Chenlei Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Chenlei Xie has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Lifu Gao
Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China
7 shared publications Daqing Wang
Chinese Academy of Sciences
5 shared publicationsQiansheng Fang
Anhui Province Key Laboratory of Intelligent Building and Building Energy-Saving, Anhui Jianzhu University, Hefei, China
4 shared publicationsJie Chen
Anhui Province Key Laboratory of Intelligent Building and Building Energy-Saving, Anhui Jianzhu University, Hefei, China
3 shared publicationsDun Hu
Chinese Academy of Sciences
2 shared publications- Dun Hu
Department of Medical Technology Anhui Medical College Hefei 230601 China
2 shared publications
Latest Publications
- 9 February 2026
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 21 (3) , 2467-2478
Robust Optimization Scheduling of Microgrids Based on Data-Driven Wind Power Uncertainty Set
- 9 February 2026
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 21 (3) , 2467-2478
Robust Optimization Scheduling of Microgrids Based on Data-Driven Wind Power Uncertainty Set
- Open Access
- 12 September 2024
- Published by IWA Publishing in Water Practice & Technology
- Vol. 19 (10) , 3987-4000
A multi-point leakage prediction statistical method using Bayesian inference in water distribution networks
Leakage in water distribution networks (WDNs) not only leads to serious water loss and pipe contamination but also affects residents’ daily water. Accurate localization of leaks in WDN is significant to conserve water resources and reduce economic losses. However, in traditional optimization and verification methods for leak detection, factors such as modeling and pressure monitoring point errors are not taken into account, resulting in the deviation from the actual location of leaks. To address the mentioned issues, this article presents a WDN leakage probability prediction method based on Bayesian inference. The method converts the prior probability of leakage events into posterior probability. Then, by utilizing the posterior probability density function, the uncertainty of modeling and measurement errors in the hydraulic simulation model are quantified. The probability distribution of leakage pipes and leakage quantity within the leakage area is calculated, allowing for the location prediction and corresponding magnitude of leakage. The experimental results indicate that the prediction model can detect unknown quantities of leakage events. By collecting multiple sets of leakage data, it is possible to accurately predict the location and quantity of leaks, enhancing the efficiency of leakage detection in large-scale water supply networks and providing decision-making assistance for water utilities.
- 12 September 2024
- Published by IWA Publishing in Water Practice & Technology
- Vol. 19 (10) , 3987-4000
Open AccessA multi-point leakage prediction statistical method using Bayesian inference in water distribution networks
Leakage in water distribution networks (WDNs) not only leads to serious water loss and pipe contamination but also affects residents’ daily water. Accurate localization of leaks in WDN is significant to conserve water resources and reduce economic losses. However, in traditional optimization and verification methods for leak detection, factors such as modeling and pressure monitoring point errors are not taken into account, resulting in the deviation from the actual location of leaks. To address the mentioned issues, this article presents a WDN leakage probability prediction method based on Bayesian inference. The method converts the prior probability of leakage events into posterior probability. Then, by utilizing the posterior probability density function, the uncertainty of modeling and measurement errors in the hydraulic simulation model are quantified. The probability distribution of leakage pipes and leakage quantity within the leakage area is calculated, allowing for the location prediction and corresponding magnitude of leakage. The experimental results indicate that the prediction model can detect unknown quantities of leakage events. By collecting multiple sets of leakage data, it is possible to accurately predict the location and quantity of leaks, enhancing the efficiency of leakage detection in large-scale water supply networks and providing decision-making assistance for water utilities.
- Open Access
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 18-22
Research on Measurement and Positioning System for Automatic Loading Robot
In the factory, the loading of bagged goods will produce a large amount of particle dust, causing serious environmental pollution and health damage of workers. Therefore, intelligent unmanned automatic loading robot is an inevitable requirement. In order to achieve safe and reliable automatic loading, the primary task is measurement and positioning of on-site truck compartment. In this paper, according to the structural characteristics of the automatic loading robot, a truck compartment measurement and positioning system for automatic loading robot is designed. The system uses the combination of lidar and laser sensor to obtain the three-dimensional information of the measured truck compartment, and calculates the coordinate position, length, width, height, tilt angle, and other data of the truck compartment through the detected data. Experimental measurements have proved that the system can operate stably in the harsh environment of the factory, the relative deviation of the truck compartment size measurement is less than 1.68%, its measurement and detection accuracy fully meets the loading requirements.
