Thermal power plant chemical supervision data processing method, device, equipment and medium
By classifying and weighting the chemical monitoring indicators of thermal power plants, and combining historical data and industry standards, the weights are dynamically adjusted to generate an operation assessment report, which solves the problem of low intelligence level in chemical monitoring of thermal power plants and achieves more accurate equipment status evaluation and risk identification.
Patent Information
- Application Number
- CN202511181825.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-22
- Publication Date
- 2025-12-23
Smart Images
Figure CN121189889A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of intelligent diagnosis, in particular to a method and device for processing chemical supervision data of a thermal power plant, equipment and a medium. BACKGROUND
[0002] With the continuous expansion of the scale of thermal power plants and the increase of equipment complexity, chemical supervision plays an increasingly important role in ensuring the safe and stable operation of thermal equipment. Chemical supervision monitors and analyzes the quality of water, steam, oil, gas, fuel and ash in thermal power plants in real time through online instrument measurement and laboratory detection analysis, obtains a large amount of monitoring data, and through data analysis, diagnoses the reliability and economy of system operation and proposes optimization adjustment suggestions.
[0003] In related technologies, the traditional statistical and analysis method relies on the comparison of single-point single-item values with standard values to obtain single-point single-item accuracy indexes, which cannot comprehensively reflect the running status of the whole process of the system and is difficult to provide accurate and effective diagnosis suggestions. When periodically counting the indexes of the whole plant, the arithmetic mean of the pass rates of single-item indexes is used, and each index has the same weight, which cannot reflect the influence degree of different indexes on the actual operation of the equipment. The traditional statistical and analysis method has low intelligence level and large personnel workload, and cannot meet the development requirements of intelligent power plants. SUMMARY
[0004] The present application provides a method and device for processing chemical supervision data of a thermal power plant, equipment, medium and program to solve the problems in related technologies that the running status of the whole process of the system cannot be comprehensively reflected, it is difficult to provide accurate and effective diagnosis suggestions, the intelligence level is low, and the overall personnel cost is high.
[0005] The first aspect embodiment of the present application provides a method for processing chemical supervision data of a thermal power plant, comprising the following steps: obtaining chemical supervision indexes of a thermal power plant and chemical supervision data of each chemical supervision index; extracting sampling values of each supervision parameter in the chemical supervision data, determining the influence weight of each supervision parameter in the chemical supervision data according to the index type of the chemical supervision index, and correcting the influence weight of the corresponding supervision parameter according to the sampling value of each supervision parameter in the chemical supervision data; calculating the influence score of the corresponding chemical supervision index on the thermal power plant by weighting according to the sampling value and influence weight of each parameter in the chemical supervision data, and generating a running evaluation report of the thermal power plant according to the influence score of each chemical supervision index and the current running data of the thermal power plant.
[0006] Optionally, determining the influence weight of each monitoring parameter in the chemical monitoring data based on the indicator type of the chemical monitoring indicator includes: inputting the indicator type of the chemical monitoring indicator into a target evaluation model, and the target evaluation model outputting the influence weight of each monitoring parameter in the chemical monitoring data, wherein the target evaluation model is trained and generated based on the historical operating data of the thermal power plant, the indicator type of each chemical monitoring indicator, and the influence weight of each monitoring parameter.
[0007] Optionally, the step of correcting the influence weight of the corresponding monitoring parameter based on the sampled value of each monitoring parameter in the chemical monitoring data includes: obtaining the fluctuation range and fluctuation duration of the sampled value of each monitoring parameter; querying a first mapping table using the fluctuation range and fluctuation duration as an index to obtain the correction coefficient of the corresponding monitoring parameter; and correcting the influence weight based on the correction coefficient.
[0008] Optionally, before obtaining the chemical monitoring data for each chemical monitoring indicator, the process includes: classifying the chemical monitoring indicators of the thermal power plant into at least one indicator type based on the physical damage mechanism of the thermal equipment caused by the chemical monitoring indicator data of the thermal power plant.
[0009] Optionally, the index type includes at least one of the following: water vapor index, scaling index, corrosion index, oil quality index, cleanliness index, and system operation index.
[0010] Optionally, generating an operation assessment report for the thermal power plant based on the impact score of each chemical monitoring indicator and the current operating data of the thermal power plant includes: if the impact score of any chemical monitoring indicator exceeds the target safety threshold, generating an operation assessment report for the thermal power plant based on the impact score of the chemical monitoring indicator and the current operating data of the thermal power plant, and generating a risk marker based on the impact score of the chemical monitoring indicator that exceeds the target safety threshold.
