MSWI process-oriented multi-demand self-organizing fuzzy neural network control system

Abstract

The invention provides a multi-demand self-organizing fuzzy neural network control system for an MSWI process, and relates to the technical field of MSWI process control, and the system comprises a self-organizing TS fuzzy neural network control module which is used for carrying out the self-organizing control of the flame state of the MSWI process, and obtaining the flame combustion state control information; the self-organizing interval type-2 fuzzy neural network control module is used for realizing self-organizing control on a hearth temperature field in the MSWI process to obtain control information of the hearth temperature field; the self-organizing width interval type-2 fuzzy neural network control module is used for achieving self-organizing control over multiple controlled variables in the MSWI process according to the control information of the chamber temperature field, the control information of the flame combustion state and the preset controlled variables. The problems that in the prior art, in the incineration process of the MSW, adaptability is insufficient, manual experience dependence is high, dynamic uncertainty disturbance is complex, intelligent control is difficult to achieve, and multi-scene demand coping capacity is insufficient are solved.

Description

Technical Field

[0001] The invention relates to the technical field of MSWI process control, and in particular to a multi-demand self-organizing fuzzy neural network control system oriented to the MSWI process. Background Art

[0002] Municipal solid waste (MSW) continues to increase at an annual growth rate of 8% to 10%. The resource disposal of MSW is one of the core issues that need to be urgently addressed in the development of environmentally friendly cities. MSW incineration (MSWI) is an important link in the recycling of renewable energy in cities worldwide and has become an effective way to solve the "garbage siege" phenomenon. Due to the differences between my country and developed countries in the composition and management of MSW, the automatic combustion control systems introduced are generally difficult to operate effectively. At present, the operation of the MSWI process mainly relies on domain experts to use their experience and knowledge to manually control the MSWI process to achieve stable control.

[0003] Fluctuations in operating conditions mean adaptive changes in control strategies. How to self-organize the adjustment of controller structure and parameters in the presence of uncertain disturbances within a limited range is a research hotspot in the industry. There are dynamic uncertainty disturbances of different levels and amplitudes in the combustion process of MSWI, which puts higher requirements on intelligent control. Building a self-organizing controller that can imitate the intelligent autonomous behavior of experts and overcome uncertain disturbances in different scenarios is an urgent goal to achieve the intelligent operation of the MSWI process. From the perspective of expert cognition, the degree of drift and causality of the operating conditions of the MSWI process determine when to perform flame control, temperature field control and overall combustion process control. Under this multi-scenario requirement, it is necessary to imitate the intelligent autonomous behavior of experts and adopt different self-organizing control strategies for different scenarios.

[0004] In summary, the automatic control technology in the process of municipal solid waste (MSW) incineration faces significant challenges, including the insufficient adaptability of the existing system to my country's specific conditions, the strong dependence on manual experience, the complexity of dynamic uncertainty disturbances, the difficulty of implementing intelligent control, and the lack of ability to respond to multi-scenario demands. Summary of the invention

[0005] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a multi-demand self-organizing fuzzy neural network control system for the MSWI process. The present invention solves the problems of insufficient adaptability, strong dependence on manual experience, complexity of dynamic uncertainty disturbances, difficulty in realizing intelligent control and lack of ability to cope with multi-scenario demands in the prior art during the incineration of municipal solid waste (MSW).

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A multi-demand self-organizing fuzzy neural network control system for MSWI process, comprising:

[0008] A self-organizing width interval type II fuzzy neural network control module and a self-organizing TS fuzzy neural network control module and a self-organizing interval type II fuzzy neural network control module, both of which are connected to the self-organizing width interval type II fuzzy neural network control module;

[0009] The self-organizing TS fuzzy neural network control module is used to perform self-organizing control on the flame state of the MSWI process to obtain flame combustion state control information; the self-organizing interval type II fuzzy neural network control module is used to perform self-organizing control on the furnace temperature field in the MSWI process to obtain control information of the furnace temperature field; the self-organizing width interval type II fuzzy neural network control module is used to perform self-organizing control on multiple controlled variables of the MSWI process according to the control information of the furnace temperature field, the flame combustion state control information and preset controlled variables, wherein the preset variables include: oxygen content and steam flow rate.

