High-alkali coal deep peak regulation self-adaptive combustion optimization system and method

Abstract

The invention relates to the technical field of power station boilers, and discloses a high-alkali coal deep peak regulation self-adaptive combustion optimization system and method.The system comprises a data acquisition module, a dimension evaluation module, an instruction analysis module, a state execution module, an optimization verification module and a real-time optimization module; obtaining a monitoring data set; the combustion state of the high-alkali coal is evaluated, and the combustion stability and the slagging tendency are obtained; instruction analysis is conducted on the combustion stability and the slagging tendency, and a parameter adjusting instruction is obtained; mapping the parameter adjustment instruction to combustion equipment in the high-alkali coal to obtain a parameter adjustment execution state of the high-alkali coal; monitoring the dynamic change of the combustion process in real time to obtain optimized verification data; according to the optimization verification data, an adaptive adjustment strategy is updated and returned to the data acquisition module, and adaptive combustion optimization of the high-alkali coal is realized; according to the method, the efficiency of deep peak regulation self-adaptive combustion optimization of the high-alkali coal can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power plant boilers, in particular to a high-alkali coal deep peak regulation self-adaptive combustion optimization system and method. BACKGROUND

[0002] In the field of high-alkali coal deep peak regulation combustion optimization, the existing technology lacks precision in the collection of combustion parameters and the evaluation of combustion state. When the traditional system collects high-alkali coal combustion parameters, it does not perform strict signal conditioning and time sequence marking, resulting in problems such as poor consistency and time sequence misplacement of parameter data, which cannot provide reliable data support for combustion state evaluation. When evaluating combustion stability and slagging tendency, only temperature or flue gas composition data is analyzed, without dynamic weight allocation based on operating conditions for comprehensive quantitative evaluation, making the evaluation results one-sided and difficult to accurately reflect the actual combustion state of high-alkali coal, which poses hidden dangers for subsequent parameter adjustment.

[0003] The existing technology has obvious defects in parameter adjustment and strategy optimization. When generating parameter adjustment instructions, the control priority is not reasonably sorted, and the applicability and logical consistency of the adjustment rules are not verified, which may lead to mismatch between the instructions and the operating state of the combustion equipment, and even cause equipment operation risks. In the optimization process, there is a lack of comprehensive monitoring of the dynamic changes of combustion after parameter adjustment, and an adaptive strategy updating mechanism based on verification data is not constructed. Only fixed strategies are used for static adjustment, which cannot adapt to the dynamic changes of the high-alkali coal combustion process in real time, and it is difficult to achieve efficient combustion optimization in the deep peak regulation scenario. SUMMARY

[0004] The present application provides a high-alkali coal deep peak regulation self-adaptive combustion optimization system and method to solve the problems raised in the background.

[0005] To achieve the above-mentioned purpose, the high-alkali coal deep peak regulation self-adaptive combustion optimization system provided by the present application is characterized in that the system comprises a data collection module, a dimension evaluation module, an instruction analysis module, a state execution module, an optimization verification module and a real-time optimization module, wherein: The data collection module is used to integrate and collect various parameter data of high-alkali coal in the combustion process to obtain a monitoring data set of the high-alkali coal; The dimension evaluation module is used to perform multi-dimensional evaluation of the combustion state of the high-alkali coal based on the monitoring data set to obtain the combustion stability and the slagging tendency of the high-alkali coal; The instruction analysis module is used to perform multi-dimensional instruction analysis on the combustion stability and the slagging tendency based on the self-adaptive adjustment strategy of the high-alkali coal to obtain parameter adjustment instructions for the high-alkali coal; The state execution module is configured to map the parameter adjustment instruction to the combustion equipment in the high-alkali coal to obtain a parameter adjustment execution state of the high-alkali coal. The optimization verification module is configured to monitor dynamic changes of the combustion process in real time according to the parameter adjustment execution state to obtain optimization verification data of the high-alkali coal. The real-time optimization module is configured to update the adaptive adjustment strategy according to the optimization verification data and return to the data acquisition module to realize adaptive combustion optimization of the high-alkali coal.

[0006] In a preferred embodiment, the data acquisition module obtains a monitoring data set of the high-alkali coal after performing integrated collection of a plurality of parameter data of the high-alkali coal in the combustion process, and is specifically configured to: synchronously collect a plurality of parameter data of the high-alkali coal in the combustion process to obtain initial parameter data of the high-alkali coal; perform signal conditioning on the initial parameter data to obtain regularized parameter data of the high-alkali coal; verify consistency of the regularized parameter data to obtain verified parameter data of the high-alkali coal; perform time series alignment on the verified parameter data based on a preset time reference to obtain time series aligned parameter data of the high-alkali coal; integrate the time series aligned parameter data into the monitoring data set of the high-alkali coal.

[0007] In a preferred embodiment, the dimension evaluation module performs multi-dimensional evaluation of the combustion state of the high-alkali coal based on the monitoring data set to obtain combustion stability and slagging tendency of the high-alkali coal, and is specifically configured to: extract combustion temperature time series data and flue gas composition time series data from the monitoring data set; perform change trend analysis on the combustion temperature time series data to obtain temperature change characteristic data of the combustion temperature time series data; perform alkali component identification on the flue gas composition time series data to obtain alkali component concentration data of the flue gas composition time series data; map the temperature change characteristic data to a preset stability standard to obtain a combustion stability determination result of the temperature change characteristic data; perform multi-level comparison between the alkali component concentration data and a preset slagging reference to obtain a slagging tendency determination result of the alkali component concentration data; generate the combustion stability and the slagging tendency of the high-alkali coal according to the combustion stability determination result and the slagging tendency determination result.

[0008] In a preferred embodiment, the dimension evaluation module, in performing linear evaluation of the weighted stability index and the weighted slagging tendency index, obtains a comprehensive combustion state evaluation value of the high-alkali coal, specifically for: obtaining operation condition data of the high-alkali coal to obtain a condition parameter representing a boiler load state in the high-alkali coal; determining a first weight factor of the combustion stability determination result and a second weight factor of the slagging tendency determination result according to the condition parameter; quantitatively correcting the combustion stability determination result based on the first weight factor to obtain a weighted stability index of the combustion stability determination result; normalizing the slagging tendency determination result based on the second weight factor to obtain a weighted slagging tendency index of the slagging tendency determination result; linearly evaluating the weighted stability index and the weighted slagging tendency index to obtain a comprehensive combustion state evaluation value of the high-alkali coal; gradually comparing the comprehensive combustion state evaluation value with a plurality of preset threshold values to determine the combustion stability and the slagging tendency of the high-alkali coal.

[0009] In a preferred embodiment, the dimension evaluation module, in performing linear evaluation of the weighted stability index and the weighted slagging tendency index, obtains a comprehensive combustion state evaluation value of the high-alkali coal, specifically for: generating a second dynamic adjustment factor of a first dynamic adjustment factor of the high-alkali coal according to the weighted stability index and the weighted slagging tendency index; nonlinearly transforming the weighted stability index based on the first dynamic adjustment factor to obtain a transformed stability index of the weighted stability index; exponentially smoothing the weighted slagging tendency index based on the second dynamic adjustment factor to obtain a transformed slagging tendency index of the weighted slagging tendency index; determining a coupling effect coefficient of the high-alkali coal according to a correlation between the transformed stability index and the transformed slagging tendency index; calculating the comprehensive combustion state evaluation value of the high-alkali coal according to the transformed stability index, the transformed slagging tendency index, and the coupling effect coefficient, wherein a calculation formula of the comprehensive combustion state evaluation value is as follows: ; In the formula, denotes the comprehensive combustion state evaluation value, denotes the transformed stability index, denotes the transformed slagging tendency index, represents the first dynamic adjustment factor, represents the second dynamic adjustment factor, represents a nonlinear adjustment parameter, represents the coupling effect coefficient, represents a logarithmic function, represents an absolute value of a numerical difference between the post-transformation stability index and the post-transformation slagging tendency index.

[0010] In a preferred embodiment, the instruction analysis module performs multi-dimensional instruction analysis on the combustion stability and the slagging tendency based on the adaptive adjustment strategy of the high-alkali coal to obtain parameter adjustment instructions of the high-alkali coal, specifically for: determining a first regulation priority of the combustion stability and a second regulation priority of the slagging tendency according to the final grade of the combustion stability and the final grade of the slagging tendency; performing strategy priority sorting on the first regulation priority and the second regulation priority to obtain a comprehensive regulation sequence of the high-alkali coal; selecting an adaptive adjustment strategy fitting rule of the high-alkali coal based on the comprehensive regulation sequence to obtain an adjustment rule set of the adaptive adjustment strategy; performing applicability verification on the adjustment rules in the adjustment rule set to obtain verified adjustment rules of the adjustment rule set; converting the verified adjustment rules into control parameter modification amounts of the high-alkali coal; generating parameter adjustment instructions of the high-alkali coal according to the control parameter modification amounts.

