Soft measurement modeling implementation method and device

Abstract

The embodiment of the invention provides a soft measurement modeling implementation method and device, and the method and device are used for a coal-fired unit deep peak regulation and rapid start-stop control system, and the method comprises the steps: determining a main variable and an auxiliary variable of a soft measurement task through mechanism analysis; carrying out data acquisition according to the main variable and the auxiliary variable, and carrying out conversion and error processing on the acquired data to obtain processed data; and according to the processed data, performing soft measurement task modeling in a mechanism modeling and / or empirical modeling mode.

Description

Technical Field

[0001] This document relates to the technical field, and in particular to a method and apparatus for implementing soft measurement modeling. Background Technology

[0002] The inherent randomness, intermittency, and volatility of new energy power generation pose significant challenges to the stable operation of the power system. Building a new power system primarily based on new energy sources urgently requires thermal power units to transform from traditional baseload power sources to flexible regulation power sources. This involves using methods such as deep peak shaving and rapid start-up and shutdown to quickly respond to dynamic changes in grid load, ensuring the safe and stable operation of the power system and a reliable energy supply.

[0003] With the further development of new energy sources and the increasing demands for grid flexibility, deep peak shaving and rapid start-up / shutdown control systems for thermal power units will become key technologies for stable operation and efficient utilization of thermal power units. By combining advanced control technologies and management models, these systems will play an important role in ensuring energy supply security, promoting the consumption of renewable energy, and improving the economic benefits of power units.

[0004] Currently, the construction of a new power system based on new energy sources places higher demands on power supply regulation capabilities. Therefore, it is necessary to improve the unit's ability to regulate load increases and decreases and to quickly start and stop through methods such as simulation, hardware and software measurement, and control optimization.

[0005] Soft sensing organically combines production process knowledge with computer technology to infer or estimate important variables that are difficult or temporarily unmeasurable by selecting other easily measurable variables and establishing mathematical relationships. This software replaces the function of hardware. Applying soft sensing technology to achieve online detection of elemental composition content is not only economical and reliable, but also provides rapid dynamic response and continuous information on elemental composition content during extraction, facilitating product quality control. Therefore, a soft sensing modeling implementation method is urgently needed. Summary of the Invention

[0006] The purpose of this invention is to provide a soft measurement modeling implementation method and apparatus, which aims to solve the above-mentioned problems in the prior art.

[0007] This invention provides a soft-sensor modeling implementation method for a deep peak shaving and rapid start-stop control system of a coal-fired power unit, comprising: The dominant and auxiliary variables of the soft measurement task were determined through mechanistic analysis; Data is collected based on the dominant and auxiliary variables, and the collected data is converted and error-processed to obtain the processed data. Based on the processed data, the soft measurement task is modeled using mechanistic modeling and / or empirical modeling methods.

[0008] This invention provides a soft measurement modeling implementation device for a deep peak shaving and rapid start-up / shutdown control system for coal-fired power units, comprising: The determination module is used to identify the dominant and auxiliary variables of the soft measurement task through mechanistic analysis; The processing module is used to collect data based on the dominant and auxiliary variables, perform conversion and error processing on the collected data, and obtain the processed data. The modeling module is used to model soft measurement tasks based on the processed data, using mechanistic modeling and / or empirical modeling methods.

[0009] This invention also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-described soft measurement modeling implementation method.

[0010] This invention also provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor, implements the steps of the above-described soft measurement modeling implementation method.

[0011] By employing the embodiments of this invention and utilizing soft measurement methods, the research results are further verified. Through cross-validation of the established mechanism model, AI model, and field data, a scientific and feasible solution for deep peak shaving and rapid start-up and shutdown of coal-fired power units is provided. Through intelligent analysis, the control logic and operating parameters of key control systems affecting rapid start-up and shutdown under deep peak shaving are further optimized, thereby improving the deep peak shaving capability and load response rate. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of the soft measurement modeling implementation method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a soft measurement modeling implementation device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0015] Method Implementation Examples According to embodiments of the present invention, a soft-sensor modeling implementation method is provided for a deep peak shaving and rapid start-stop control system for coal-fired power units. Figure 1 This is a flowchart of the soft measurement modeling implementation method according to an embodiment of the present invention, such as... Figure 1 As shown, the soft measurement modeling implementation method according to an embodiment of the present invention specifically includes: Step S101 involves determining the dominant and auxiliary variables of the soft measurement task through mechanistic analysis; specifically including: Through mechanistic analysis, dominant and auxiliary variables are determined based on the process flow of the device. The auxiliary variables meet the criteria of correlation, specificity, process adaptability, accuracy, and robustness. Specifically, the auxiliary variables include: variable type, number of variables, and detection point locations. The lower limit of the number of auxiliary variables is the estimated number of dominant variables, while the upper limit is determined based on the system's degrees of freedom and the characteristics of the production process.