[0010] Preferably, the self-organizing TS fuzzy neural network control module comprises:

[0011] A first correlation analysis submodule and a first control submodule connected to each other;

[0012] The first correlation analysis submodule is used to obtain the influencing factors of the quantitative values, wherein the quantitative values ​​are the height, brightness and length of flame combustion; the first control submodule is used to construct a flame combustion state controller according to the influencing factors and the flame combustion mechanism, wherein the controlled variables of the flame combustion state controller are the flame height, brightness and length, the burning state controller has a multi-output post-processing layer, and the flame combustion state controller is used to output flame combustion state control information.

[0013] Preferably, the first correlation analysis submodule includes:

[0014] A first analysis unit, a second analysis unit and a third analysis unit connected in sequence;

[0015] The first analysis unit is used to determine the delay characteristics of the quantized value, the second analysis unit is used to obtain the bias of the wind and fabric control variables, and the third analysis unit is used to obtain the influencing factor of the quantized value according to the delay characteristics of the quantized value and the bias of the wind and fabric control variables.

[0016] Preferably, the self-organizing interval type-2 fuzzy neural network control module comprises:

[0017] a second correlation analysis submodule and a second control submodule connected to each other;

[0018] The second correlation analysis submodule is used to analyze the correlation between the real and virtual temperature fields and the air distribution and material distribution operations to obtain the first analysis result, the second analysis result and the third analysis result. The second control submodule is used to establish a self-organizing controller for the furnace temperature based on the first analysis result, the second analysis result, the third analysis result, the quantitative analysis result of the furnace temperature condition drift and the interval type-2 fuzzy neural network. The self-organizing controller for the furnace temperature is used to output control information of the furnace temperature field.

[0019] Preferably, the second correlation analysis submodule includes:

[0020] A fourth analysis unit, a fifth analysis unit and a sixth analysis unit connected in sequence;

[0021] The fourth analysis unit is used to analyze the correlation between the actual furnace temperature and the air and material distribution operation to obtain a first analysis result. The fifth analysis unit is used to analyze the relationship between the actual thermocouple temperature measurement point and the air and material distribution operation rules to obtain a second analysis result. The sixth analysis unit is used to analyze the correlation between the virtual temperature field and the air and material distribution control variables to obtain a third analysis result.

[0022] Preferably, the self-organizing width interval type II fuzzy neural network control module comprises:

[0023] a third correlation analysis submodule and a third control submodule connected to each other;

[0024] The third correlation analysis submodule is used to perform correlation analysis on preset variables and wind and material distribution control variables to obtain a fourth analysis result. The third control submodule is used to construct a combustion process controller based on the fourth analysis result, the control information of the chamber temperature field, and the flame combustion state control. The combustion process controller is used to realize self-organizing control of multiple controlled variables of the MSWI process.

[0025] The present invention discloses the following technical effects:

[0026] The present invention provides a multi-demand self-organizing fuzzy neural network control system for an MSWI process, comprising: a self-organizing width interval type II fuzzy neural network control module and a self-organizing TS fuzzy neural network control module and a self-organizing interval type II fuzzy neural network control module, both of which are connected to the self-organizing width interval type II fuzzy neural network control module; the self-organizing TS fuzzy neural network control module is used to self-organize the flame state of the MSWI process to obtain flame combustion state control information; the self-organizing interval type II fuzzy neural network control module is used to self-organize the furnace temperature field in the MSWI process to obtain the control information of the furnace temperature field; the self-organizing width interval type II fuzzy neural network control module is used to self-organize the multiple controlled variables of the MSWI process according to the control information of the furnace temperature field, the flame combustion state control information and preset controlled variables, wherein the preset variables include: oxygen content and steam flow rate. The present invention performs self-organizing TS fuzzy neural network control for the quantized value of flame combustion state, and realizes self-organizing control of flame combustion state by taking three quantized values ​​of flame height, length and brightness as feedback; then, performs self-organizing interval type II fuzzy neural network control for furnace temperature field, and performs self-organizing control of furnace temperature field by taking virtual and real furnace temperatures as feedback; finally, performs self-organizing width interval type II fuzzy neural network control for the overall combustion process, and realizes self-organizing control of multiple controlled variables. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0028] Figure 1 A schematic diagram of the structure of a multi-demand self-organizing fuzzy neural network control system for a MSWI process provided by an embodiment of the present invention.

