US 12,436,510 B2
Industrial process soft sensor method based on federated stochastic configuration network
Wei Dai, Jiangsu (CN); Lanhao Wang, Jiangsu (CN); Liang Dong, Jiangsu (CN); Mengjie Hu, Jiangsu (CN); Guanghui Wang, Jiangsu (CN); Jing Nan, Jiangsu (CN); Langlong Ji, Jiangsu (CN); Yanshuang Ao, Jiangsu (CN); and Dianhui Wang, Jiangsu (CN)
Assigned to CHINA UNIVERSITY OF MINING AND TECHNOLOGY, Jiangsu (CN)
Appl. No. 18/002,274
Filed by CHINA UNIVERSITY OF MINING AND TECHNOLOGY, Jiangsu (CN)
PCT Filed Jun. 23, 2022, PCT No. PCT/CN2022/100744
§ 371(c)(1), (2) Date Dec. 19, 2022,
PCT Pub. No. WO2023/035727, PCT Pub. Date Mar. 16, 2023.
Claims priority of application No. 202111054478.9 (CN), filed on Sep. 9, 2021.
Prior Publication US 2024/0027976 A1, Jan. 25, 2024
Int. Cl. G06N 3/045 (2023.01); G05B 13/02 (2006.01)
CPC G05B 13/027 (2013.01) [G06N 3/045 (2023.01)] 8 Claims
OG exemplary drawing
 
1. An industrial process soft sensor method based on a federated stochastic configuration network, comprising the following steps:
step 1. acquiring, by each factory, historical industrial process auxiliary data and corresponding product quality data, and initializing parameters required for local stochastic configuration network model learning, each factory being a client, and each client putting hidden layer nodes that meet local data constraints into a candidate pool, selecting best candidate nodes from the candidate pool, and uploading same to a central server;
step 2. performing, by the central server, weighted aggregation or greedy selection on the uploaded best candidate nodes to obtain global parameters, and downloading the global parameters to each client as hidden layer parameters for a local stochastic configuration network model;
step 3. after obtaining the global parameters, calculating, by each client, newly added hidden layer outputs, and uploading output weights to the central server for weighted aggregation, and continuing to start a next round of training;
step 4. when the number of hidden layer nodes in a current network exceeds a maximum given value or a residual in current iteration meets an expected tolerance, adding no new nodes, and stopping federated training to obtain a trained global model; and
step 5. distributing the trained global model, by the server, to each local factory as a soft sensor model;
wherein in step 1, a total of K factories are set to participate in the federated training, and for the kth factory, nk groups of historical industrial process auxiliary data Xk and corresponding product quality data Tk are obtained, denoted as {Xk,Tk}; the historical industrial process auxiliary datain the ith group of the kth factory contains z auxiliary process variables, the corresponding product quality data ti contains m product quality data, and if the value of i is 1 to nk, then an input sample matrix is; and the set of z auxiliary process variables in the ith group is denoted as, where represents the zth auxiliary process variable in the ith group of the kth factory.