公开(公告)号：US12002014B2

公开(公告)日：2024-06-04

申请号：US16967408

申请日：2019-12-02

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Jian Tang ,  Junfei Qiao ,  Zihao Guo ,  Haijun He

IPC: G06Q10/30 ,  G05B13/02 ,  G05B13/04 ,  G06N20/10

CPC classification number: G06Q10/30 ,  G05B13/027 ,  G05B13/042 ,  G05B13/048 ,  G06N20/10

Abstract: Disclosed is a soft measurement method of DXN emission concentration based on multi-source latent feature selective ensemble (SEN) modeling. First, MSWI process data is divided into subsystems of different sources according to industrial processes, and principal component analysis (PCA) is used to separately extract the subsystems' latent features and conduct multi-source latent feature primary selection according to the threshold value of the principal component contribution rate preset by experience. Using mutual information (MI) to evaluate the correlation between the latent features of the primary selection and DXN, and adaptively determine the upper and lower limits and thresholds of the latent feature reselection; finally, based on the reselected latent features, a least squares-support vector machine (LS-SVM) algorithm with a hyperparameter adaptive selection mechanism is used to establish DXN emission concentration sub-models for different subsystems, and based on branch and bound (BB) and prediction error information entropy weighting algorithm to optimize the selection of sub-models and calculation weights coefficient, a SEN soft measurement model of DXN emission concentration is constructed.

公开(公告)号：US20170185892A1

公开(公告)日：2017-06-29

申请号：US15186260

申请日：2016-06-17

Applicant: Beijing University of Technology

Inventor： Honggui Han ,  Yanan Guo ,  Junfei Qiao

IPC: G06N3/08 ,  G05B19/406

CPC classification number: G05B19/406 ,  G06N3/0445 ,  G06N3/082 ,  Y02P80/114

Abstract: Under conventional techniques, wastewater treatment has many problems such as poor production conditions, serious random interference, strong nonlinear behavior, large time-varying, and serious lagging. These problem cause difficult detection of various wastewater treatment parameter such as biochemical oxygen demand (BOD) values that are used to monitor water quality. To solve problems associated with monitoring BOD values in real-time, the present disclosure utilizes a self-organizing recurrent RBF neural network designed for intelligent detecting of BOD values. Implementations of the present disclosure build a computing model of BOD values based on the self-organizing recurrent RBF neural network to achieve real-time and more accurate detection of the BOD values (e.g., a BOD concentration). The implementations herein quickly and accurately obtain BOD concentrations and improve the quality and efficiency of wastewater treatment.

公开(公告)号：US09633307B2

公开(公告)日：2017-04-25

申请号：US14668836

申请日：2015-03-25

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Junfei Qiao ,  Ying Hou ,  Honggui Han ,  Wenjing Li

IPC: G06N3/08 ,  G01N33/18 ,  G06N3/04 ,  C02F3/00 ,  C02F101/16

CPC classification number: G06N3/088 ,  C02F3/006 ,  C02F2101/16 ,  C02F2209/001 ,  C02F2209/006 ,  C02F2209/04 ,  C02F2209/10 ,  C02F2209/14 ,  C02F2209/18 ,  C02F2209/22 ,  C02F2209/40 ,  G01N33/18 ,  G01N33/188 ,  G06N3/0445

Abstract: An intelligent method is designed for predicting the effluent ammonia-nitrogen concentration in the urban wastewater treatment process (WWTP). The technology of this invention is part of advanced manufacturing technology, belongs to both the field of control engineering and environment engineering. In order to improve the predicting efficiency, a recurrent self-organizing neural network, which can adjust the structure and parameters concurrently to train the parameters, is developed to design this intelligent method. This intelligent method can predict the effluent ammonia-nitrogen concentration with acceptable accuracy and solve the problem that the effluent ammonia-nitrogen concentration is difficult to be measured online. Moreover, the online information of effluent ammonia-nitrogen concentration, predicted by this intelligent method, can enhance the quality monitoring level and alleviate the current situation of wastewater to strengthen the whole management of WWTP.