[0029] Description of reference numerals:

[0030] 1-Self-organizing width interval type II fuzzy neural network control module 2-Self-organizing interval type II fuzzy neural network control module, 3-Self-organizing TS fuzzy neural network control module. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] like Figure 1 As shown, the present invention provides a multi-demand self-organizing fuzzy neural network control system for MSWI process, comprising:

[0034] A self-organizing width interval type II fuzzy neural network control module 1 and a self-organizing TS fuzzy neural network control module 3 and a self-organizing interval type II fuzzy neural network control module 2, both of which are connected to the self-organizing width interval type II fuzzy neural network control module 1;

[0035] The self-organizing TS fuzzy neural network control module 3 is used to perform self-organizing control on the flame state of the MSWI process to obtain flame combustion state control information; the self-organizing interval type II fuzzy neural network control module 2 is used to perform self-organizing control on the furnace temperature field in the MSWI process to obtain control information of the furnace temperature field; the self-organizing width interval type II fuzzy neural network control module 1 is used to perform self-organizing control on multiple controlled variables of the MSWI process according to the control information of the furnace temperature field, the flame combustion state control information and preset controlled variables, wherein the preset variables include: oxygen content and steam flow rate.

[0036] Specifically, the relationship between the three modules is as follows: the self-organizing TS fuzzy neural network control module 3 for the quantization value of the flame combustion state provides the self-organizing interval type II fuzzy neural network control module 2 for the furnace temperature field and the self-organizing width interval type II fuzzy neural network control module 1 for the combustion process with the flame combustion state control information of the local range; the self-organizing interval type II fuzzy neural network control module 2 for the furnace temperature field provides the self-organizing width interval type II fuzzy neural network control module 1 for the combustion process with the control information of the local range of the furnace temperature field; the self-organizing width interval type II fuzzy neural network control module 1 for the combustion process integrates the flame combustion control, the furnace temperature field control and other controlled variables to perform the global self-organizing control of the combustion process.

[0037] Furthermore, the self-organizing TS fuzzy neural network control module 3 includes:

[0038] A first correlation analysis submodule and a first control submodule connected to each other;

[0039] The first correlation analysis submodule is used to obtain the influencing factors of the quantitative values, wherein the quantitative values ​​are the height, brightness and length of flame combustion; the first control submodule is used to construct a flame combustion state controller according to the influencing factors and the flame combustion mechanism, wherein the controlled variables of the flame combustion state controller are the flame height, brightness and length, the burning state controller has a multi-output post-processing layer, and the flame combustion state controller is used to output flame combustion state control information.

[0040] Self-organizing TS fuzzy neural network control module 3 for flame combustion state quantization value: Taking the three local quantization values ​​of flame brightness, height and length as controlled variables, the control system's operating time scale, local quantization values, and correlation analysis between control variables are performed. Aiming at the composition uncertainty of a bucket of material and combining the quantitative analysis of operating condition drift, a multi-layer self-organizing TS fuzzy neural network algorithm is used to achieve self-organizing control of the flame combustion state.

[0041] Furthermore, the first correlation analysis submodule includes:

[0042] A first analysis unit, a second analysis unit and a third analysis unit connected in sequence;

[0043] The first analysis unit is used to determine the delay characteristics of the quantized value, the second analysis unit is used to obtain the bias of the wind and fabric control variables, and the third analysis unit is used to obtain the influencing factor of the quantized value according to the delay characteristics of the quantized value and the bias of the wind and fabric control variables.

[0044] Specifically, the material distribution operation is very likely to result in uneven material layers, resulting in uncertainty in the combustion process. The flame combustion state is the first controlled variable to be affected. Self-organizing TS fuzzy neural network control for the quantization value of the flame combustion state is carried out, including two sub-modules: correlation analysis between the quantization value of the flame combustion state and the air distribution and material distribution operation, and self-organizing TS fuzzy neural network controller.

