US 12,436,522 B1
End-edge-cloud collaborative furnace temperature (FT) control method and system in municipal solid waste incineration (MSWI) process
Junfei Qiao, Beijing (CN); Yahui Peng, Beijing (CN); and Xi Meng, Beijing (CN)
Assigned to BEIJING UNIVERSITY OF TECHNOLOGY, Beijing (CN)
Filed by BEIJING UNIVERSITY OF TECHNOLOGY, Beijing (CN)
Filed on Dec. 10, 2024, as Appl. No. 18/975,328.
Claims priority of application No. 202410410675.7 (CN), filed on Apr. 8, 2024.
Int. Cl. G05B 19/4155 (2006.01)
CPC G05B 19/4155 (2013.01) [G05B 2219/50333 (2013.01)] 5 Claims
OG exemplary drawing
 
1. An end-edge-cloud collaborative furnace temperature (FT) control system in a municipal solid waste incineration (MSWI) process, configured to implement an end-edge-cloud collaborative FT control method in the MSWI process, and comprising: an end side, an edge side, and a cloud side connected in sequence, wherein
the end side comprises sensing devices and execution devices; the sensing devices comprise a temperature sensor and an air flow sensor; each of the sensing devices is configured to acquire process data at each moment of MSWI; and the execution devices comprise a primary fan, a secondary fan, and an air preheater;
the edge side is configured to store the process data at each moment, and is configured to:
obtain process data of MSWI at a previous moment, wherein the process data comprises an FT, a primary air flow, a secondary air flow, a primary air heating temperature, a secondary air heating temperature, and a grate speed;
determine an FT prediction value at a current moment by using a current FT prediction model according to the process data at the previous moment, wherein the current FT prediction model is obtained by updating a network parameter of an FT prediction model at the previous moment by using a self-correcting mechanism (SCM); an FT prediction model at an initial moment is obtained by determining a network structure and a network parameter of a fuzzy neural network (FNN) by using a self-organizing mechanism and an improved second-order algorithm based on a sample dataset; the network parameter comprises an antecedent parameter and a consequent parameter; the antecedent parameter comprises a center vector and a width; the consequent parameter comprises a connection weight; the sample dataset comprises process data at a historical moment and an expected FT; and the FNN comprises an input layer, a radial basis function (RBF) layer, a normalized layer, and an output layer;
optimize an objective function by using a gradient descent method according to the FT prediction value at the current moment and a set FT value at the current moment, and determine an optimal control law (OCL), wherein the OCL comprises a primary air flow adjustment amount, a secondary air flow adjustment amount, and a primary air heating temperature adjustment amount; and
send the OCL to the end side to control the FT; and
the cloud side is configured to: determine the network structure and the network parameter of the FNN based on the sample dataset by using the self-organizing mechanism and the improved second-order algorithm, to obtain the FT prediction model at the initial moment; update the network parameter of the FT prediction model at the previous moment by using the SCM, to obtain an FT prediction model at the current moment; and send the FT prediction model at the current moment to the edge side; and
the end-edge-cloud collaborative FT control method in the MSWI process comprises:
obtaining the process data of MSWI at the previous moment, wherein the process data comprises the FT, the primary air flow, the secondary air flow, the primary air heating temperature, the secondary air heating temperature, and the grate speed;
determining the FT prediction value at the current moment by using the current FT prediction model according to the process data at the previous moment, wherein the current FT prediction model is obtained by updating the network parameter of the FT prediction model at the previous moment by using the SCM; the FT prediction model at the initial moment is obtained by determining the network structure and the network parameter of the FNN by using the self-organizing mechanism and the improved second-order algorithm based on the sample dataset; the network parameter comprises the antecedent parameter and the consequent parameter; the antecedent parameter comprises the center vector and the width; the consequent parameter comprises the connection weight; the sample dataset comprises process data at the historical moment and the expected FT; and the FNN comprises an input layer, the RBF layer, the normalized layer, and the output layer; and
optimizing the objective function by using the gradient descent method according to the FT prediction value at the current moment and the set FT value at the current moment, and determining the OCL, to control the FT according to the OCL, wherein the OCL comprises the primary air flow adjustment amount, the secondary air flow adjustment amount, and the primary air heating temperature adjustment amount.