Accurate prediction of the throttle value and state for wheel loaders can help to achieve autonomous operation, thereby reducing the cost and accident rate. However, existing methods based on a physical model cannot accurately reflect the operator’s driving habits and the interaction between wheel loaders and the environment. In this paper, a deep-learning-based prediction model is developed to predict the throttle value and state for wheel loaders by learning from driving data. Multiple long–short-term memory (LSTM) networks are used to extract the temporal features of different stages during the operation of the wheel loader. Two backward-propagation neural networks (BPNNs), which use the temporal feature extracted by LSTM as the input, are designed to output the final prediction results of throttle value and state, respectively. The proposed prediction model is trained and tested using the data from two different conditions. The end-to-end LSTM prediction model and BPNNs are used as benchmark models. The results indicate that the proposed prediction model has good prediction accuracy and adaptability. Furthermore, the relationship between the prediction performance and signal sampling frequency is also studied. The proposed prediction method that combines driving data and deep learning can make the throttle action conform to the decisions of an experienced operator, providing technical support for the autonomous operation of construction machinery.

The torque extrapolation of the excavator internal combustion engine (ICE) is unknown and challenging. In this paper, an extrapolation framework for ICE torque of excavator is proposed. Data pre-processing, distribution estimation, load extrapolation, and damage evaluation are included in the framework. In estimating measurements, bivariate diffusion-based kernel density estimation is used to obtain the probability density. The cumulative cycle frequency and pseudo damage are compared with the results obtained by the other extrapolation methods. The results show that the proposed method can realize reasonable extrapolation. This extrapolation process can provide a reference for other engineering equipment in cyclic operation.

The load spectrum of rotary drilling rig’s drill pipe is used for drill pipe design, simulated fatigue testing, and reliability assessment. However, the proper extrapolation of the drill pipe double load is challenging, especially to meet the requirements of both load sequence and load strengthening. In this paper, an extrapolation technique for a double load of drill pipe is proposed. The time sequence rainflow counting technique is proposed to keep the torque and pressure sequence. Meanwhile, the individual distributions of the loads are accurately estimated. Finally, the torque and pressure are simulated and extrapolated by the percentile extrapolation method. The results show that the proposed extrapolation method for maintaining the load sequence enriches the dynamics and diversity of the loads while ensuring the load sequence.