Optimized BP neural network for Dissolved Oxygen prediction

Wu, Jian; Li, Zhenbo; Zhu, Ling; Li, Guangyao; Niu, Bingshan; Peng, Fang-Le

doi:10.1016/j.ifacol.2018.08.132

Cited by 31 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A BP neural network is an artificial neural network based on a back-propagation learning algorithm, which is the main component of an artificial neural network [24]. Most of the existing BP neural network models are variations or improvements of the standard BP neural network model.…”

Section: Load Predicting Modelmentioning

confidence: 99%

Performance Degradation Analysis and Optimization of the Stepless Capacity Regulation System for Reciprocating Compressors

et al. 2020

View full text Add to dashboard Cite

The regulating performance degradation of the stepless capacity regulation system for reciprocating compressors occurs frequently in long-term operations. It affects the safe and stable operation of the compressor seriously. The degradation mechanisms in a stepless capacity regulation system are mainly caused by valve leakage, degeneration of the reset spring of the unloader, and (or) deviation of the solenoid valve’s characteristic parameters. In this study, to research the system performance degradation mechanisms and the influence of control parameters on system behavior, a multi-subsystem mathematics model which integrates compressor, gas pipeline, buffer tank, and actuator was built. In order to calculate the rate of degradation, a load prediction model based on a modified back-propagation neural network was established. The rate of degradation can be calculated using the predicted results. In order to optimize system regulation performance, a degradation-based optimization framework was developed which determines optimum control parameter compensation to achieve a minimum degradation rate. In addition, in order to avoid over-compensation, an adaptive control parameter compensation optimization method was adopted. According to the deviation between the given load and the prediction load, the control parameter compensations are obtained adaptively. Finally, two optimization experiments are carried out to show the effectiveness of the developed framework. The optimization results illustrate the degradation rate of the system gradually returning to normal during 60s without any over-compensation.

show abstract

Section: Load Predicting Modelmentioning

confidence: 99%

Performance Degradation Analysis and Optimization of the Stepless Capacity Regulation System for Reciprocating Compressors

et al. 2020

View full text Add to dashboard Cite

show abstract

“…These parameters include water quality parameters and meteorological parameters. Many studies have been conducted at present [14][15][16][17][18][19][20][21][22][23][24].…”

Section: B Multi-parameter Predictionmentioning

confidence: 99%

“…Yu et al [16] developed a new hybrid dissolved oxygen content forecasting model based on the radial basis function neural networks (RBFNN) data fusion method and least squares support vector machine (LSSVM) with an optimal improved particle swarm optimization (IPSO). Wu et al [17] established a new model of dissolved oxygen prediction based on sliding window, particle swarm optimization (PSO) and BP neural network. A dissolved oxygen prediction model based on fuzzy neural networks is proposed in [18].…”

Section: B Multi-parameter Predictionmentioning

confidence: 99%

An Enhanced Extreme Learning Machine for Dissolved Oxygen Prediction in Wireless Sensor Networks

Kuang¹,

Shi

Hua³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Water quality monitoring using Wireless Sensor Networks (WSNs) is essential in aquaculture water quality management. In the field of water quality monitoring, dissolved oxygen (DO) is a key parameter, and its prediction can provide decision support for aquaculture production, thereby reducing farming risk. However, it is difficult to build a precise prediction model, and existing methods of DO prediction neglect the importance of analyzing DO content. To address this problem, this study proposes a hybrid DO prediction model, named KIG-ELM, which is composed of K-means, improved genetic algorithm (IGA), and extreme learning machine (ELM). This model is based on edge computing architecture, in which data acquisition, processing and dissolved oxygen prediction are distributed in sensing nodes, routing nodes and server respectively. Sensing technique and clustering operation are applied in the process of data acquisition and processing. Meanwhile, an optimized extreme learning machine is implemented for DO prediction. We evaluate the efficiency and accuracy of proposed prediction approach in a practical aquaculture on massive water quality data. Experimental results show that the hybrid model achieves significant prediction results and can meet the needs of practical production and management.

show abstract

“…It is a multilayer feed‐forward neural network trained by the error BP algorithm. BP is a typical neural network model because of its excellent ability in arbitrary complex pattern classification and multidimensional function mapping, as well as its mature training method [29, 30]. The BP neural network algorithm repeats two phases: forward propagation and BP.…”

Section: Selection Of Pss Base Types Using a Knowledge‐based Annmentioning

confidence: 99%

Base types selection of PSS based on a priori algorithm and knowledge‐based ANN

Zhang

Chai

Liu

et al. 2019

IET Collaborative Intelligent Manufacturing

View full text Add to dashboard Cite

Manufacturers tend to bundle a product with its related services as a product service system (PSS), to create more values for customers and gain competitive advantages for themselves. Configuration design is the key process of PSS development. Configuring a PSS involves selecting and combining appropriate product and service components, to satisfy individual customer requirements. This study studies the mapping relationship between customer requirement attributes and PSS base types in PSS for CNC machine tools, which provides a great reference value for engineers in configuration design. Owing to the high complexity and non‐linearity between customer requirement and product, an integrated intelligent learning method based on a priori algorithm and knowledge‐based artificial neural network (ANN) is proposed in this study. First, the data of historical configuration instance data sets are processed and then a priori algorithm is used to extract the effective rules as domain knowledge. Domain knowledge is used to build the initial structure of ANN. Moreover, data sets are used to further optimize the network. The knowledge‐based ANN is used to realize the mapping between customer requirement attributes and PSS base types. The proposed method is validated in the selection of the PSS base type for CNC machine tools.

show abstract

Optimized BP neural network for Dissolved Oxygen prediction

Cited by 31 publications

References 11 publications

Performance Degradation Analysis and Optimization of the Stepless Capacity Regulation System for Reciprocating Compressors

Performance Degradation Analysis and Optimization of the Stepless Capacity Regulation System for Reciprocating Compressors

An Enhanced Extreme Learning Machine for Dissolved Oxygen Prediction in Wireless Sensor Networks

Base types selection of PSS based on a priori algorithm and knowledge‐based ANN

Contact Info

Product

Resources

About