公开(公告)号：US12105075B2

公开(公告)日：2024-10-01

申请号：US17472433

申请日：2021-09-10

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Honggui Han ,  Chenxuan Sun ,  Junfei Qiao

IPC: G06N3/043 ,  C02F1/00 ,  G01N33/18 ,  G06N3/08

CPC classification number: G01N33/1806 ,  G06N3/043 ,  G06N3/08 ,  C02F1/008 ,  C02F2209/16

Abstract: A total nitrogen intelligent detection system based on multi-objective optimized fuzzy neural network belongs to both the field of environment engineer and control engineer. The total nitrogen in wastewater treatment process is an important index to measure the quality of effluent. However, it is extremely difficult to detect the total nitrogen concentration due to the long detection time and the low prediction accuracy in the wastewater treatment process. To solve the problem, multi-objective optimized fuzzy neural network with global optimization capability may be established to optimize the structure and parameters to solve the problem of the poor generalization ability of fuzzy neural network. The experimental results show that total nitrogen intelligent detection system can automatically collect the variables information of wastewater treatment process and predict total nitrogen concentration. Meanwhile, in this system, the detection method can improve the prediction accuracy, as well as ensure the total nitrogen concentration be obtained in real-time and low-cost.

公开(公告)号：US20220383062A1

公开(公告)日：2022-12-01

申请号：US17678949

申请日：2022-02-23

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Honggui Han ,  Xing Bai ,  Ying Hou ,  Hongyan Yang ,  Junfei Qiao

IPC: G06N3/00 ,  G05B19/05

Abstract: An optimal control method for wastewater treatment process (WWTP) based on a self-adjusting multi-task particle swarm optimization (SA-MTPSO) algorithm belongs to the field of WWTP. To balance the relationship between the effluent water quality (EQ) and energy consumption (EC) and achieve optimization online quickly, the invention establishes a data-based multi-task optimization model for WWTP to describe the relationship between the control variables and EQ, EC. Then, the SA-MTPSO algorithm is adopted to solve the optimal set-points of the nitrate nitrogen and dissolved oxygen concentration for WWTP. The PID controller is used to track the optimal set-points, so as to reduce EC while ensuring EQ, and realize the online optimal control of WWTP.

公开(公告)号：US11346831B2

公开(公告)日：2022-05-31

申请号：US15186260

申请日：2016-06-17

Applicant: Beijing University of Technology

Inventor： Honggui Han ,  Yanan Guo ,  Junfei Qiao

IPC: G01N33/18 ,  G06N3/04 ,  G06N3/08 ,  C02F3/00 ,  C02F3/12 ,  G05B19/406

Abstract: Under conventional techniques, wastewater treatment has many problems such as poor production conditions, serious random interference, strong nonlinear behavior, large time-varying, and serious lagging. These problems cause difficulty in detecting wastewater treatment parameters such as biochemical oxygen demand (BOD) values that are used to monitor water quality. To solve problems associated with monitoring BOD values in real-time, the present disclosure utilizes a self-organizing recurrent RBF neural network designed for intelligent detecting of BOD values. Implementations of the present disclosure build a computing model of BOD values based on the self-organizing recurrent RBF neural network to achieve real-time and more accurate detection of the BOD values (e.g., a BOD concentration). The implementations herein quickly and accurately obtain BOD concentrations and improve the quality and efficiency of wastewater treatment.

公开(公告)号：US20180164272A1

公开(公告)日：2018-06-14

申请号：US15891175

申请日：2018-02-07

Applicant: Beijing University of Technology

Inventor： Honggui Han ,  Junfei Qiao ,  Wendong Zhou

IPC: G01N33/18 ,  G06N3/08 ,  C02F3/30

CPC classification number: G01N33/18 ,  C02F3/006 ,  C02F3/30 ,  C02F3/308 ,  C02F2101/105 ,  C02F2209/001 ,  C02F2209/003 ,  C02F2209/005 ,  C02F2209/02 ,  C02F2209/04 ,  C02F2209/06 ,  C02F2209/08 ,  C02F2209/10 ,  C02F2209/16 ,  C02F2209/22 ,  G06N3/006 ,  G06N3/0472 ,  G06N3/0481 ,  G06N3/08 ,  G06N3/088

Abstract: In various implementations, methods and systems are designed for predicting effluent total phosphorus (TP) concentrations in an urban wastewater treatment process (WWTP). To improve the efficiency of TP prediction, a particle swarm optimization self-organizing radial basis function (PSO-SORBF) neural network may be established. Implementations may adjust structures and parameters associated with the neural network to train the neural network. The implementations may predict the effluent TP concentrations with reasonable accuracy and allow timely measurement of the effluent TP concentrations. The implementations may further collect online information related to the estimated effluent TP concentrations. This may improve the quality of monitoring processes and enhance management of WWTP.

