectively improves the prediction accuracy. Zhang et al [ 21 ] extracted features from the shield machine torque feature data and uses a hybrid multi-model approach to predict torque.…”

A comparative study of driver torque demand prediction methods

“…Five driving cycles have been used for training and the other one for testing. In the study conducted by Zeng et al [19], a single-hidden layer feedforward neural network (SLFN) has been presented to predict gasoline engine output torque with high accuracy but using features computed on engine characteristics rather than driving profiles, such as engine speed, intake manifold pressure, barometric pressure, intake air. Also, stochastic approaches have been employed to predict torque demand.…”