[0016] Step S102 involves collecting data based on the dominant and auxiliary variables, performing conversion and error processing on the collected data to obtain processed data; specifically including: Data is collected based on the dominant and auxiliary variables. The collected data is then converted and error-processed. The conversion includes scaling, transformation, and weight function conversion. The error processing includes handling random errors and gross errors. Random errors are processed using filtering methods, while gross errors are processed using statistical hypothesis testing, generalized likelihood method, Bayesian method, and / or neural network method.

[0017] Step S103: Based on the processed data, perform soft measurement task modeling using mechanistic modeling and / or empirical modeling.

[0018] The above technical solution will be described in detail below.

[0019] Soft sensing organically combines production process knowledge with computer technology to select other easily measurable variables for important variables that are difficult or temporarily unmeasurable. By establishing mathematical relationships, it infers or estimates these variables, replacing the functions of hardware with software. Applying soft sensing technology to achieve online detection of elemental composition content is not only economical and reliable, but also provides rapid dynamic response and continuous information on elemental composition content during the extraction process, facilitating product quality control.

[0020] Mechanism analysis primarily clarifies the tasks of soft sensing, identifies dominant variables, and deepens understanding of the plant's process flow. It also preliminarily determines auxiliary variables. Auxiliary variables include variable type, number of variables, and detection point locations. The selection of auxiliary variables should conform to the principles of correlation, specificity, process adaptability, accuracy, and robustness. The lower limit of auxiliary variables is the number of estimated dominant variables; however, there is no unified theoretical guideline for the upper limit, which can be appropriately increased based on the system's degrees of freedom and the characteristics of the production process.

[0021] In theory, the more data collected, the better, as it can be used not only for modeling but also for model validation. To ensure the accuracy of soft sensing, data acquisition must be correct and reliable, and processed: conversion and error handling. Conversion includes scaling, transformation, and weighting functions. Error analysis mainly refers to random errors and gross errors. Random errors can be addressed using filtering methods, while gross errors can be addressed using statistical hypothesis testing, generalized likelihood estimation, Bayesian methods, and, more recently, neural network methods.

[0022] Soft measurement modeling is a key and challenging aspect of soft measurement technology. This invention employs mechanistic modeling, empirical modeling, and a combination of both. Empirical modeling involves obtaining empirical models through actual measurements or based on accumulated operational data, using mathematical regression and neural network methods. Theoretically, there are many modeling methods available, but difficulties arise during engineering implementation because processes do not allow for significant changes in operating conditions. Its advantages and disadvantages are the opposite of those of mechanistic modeling.

[0023] Device Example 1 According to embodiments of the present invention, a soft measurement modeling implementation device is provided for a deep peak shaving and rapid start-up / shutdown control system for coal-fired power units. Figure 2 This is a schematic diagram of the soft measurement modeling implementation device according to an embodiment of the present invention, such as... Figure 2 As shown, the soft measurement modeling implementation apparatus according to an embodiment of the present invention specifically includes: Module 20 is used to determine the dominant and auxiliary variables of the soft measurement task through mechanistic analysis; specifically, it is used for: Through mechanistic analysis, dominant and auxiliary variables are determined based on the process flow of the device. The auxiliary variables meet the requirements of correlation, specificity, process adaptability, accuracy, and robustness. The auxiliary variables specifically include: variable type, number of variables, and detection point location.

[0024] The lower limit of the number of auxiliary variables is the number of the estimated dominant variables, and the upper limit of the number of auxiliary variables is determined according to the system's degrees of freedom and the characteristics of the production process.