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 18-22
Open AccessResearch on Measurement and Positioning System for Automatic Loading Robot
In the factory, the loading of bagged goods will produce a large amount of particle dust, causing serious environmental pollution and health damage of workers. Therefore, intelligent unmanned automatic loading robot is an inevitable requirement. In order to achieve safe and reliable automatic loading, the primary task is measurement and positioning of on-site truck compartment. In this paper, according to the structural characteristics of the automatic loading robot, a truck compartment measurement and positioning system for automatic loading robot is designed. The system uses the combination of lidar and laser sensor to obtain the three-dimensional information of the measured truck compartment, and calculates the coordinate position, length, width, height, tilt angle, and other data of the truck compartment through the detected data. Experimental measurements have proved that the system can operate stably in the harsh environment of the factory, the relative deviation of the truck compartment size measurement is less than 1.68%, its measurement and detection accuracy fully meets the loading requirements.
- Open Access
- 20 July 2023
- Published by IWA Publishing in Water Supply
- Vol. 23 (8) , 3432-3452
A method for water supply network DMA partitioning planning based on improved spectral clustering
Recently, the scale and complexity of water distribution networks (WDNs) have been increasing with the acceleration of urbanization process. It has become a hot research focus to use district metering area (DMA) for more efficient management and control of WDNs. This article proposes a multistage DMA planning method based on improved weighted spectral clustering and genetic algorithm, aiming to address issues such as high investment cost and large differences in the water network demand distribution. First, the actual case pipe network is transformed into an undirected weighted graph based on graph theory, and a similarity matrix is formed by combining the physical properties and hydraulic characteristics of the water network. Then, based on the similarity matrix, the weighted spectral clustering algorithm is used to preliminarily divide the WDN, and the performance of the water supply pipe network formed with different division quantities and different weighting schemes is discussed. Finally, the genetic algorithm is used to optimize the arrangement of valves and flow meters on boundary pipes to generate the final configuration of DMA. The results show that the proposed method has a significant improvement in pipe network topology, hydraulic performance index, and economy compared with the traditional DMA method.
- 20 July 2023
- Published by IWA Publishing in Water Supply
- Vol. 23 (8) , 3432-3452
Open AccessA method for water supply network DMA partitioning planning based on improved spectral clustering
Recently, the scale and complexity of water distribution networks (WDNs) have been increasing with the acceleration of urbanization process. It has become a hot research focus to use district metering area (DMA) for more efficient management and control of WDNs. This article proposes a multistage DMA planning method based on improved weighted spectral clustering and genetic algorithm, aiming to address issues such as high investment cost and large differences in the water network demand distribution. First, the actual case pipe network is transformed into an undirected weighted graph based on graph theory, and a similarity matrix is formed by combining the physical properties and hydraulic characteristics of the water network. Then, based on the similarity matrix, the weighted spectral clustering algorithm is used to preliminarily divide the WDN, and the performance of the water supply pipe network formed with different division quantities and different weighting schemes is discussed. Finally, the genetic algorithm is used to optimize the arrangement of valves and flow meters on boundary pipes to generate the final configuration of DMA. The results show that the proposed method has a significant improvement in pipe network topology, hydraulic performance index, and economy compared with the traditional DMA method.
- Open Access
- 24 January 2023
- Published by IWA Publishing in Water Supply
- Vol. 23 (2) , 645-656
Research on leakage area detection method in water distribution network based on gray wolf optimization
Leakage in a water distribution network (WDN) leads to a large amount of water loss and water pipe pollution and affects residents’ domestic water supply. Therefore, network leakage detection significantly saves water resources. The traditional model approach has ample search space in solving large distribution network applications, a challenging and complex leakage detection process and a low detection accuracy. For the above problems, this study proposes a new method of leakage area detection based on gray wolf optimization (GWO). First, the extensive WDN is divided into several virtual areas. Then, the leakage is simulated by the additional water demand of nodes, and the node demand of the distribution network is calibrated based on the GWO algorithm. Finally, the leakage area is identified, and the size of the leakage in that area is estimated. The method was experimented on in two cases, simulating single-point leakage and multi-point simultaneous leakage, respectively. The results show that the method estimates the size of leakage in the corresponding area based on accurate identification of leakage areas, and the detection error of leakage is within 17.14%. The method provides water workers with guidance on leak detection, significantly reducing staff time to repair pipes.
