Hybrid Loader Automatic Shift Strategy Based on Neural Network

Hybrid loader 's comprehensive performance mainly depends on the performance of hydraulic torque converter during its driving and working. Hybrid loader and hydraulic torque converter are taken for the research objects. The primary characteristic curve of hydraulic torque converter and the traction curve of hybrid loader are acquired by analyzing the characteristic parameters of hydraulic torque converter, the characteristic parameters of engine, the characteristic parameters of battery pack and geometric parameters of hybrid loader. The gear shift curves based on the best energy saving performance and the best power performance are acquired respectively with the opening of throttle,the speed of pump wheel and the speed of turbine as parameters. Then the two curves are combined to get the comprehensive gear shift curve. Radical basis function( RBF) neural network is applied to building the gear shift strategy to keep hybrid loader with the best power performance and energy saving performance. The experimental bench is set up for experimental verification. It proves that both of the power performance and energy saving performance of hybrid loader are improved effectively by using the automatic shift strategy.

STUDY ON SHIFT SCHEDULE AND SIMULATION OF AUTOMATIC TRANSMISSION

From the point of view of saving energy, a new shift schedule and auto-controlling strategy for automatic transmission are proposed. In order to verify this shift schedule, a simulation program using a software package of Matlab/ Simulink is developed. The simulation results show the shift schedule is correct. This shift schedule has enriched the theory of vehicle automatic maneuvering and will improve the efficiency of hydrodynanic drive system of the vehicle.

ASCS Online Fault Detection and Isolation Based on an Improved MPCA

Multi-way principal component analysis（MPCA）has received considerable attention and been widely used in process monitoring.A traditional MPCA algorithm unfolds multiple batches of historical data into a two-dimensional matrix and cut the matrix along the time axis to form subspaces.However,low efficiency of subspaces and difficult fault isolation are the common disadvantages for the principal component model.This paper presents a new subspace construction method based on kernel density estimation function that can effectively reduce the storage amount of the subspace information.The MPCA model and the knowledge base are built based on the new subspace.Then,fault detection and isolation with the squared prediction error（SPE）statistic and the Hotelling（T2）statistic are also realized in process monitoring.When a fault occurs,fault isolation based on the SPE statistic is achieved by residual contribution analysis of different variables.For fault isolation of subspace based on the T2 statistic,the relationship between the statistic indicator and state variables is constructed,and the constraint conditions are presented to check the validity of fault isolation.Then,to improve the robustness of fault isolation to unexpected disturbances,the statistic method is adopted to set the relation between single subspace and multiple subspaces to increase the corrective rate of fault isolation.Finally fault detection and isolation based on the improved MPCA is used to monitor the automatic shift control system（ASCS）to prove the correctness and effectiveness of the algorithm.The research proposes a new subspace construction method to reduce the required storage capacity and to prove the robustness of the principal component model,and sets the relationship between the state variables and fault detection indicators for fault isolation.