[0011] In a preferred embodiment, the instruction analysis module performs generating parameter adjustment instructions of the high-alkali coal according to the control parameter modification amounts, specifically for: performing regional situation division on real-time state data of the high-alkali coal based on a preset safe operation parameter range to obtain a safe adjustment boundary of the high-alkali coal; comparing and verifying the control parameter modification amounts with the safe adjustment boundary to obtain checked parameter modification amounts of the high-alkali coal; determining an execution time sequence relationship of parameter adjustment in the high-alkali coal according to the checked parameter modification amounts and the comprehensive regulation sequence; performing instruction sequence assembly on execution actions of the parameter adjustment according to the execution time sequence relationship to obtain preliminary adjustment instructions of the high-alkali coal; eliminating logical conflicts in the preliminary adjustment instructions to obtain parameter adjustment instructions of the high-alkali coal.

[0012] In a preferred implementation, the state execution module executes mapping of the parameter adjustment instruction to the combustion equipment in the high-alkali coal to obtain a parameter adjustment execution state of the high-alkali coal, and is specifically configured to: perform multi-level analysis on the parameter adjustment instruction to obtain a control parameter identifier and a target set value of the parameter adjustment instruction; match an execution mechanism in the combustion equipment according to the control parameter identifier to obtain a parameter mapping relationship of the combustion equipment; map the target set value to the parameter mapping relationship to obtain a driving signal of the combustion equipment; transmit the driving signal to the execution mechanism to trigger a parameter adjustment action of the combustion equipment; monitor an actual response state of the parameter adjustment action to obtain a parameter actual adjustment value of the parameter adjustment action; perform consistency degree checking on the parameter actual adjustment value and the target set value to obtain the parameter adjustment execution state of the high-alkali coal.

[0013] In a preferred implementation, the optimization verification module executes real-time monitoring of dynamic changes of the combustion process according to the parameter adjustment execution state to obtain optimization verification data of the high-alkali coal, and is specifically configured to: identify a target control parameter of the high-alkali coal according to the parameter adjustment execution state; track a key indicator change trajectory of the combustion process in the target control parameter within a preset time window; extract a first verification feature representing an improvement degree of combustion stability from the key indicator change trajectory; collect a second verification feature representing a change degree of slagging tendency from the key indicator change trajectory; construct the optimization verification data of the high-alkali coal according to the first verification feature and the second verification feature.

[0014] To solve the above problems, the application further provides a high-alkali coal deep peak-shaving self-adaptive combustion optimization method, which comprises: S1. Integrating and collecting various parameter data of the high-alkali coal in the combustion process to obtain a monitoring data set of the high-alkali coal; S2. Performing multi-dimensional evaluation of the combustion state of the high-alkali coal based on the monitoring data set to obtain combustion stability and slagging tendency of the high-alkali coal; S3. Performing multi-dimensional instruction analysis on the combustion stability and the slagging tendency based on a self-adaptive adjustment strategy of the high-alkali coal to obtain a parameter adjustment instruction of the high-alkali coal; S4. mapping the parameter adjustment instruction to the combustion equipment in the high-alkali coal to obtain a parameter adjustment execution state of the high-alkali coal; S5. monitoring a dynamic change of the combustion process in real time according to the parameter adjustment execution state to obtain optimization verification data of the high-alkali coal; S6. updating the adaptive adjustment strategy according to the optimization verification data and returning to S1 to realize adaptive combustion optimization of the high-alkali coal.

[0015] Compared with the prior art, the present application has the following beneficial effects: 1. The high-alkali coal deep peak regulation adaptive combustion optimization system and method provided by the present application can significantly improve the precision and effectiveness of high-alkali coal combustion optimization. The technology performs signal conditioning, consistency verification and time sequence marking on various parameters of the combustion process through the data acquisition module to generate high-quality monitoring data sets, providing reliable data basis for combustion state evaluation; the dimension evaluation module extracts temperature and flue gas composition time sequence data, dynamically allocates weights combined with operating conditions, calculates a comprehensive combustion state evaluation value through a formula, accurately determines combustion stability and slagging tendency, and makes combustion state evaluation more in line with actual operating conditions, thereby providing a scientific basis for parameter adjustment.

[0016] 2. The instruction analysis module selects adaptive rules according to control priority, generates parameter adjustment instructions after applicability verification and logical conflict elimination, and ensures that the instructions match the operating state of the combustion equipment; the state execution module maps the instructions to the combustion equipment and monitors the execution state, the optimization verification module tracks changes in key indicators to construct optimization verification data, and the real-time optimization module updates the adaptive adjustment strategy based on the verification data, forming a closed loop of "data acquisition-state evaluation-instruction execution-optimization verification-strategy update", realizing dynamic adaptive optimization of high-alkali coal combustion, and effectively improving combustion efficiency and safety in deep peak regulation scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The system architecture diagram of the high-alkali coal deep peak regulation adaptive combustion optimization system provided by an embodiment of the present application is shown in the figure. Figure 2 The flowchart of the high-alkali coal deep peak regulation adaptive combustion optimization method provided by an embodiment of the present application is shown in the figure.

[0018] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments belong to some of the embodiments of the present application but not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0020] The terms used in the embodiments of the present application are only for the purpose of describing particular embodiments and are not intended to limit the present application. The singular forms "the" and "this" used in the embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0021] Depending on the context, the word "if" or "if" as used herein can be interpreted as "when" or "when" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0022] In addition, the step sequence in each of the following method embodiments is only an example and is not strictly limited.

[0023] In fact, the server equipment deployed by the high-alkali coal deep peak shaving adaptive combustion optimization system can be composed of one or more devices. The high-alkali coal deep peak shaving adaptive combustion optimization system can be implemented as a business instance, a virtual machine, or a hardware device. For example, the high-alkali coal deep peak shaving adaptive combustion optimization system can be implemented as a business instance deployed on one or more devices in a cloud node. In short, the high-alkali coal deep peak shaving adaptive combustion optimization system can be understood as a software deployed on a cloud node for providing high-alkali coal deep peak shaving adaptive combustion optimization system for each user end. Alternatively, the high-alkali coal deep peak shaving adaptive combustion optimization system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine has application software installed for managing each user end. Alternatively, the high-alkali coal deep peak shaving adaptive combustion optimization system can also be implemented as a server composed of a plurality of same or different types of hardware devices, and one or more hardware devices are set to provide high-alkali coal deep peak shaving adaptive combustion optimization system for each user end.

[0024] In an implementation form, the high-alkali coal deep peak shaving adaptive combustion optimization system and the user end are mutually adaptive. That is, the high-alkali coal deep peak shaving adaptive combustion optimization system is installed as an application on a cloud service platform, and the user end is a client that establishes a communication connection with the application; or the high-alkali coal deep peak shaving adaptive combustion optimization system is implemented as a website, and the user end is implemented as a webpage; or the high-alkali coal deep peak shaving adaptive combustion optimization system is implemented as a cloud service platform, and the user end is implemented as an applet in an instant messaging application.

[0025] As shown in Figure 1 FIG. 1 is a system architecture diagram of a high-alkali coal deep peak shaving adaptive combustion optimization system according to an embodiment of the present application.

[0026] The high-alkali coal deep peak shaving adaptive combustion optimization system 100 can be disposed in a cloud server, and in an implementation form, can be one or more service devices, or can be installed as an application on a cloud (for example, a server of a mobile service operator, a server cluster, etc.), or can be developed as a website. According to the functions implemented, the high-alkali coal deep peak shaving adaptive combustion optimization system 100 can include a system including a data acquisition module 101, a dimension evaluation module 102, an instruction analysis module 103, a state execution module 104, an optimization verification module 105, and a real-time optimization module 106. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0027] In the embodiment of the present application, each of the above modules in the high-alkali coal deep peak shaving adaptive combustion optimization system can be independently implemented and called by other modules. The calling here can be understood as that a module can connect multiple modules of another type and provide corresponding services for the connected multiple modules. In the high-alkali coal deep peak shaving adaptive combustion optimization system provided by the embodiment of the present application, without modifying the program code, the application range of the high-alkali coal deep peak shaving adaptive combustion optimization system architecture can be adjusted by adding modules and directly calling, realizing cluster horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the high-alkali coal deep peak shaving adaptive combustion optimization system. In actual application, the above modules can be disposed in the same device or different devices, or can be disposed in a virtual device, such as a service instance in a cloud server.

[0028] The following will be described in combination with specific embodiments, respectively for each component and specific work flow of the high-alkali coal deep peak shaving adaptive combustion optimization system: The data acquisition module 101 is configured to integrate and acquire a plurality of parameter data of the high-alkali coal in the combustion process to obtain a monitoring data set of the high-alkali coal. In the embodiment of the present application, the data acquisition module acquires a plurality of parameter data of the high-alkali coal in the combustion process after performing integrated acquisition, to obtain a monitoring data set of the high-alkali coal, which is specifically used for: synchronously acquiring a plurality of parameter data of the high-alkali coal in the combustion process, to obtain initial parameter data of the high-alkali coal; performing signal conditioning on the initial parameter data, to obtain regularized parameter data of the high-alkali coal; verifying consistency of the regularized parameter data, to obtain verified parameter data of the high-alkali coal; based on a preset time reference, performing time sequence alignment on the verified parameter data, to obtain time sequence aligned parameter data of the high-alkali coal; integrating the time sequence aligned parameter data into the monitoring data set of the high-alkali coal.