[0045] More specifically, the time delay characteristics of the local quantitative values ​​of flame combustion and the control variables of air distribution and cloth are analyzed. For the three local quantitative values ​​of flame combustion, namely, height, brightness and length, the delay characteristics between the brightness and length of flame combustion and the control variables are determined based on expert knowledge and the operating characteristics of the cloth actuator; ② The correlation analysis between the local quantitative values ​​of flame combustion and the control variables of air distribution and cloth. In the actual process, the domain engineer controls the area occupied by the flame on the grate in the furnace through the air distribution and cloth, analyzes the correlation between the three local quantitative values ​​and the air distribution and cloth, and obtains the bias towards the control variables of air distribution and cloth; ③ The correlation analysis between the global quantitative values ​​of flame combustion and the control variables of air distribution and cloth. Based on the process technology design and the principles of the automatic combustion system, it can be seen that the grate area occupied by flame combustion cannot be too small or too large. The correlation between the global quantitative value and the control variables of air distribution and cloth is analyzed, and the influencing factors of the air distribution and cloth operation on the global quantitative value are determined to provide support for control.

[0046] ① Flame combustion state control system design, taking flame height, brightness and length as controlled variables, constructing a controller that can overcome disturbances caused by uncertainty of materials in the same hopper; ② Fuzzy rule self-organization of TS fuzzy neural network, targeting flame combustion fluctuations, designing fuzzy rule self-organization algorithm based on drift quantification analysis to improve the robustness of the controller; ③ TS fuzzy neural network controller parameter learning, designing a post-processing layer with multiple outputs based on the flame combustion mechanism and the results of the previous correlation analysis and the characteristics of multiple control quantities, and performing corresponding network parameter learning according to the characteristics of the multi-output post-processing layer.

[0047] Furthermore, the self-organizing interval type II fuzzy neural network control module 2 comprises:

[0048] a second correlation analysis submodule and a second control submodule connected to each other;

[0049] The second correlation analysis submodule is used to analyze the correlation between the real and virtual temperature fields and the air distribution and material distribution operations to obtain the first analysis result, the second analysis result and the third analysis result. The second control submodule is used to establish a self-organizing controller for the furnace temperature based on the first analysis result, the second analysis result, the third analysis result, the quantitative analysis result of the furnace temperature condition drift and the interval type-2 fuzzy neural network. The self-organizing controller for the furnace temperature is used to output control information of the furnace temperature field.

[0050] Specifically, the self-organizing TS fuzzy neural network control module 3 for the quantization value of the flame combustion state: analyzes the correlation between the furnace temperature field composed of the real temperature points that can be detected by the real thermocouples and the virtual temperature points that cannot be detected, as well as the air distribution and material distribution control variables, and designs a self-organizing interval type II fuzzy neural network algorithm considering the prior information between uncertainty and membership degree to realize self-organizing control of the furnace temperature field.

[0051] Furthermore, the second correlation analysis submodule includes:

[0052] A fourth analysis unit, a fifth analysis unit and a sixth analysis unit connected in sequence;

[0053] The fourth analysis unit is used to analyze the correlation between the actual furnace temperature and the air and material distribution operation to obtain a first analysis result. The fifth analysis unit is used to analyze the relationship between the actual thermocouple temperature measurement point and the air and material distribution operation rules to obtain a second analysis result. The sixth analysis unit is used to analyze the correlation between the virtual temperature field and the air and material distribution control variables to obtain a third analysis result.

[0054] Specifically, the actual furnace temperature field is difficult to be fully characterized by the temperatures detected by a limited number of thermocouples. Compared with flame combustion, it has more uncertain factors and larger amplitude changes. Therefore, a self-organizing interval type-II fuzzy neural network control for the furnace temperature field is carried out, including two sub-modules: correlation analysis of the real and virtual temperature fields and the air and material distribution operations, and a self-organizing interval type-II fuzzy neural network controller.

[0055] More specifically, the correlation analysis between the actual furnace temperature and the air distribution and distribution control variables is carried out. Based on the furnace temperature measurement points and air distribution and distribution process design of the actual process, the correlation between the actual furnace temperature and the air distribution and distribution operations is analyzed, and the timing of the influence of the air distribution and distribution operations on the furnace temperature is determined to support the design of the furnace temperature field controller; ② The correlation analysis between the actual thermocouple temperature measurement points in the furnace and the air distribution and distribution control variables. In the furnace temperature field control, the constructed temperature field mapping model needs to be used to online identify the virtual temperature value, and the relationship between the installed real thermocouple temperature measurement points and the air distribution and distribution operation rules is analyzed; ③ The correlation analysis between the virtual temperature field and the air distribution and distribution control variables. Due to the different distribution positions, the virtual temperature value responds differently to the air distribution and distribution operation rules. The correlation between the virtual temperature field and the air distribution and distribution control variables is analyzed to support the stable control of the furnace temperature.

