BP neural network based continuous objects distribution detection in WSNs

A 10 kV distribution network is a crucial piece of infrastructure to guarantee enterprises’ and households’ access to electricity. Stripping cables is one of many power grid maintenance procedures that are now quickly expanding. However, typical cable-stripping procedures are manual and harmful to workers. Although numerous automated solutions for grid maintenance have been created, none of them focus on cable stripping, and most of them have large dimensions to guarantee multi-functions. In this paper, a new cable-stripping robot for the 10 kV power system is introduced. The design of a live working cable-stripping robot that is appropriate for installing insulating rods is introduced, taking into account the working environment of 10 kV overhead lines and the structural characteristics of overhead cables. The robot is managed by an auxiliary remote control device. A cascade PID control technology based on the back propagation neural network (BPNN) method was developed, as the stripper robot’s whole system is nonlinear and the traditional PID controller lacked robustness and adaptability in complex circumstances. To validate the structural feasibility of the cable-stripping robot, as well as the working stability and adaptability of the BPNN–PID controller, a 95 mm2 cable-stripping experiment are carried out. A comparison of the BPNN–PID controller with the traditional PID method revealed that the BPNN–PID controller has a greater capacity for speed tracking and system stability. This robot demonstrated its ability to replace manual stripping procedures and will be used for practical routine power maintenance.

show abstract

“…In summary, w hi first affects β h , then affects y h , and finally affects Ek [ 15 ]. Therefore, the weight correction Δ w hi ( n ) is

…”

Section: A Cascade Bpnn–pid Controller For the Cable-stripping Robotmentioning

confidence: 99%

A Cascade BP Neural Network Tuned PID Controller for a High-Voltage Cable-Stripping Robot

Zhong

Wang

et al. 2023

Micromachines

View full text Add to dashboard Cite

show abstract

“…For example, for a polysemous word W(w 1 , w 2 , w 3 ), there are 20 example sentences about w 1 , 30 example sentences about w 2 , and 50 example sentences about w 3 . In the process of training corpus, we must choose the same example sentences to train, that is, 20 sentences of each choice to train, in order to prevent the inconsistency between meanings leading to the instability of the model [25].…”

Section: The Process Of Training Modelsmentioning

confidence: 99%

Feature Input Symmetry Algorithm of Multi-Modal Natural Language Library Based on BP Neural Network

Lin

2019

Symmetry

View full text Add to dashboard Cite

When using traditional knowledge retrieval algorithms to analyze whether the feature input of words in multi-modal natural language library is symmetrical, the symmetry of words cannot be analyzed, resulting in inaccurate analysis results. A feature input symmetric algorithm of multi-modal natural language library based on BP (back propagation) neural network is proposed in this paper. A Chinese abstract generation method based on multi-modal neural network is used to extract Chinese abstracts from images in multi-modal natural language library. The Word Sense Disambiguation (WSD) Model is constructed by the BP neural network. After the word or text disambiguation is performed on the Chinese abstract in the multi-modal natural language library, the feature input symmetry problem in the multi-modal natural language library is analyzed according to the sentence similarity. The experimental results show that the proposed algorithm can effectively analyze the eigenvalue symmetry problem of the multi-modal natural language library. The maximum error rate of the analysis algorithm is 7%, the growth rate of the analysis speed is up to 50%, and the average analysis time is 540.56 s. It has the advantages of small error and high efficiency.

show abstract

“…For this reason, many people utilized it to improve the efficiency of information fusion. 15,16 Therefore, many information fusion technologies based on neural networks are widely used. [17][18][19][20] The LSTM network is a kind of time RNN.…”

Section: Related Workmentioning

confidence: 99%

Sparse long short-term memory for information fusion in wireless sensor networks

Zhou

Zhang

Xie

et al. 2019

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Wireless sensor networks are designed to perceive, gather, and process external environmental information and send it to the observer. However, the transmission of mass information is a challenge to the sensor nodes. To address this challenge, information fusion technologies are proposed to reduce mass redundant data. However, these techniques rarely consider the historical information, and thereby often encounter the difficulty of low prediction accuracy. In order to solve this difficulty, we propose a novel information fusion approach for the cluster heads. The proposed approach is based on time-recurrent neural network, called sparse long short-term memory, which is derived from the long shortterm memory network. The sparse long short-term memory uses sparse matrix to reduce the dimension for a highdimensional coefficient matrix. Therefore, the computational cost of the fusion algorithm is reduced in wireless sensor networks. The simulation results show that the sparse long short-term memory algorithm increases the survival number of sensor nodes in wireless sensor networks. Furthermore, the prediction accuracy of the sparse long short-term memory algorithm is almost the same as the other comparison algorithms.

show abstract

BP neural network based continuous objects distribution detection in WSNs

Cited by 20 publications

References 16 publications

A Cascade BP Neural Network Tuned PID Controller for a High-Voltage Cable-Stripping Robot

A Cascade BP Neural Network Tuned PID Controller for a High-Voltage Cable-Stripping Robot

Feature Input Symmetry Algorithm of Multi-Modal Natural Language Library Based on BP Neural Network

Sparse long short-term memory for information fusion in wireless sensor networks

Contact Info

Product

Resources

About