[0029] Specifically, when the plurality of parameter data of the high-alkali coal in the combustion process are synchronously acquired to obtain the initial parameter data of the high-alkali coal, temperature, pressure, flue gas composition and other sensors are deployed at key positions of the combustion equipment, and original data are simultaneously acquired and stored in a unified frequency.

[0030] Further, when the initial parameter data are subjected to signal conditioning to obtain the regularized parameter data of the high-alkali coal, moving average is used to replace abnormal peak data, weak signals are amplified to a standard range, and low-frequency interference is filtered to standardize the data format.

[0031] Further, when the consistency of the regularized parameter data is verified to obtain the verified parameter data of the high-alkali coal, the data correlation is checked against a preset parameter logical relationship library, abnormal data are corrected by linear interpolation, and the verification is completed.

[0032] Further, when the verified parameter data are subjected to time sequence alignment based on a preset time reference, to obtain the time sequence aligned parameter data of the high-alkali coal, the time stamps of all data are converted into a unified format, and time deviation is corrected to ensure accurate time sequence correspondence.

[0033] Further, when the time sequence aligned parameter data are integrated into the monitoring data set of the high-alkali coal, the parameter types are sorted and added with identifiers to form a comprehensive data set with clear structure and consistent time sequence.

[0034] In summary, by synchronously acquiring a plurality of parameter data of the high-alkali coal in the combustion process, various information of the high-alkali coal during combustion can be comprehensively obtained, information loss caused by acquisition of only single or partial data is avoided, and a rich and complete data basis is provided for subsequent analysis and processing, which helps to more accurately understand the combustion characteristics and process of the high-alkali coal.

[0035] In summary, signal conditioning is performed on the initial parameter data, which can convert the original signal that may have noise or irregularities into regular parameter data, making the data easier to process and analyze, improving the quality and usability of the data, and reducing errors and errors caused by data quality problems in subsequent analysis processes.

[0036] In summary, the consistency of the regularized parameter data is verified to ensure that data from different sources or different types match and confirm each other, avoid data conflicts and contradictions, ensure the accuracy and reliability of the data, and make decisions and judgments based on the data more reliable.

[0037] In summary, the time sequence of the verified parameter data is aligned based on the preset time reference, which can make the data collected at different times have a clear time sequence and corresponding relationship, which is very important for analyzing the trend of parameters changing over time and the dynamic correlation between parameters in the high-alkali coal combustion process, and helps to find potential rules and problems in the combustion process.

[0038] In summary, the time sequence alignment parameter data is integrated into a monitoring data set, which realizes centralized management and unified storage of data, facilitates subsequent query, call and comprehensive analysis, provides convenient data support for optimization control and performance evaluation of high-alkali coal combustion process, and helps to improve the operation efficiency and safety of the high-alkali coal combustion system.

[0039] The dimension evaluation module 102 is configured to perform multi-dimensional evaluation on the combustion state of the high-alkali coal based on the monitoring data set, and obtain the combustion stability and slagging tendency of the high-alkali coal. In the embodiment of the present application, the dimension evaluation module performs multi-dimensional evaluation on the combustion state of the high-alkali coal based on the monitoring data set, and obtains the combustion stability and slagging tendency of the high-alkali coal, which is specifically used for: extracting the combustion temperature time sequence data and the flue gas composition time sequence data in the monitoring data set; performing trend analysis on the combustion temperature time sequence data to obtain temperature change characteristic data of the combustion temperature time sequence data; performing alkali component identification on the flue gas composition time sequence data to obtain alkali component concentration data of the flue gas composition time sequence data; mapping the temperature change characteristic data to a preset stability standard to obtain a combustion stability determination result of the temperature change characteristic data; performing multi-level comparison between the alkali component concentration data and a preset slagging reference to obtain a slagging tendency determination result of the alkali component concentration data; generating the combustion stability and slagging tendency of the high-alkali coal according to the combustion stability determination result and the slagging tendency determination result.

[0040] The dimension evaluation module executes the linear evaluation of the weighted stability index and the weighted slagging tendency index to obtain a comprehensive combustion state evaluation value of the high-alkali coal, specifically for: obtaining operation condition data of the high-alkali coal to obtain a condition parameter representing a boiler load state in the high-alkali coal; determining a first weight factor of the combustion stability determination result and a second weight factor of the slagging tendency determination result according to the condition parameter; quantitatively correcting the combustion stability determination result based on the first weight factor to obtain a weighted stability index of the combustion stability determination result; normalizing the slagging tendency determination result based on the second weight factor to obtain a weighted slagging tendency index of the slagging tendency determination result; linearly evaluating the weighted stability index and the weighted slagging tendency index to obtain the comprehensive combustion state evaluation value of the high-alkali coal; gradually correcting the comprehensive combustion state evaluation value with a plurality of preset threshold values to determine the combustion stability and the slagging tendency of the high-alkali coal.

[0041] The dimension evaluation module executes the linear evaluation of the weighted stability index and the weighted slagging tendency index to obtain a comprehensive combustion state evaluation value of the high-alkali coal, specifically for: generating a second dynamic adjustment factor of a first dynamic adjustment factor of the high-alkali coal according to the weighted stability index and the weighted slagging tendency index; nonlinearly transforming the weighted stability index based on the first dynamic adjustment factor to obtain a transformed stability index of the weighted stability index; exponentially smoothing the weighted slagging tendency index based on the second dynamic adjustment factor to obtain a transformed slagging tendency index of the weighted slagging tendency index; determining a coupling effect coefficient of the high-alkali coal according to a correlation between the transformed stability index and the transformed slagging tendency index; calculating the comprehensive combustion state evaluation value of the high-alkali coal according to the transformed stability index, the transformed slagging tendency index, and the coupling effect coefficient, wherein a calculation formula of the comprehensive combustion state evaluation value is as follows: ; In the formula, denotes the comprehensive combustion state evaluation value, denotes the transformed stability index, denotes the transformed slagging tendency index, denotes the first dynamic adjustment factor, denotes the second dynamic adjustment factor, denotes a non-linear adjustment parameter, denotes the coupling effect coefficient, denotes a logarithmic function, denotes an absolute value of a numerical difference between the post-transformation stability index and the post-transformation slagging tendency index.

[0042] Specifically, when extracting the combustion temperature time series data and the flue gas composition time series data in the monitoring data set, the core numerical data and the corresponding time markers are filtered according to the classification identifier to form two independent time series data sets.

[0043] Further, when performing trend analysis on the combustion temperature time series data to obtain temperature change characteristic data of the combustion temperature time series data, a fixed analysis period is divided, average temperature, extreme temperature, fluctuation amplitude and other indexes are calculated, temperature trend is judged and duration is counted, and temperature change characteristic data is integrated.

[0044] Further, when performing basic component identification on the flue gas composition time series data to obtain basic component concentration data of the flue gas composition time series data, the basic components are filtered by referring to the basic component characteristic library, the concentration values of each substance at different time points are extracted and arranged in sequence according to time.

[0045] Further, when mapping the temperature change characteristic data to the preset stability standard to obtain the combustion stability determination result of the temperature change characteristic data, the combustion stability determination result is obtained by matching the data indexes according to the preset stable, basically stable, unstable and other level standards.

[0046] Further, when performing multi-level comparison between the basic component concentration data and the preset slagging benchmark to obtain the slagging tendency determination result of the basic component concentration data, the slagging grade of each component is determined by referring to the concentration interval of the four-level slagging benchmark, and the highest grade is taken as the slagging tendency determination result.

[0047] Further, when generating the combustion stability and slagging tendency of high-alkali coal according to the combustion stability determination result and the slagging tendency determination result, the final expression of the two types of determination results is integrated to form a complete evaluation result.

[0048] Specifically, when obtaining the operation condition data of high-alkali coal to obtain the condition parameters representing the boiler load state, the fuel supply amount, steam output amount and other related data are extracted through the boiler operation data acquisition system, and the core data that can intuitively reflect the boiler load condition is selected as the condition parameters representing the boiler load state.

[0049] Further, when the first weight factor and the second weight factor are determined according to the working condition parameters, a preset working condition and weight corresponding relationship table is referred to, and the weight proportion is allocated according to the current boiler load, so that the first weight factor of the combustion stability determination result is increased at high load, and the second weight factor of the slagging tendency determination result is increased at low load.

[0050] Further, when the weighted stability index is obtained based on the first weight factor, the combustion stability determination result is assigned a basic quantization value according to the level, and then multiplied by the first weight factor, so that the weighted stability index is obtained after quantization correction.