[0056] ① Design of furnace temperature field control system. According to the multi-control variable characteristics of the air distribution and material distribution process, an interval type-2 fuzzy neural network is used to establish a self-organizing controller for furnace temperature to adapt to the disturbance caused by the uncertainty between different bucket materials; ② Fuzzy rule self-organization of interval type-2 neural network. The furnace temperature field has a wider range of uncertainties than the control of the flame combustion state. Based on the quantitative analysis of the furnace temperature operating condition drift and the correlation analysis results, a type-2 fuzzy rule self-organizing algorithm is designed to improve the robustness of the controller; ③ Parameter learning of interval type-2 fuzzy neural network controller. Multiple consequent outputs with single interval type-2 fuzzy rules and parameter learning strategies of interval type-2 fuzzy neural networks are designed.

[0057] Furthermore, the self-organizing width interval type II fuzzy neural network control module 1 comprises:

[0058] a third correlation analysis submodule and a third control submodule connected to each other;

[0059] The third correlation analysis submodule is used to perform correlation analysis on preset variables and wind and material distribution control variables to obtain a fourth analysis result. The third control submodule is used to construct a combustion process controller based on the fourth analysis result, the control information of the chamber temperature field, and the flame combustion state control. The combustion process controller is used to realize self-organizing control of multiple controlled variables of the MSWI process.

[0060] Specifically, the self-organizing TS fuzzy neural network control module 3 for the flame combustion state quantization value analyzes the correlation and delay characteristics among the controlled variables such as the flame combustion state quantization value, furnace temperature, oxygen content and steam flow rate, and adopts the wide interval type II fuzzy neural network algorithm of online learning that can adapt to wider uncertainty factors to realize the self-organizing control of multiple controlled variables.

[0061] The combustion process requires simultaneous control of multiple variables such as flame combustion state, furnace temperature, oxygen content and steam flow rate. Considering the inherent multimodality and uncertain interference characteristics, the self-organizing wide interval type II fuzzy neural network control for the overall combustion process is studied, including two sub-modules: correlation analysis between multiple controlled variables and air distribution and material distribution control variables, and self-organizing wide interval type II fuzzy neural network control.

[0062] More specifically, ① the correlation and delay characteristics analysis between oxygen content and air distribution and material distribution control variables. Based on the location of the oxygen content detection point and the process flow design, the correlation between oxygen content and air distribution and material distribution control variables is analyzed to determine the delay characteristics between the two. ② The correlation and delay characteristics analysis between steam flow and air distribution and material distribution control variables. Based on the boiler process design and the incinerator design, the correlation between steam flow and air distribution and material distribution control variables is analyzed to determine the delay characteristics between the two. ③ The correlation and delay characteristics analysis between the controlled variables. Taking the flame combustion state, furnace temperature, oxygen content and steam flow as the controlled variables, starting from the combustion mechanism, the correlation between the controlled variables is analyzed, and the delay characteristics between the controlled variables are further studied according to the process mechanism to provide support for subsequent control.

[0063] ① Design a multi-input and multi-output combustion process control system, take the global quantitative value of the flame combustion state, furnace temperature, oxygen content and steam flow as the controlled variables, design a self-organizing wide interval type II fuzzy neural network, and build a multi-input and multi-output control system; ② Carry out fuzzy rule self-organization of the wide interval type II fuzzy neural network, study the type II fuzzy rule self-organization algorithm under online addition, deletion and constant conditions, and improve the robustness and anti-interference performance of the controller; ③ Take the current output control quantity and the actual feedback signal of the controlled object at the previous moment as input, set the threshold through empirical knowledge to trigger the online incremental learning process; ④ Parameter learning of the wide interval type II fuzzy neural network controller, based on the global operating condition drift quantification analysis, correlation analysis results and multi-controlled variable characteristics, design the post-processing layer of the wide interval type II fuzzy neural network, and obtain the parameter learning strategy of the wide interval type II fuzzy neural network according to the post-processing layer structure characteristics.