[0011] A second aspect of this application provides a chemical monitoring data processing device for a thermal power plant, comprising: an acquisition module for acquiring chemical monitoring indicators of the thermal power plant and chemical monitoring data for each chemical monitoring indicator; an extraction module for extracting sampled values of each monitoring parameter from the chemical monitoring data, determining the influence weight of each monitoring parameter in the chemical monitoring data according to the indicator type of the chemical monitoring indicator, and correcting the influence weight of the corresponding monitoring parameter according to the sampled values of each monitoring parameter in the chemical monitoring data; and a calculation module for calculating the weighted impact score of the corresponding chemical monitoring indicator on the thermal power plant according to the sampled values and influence weights of each parameter in the chemical monitoring data, and generating an operation evaluation report of the thermal power plant according to the impact score of each chemical monitoring indicator and the current operating data of the thermal power plant.
[0012] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the chemical monitoring data processing method for thermal power plants as described in the above embodiments.
[0013] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to perform the chemical monitoring data processing method for thermal power plants as described in the above embodiments.
[0014] A fifth aspect of this application provides a computer program product, including a computer program or instructions, which, when executed, implement the chemical monitoring data processing method for thermal power plants as described in the above embodiments.
[0015] Therefore, this application has at least the following beneficial effects: This application embodiment can extract the sampled value of each monitoring parameter in the chemical monitoring data, determine the influence weight of each monitoring parameter in the chemical monitoring data according to the index type of the chemical monitoring index, and correct the influence weight of the corresponding monitoring parameter according to the sampled value of each monitoring parameter in the chemical monitoring data. The dynamic weight correction improves risk sensitivity and significantly enhances the ability to capture hidden risks. According to the sampled value and influence weight of each parameter in the chemical monitoring data, the influence score of the corresponding chemical monitoring index on the thermal power plant is calculated by weighting. According to the influence score of each chemical monitoring index and the current operating data of the thermal power plant, an operation assessment report of the thermal power plant is generated, which improves the diagnostic accuracy and subsequent processing efficiency.
[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a chemical monitoring data processing method for a thermal power plant according to an embodiment of this application; Figure 2 This is a block diagram of a chemical monitoring data processing device for a thermal power plant provided according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation
[0018] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0019] In related technologies, statistical and analytical methods have the following shortcomings: First, the pass rate of analytical indicators is based on the arithmetic mean of individual indicators, with each individual value having the same weight, which may mask the impact of some non-compliant values. Second, it fails to differentiate and analyze the actual impact of each data point on the thermal system, making it impossible to provide professional diagnostic opinions. Third, it judges whether data is qualified based on a single standard, ignoring the impact of data fluctuation range. Fourth, the current statistical and evaluation methods for chemical monitoring data mostly rely on manual data recording and calculation, which does not meet the development needs of modern smart power plants.
[0020] To address these issues, this application proposes a novel chemical monitoring data analysis method. By introducing the concept of an influence index, different indicators are classified and weighted to achieve a more scientific and reasonable evaluation of the system and equipment status. Specifically: Chemical monitoring indicators are categorized according to the different states of the systems and equipment they reflect. For example, water and steam monitoring indicators are categorized based on their impact on scaling, salt deposits, and corrosion in the thermal system; oil quality indicators are categorized based on their potential impact on the system, causing blockages, corrosion, and overheating; and coal quality indicators are categorized and statistically analyzed based on their impact on combustion, heat exchange surface wear, and corrosion. Each category of indicators is further subdivided, and each indicator is assigned a corresponding factor weight (i.e., an impact index) based on its degree of impact on system and equipment operation. Finally, a coefficient is added to the impact index based on the range of indicator fluctuations, incorporating the impact of the indicator's fluctuation range into the evaluation system.
[0021] For example, in water and steam monitoring, the iron content in feedwater is given a high weight due to its impact on scaling on the heating surface; the conductivity of feedwater and steam are important factors affecting corrosion and salt accumulation on the heating surface, as are pH value and inorganic anion content, but different weights are assigned to these factors because of their varying degrees of influence; for non-compliant indicators, different coefficients are given based on the extent of their exceeding the limit, thus enhancing the evaluation of the degree to which the indicator exceeds the limit.