[0051] Further, when the weighted slagging tendency index is obtained based on the second weight factor, the slagging tendency determination result is assigned an original quantization value, and then multiplied by the second weight factor to adjust to a standard value interval, and the weighted slagging tendency index is obtained after normalization processing.

[0052] Further, when the comprehensive combustion state evaluation value is obtained, the two weighted indexes are linearly combined according to a preset fixed proportion, the respective product results are added, and finally the comprehensive combustion state evaluation value is obtained.

[0053] Further, when the combustion stability and the slagging tendency of high-alkali coal are determined, the comprehensive combustion state evaluation value is compared with a plurality of preset threshold values one by one, and the final combustion stability and slagging tendency results are obtained according to the matched threshold interval.

[0054] Specifically, when the first dynamic adjustment factor and the second dynamic adjustment factor are generated according to the weighted stability index and the weighted slagging tendency index, a preset adjustment factor rule library is called, the two indexes are matched with the value intervals in the library respectively, the corresponding adjustment factor value is determined according to the interval where the index is located, and it is ensured that the factor can adapt to the correction demand of the current combustion state.

[0055] Further, when the weighted stability index is nonlinearly transformed based on the first dynamic adjustment factor, a preset nonlinear processing mode is adopted, the transformation strength is dynamically controlled according to the size of the adjustment factor, the deviation part of the original index is corrected, and finally the transformed stability index accurately reflecting the actual situation of the combustion stability is obtained.

[0056] Further, when the weighted slagging tendency index is exponentially smoothed based on the second dynamic adjustment factor, a fixed smoothing initial value is taken as the basis, an adjustment amount is obtained by combining the product of the index and the adjustment factor, a smoothing value is generated by multiple rounds of iteration fusion, short-term fluctuation interference is eliminated, and the transformed slagging tendency index reflecting the long-term trend of the slagging tendency is obtained.

[0057] Further, when determining the coupling effect coefficient, the change trend correlation of the two transformed indexes is analyzed, the change amplitude ratio in the same time period is calculated, and the corresponding coefficient is matched according to the preset coupling effect coefficient corresponding table according to the ratio. The coefficient size is positively correlated with the index correlation degree.

[0058] Further, when calculating the comprehensive combustion state evaluation value, first, fixed basic weights are allocated to the two transformed indexes and the weighted sum is calculated, and then the weighted sum is multiplied by the coupling effect coefficient, so as to fully integrate the information of the combustion stability, the slagging tendency and the coupling relationship between the two, and obtain the comprehensive combustion state evaluation value.

[0059] Specifically, the transformed stability index is obtained by nonlinear transformation of the weighted stability index based on the first dynamic adjustment factor, and the weighted stability index is obtained by quantitatively correcting the combustion stability determination result by the first weight factor, and the combustion stability determination result is obtained by mapping the temperature change characteristic data to the preset stability standard.

[0060] Further, the transformed slagging tendency index is the product of exponential smoothing processing of the weighted slagging tendency index based on the second dynamic adjustment factor, and the weighted slagging tendency index is obtained by normalizing the slagging tendency determination result by the second weight factor, and the slagging tendency determination result is obtained by multi-level comparison of the basic component concentration data with the preset slagging reference.

[0061] Further, the first dynamic adjustment factor and the second dynamic adjustment factor are determined by matching the numerical interval of the weighted stability index and the weighted slagging tendency index according to the preset adjustment factor rule library.

[0062] Further, the nonlinear adjustment parameter is a preset fixed parameter calibrated based on a large amount of high-alkali coal combustion experimental data, and is used to regulate the amplitude of nonlinear transformation.

[0063] Further, the coupling effect coefficient is obtained by analyzing the change trend correlation of the transformed stability index and the transformed slagging tendency index, calculating the change amplitude ratio of the two in the same time period, and then matching the preset coupling effect coefficient corresponding table.

[0064] Further, the formula has the meaning of comprehensively integrating the information related to the combustion stability and slagging tendency in the high-alkali coal combustion process, and accurately calculating the comprehensive combustion state evaluation value. By introducing the first dynamic adjustment factor and the second dynamic adjustment factor, the transformed stability index and the transformed slagging tendency index are respectively corrected, and the accuracy of the single index is improved. The non-linear transformation degree of the index is adjusted by means of the non-linear adjustment parameter, so that the index is more in line with the actual combustion state characteristics. The coupling effect coefficient is used to quantify the coupling effect between the two indexes according to the numerical difference between the two indexes, and finally the evaluation value which can comprehensively reflect the overall state of high-alkali coal combustion is obtained by integration calculation, which provides a scientific basis for the judgment of the combustion state.

[0065] Further, from the trend of the formula, the higher the transformed stability index and the lower the transformed slagging tendency index, the higher the comprehensive combustion state evaluation value. The increase of the first dynamic adjustment factor and the decrease of the second dynamic adjustment factor will respectively improve the positive contribution of the two indexes to the evaluation value. When the non-linear adjustment parameter increases, the sensitivity of the index to the evaluation value decreases. When the coupling effect coefficient increases, the larger the numerical difference between the two indexes, the more obvious the adjustment of the evaluation value, and the smaller the numerical difference, the weaker the adjustment effect.

[0066] Overall, the combustion temperature time series data and the flue gas composition time series data in the monitoring data set are extracted, the core data dimension closely related to the combustion stability and slagging tendency of high-alkali coal is accurately locked, the interference of irrelevant data is avoided, and strong data support is provided for subsequent accurate evaluation, ensuring that the evaluation work focuses on key elements.

[0067] Overall, the temperature change characteristic data is obtained by analyzing the change trend of the combustion temperature time series data, which can clearly capture the key information such as the fluctuation rule and the change rate of the temperature in the combustion process. These information directly reflects the stability degree of the combustion state, and provides detailed characteristics for the judgment of the combustion stability, making the stability evaluation more scientific.

[0068] Overall, the alkali component concentration data is obtained by identifying the alkali component of the flue gas composition time series data, and the core substance concentration information affecting the slagging tendency of high-alkali coal is accurately obtained. Because the content of alkali component is the key factor leading to slagging of the combustion equipment, this step provides accurate quantitative data basis for the evaluation of slagging tendency.

[0069] Overall, the combustion stability judgment result is obtained by mapping the temperature change characteristic data to the preset stability standard. Through the standardized comparison, the evaluation of the combustion stability has a clear reference basis, avoiding the error caused by subjective judgment, and ensuring the objectivity and consistency of the judgment result.

[0070] In summary, the concentration data of the basic component is compared with the preset slagging benchmark in multiple stages to obtain the slagging tendency determination result, and the multiple-stage comparison can finely distinguish the difference in slagging tendency in different concentration intervals, making the evaluation of the slagging tendency more accurate and comprehensive, and providing a precise direction for subsequent targeted adjustment.

[0071] In summary, the combustion stability and slagging tendency of high-alkali coal are generated according to the combustion stability determination result and the slagging tendency determination result, integrating the evaluation results of two key dimensions to form a complete understanding of the combustion state of high-alkali coal, effectively solving the one-sidedness problem of single-dimensional evaluation in traditional technology, and providing a comprehensive and reliable decision basis for the generation of subsequent parameter adjustment instructions.

[0072] In summary, the operating condition data of high-alkali coal is obtained and the condition parameter representing the load state of the boiler is obtained, which can accurately capture the key external operating conditions affecting the combustion state of high-alkali coal, because different boiler loads will directly change the combustion intensity, temperature distribution and flue gas composition. By including this parameter in the evaluation process, the evaluation deviation caused by deviating from the actual running scene can be avoided, and the subsequent evaluation can be more in line with the real running state of the equipment.

[0073] In summary, the first weight factor of the combustion stability determination result and the second weight factor of the slagging tendency determination result are determined according to the condition parameter, realizing the dynamic adaptation of the evaluation weight, for example, the combustion stability has a more significant impact on the safe operation of the equipment in high-load conditions, and the first weight factor can be increased, and the slagging tendency prevention and control is more critical in low-load conditions, and the second weight factor can be increased, avoiding the limitations of traditional fixed weight evaluation that cannot adapt to different conditions, and making the weight distribution more reasonable and targeted.

[0074] In summary, the weighted stability index is obtained by quantitatively correcting the combustion stability determination result based on the first weight factor, and the influence of the condition is integrated into the quantification process of the stability determination result, so that the stability index not only reflects the temperature change characteristics, but also reflects the actual importance of stability under the current condition, improving the scene adaptability and quantitative accuracy of the stability index, and providing more reliable single-dimensional data support for subsequent comprehensive evaluation.

[0075] In summary, the weighted slagging tendency index is obtained by normalizing the slagging tendency determination result based on the second weight factor, on the one hand, the data dimension difference under different slagging determination standards is eliminated through normalization, and on the other hand, the condition-related attribute is given a weight, so that the slagging tendency index can not only accurately reflect the influence of the concentration of the basic component, but also match the priority of slagging prevention and control under the current condition, ensuring that the index and the weighted stability index have a comparable and integrable basis.