- 24 January 2023
- Published by IWA Publishing in Water Supply
- Vol. 23 (2) , 645-656
Open AccessResearch on leakage area detection method in water distribution network based on gray wolf optimization
Leakage in a water distribution network (WDN) leads to a large amount of water loss and water pipe pollution and affects residents’ domestic water supply. Therefore, network leakage detection significantly saves water resources. The traditional model approach has ample search space in solving large distribution network applications, a challenging and complex leakage detection process and a low detection accuracy. For the above problems, this study proposes a new method of leakage area detection based on gray wolf optimization (GWO). First, the extensive WDN is divided into several virtual areas. Then, the leakage is simulated by the additional water demand of nodes, and the node demand of the distribution network is calibrated based on the GWO algorithm. Finally, the leakage area is identified, and the size of the leakage in that area is estimated. The method was experimented on in two cases, simulating single-point leakage and multi-point simultaneous leakage, respectively. The results show that the method estimates the size of leakage in the corresponding area based on accurate identification of leakage areas, and the detection error of leakage is within 17.14%. The method provides water workers with guidance on leak detection, significantly reducing staff time to repair pipes.
- Open Access
- 1 January 2023
- Published by Tech Science Press in Computer Modeling in Engineering & Sciences
- Vol. 134 (2) , 1237-1250
Research on Leak Location Method of Water Supply Pipeline Based on MVMD
At present, the leakage rate of the water distribution network in China is still high, and the waste of water resources caused by water distribution network leakage is quite serious every year. Therefore, the location of pipeline leakage is of great significance for saving water resources and reducing economic losses. Acoustic emission technology is the most widely used pipeline leak location technology. The traditional non-stationary random signal de-noising method mainly relies on the estimation of noise parameters, ignoring periodic noise and components unrelated to pipeline leakage. Aiming at the above problems, this paper proposes a leak location method for water supply pipelines based on a multivariate variational mode decomposition algorithm. This method combines the two parameters of the energy loss coefficient and the correlation coefficient between adjacent modes, and adaptively determines the decomposition mode number K according to the characteristics of the signal itself. According to the correlation coefficient, the effective component is selected to reconstruct the signal and the cross-correlation time delay is estimated to determine the location of the pipeline leakage point. The experimental results show that this method has higher accuracy than the cross-correlation method based on VMD and the cross-correlation method based on EMD, and the average relative positioning error is less than 2.2%.
- 1 January 2023
- Published by Tech Science Press in Computer Modeling in Engineering & Sciences
- Vol. 134 (2) , 1237-1250
Open AccessResearch on Leak Location Method of Water Supply Pipeline Based on MVMD
At present, the leakage rate of the water distribution network in China is still high, and the waste of water resources caused by water distribution network leakage is quite serious every year. Therefore, the location of pipeline leakage is of great significance for saving water resources and reducing economic losses. Acoustic emission technology is the most widely used pipeline leak location technology. The traditional non-stationary random signal de-noising method mainly relies on the estimation of noise parameters, ignoring periodic noise and components unrelated to pipeline leakage. Aiming at the above problems, this paper proposes a leak location method for water supply pipelines based on a multivariate variational mode decomposition algorithm. This method combines the two parameters of the energy loss coefficient and the correlation coefficient between adjacent modes, and adaptively determines the decomposition mode number K according to the characteristics of the signal itself. According to the correlation coefficient, the effective component is selected to reconstruct the signal and the cross-correlation time delay is estimated to determine the location of the pipeline leakage point. The experimental results show that this method has higher accuracy than the cross-correlation method based on VMD and the cross-correlation method based on EMD, and the average relative positioning error is less than 2.2%.
