Multisensor information-based adaptive control method for cutting head speed of roadheader

Wang, Pengjiang; Yang, Sixu; Zong, Kai; Fu, Shichen; Wu, Miao

doi:10.1177/0954406220952494

Cited by 6 publications

(4 citation statements)

References 24 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the designed BP neural network prediction controller, the selected training function is Levenberg-Marquardt, the training algorithm is trainlm, the activation function of the hidden layer is the logarithmic sigmoid activation function logsig, and the activation function of the output layer is the linear activation function purelin. The target error of training is set as 3 1 10 − × , which is far higher than the requirement of cutting control accuracy in engineering [19], and the maximum number of iterations is set to 1000 times.…”

Section: Load Identification Methods Of Cutting Head Based On Trainin...mentioning

confidence: 99%

Non-Uniform Input-Based Adaptive Growing Neural Gas for Unstructured Environment Map Construction

Wang

Ren

2022

Applied Sciences

Self Cite

View full text Add to dashboard Cite

The research and development of special robots such as excavation robots is an important way to achieve safe and efficient production in coal mines. Affected by the unstructured environment such as complex working conditions and unsteady factor disturbances, the real-time construction of section environment maps that can accurately describe the environment and facilitate trajectory planning and decision making has become a key scientific problem to be solved as soon as possible. Therefore, non-uniform input based adaptive growing neural gas for unstructured environment map construction has been proposed. Considering complex load identification, real-time location identification, and the types of unsteady disturbance factors and working conditions, a set of environment identification models has been established based on a large amount of underground measured data training. These models can express whether the section environment has changed, as well as the type and magnitude of the change, to realize the overall knowledge extraction and parametric representation of the unstructured environment. Then, in order to solve the problems of inaccurate topology, excessive aging of connecting edges, and excessive deletion of nodes in non-uniform input environment, an adaptive growing neural gas algorithm based on non-uniform input environment (AGNG-NU) is proposed. Featured by a dynamic response deletion mechanism and adaptive adjustment mechanism of neuron parameters, the generated nodes and their topology can be dynamically adjusted according to the density of regional sample points. Several sets of non-uniform input environments are set to test the algorithm. The experimental results show that the topological maps established by AGNG-NU express clearer environmental information and, at the same time, the accuracy and distribution are improved by 8% and 15%, respectively, compared with the basic GNG algorithm. The accuracy and the distribution have also been significantly improved compared with other common SOM and GCS algorithms.

show abstract

Section: Load Identification Methods Of Cutting Head Based On Trainin...mentioning

confidence: 99%

Non-Uniform Input-Based Adaptive Growing Neural Gas for Unstructured Environment Map Construction

Wang

Ren

2022

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…[11][12][13] Adaptive control methods ensured the system control accuracy under changeful operating conditions. [14][15][16] However, the performance limit of the hardware limits further enhancement of the system performance.…”

Section: Introductionmentioning

confidence: 99%

Flow-reduced double valve actuation for improving the dynamic performance of electro-hydraulic servo drive

Xie

Chen

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Due to the negative correlation between the frequency response and the rated flow of the servo valve, there remains challenge to achieve high dynamic response of large-flow servo valve-controlled hydraulic systems under extreme operating conditions. Although the effective bandwidth of such system can be extended via various control methods, the inherent performance limit of hardware limits further improvement of the system dynamic response. In this paper, a flow-reduced double valve actuation strategy is proposed to improve the performance of electro-hydraulic servo drives. By reducing the actually used flow, the frequency response of the servo valve is enhanced due to the decreased hydraulic spring force and transient flow force acting on the spool. Two flow-reduced servo valves are adopted in parallel to meet large flow along with the improved dynamic performance. Simulation research is conducted and a servo valve-controlled shaking table with a specially designed valve block is used for experimental validation. Simulation and experimental results prove that the proposed strategy possesses better dynamic performance than the conventional single valve actuation.

show abstract

“…Gao et al [14] used the power supply panel as the controller to realize the automatic forming of the roadway section and the automatic traction and the speed regulation of the cutting arm. Wang et al [15] proposed a control method to improve the speed of roadheader by using multi-sensor information fusion and solved the problem of low efficiency of roadheader by classifying the speed of cutting head to adapt to the change of coal and rock hardness. Zhao et al [16] took the current as the control object and adjusted the motor speed by setting the rated current and using vector control to make the cutting motor operate at constant power.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Cutting Control for Roadheaders Based on Performance Optimization

Liu

et al. 2021

Machines

View full text Add to dashboard Cite

Aiming at addressing the problems of high specific energy consumption for cutting and slow response to the change of hardness in the control of existing mining roadheaders, an adaptive variable speed cutting control method based on cutting performance optimization is proposed by analyzing the working principle of roadheaders. Firstly, cylinder pressure and motor current are invoked as the criteria to judge load changes. Particle swarm optimization is utilized to optimize the cutting parameters under different impedance. Then, the relation between cutting speed, motor current and cylinder pressure is established by using fuzzy neural network to train cutting parameters and identification parameters under different conditions. Finally, the vector control of motor and electro-hydraulic servo valve is used to control the cutting speed. The results show that the cutting unit can adapt to different load signals and always keep the roadheader in the optimal working state. The rotation speed regulation of the cutting head reaches the stable state after 0.05 s, with the overshoot of 1.42%. The swing speed regulation of the cutting head reaches the stable state after 1 s, with the overshoot of 5.3%. Conclusions provide a basis for improving the cutting efficiency and prolonging the working life of the roadheader.

show abstract

Multisensor information-based adaptive control method for cutting head speed of roadheader

Cited by 6 publications

References 24 publications

Non-Uniform Input-Based Adaptive Growing Neural Gas for Unstructured Environment Map Construction

Non-Uniform Input-Based Adaptive Growing Neural Gas for Unstructured Environment Map Construction

Flow-reduced double valve actuation for improving the dynamic performance of electro-hydraulic servo drive

Adaptive Cutting Control for Roadheaders Based on Performance Optimization

Contact Info

Product

Resources

About