[0064] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0065] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A multi-demand self-organizing fuzzy neural network control system for MSWI process, characterized in that: include: A self-organizing width interval type II fuzzy neural network control module and a self-organizing TS fuzzy neural network control module and a self-organizing interval type II fuzzy neural network control module, both of which are connected to the self-organizing width interval type II fuzzy neural network control module; The self-organizing TS fuzzy neural network control module is used to perform self-organizing control on the flame state of the MSWI process to obtain flame combustion state control information; the self-organizing interval type II fuzzy neural network control module is used to perform self-organizing control on the furnace temperature field in the MSWI process to obtain control information of the furnace temperature field; the self-organizing width interval type II fuzzy neural network control module is used to perform self-organizing control on multiple controlled variables of the MSWI process according to the control information of the furnace temperature field, the flame combustion state control information and preset controlled variables, wherein the preset variables include: oxygen content and steam flow rate.

2. The multi-demand self-organizing fuzzy neural network control system for MSWI process according to claim 1 is characterized in that: The self-organizing TS fuzzy neural network control module comprises: A first correlation analysis submodule and a first control submodule connected to each other; The first correlation analysis submodule is used to obtain the influencing factors of the quantitative values, wherein the quantitative values ​​are the height, brightness and length of flame combustion; the first control submodule is used to construct a flame combustion state controller according to the influencing factors and the flame combustion mechanism, wherein the controlled variables of the flame combustion state controller are the flame height, brightness and length, the burning state controller has a multi-output post-processing layer, and the flame combustion state controller is used to output flame combustion state control information.

3. A multi-demand self-organizing fuzzy neural network control system for MSWI process according to claim 2, characterized in that: The first correlation analysis submodule includes: A first analysis unit, a second analysis unit and a third analysis unit connected in sequence; The first analysis unit is used to determine the delay characteristics of the quantized value, the second analysis unit is used to obtain the bias of the wind and fabric control variables, and the third analysis unit is used to obtain the influencing factor of the quantized value according to the delay characteristics of the quantized value and the bias of the wind and fabric control variables.

4. The multi-demand self-organizing fuzzy neural network control system for MSWI process according to claim 2 is characterized in that: The self-organizing interval type II fuzzy neural network control module comprises: a second correlation analysis submodule and a second control submodule connected to each other; The second correlation analysis submodule is used to analyze the correlation between the real and virtual temperature fields and the air distribution and material distribution operations to obtain the first analysis result, the second analysis result and the third analysis result. The second control submodule is used to establish a self-organizing controller for the furnace temperature based on the first analysis result, the second analysis result, the third analysis result, the quantitative analysis result of the furnace temperature condition drift and the interval type-2 fuzzy neural network. The self-organizing controller for the furnace temperature is used to output control information of the furnace temperature field.

5. The multi-demand self-organizing fuzzy neural network control system for MSWI process according to claim 4 is characterized in that: The second correlation analysis submodule includes: A fourth analysis unit, a fifth analysis unit and a sixth analysis unit connected in sequence; The fourth analysis unit is used to analyze the correlation between the actual furnace temperature and the air and material distribution operation to obtain a first analysis result. The fifth analysis unit is used to analyze the relationship between the actual thermocouple temperature measurement point and the air and material distribution operation rules to obtain a second analysis result. The sixth analysis unit is used to analyze the correlation between the virtual temperature field and the air and material distribution control variables to obtain a third analysis result.

6. The multi-demand self-organizing fuzzy neural network control system for MSWI process according to claim 1 is characterized in that: The self-organizing width interval type II fuzzy neural network control module comprises: a third correlation analysis submodule and a third control submodule connected to each other; The third correlation analysis submodule is used to perform correlation analysis on preset variables and wind and material distribution control variables to obtain a fourth analysis result. The third control submodule is used to construct a combustion process controller based on the fourth analysis result, the control information of the chamber temperature field, and the flame combustion state control. The combustion process controller is used to realize self-organizing control of multiple controlled variables of the MSWI process.

Images