- Open Access
- 29 November 2021
- Published by MDPI AG in Electronics
- Vol. 10 (23) , 2972
Estimation of Knee Joint Extension Force Using Mechanomyography Based on IGWO-SVR Algorithm
Muscle force is an important physiological parameter of the human body. Accurate estimation of the muscle force can improve the stability and flexibility of lower limb joint auxiliary equipment. Nevertheless, the existing force estimation methods can neither satisfy the accuracy requirement nor ensure the validity of estimation results. It is a very challenging task that needs to be solved. Among many optimization algorithms, gray wolf optimization (GWO) is widely used to find the optimal parameters of the regression model because of its superior optimization ability. Due to the traditional GWO being prone to fall into local optimum, a new nonlinear convergence factor and a new position update strategy are employed to balance local and global search capability. In this paper, an improved gray wolf optimization (IGWO) algorithm to optimize the support vector regression (SVR) is developed to estimate knee joint extension force accurately and timely. Firstly, mechanomyography (MMG) of the lower limb is measured by acceleration sensors during leg isometric muscle contractions extension training. Secondly, root mean square (RMS), mean absolute value (MAV), zero crossing (ZC), mean power frequency (MPF), and sample entropy (SE) of the MMG are extracted to construct feature sets as candidate data sets for regression analysis. Lastly, the features are fed into IGWO-SVR for further training. Experiments demonstrate that the IGWO-SVR provides the best performance indexes in the estimation of knee joint extension force in terms of RMSE, MAPE, and R compared with the other state-of-art models. These results are expected to become the most effective as guidance for rehabilitation training, muscle disease diagnosis, and health evaluation.
- 29 November 2021
- Published by MDPI AG in Electronics
- Vol. 10 (23) , 2972
Open AccessEstimation of Knee Joint Extension Force Using Mechanomyography Based on IGWO-SVR Algorithm
Muscle force is an important physiological parameter of the human body. Accurate estimation of the muscle force can improve the stability and flexibility of lower limb joint auxiliary equipment. Nevertheless, the existing force estimation methods can neither satisfy the accuracy requirement nor ensure the validity of estimation results. It is a very challenging task that needs to be solved. Among many optimization algorithms, gray wolf optimization (GWO) is widely used to find the optimal parameters of the regression model because of its superior optimization ability. Due to the traditional GWO being prone to fall into local optimum, a new nonlinear convergence factor and a new position update strategy are employed to balance local and global search capability. In this paper, an improved gray wolf optimization (IGWO) algorithm to optimize the support vector regression (SVR) is developed to estimate knee joint extension force accurately and timely. Firstly, mechanomyography (MMG) of the lower limb is measured by acceleration sensors during leg isometric muscle contractions extension training. Secondly, root mean square (RMS), mean absolute value (MAV), zero crossing (ZC), mean power frequency (MPF), and sample entropy (SE) of the MMG are extracted to construct feature sets as candidate data sets for regression analysis. Lastly, the features are fed into IGWO-SVR for further training. Experiments demonstrate that the IGWO-SVR provides the best performance indexes in the estimation of knee joint extension force in terms of RMSE, MAPE, and R compared with the other state-of-art models. These results are expected to become the most effective as guidance for rehabilitation training, muscle disease diagnosis, and health evaluation.
- 24 July 2021
- Published by Springer Nature
- p. 551-561
Estimation of Knee Joint Motion Acceleration Using Mechanomyography Signals
- 24 July 2021
- Published by Springer Nature
- p. 551-561
Estimation of Knee Joint Motion Acceleration Using Mechanomyography Signals
- Open Access
- 1 November 2020
- Published by SAGE Publications in International Journal of Advanced Robotic Systems
- Vol. 17 (6)
A long short-term memory neural network model for knee joint acceleration estimation using mechanomyography signals
With the growth of the number of elderly and disabled with motor dysfunction, the demand for assisted exercise is increasing. Wearable power assistance robots are developed to provide athletic ability of limbs for the elderly or the disabled who have weakened limbs to better self-care ability. Existing wearable power-assisted robots generally use surface electromyography (sEMG) to obtain effective human motion intentions. Due to the characteristics of sEMG signals, it is limited in many applications. To solve the above problems, we design a long short-term memory (LSTM) neural network model based on human mechanomyography (MMG) signals to estimate the motion acceleration of knee joint. The acceleration can be further calculated by the torque required for movement control of the wearable power assistance robots for the lower limb. We detect MMG signals on the clothed thigh, extract features of the MMG signals, and then, use principal component analysis to reduce the features’ dimensions. Finally, the dimension-reduced features are inputted into the LSTM neural network model in time series for estimating the acceleration. The experimental results show that the average correlation coefficient (R) is 94.48 ± 1.91% for the estimation of acceleration in the process of continuously performing under approximately π/4 rad/s. This approach can be applied in the practical applications of wearable field.