公开(公告)号：US20160123949A1

公开(公告)日：2016-05-05

申请号：US14620088

申请日：2015-02-11

Applicant: Beijing University of Technology

Inventor： Honggui Han ,  Junfei Qiao ,  Wendong Zhou

IPC: G01N33/18 ,  G06N3/08

CPC classification number: G01N33/18 ,  G06N3/006 ,  G06N3/088

Abstract: In various implementations, methods and systems are designed for predicting effluent total phosphorus (TP) concentrations in an urban wastewater treatment process (WWTP). To improve efficiency of TP prediction, a particle swarm optimization self-organizing radial basis function (PSO-SORBF) neural network may be established. Implementations may adjust structures and parameters associated with the neural network to train the neural network. The implementations may predict the effluent TP concentrations with reasonably accuracy and allow timely measurement of the effluent TP concentrations. The implementations may further collect online information related to the estimated effluent TP concentrations. This may improve the quality of monitoring processes and enhance management of WWTP.

Abstract translation: 在各种实施方案中，设计了用于预测城市废水处理过程（WWTP）中的流出物总磷（TP）浓度的方法和系统。 为了提高TP预测的效率，可以建立粒子群优化自组织径向基函数（PSO-SORBF）神经网络。 实现可以调整与神经网络相关联的结构和参数来训练神经网络。 这些实施方案可以相当准确地预测流出物TP浓度，并允许及时测量流出物TP浓度。 实施方案可以进一步收集与估计的流出物TP浓度相关的在线信息。 这可能会提高监测过程的质量，加强污水处理厂的管理。

公开(公告)号：US12271665B2

公开(公告)日：2025-04-08

申请号：US18796867

申请日：2024-08-07

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Xi Meng ,  Qizheng Hou ,  Junfei Qiao

IPC: G06F30/25 ,  F23G5/50

Abstract: Provided is an intelligent operational optimization method in the municipal solid waste incineration process, which belongs to both the field of municipal solid waste treatment and the field of intelligent optimization. The method includes: constructing a sample data set by collecting historical data in the municipal solid waste incineration process; with optimization objectives of nitrogen oxide emissions and combustion efficiency, establishing an SORBF neural network-based indicator model to characterize the mapping relationship between operational variables and optimization objectives in the municipal solid waste incineration process; and setting the established indicator model as evaluation functions of a multi-objective optimization algorithm, and obtaining optimal setting values of the operational variables by the multi-objective particle swarm optimization algorithm, so as to improve combustion efficiency while reducing concentrations of nitrogen oxide emissions.

公开(公告)号：US20240310350A1

公开(公告)日：2024-09-19

申请号：US18334725

申请日：2023-06-14

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Cuili Yang ,  Sheng Yang ,  Junfei Qiao

IPC: G01N33/18

CPC classification number: G01N33/188 ,  C02F1/00 ,  C02F2101/16

Abstract: The present disclosure provides a method and system for predicting effluent ammonia nitrogen (NH4—N) and an electronic device. The method includes: obtaining data to be tested; and inputting the data to be tested into a trained deep echo state network, to obtain predicted NH4—N concentration. A method for establishing the deep echo state network includes: establishing an original network, where the original network includes a plurality of input variables and reservoirs, and a principal component analysis (PCA) mapping layer is added between adjacent ones of the reservoirs; initializing the original network to obtain an initialized network; performing parameter optimization on the initialized network by a matrix generation method of singular value decomposition and a competitive swarm optimizer (CSO) algorithm, to obtain an optimized network; and training and testing the optimized network, to obtain the trained deep echo state network.