[0076] Overall, the comprehensive combustion state evaluation value is obtained by linear evaluation of the weighted stability index and the weighted slagging tendency index, realizing the organic integration of the two key evaluation dimensions, avoiding the one-sidedness of single-dimensional evaluation, reasonably reflecting the influence of the two indexes in the comprehensive result through linear evaluation, forming the overall quantitative cognition of the high-alkali coal combustion state, and providing intuitive and comprehensive numerical basis for subsequent judgment.

[0077] Overall, the combustion stability and slagging tendency are determined by comparing the comprehensive combustion state evaluation value with the preset multi-level threshold value, and the evaluation level is refined by the multi-level threshold value, which can accurately distinguish the differences in combustion state corresponding to different comprehensive evaluation values, such as the levels of good, medium and poor of combustion stability and the levels of high, medium and low of slagging tendency when the comprehensive value is in different intervals, avoiding the problem of too rough judgment by traditional single threshold value, making the final combustion stability and slagging tendency more accurate and specific, and providing clear and reliable decision support for the generation of targeted parameter adjustment instructions by the instruction analysis module.

[0078] Overall, the first dynamic adjustment factor and the second dynamic adjustment factor are generated according to the weighted stability index and the weighted slagging tendency index, which can deeply bind the adjustment factor with the actual numerical characteristics of the two core indexes, avoid the problem of insufficient adaptability caused by using fixed adjustment coefficient, and ensure that the subsequent processing of the two indexes can accurately match the actual influence degree of the indexes under the current combustion state, providing an adaptive basis for index optimization processing.

[0079] Overall, the transformed stability index is obtained by nonlinear transformation of the weighted stability index based on the first dynamic adjustment factor, which can amplify or correct the numerical characteristics that are critical to the evaluation of the combustion state in the weighted stability index, such as increasing the influence weight of the index value close to the critical value on the comprehensive evaluation, solving the problem that linear processing cannot highlight the key numerical differences, and making the stability index more accurately reflect the actual combustion stability state.

[0080] Overall, the transformed slagging tendency index is obtained by exponential smoothing processing of the weighted slagging tendency index based on the second dynamic adjustment factor, which can effectively eliminate the abnormal data interference in the slagging tendency index caused by measurement fluctuations, and adapt the smoothing degree to the change rate of the slagging tendency under the current working condition through the dynamic adjustment factor, avoiding the problems of lagging or excessive smoothing caused by fixed smoothing parameters, making the slagging tendency index more stable and reliable.

[0081] In general, the coupling effect coefficient is determined according to the correlation between the transformed stability index and the transformed slagging tendency index, the mutual influence relationship between the two indexes can be accurately captured, for example, the correlation rule that the improvement of combustion stability may be accompanied by the change of slagging tendency, the correlation rule is quantified as the coupling effect coefficient and is included in the comprehensive evaluation, the deviation of the result caused by ignoring the interaction between indexes in the traditional evaluation is avoided, and the comprehensive evaluation is more in line with the actual situation of the interaction between various factors of the combustion system.

[0082] In general, by combining the transformed stability, the slagging tendency index and the coupling effect coefficient, the comprehensive combustion state evaluation value is calculated through a specific formula, the dynamic weight distribution, the index correlation influence and the numerical difference refinement processing are integrated, multi-dimensional fine quantitative evaluation is realized, the one-sidedness problem of the traditional evaluation is solved, and the obtained evaluation value can accurately reflect the actual combustion state, thereby providing a scientific basis for subsequent determination.

[0083] The instruction analysis module 103 is configured to perform multi-dimensional instruction analysis on the combustion stability and the slagging tendency based on the adaptive adjustment strategy of the high-alkali coal, and obtain parameter adjustment instructions of the high-alkali coal. In the embodiment of the present application, the instruction analysis module performs multi-dimensional instruction analysis on the combustion stability and the slagging tendency based on the adaptive adjustment strategy of the high-alkali coal, and obtains parameter adjustment instructions of the high-alkali coal, and is specifically configured to: determine a first control priority of the combustion stability and a second control priority of the slagging tendency according to the final grade of the combustion stability and the final grade of the slagging tendency; perform strategy priority sorting on the first control priority and the second control priority, and obtain a comprehensive control sequence of the high-alkali coal; select an adaptive adjustment strategy adaptation rule of the high-alkali coal based on the comprehensive control sequence, and obtain an adjustment rule set of the adaptive adjustment strategy; verify the adjustment rules in the adjustment rule set for applicability, and obtain verified adjustment rules of the adjustment rule set; convert the verified adjustment rules into control parameter modification amounts of the high-alkali coal; generate parameter adjustment instructions of the high-alkali coal according to the control parameter modification amounts.

[0084] The instruction analysis module generates parameter adjustment instructions of the high-alkali coal according to the control parameter modification amounts, and is specifically configured to: divide the real-time state data of the high-alkali coal into a region situation based on a preset safe operation parameter range, and obtain a safe adjustment boundary of the high-alkali coal; The control parameter modification amount is compared with the safety adjustment boundary to obtain a verified parameter modification amount of the high-alkali coal; According to the verified parameter modification amount and the comprehensive regulation sequence, an execution time sequence relationship of parameter adjustment in the high-alkali coal is determined. According to the execution time sequence relationship, an instruction sequence of execution actions of the parameter adjustment is assembled to obtain a preliminary adjustment instruction of the high-alkali coal. Logical conflicts in the preliminary adjustment instruction are eliminated to obtain a parameter adjustment instruction of the high-alkali coal.

[0085] Specifically, according to the final level of the combustion stability and the final level of the slagging tendency, the importance of the two in the regulation process is determined, so as to determine a first regulation priority of the combustion stability and a second regulation priority of the slagging tendency, wherein the high and low of the priority is directly reflected in the object to be processed in priority in the regulation process.

[0086] Further, the first regulation priority and the second regulation priority are arranged in a preset order to form a comprehensive regulation sequence of the high-alkali coal, which determines whether the adjustment related to the combustion stability or the adjustment related to the slagging tendency is processed first in the subsequent regulation process.

[0087] Further, according to the order of the comprehensive regulation sequence, the adaptive adjustment strategy of the high-alkali coal is selected from the adaptive adjustment strategy corresponding to each priority in the sequence, and these rules are combined to form an adjustment rule set of the adaptive adjustment strategy, so as to ensure that the rules in the rule set can match the requirements of the comprehensive regulation sequence.

[0088] Further, for each adjustment rule in the adjustment rule set, the actual working condition and the equipment running state of the current high-alkali coal combustion are combined to determine whether it can be effectively executed and achieve the expected regulation effect under the current condition, and the rules remaining after the verification are the verified adjustment rules of the adjustment rule set.

[0089] Further, each regulation requirement involved in the verified adjustment rule is converted into a variation value of a specific control parameter in the high-alkali coal combustion process, and the variation value directly corresponds to the specific change amount of the control parameter to be modified.

[0090] Further, according to the obtained control parameter modification amount, specific operation instructions are formed, which clearly indicate which control parameters need to be modified and the specific content of the modification, and finally the parameter adjustment instruction of the high-alkali coal is generated.

[0091] Specifically, the pre-set high-alkali coal safe operation parameter range standard is called, real-time state data in the high-alkali coal combustion process is collected, the real-time state data is classified and divided by comparing with the safe operation parameter range, and the parameter interval meeting the safe operation requirement is determined, which is the safe adjustment boundary of the high-alkali coal.

[0092] Further, the control parameter modification quantity obtained before is compared one by one in the parameter interval of the safe adjustment boundary, whether the control parameter modification quantity is in the safe adjustment boundary is checked, the modification quantity exceeding the boundary is corrected to meet the safety requirement, and the verified parameter modification quantity of the high-alkali coal is formed after comparison and correction.

[0093] Further, the priority order of each control content in the determined comprehensive control sequence is referred to, different control objects corresponding to the verified parameter modification quantity are combined, the execution order of different parameter adjustment actions is determined, and the execution time sequence relationship of the parameter adjustment of the high-alkali coal is determined.

[0094] Further, according to the order specified in the execution time sequence relationship, the specific execution action corresponding to each parameter adjustment is converted into a corresponding instruction segment, and the instruction segments are sequentially combined in the time sequence order to form a complete instruction framework, and the preliminary adjustment instruction of the high-alkali coal is obtained.

[0095] Further, all instruction contents in the preliminary adjustment instruction are logically checked, instruction contents that cannot be executed simultaneously due to mutual contradiction are found out, the logically conflicting instruction contents are removed from the preliminary adjustment instruction, and finally the parameter adjustment instruction of the high-alkali coal is obtained after the conflict removal processing.

[0096] In general, the first and second control priorities are determined according to the final grades of the combustion stability and the slagging tendency, which can accurately match the core needs of high-alkali coal combustion - when a certain index has a more significant impact on equipment safety or combustion efficiency, the control can be prioritized, avoiding the lag processing of key problems caused by traditional non-discriminatory control, and clearly defining the core direction for subsequent strategy execution.