- 1 November 2020
- Published by SAGE Publications in International Journal of Advanced Robotic Systems
- Vol. 17 (6)
Open AccessA long short-term memory neural network model for knee joint acceleration estimation using mechanomyography signals
With the growth of the number of elderly and disabled with motor dysfunction, the demand for assisted exercise is increasing. Wearable power assistance robots are developed to provide athletic ability of limbs for the elderly or the disabled who have weakened limbs to better self-care ability. Existing wearable power-assisted robots generally use surface electromyography (sEMG) to obtain effective human motion intentions. Due to the characteristics of sEMG signals, it is limited in many applications. To solve the above problems, we design a long short-term memory (LSTM) neural network model based on human mechanomyography (MMG) signals to estimate the motion acceleration of knee joint. The acceleration can be further calculated by the torque required for movement control of the wearable power assistance robots for the lower limb. We detect MMG signals on the clothed thigh, extract features of the MMG signals, and then, use principal component analysis to reduce the features’ dimensions. Finally, the dimension-reduced features are inputted into the LSTM neural network model in time series for estimating the acceleration. The experimental results show that the average correlation coefficient (R) is 94.48 ± 1.91% for the estimation of acceleration in the process of continuously performing under approximately π/4 rad/s. This approach can be applied in the practical applications of wearable field.
- Open Access
- 1 April 2020
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 495 (1) , 012015
Research on PCA-LSTM-based Short-term Load Forecasting Method
Accurate load forecasting not only makes the power company’s power dispatch more reasonable, but also improves the economics and safety of grid operation. In order to make load forecasting more accurate, it is necessary to use a variety of factors that affect load changes, such as temperature and holidays, to build a huge data set, which will reduce the speed of calculations. In addition, deep learning has advantages over traditional prediction methods in time series prediction. Therefore, this paper adopts a load prediction method based on principal component analysis (PCA) and long short-term memory neural network (LSTM). First, build a multi-dimensional data set with a time series. Second, PCA is used to reduce the dimensionality of the data set, retaining the feature that the sum of the proportions of the k-dimensional principal components reaches or exceeds 85%. Thirdly, the LSTM was trained using the data set and a load prediction model was obtained, with a correlation coefficient of 94%. Finally, the experimental simulation is compared with the traditional method. Experimental results show that the method has higher accuracy and practicability.
- 1 April 2020
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 495 (1) , 012015
Open AccessResearch on PCA-LSTM-based Short-term Load Forecasting Method
Accurate load forecasting not only makes the power company’s power dispatch more reasonable, but also improves the economics and safety of grid operation. In order to make load forecasting more accurate, it is necessary to use a variety of factors that affect load changes, such as temperature and holidays, to build a huge data set, which will reduce the speed of calculations. In addition, deep learning has advantages over traditional prediction methods in time series prediction. Therefore, this paper adopts a load prediction method based on principal component analysis (PCA) and long short-term memory neural network (LSTM). First, build a multi-dimensional data set with a time series. Second, PCA is used to reduce the dimensionality of the data set, retaining the feature that the sum of the proportions of the k-dimensional principal components reaches or exceeds 85%. Thirdly, the LSTM was trained using the data set and a load prediction model was obtained, with a correlation coefficient of 94%. Finally, the experimental simulation is compared with the traditional method. Experimental results show that the method has higher accuracy and practicability.