[0025] Processing module 22 is used to collect data based on the dominant and auxiliary variables, perform conversion and error processing on the collected data, and obtain processed data; specifically, it is used for: Data is collected based on the dominant and auxiliary variables. The collected data is then converted and error-processed. The conversion includes scaling, transformation, and weight function conversion. The error processing includes handling random errors and gross errors. Random errors are processed using filtering methods, while gross errors are processed using statistical hypothesis testing, generalized likelihood method, Bayesian method, and / or neural network method.

[0026] Modeling module 24 is used to model soft measurement tasks based on the processed data using mechanistic modeling and / or empirical modeling methods.

[0027] The embodiments of the present invention are device embodiments corresponding to the above method embodiments. The specific operation of each module can be understood with reference to the description of the method embodiments, and will not be repeated here.

[0028] Device Example 2 This invention provides an electronic device, such as... Figure 3 As shown, it includes: a memory 30, a processor 32, and a computer program stored in the memory 30 and executable on the processor 32, wherein the computer program, when executed by the processor 32, performs the steps as described in the method embodiment.

[0029] Device Example 3 This invention provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor 32, performs the steps described in the method embodiment.

[0030] The computer-readable storage media described in this embodiment include, but are not limited to, ROM, RAM, disk, or optical disk.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for implementing soft-sensing modeling, characterized in that, The method comprises the following steps: The dominant variables and auxiliary variables of the soft measurement task are determined through mechanism analysis; Data acquisition is performed according to the dominant variables and auxiliary variables, and the acquired data is converted and error processed to obtain processed data; The soft measurement task modeling is performed according to the processed data by using mechanism modeling and / or empirical modeling.

2. The method of claim 1, wherein, The dominant variables and auxiliary variables of the soft measurement task are determined through mechanism analysis, and the auxiliary variables meet the correlation, specificity, process adaptability, accuracy and robustness, and the auxiliary variables specifically include variable types, variable numbers and detection point positions. The number of the auxiliary variables is determined according to the degrees of freedom of the system and the characteristics of the production process.

3. The method of claim 2, wherein, The data acquisition is performed according to the dominant variables and auxiliary variables, and the acquired data is converted and error processed to obtain processed data, which specifically includes the following steps:

4. The method of claim 1, wherein, The data acquisition is performed according to the dominant variables and auxiliary variables, and the acquired data is converted and error processed, wherein the conversion includes scaling, conversion and weight function conversion, and the error processing includes random error processing and fault error processing, wherein the random error is processed by using a filtering method, and the fault error is processed by using a statistical hypothesis checking method, a generalized likelihood method, a Bayesian method and / or a neural network method. The device comprises:

5. A soft-sensing modeling implementation apparatus, characterized by comprising: A determination module configured to determine the dominant variables and auxiliary variables of the soft measurement task through mechanism analysis; A processing module configured to perform data acquisition according to the dominant variables and auxiliary variables, and to convert and error process the acquired data to obtain processed data; A modeling module configured to perform soft measurement task modeling according to the processed data by using mechanism modeling and / or empirical modeling. The determination module is specifically configured to:

6. The apparatus of claim 5, wherein, The dominant variables and auxiliary variables are determined through mechanism analysis according to the process flow of the device, and the auxiliary variables meet the correlation, specificity, process adaptability, accuracy and robustness, and the auxiliary variables specifically include variable types, variable numbers and detection point positions. The number of the auxiliary variables is determined according to the degrees of freedom of the system and the characteristics of the production process.

7. The apparatus of claim 6, wherein, The processing module is specifically configured to:

8. The apparatus of claim 5, wherein, The data acquisition is performed according to the dominant variables and auxiliary variables, and the acquired data is converted and error processed, wherein the conversion includes scaling, conversion and weight function conversion, and the error processing includes random error processing and fault error processing, wherein the random error is processed by using a filtering method, and the fault error is processed by using a statistical hypothesis checking method, a generalized likelihood method, a Bayesian method and / or a neural network method. The device comprises:

9. An electronic device, comprising: ​ A memory, a processor, and a computer program stored on the memory and executable on the processor, which, when executed by the processor, implements the steps of the soft-sensor modeling implementation method according to any one of claims 1 to 4.

10. A computer readable storage medium characterized by, The computer readable storage medium stores an information transmission implementation program, and the program, when executed by a processor, implements the steps of the soft-sensor modeling implementation method according to any one of claims 1 to 4.

Images