[0097] In general, the first and second control priorities are determined according to the final grades of the combustion stability and the slagging tendency, which can accurately match the core needs of high-alkali coal combustion - when a certain index has a more significant impact on equipment safety or combustion efficiency, the control can be prioritized, avoiding the lag processing of key problems caused by traditional non-discriminatory control, and clearly defining the core direction for subsequent strategy execution.

[0098] In summary, the adaptation rules of the adaptive adjustment strategy selected based on the comprehensive control sequence form an adjustment rule set, which allows the rule selection to closely match the current control priority and avoid selecting rules unrelated to the core demand, ensuring that each rule in the rule set can directly serve the optimization of combustion stability or slagging tendency, and improving the relevance and practicality of the rules.

[0099] In summary, the verification of the adjustment rule set for applicability obtains verified adjustment rules, which can exclude rules that do not match the current high-alkali coal combustion conditions, such as high-load control rules that are not applicable in low-load conditions, avoiding parameter adjustment deviations caused by rule mismatch and ensuring the rationality of subsequent control parameter modification.

[0100] In summary, the verified adjustment rules are converted into control parameter modification, abstract rule requirements are converted into specific and executable parameter variation standards, and quantitative basis is provided for the generation of parameter adjustment instructions, avoiding the lack of specific numerical support for the implementation of the instructions.

[0101] In summary, the parameter adjustment instructions are generated based on the control parameter modification, integrating all previous control logic and quantitative data to form operation instructions that can be directly issued to the combustion equipment, effectively solving the problem of disconnection between traditional instruction generation and control demand and working condition adaptation, ensuring that the instructions can accurately point to the optimization target of combustion stability and slagging tendency, and providing clear basis for the operation of the subsequent state execution module.

[0102] In summary, the real-time state data of high-alkali coal is divided into regional situations based on the preset safe operation parameter range to obtain a safe adjustment boundary, which can clearly define the safe interval of parameter adjustment, avoid subsequent parameter modification exceeding the safe operation range of the equipment, and prevent equipment failure or combustion safety risks caused by parameter abnormalities from the source, providing a safety benchmark for parameter adjustment.

[0103] In summary, the control parameter modification is compared and verified with the safe adjustment boundary to obtain the checked parameter modification, which can filter and correct the parameter modification that exceeds the safe boundary, ensuring that the parameter modification used to generate the instructions fully meets the safety requirements, solving the problem of hidden dangers caused by ignoring safety verification in traditional parameter adjustment, and ensuring the safe operation of the combustion equipment.

[0104] In summary, the execution timing relationship of parameter adjustment is determined based on the checked parameter modification and the comprehensive control sequence, which allows the parameter adjustment actions to be carried out in an orderly manner according to the control priority, such as prioritizing parameter adjustment related to high-priority control targets, avoiding the confusion caused by simultaneous adjustment of multiple parameters, ensuring that the adjustment actions accurately match the control demand, and improving the logicality of parameter adjustment.

[0105] In general, the parameter adjustment execution action is instructed by assembling the sequence of instructions according to the execution time sequence relationship to obtain the preliminary adjustment instruction, the scattered parameter adjustment actions are converted into an ordered instruction framework, the instruction structure is clear, the execution sequence is clear, the equipment execution confusion caused by unordered instructions is avoided, and an ordered basis is provided for subsequent instruction issuing and execution.

[0106] In general, the parameter adjustment instruction is obtained by eliminating the logical conflicts in the preliminary adjustment instruction, which can eliminate the contradictory contents in the instruction, ensure the executability of the instruction, avoid the device from responding normally or executing incorrect actions due to logical conflicts, and ensure that the parameter adjustment instruction can be accurately and effectively implemented.

[0107] In general, the first control priority of combustion stability and the second control priority of slagging tendency are clear, the focus of control is clear, the subsequent parameter adjustment instruction generation can focus on high-priority targets, and the problem of lagging processing of key problems caused by indiscriminate control is avoided, so that the instruction can solve the core problems in the current combustion process and improve the efficiency of combustion optimization.

[0108] The state execution module 104 is configured to map the parameter adjustment instruction to the combustion equipment in the high-alkali coal to obtain a parameter adjustment execution state of the high-alkali coal. In the embodiment of the present application, the state execution module is configured to map the parameter adjustment instruction to the combustion equipment in the high-alkali coal to obtain a parameter adjustment execution state of the high-alkali coal, and specifically configured to: The parameter adjustment instruction is analyzed in multiple levels to obtain a control parameter identifier and a target setting value of the parameter adjustment instruction. According to the control parameter identifier, the execution mechanism in the combustion equipment is matched to obtain a parameter mapping relationship of the combustion equipment. The target setting value is mapped to the parameter mapping relationship to obtain a driving signal of the combustion equipment. The driving signal is transmitted to the execution mechanism to trigger a parameter adjustment action of the combustion equipment. The actual response state of the parameter adjustment action is monitored to obtain a parameter actual adjustment value of the parameter adjustment action. The parameter actual adjustment value and the target setting value are subjected to consistency degree checking to obtain a parameter adjustment execution state of the high-alkali coal.

[0109] Specifically, the generated parameter adjustment instruction is hierarchically disassembled, the exclusive identification information of each control object involved in the instruction is extracted first, and then the specific numerical standard required to be reached by each control object is determined, and through such multi-level analysis operation, the control parameter identifier and the target setting value of the parameter adjustment instruction are finally obtained.

[0110] Further, according to the control parameter identifier obtained by analysis, a precise search is performed in all actuators included in the combustion equipment, the actuator responsible for executing the adjustment of each control parameter identifier is found, and a corresponding association between the control parameter identifier and the actuator is established, thereby obtaining the parameter mapping relationship of the combustion equipment.

[0111] Further, the target set value obtained by analysis is filled in the parameter mapping relationship, so that each actuator has a clear corresponding target value requirement, and the corresponding relationship with the target set value is converted into an electrical signal or a mechanical signal that can be recognized and responded by the actuator, and then the driving signal of the combustion equipment is obtained.

[0112] Further, the generated driving signal is accurately sent to the corresponding actuator through the signal transmission line inside the combustion equipment, and the actuator starts to operate immediately after receiving the driving signal and performs specific operations according to the instruction content of the signal, thereby triggering the parameter adjustment action of the combustion equipment.

[0113] Further, the state monitoring device installed on the combustion equipment is used to track the development process of the parameter adjustment action in real time, record the actual changes of various parameters after the operation of the actuator, and accurately obtain the specific value after the implementation of the parameter adjustment action, i.e., the actual adjustment value of the parameter adjustment action.

[0114] Further, the actual adjustment value obtained and the target set value determined before are compared one by one to judge the degree of coincidence between them, if the actual adjustment value is completely consistent with the target set value or within the preset allowed coincidence range, it is determined that the execution state is qualified, if it exceeds the allowed range, it is determined that the execution state is unqualified, according to the consistency checking result, the parameter adjustment execution state of the high-alkali coal is finally obtained.

[0115] In summary, the control parameter identifier and the target set value are obtained by multi-level analysis of the parameter adjustment instruction, which can accurately split the core information in the instruction, clearly specify the specific parameters to be adjusted and the target value to be reached, avoid the execution deviation caused by ambiguous instruction information, lay a foundation for subsequent precise matching with the combustion equipment, and ensure that the instruction analysis and equipment control requirements are highly consistent.

[0116] In summary, the actuator in the combustion equipment is matched according to the control parameter identifier, and the parameter mapping relationship is obtained, the direct association between the instruction parameter and the equipment execution component is established, for example, the "air supply flow adjustment" parameter is corresponded to the fan actuator, the adjustment invalidation problem caused by the mismatch between the parameter and the actuator is avoided, and the accuracy of the instruction landing is improved.

[0117] In general, the target set value is mapped to the parameter mapping relationship to generate a driving signal, which converts the abstract parameter target into a specific signal recognizable by the actuator, so that the actuator can clearly know the adjustment direction and target, solves the problem of incompatibility between the instruction and the device signal, and ensures that the actuator can accurately start the adjustment action according to the driving signal.

[0118] In general, the driving signal is transmitted to the actuator to trigger the parameter adjustment action, which realizes the effective connection from the instruction to the device operation, avoids the adjustment lag caused by the interruption or delay of signal transmission, ensures that the parameter adjustment action starts in time according to the instruction requirement, guarantees that the combustion equipment can quickly respond to the optimization demand, and improves the timeliness of parameter adjustment.

[0119] In general, the actual response state of the parameter adjustment action is monitored to obtain the actual parameter adjustment value, which can realize real-time control of the actual effect of the device after executing the adjustment, avoid the situation of only relying on the instruction issuing and ignoring the actual execution result, provide real data support for subsequent verification of the adjustment effect, and ensure dynamic control of the running state of the combustion equipment.

[0120] In general, the actual parameter adjustment value and the target set value are consistent to obtain the parameter adjustment execution state, which can clearly judge whether the adjustment action reaches the expected target, and clearly indicate the execution qualified or unqualified state, provide a basis for the subsequent optimization verification module to monitor the dynamic changes of the combustion process, and also provide feedback for the iteration and update of the adaptive adjustment strategy, and ensure the effective operation of the combustion optimization closed loop.

[0121] The optimization verification module 105 is configured to monitor the dynamic changes of the combustion process in real time according to the parameter adjustment execution state, and obtain the optimization verification data of the high-alkali coal. In the embodiment of the present application, the optimization verification module is configured to monitor the dynamic changes of the combustion process in real time according to the parameter adjustment execution state, and obtain the optimization verification data of the high-alkali coal, and specifically configured to: According to the parameter adjustment execution state, the target control parameter of the high-alkali coal is identified; In a preset time window, the change trajectory of the key indicators of the target control parameter in the combustion process is tracked; The first verification feature representing the improvement degree of combustion stability in the change trajectory of the key indicators is extracted; The second verification feature representing the change degree of the slagging tendency in the change trajectory of the key indicators is collected; According to the first verification feature and the second verification feature, the optimization verification data of the high-alkali coal is constructed.

[0122] Specifically, according to the qualified or unqualified determination result recorded in the parameter adjustment execution state, the control parameters that are modified in the current parameter adjustment action and directly affect the combustion effect are locked, and it is clear that these parameters are the target control parameters of high-alkali coal that need to be focused on.

[0123] Further, a fixed time length is set as a time window, and the numerical value changes of the key indicators in the target control parameters closely related to the combustion process are continuously recorded in the time window to form a complete numerical fluctuation path, so as to track the change trajectory of the key indicators.

[0124] Further, the key indicator change trajectory is feature extracted, and specific information that can reflect the improvement of flame stability and combustion efficiency in the combustion process is screened out. These information can directly reflect the improvement degree of combustion stability, and is determined as the first verification feature.

[0125] Further, the key indicator change trajectory is continuously data collected, and the indicator change information related to the slagging situation of the inner wall of the combustion equipment is focused on. These information can clearly show the strengthening or weakening of the slagging tendency, and is determined as the second verification feature.

[0126] Further, the first verification feature and the second verification feature extracted are classified and arranged, and the specific contents of the two types of features are combined according to the preset format to form a complete data set that can reflect the combustion optimization effect, that is, the optimization verification data of high-alkali coal.

[0127] In general, the target control parameters of high-alkali coal are identified according to the parameter adjustment execution state, which can accurately lock the core control object affected by the current parameter adjustment, avoid invalid monitoring of irrelevant parameters, ensure that the subsequent monitoring focuses on parameters directly related to the combustion optimization effect, reduce the waste of monitoring resources, improve the pertinence and efficiency of monitoring, and lay a precise parameter foundation for subsequent tracking of key indicators.

[0128] In general, the change trajectory of the key indicators in the target control parameters in the combustion process is tracked in the preset time window, which can record the dynamic change process of the key indicators over time after parameter adjustment, avoid information fragmentation or redundancy caused by non-fixed monitoring time, ensure that the trajectory data obtained is continuous and complete, and provide comprehensive data support for subsequent extraction of verification features, and accurately reflect the dynamic influence of parameter adjustment on the combustion process.

[0129] Overall, the first verification feature representing the improvement degree of combustion stability in the extracted key indicator change trajectory can convert abstract trajectory data into quantifiable stability optimization basis, intuitively present the improvement of combustion stability after parameter adjustment, solve the problem of difficult precise measurement of stability optimization effect in traditional monitoring, and provide clear feature support for judging whether the combustion stability meets the expected target.

[0130] Overall, the second verification feature representing the change degree of slagging tendency in the collected key indicator change trajectory can accurately capture the changes of parameters related to slagging after parameter adjustment, clearly reflect the strengthening or weakening trend of slagging tendency, avoid potential safety hazards caused by ignoring slagging tendency change monitoring, provide reliable feature basis for slagging prevention and control effect evaluation, and ensure that combustion optimization considers both efficiency and safety.

[0131] Overall, the optimization verification data constructed based on the first and second verification features integrates the core effect data of combustion stability and slagging tendency, avoiding one-sided evaluation. This data provides precise feedback for strategy updating, ensures the effective operation of the adaptive closed loop, and improves the precision of high-alkali coal deep peak-shaving combustion optimization.

[0132] The real-time optimization module 106 is configured to update the adaptive adjustment strategy according to the optimization verification data and return the data collection module, thereby realizing adaptive combustion optimization of the high-alkali coal.

[0133] In the embodiment of the present application, the optimization verification data is comprehensively analyzed, and the improvement effect of combustion stability reflected by the first verification feature and the change of slagging tendency embodied by the second verification feature are focused on to determine whether the current adaptive adjustment strategy can meet the expected demand of high-alkali coal combustion optimization.

[0134] Further, according to the analysis result, if the combustion stability does not reach the ideal state or the slagging tendency is not effectively controlled, the content such as the adjustment priority sorting rule, the adaptation rule screening standard, etc. in the adaptive adjustment strategy is modified and improved, and if the optimization effect meets the expectation, the original strategy core content is retained and the details are fine-tuned, thereby completing the update of the adaptive adjustment strategy.

[0135] Further, the updated adaptive adjustment strategy is transmitted to the data collection module, so that the data collection module can accurately collect relevant data according to the new strategy requirement in the subsequent high-alkali coal combustion state monitoring process, start the next round of combustion state analysis, parameter adjustment and optimization verification process, and realize adaptive combustion optimization of the high-alkali coal.

[0136] In general, the real-time optimization module updates the adaptive adjustment strategy according to the optimization verification data, which can bind the adjustment strategy and the actual optimization effect of high-alkali coal combustion in depth - the first verification feature and the second verification feature in the optimization verification data directly reflect the effectiveness of the current strategy, if the stability does not meet the standard or the slagging tendency is not alleviated, the adjustment strategy can be modified in terms of control priority, adaptation rule and other contents, avoiding the limitation that the traditional fixed strategy cannot adapt to the dynamic changes of combustion, ensuring that the adjustment strategy always fits the actual combustion demand, and improving the dynamic adaptability and optimization accuracy of the strategy.

[0137] In general, the updated adaptive adjustment strategy is returned to the data acquisition module, which can start the next round of "data acquisition - state assessment - instruction analysis - execution verification - strategy update" closed-loop process, so that the high-alkali coal combustion optimization forms a continuous iterative adaptive mechanism. The data acquisition module can more accurately collect parameter data matching the current optimization target according to the requirements of the new strategy, provide data support for the adaptation of the new strategy for subsequent combustion state assessment and parameter adjustment instruction generation, avoid interruption or disconnection of the optimization process, ensure continuous progress of the combustion optimization, and effectively improve the stability of the combustion efficiency and equipment operation safety in the deep peak regulation scenario of high-alkali coal.

[0138] Referring to Figure 2 FIG. 1 is a flowchart of a high-alkali coal deep peak regulation adaptive combustion optimization method provided by an embodiment of the present application. In this embodiment, the high-alkali coal deep peak regulation adaptive combustion optimization method comprises: S1. Integrating a plurality of parameter data of high-alkali coal in the combustion process after collection to obtain a monitoring data set of the high-alkali coal; S2. Based on the monitoring data set, performing multi-dimensional assessment of the combustion state of the high-alkali coal to obtain the combustion stability and the slagging tendency of the high-alkali coal; S3. Based on the adaptive adjustment strategy of the high-alkali coal, performing multi-dimensional instruction analysis on the combustion stability and the slagging tendency to obtain parameter adjustment instructions for the high-alkali coal; S4. Mapping the parameter adjustment instructions to the combustion equipment in the high-alkali coal to obtain a parameter adjustment execution state of the high-alkali coal; S5. Real-time monitoring of the dynamic changes of the combustion process according to the parameter adjustment execution state to obtain optimization verification data of the high-alkali coal; S6. Updating the adaptive adjustment strategy according to the optimization verification data, and returning to S1 to realize adaptive combustion optimization of the high-alkali coal.

[0139] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0140] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. The artificial intelligence is a theory, method, technology and application system for simulating, extending and expanding human intelligence by using a digital computer or a machine controlled by a digital computer, perceiving an environment, acquiring knowledge and using the knowledge to obtain optimal results.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A deep peak-shaving adaptive combustion optimization system for high-alkali coal, characterized in that, The system includes a data acquisition module, a dimension evaluation module, an instruction parsing module, a state execution module, an optimization verification module, and a real-time optimization module, wherein: The data acquisition module is used to integrate various parameter data of high-alkali coal during the combustion process after acquisition to obtain the monitoring dataset of the high-alkali coal. The dimensional assessment module is used to perform a multi-dimensional assessment of the combustion state of the high-alkali coal based on the monitoring dataset, and to obtain the combustion stability and slagging tendency of the high-alkali coal. The instruction parsing module is used to perform multi-dimensional instruction parsing on the combustion stability and slagging tendency based on the adaptive adjustment strategy of the high-alkali coal, so as to obtain the parameter adjustment instructions for the high-alkali coal. The status execution module is used to map the parameter adjustment command to the combustion equipment in the high-alkali coal to obtain the parameter adjustment execution status of the high-alkali coal; The optimization verification module is used to adjust the execution state according to the parameters, monitor the dynamic changes of the combustion process in real time, and obtain the optimization verification data of the high-alkali coal. The real-time optimization module is used to update the adaptive adjustment strategy based on the optimization verification data and return it to the data acquisition module to realize the adaptive combustion optimization of the high-alkali coal.

2. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 1, characterized in that, The data acquisition module, after performing integrated acquisition, collects various parameter data of high-alkali coal during the combustion process, obtaining a monitoring dataset of the high-alkali coal, which is specifically used for: Multiple parameter data of high-alkali coal are collected simultaneously during the combustion process to obtain the initial parameter data of the high-alkali coal; Signal conditioning is performed on the initial parameter data to obtain the regularized parameter data of the high-alkali coal; The consistency of the regularized parameter data is verified to obtain the verified parameter data of the high-alkali coal; Based on a preset time reference, the verified parameter data is time-series aligned to obtain the time-series aligned parameter data of the high-alkali coal. The time-series alignment parameter data are integrated into the monitoring dataset for the high-alkali coal.

3. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 1, characterized in that, The dimensional assessment module performs a multi-dimensional assessment of the combustion state of the high-alkali coal based on the monitoring dataset, obtaining the combustion stability and slagging tendency of the high-alkali coal. Specifically, it is used for: Extract the combustion temperature time-series data and flue gas composition time-series data from the monitoring dataset; By performing trend analysis on the combustion temperature time series data, the temperature change characteristic data of the combustion temperature time series data are obtained; The alkaline component concentration data of the flue gas composition time series data are obtained by identifying alkaline components in the flue gas composition time series data. The temperature change feature data is mapped to a preset stability standard to obtain the combustion stability determination result of the temperature change feature data; The alkaline component concentration data is compared with a preset slagging benchmark at multiple levels to obtain the slagging tendency determination result of the alkaline component concentration data. Based on the combustion stability determination results and the slagging tendency determination results, the combustion stability and slagging tendency of the high-alkali coal are generated.

4. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 3, characterized in that, The dimensional assessment module, based on the combustion stability determination result and the slagging tendency determination result, generates the combustion stability and slagging tendency of the high-alkali coal, specifically for: The operating condition data of the high-alkali coal are obtained to obtain the operating condition parameters in the high-alkali coal that characterize the boiler load status. Based on the operating parameters, determine the first weighting factor of the combustion stability determination result and the second weighting factor of the slagging tendency determination result; Based on the first weighting factor, the combustion stability determination result is quantitatively corrected to obtain the weighted stability index of the combustion stability determination result. Based on the second weighting factor, the slagging tendency determination result is normalized to obtain the weighted slagging tendency index of the slagging tendency determination result. The comprehensive combustion state assessment value of the high-alkali coal is obtained by linearly evaluating the weighted stability index and the weighted slagging tendency index. The comprehensive combustion state assessment value is compared with the preset multi-level thresholds step by step to determine the combustion stability and slagging tendency of the high-alkali coal.

5. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 4, characterized in that, The dimensional assessment module performs a linear assessment of the weighted stability index and the weighted slagging tendency index to obtain a comprehensive combustion state assessment value for the high-alkali coal, specifically used for: Based on the weighted stability index and the weighted slagging tendency index, the second dynamic adjustment factor of the first dynamic adjustment factor of the high-alkali coal is generated. Based on the first dynamic adjustment factor, the weighted stability index is subjected to a nonlinear transformation to obtain the transformed stability index of the weighted stability index. Based on the second dynamic adjustment factor, the weighted slagging tendency index is subjected to exponential smoothing to obtain the transformed slagging tendency index of the weighted slagging tendency index. The coupling effect coefficient of the high-alkali coal is determined based on the correlation between the transformed stability index and the transformed slagging tendency index. Based on the transformed stability index, transformed slagging tendency index, and coupling effect coefficient, the comprehensive combustion state assessment value of the high-alkali coal is calculated, wherein the calculation formula for the comprehensive combustion state assessment value is as follows: ； In the formula, This represents the comprehensive combustion status assessment value. This represents the stability index after the transformation. This indicates the slagging tendency index after the transformation. This represents the first dynamic adjustment factor. This represents the second dynamic adjustment factor. This represents the nonlinear adjustment parameter. This represents the coupling effect coefficient. Represents the logarithmic function. This represents the absolute value of the numerical difference between the transformed stability index and the transformed slagging tendency index.

6. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 1, characterized in that, The instruction parsing module executes an adaptive adjustment strategy based on the high-alkali coal, performing multi-dimensional instruction parsing on the combustion stability and slagging tendency to obtain parameter adjustment instructions for the high-alkali coal, specifically used for: Based on the final level of combustion stability and the final level of slagging tendency, a first control priority for combustion stability and a second control priority for slagging tendency are determined. The first and second control priorities are ranked by strategy priority to obtain the comprehensive control sequence for the high-alkali coal. Based on the comprehensive control sequence, the adaptation rules of the adaptive adjustment strategy in the high-alkali coal are selected to obtain the adjustment rule set of the adaptive adjustment strategy; The applicability of the adjustment rules in the adjustment rule set is verified to obtain the verified adjustment rules of the adjustment rule set. The verification adjustment rules are then converted into the control parameter modification amounts for the high-alkali coal. Based on the modification amount of the control parameters, a parameter adjustment instruction for the high-alkali coal is generated.

7. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 6, characterized in that, The instruction parsing module, when executing the parameter adjustment instruction for the high-alkali coal based on the control parameter modification amount, is specifically used for: Based on the preset safe operating parameter range, the real-time status data of the high-alkali coal is divided into regional situations to obtain the safe adjustment boundary of the high-alkali coal. The control parameter modification amount is compared and verified with the safety adjustment boundary to obtain the verified parameter modification amount for the high-alkali coal; Based on the verified parameter modification amount and the comprehensive control sequence, the execution timing relationship of parameter adjustment in the high-alkali coal is determined; According to the execution timing relationship, the execution actions of the parameter adjustment are assembled into an instruction sequence to obtain the preliminary adjustment instruction for the high-alkali coal; By eliminating logical conflicts in the preliminary adjustment instructions, the parameter adjustment instructions for the high-alkali coal are obtained.

8. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 1, characterized in that, The state execution module, when executing the parameter adjustment instruction mapped to the combustion equipment in the high-alkali coal, obtains the parameter adjustment execution state of the high-alkali coal, specifically for: The parameter adjustment command is parsed at multiple levels to obtain the control parameter identifier and target setting value of the parameter adjustment command. Based on the control parameter identifier, the actuator in the combustion device is matched to obtain the parameter mapping relationship of the combustion device; The target setpoint is mapped to the parameter mapping relationship to obtain the drive signal of the combustion device; The drive signal is transmitted to the actuator to trigger the parameter adjustment action of the combustion device; Monitor the actual response status of the parameter adjustment action to obtain the actual parameter adjustment value of the parameter adjustment action; The consistency between the actual adjusted value of the parameter and the target set value is verified to obtain the parameter adjustment execution status of the high-alkali coal.

9. The high-alkali coal deep peak-shaving adaptive combustion optimization system as described in claim 1, characterized in that, The optimization verification module, while adjusting the execution state according to the parameters and monitoring the dynamic changes of the combustion process in real time, obtains the optimization verification data of the high-alkali coal, specifically used for: Adjust the execution status according to the parameters, and identify the target control parameters for the high-alkali coal; Within a preset time window, track the changes in key indicators of the combustion process in the target control parameters; Extract the first verification feature characterizing the degree of improvement in combustion stability from the change trajectory of the key indicators; Collect the second verification feature representing the degree of change in slagging tendency from the change trajectory of the key indicators; Based on the first verification feature and the second verification feature, optimized verification data for the high-alkali coal is constructed.

10. A deep peak-shaving adaptive combustion optimization method for high-alkali coal, characterized in that, The method includes: S1. Integrate the collected data on various parameters of high-alkali coal during the combustion process to obtain the monitoring dataset of the high-alkali coal; S2. Based on the monitoring dataset, the combustion state of the high-alkali coal is evaluated in multiple dimensions to obtain the combustion stability and slagging tendency of the high-alkali coal; S3. Based on the adaptive adjustment strategy of the high-alkali coal, perform multi-dimensional instruction analysis on the combustion stability and slagging tendency to obtain the parameter adjustment instructions for the high-alkali coal; S4. Map the parameter adjustment command to the combustion equipment in the high-alkali coal to obtain the parameter adjustment execution status of the high-alkali coal; S5. Adjust the execution status according to the parameters and monitor the dynamic changes of the combustion process in real time to obtain the optimized verification data of the high-alkali coal; S6. Based on the optimized verification data, update the adaptive adjustment strategy and return to S1 to achieve adaptive combustion optimization of the high-alkali coal.

Images