[0022] Therefore, this application classifies and evaluates various chemical indicators, and assigns different weight values to each indicator based on historical data and industry standards. This allows for precise monitoring of the water-gasoline system and combustion system of thermal power plants through chemical monitoring data analysis. This method not only improves the rationality of data analysis but also provides a scientific basis for equipment maintenance and system improvement. By introducing professional statistical analysis tools and intelligent algorithms, this method can collect and process large amounts of chemical monitoring data in real time, automatically identify potential risk factors, and generate early warning information, thereby effectively reducing equipment failure rates and improving energy efficiency. The successful implementation of this application will significantly improve the effectiveness and reliability of chemical monitoring in thermal power plants, promoting the development of technical supervision work towards a more efficient and intelligent direction.
[0023] Compared to existing technologies, this application has the following advantages: it improves the rationality of the statistical methods for chemical monitoring data, making the statistical results more realistic and comparable; by introducing the concept of an influence index, it enables a reasonable allocation of weights for different indicators, avoiding a "one-size-fits-all" evaluation approach; this method can quantify the degree of impact of different indicators on equipment operation, providing a scientific basis for subsequent diagnosis and optimization. This application introduces intelligent analysis methods, which can reduce the intensity of manual statistical and analytical work, improve analytical efficiency, and enhance the level of intelligent monitoring in thermal power plants.
[0024] The following description, with reference to the accompanying drawings, outlines a method, apparatus, equipment, medium, and program for processing chemical monitoring data in thermal power plants, according to embodiments of this application.
[0025] Specifically, Figure 1 This is a flowchart illustrating a chemical monitoring data processing method for a thermal power plant, provided as an embodiment of this application.
[0026] like Figure 1 As shown, the chemical monitoring data processing method for this thermal power plant includes the following steps: In step S101, chemical monitoring indicators of thermal power plants and chemical monitoring data for each chemical monitoring indicator are obtained. It is understood that the embodiments of this application can obtain chemical monitoring indicators of thermal power plants and chemical monitoring data for each chemical monitoring indicator, so as to facilitate the subsequent extraction of the sampled value of each monitoring parameter in the chemical monitoring data and the determination of the influence weight of each monitoring parameter in the chemical monitoring data according to the indicator type of the chemical monitoring indicator.
[0027] In this embodiment of the application, before obtaining the chemical monitoring data for each chemical monitoring indicator, the process includes: classifying the chemical monitoring indicators of the thermal power plant into at least one indicator type based on the physical damage mechanism of the thermal equipment caused by the chemical monitoring indicator data of the thermal power plant.
[0028] The types of indicators include at least one of the following: water vapor indicators, scaling indicators, corrosion indicators, oil quality indicators, cleanliness indicators, and system operation indicators.
[0029] It is understood that, in this embodiment of the application, since different categories of indicators have different impact paths on equipment safety, the chemical monitoring indicators are scientifically classified according to the physical damage mechanism, thereby improving the scientific nature and pertinence of the assessment method.
[0030] In step S102, the sampled value of each monitoring parameter in the chemical monitoring data is extracted, the influence weight of each monitoring parameter in the chemical monitoring data is determined according to the index type of the chemical monitoring index, and the influence weight of the corresponding monitoring parameter is corrected according to the sampled value of each monitoring parameter in the chemical monitoring data. It is understood that the embodiments of this application can extract the sampled value of each monitoring parameter in the chemical monitoring data, determine the influence weight of each monitoring parameter according to the index type, and then dynamically correct the weight based on the sampled value. This enhances the ability to identify early anomalies and gradual trends, helps to accurately locate the root cause of the problem, avoids misjudgment caused by the mixture of multiple risks, improves the scientificity and rationality of the subsequent overall assessment, and makes the diagnosis more accurate.
[0031] Specifically, the water vapor indicators in the chemical monitoring data are categorized into those reflecting scaling trends, corrosion trends, and salt accumulation trends on the heating surface, and each category is assigned a specific weight value. For example, in the scaling impact index, the feedwater iron content has the largest weight value (0.40), followed by feedwater hydrogen conductivity (0.25), feedwater pH value (0.20), and steam hydrogen conductivity (0.15), etc. In the corrosion impact index, feedwater chloride ion content (0.5), feedwater pH value (0.4), and feedwater hydrogen conductivity (0.10), etc. In this way, the patent can more accurately reflect the actual impact of different indicators on the equipment's operating status. Furthermore, this method also considers the impact of the time and range of data fluctuations. For example, if the pass rate of hydrogen conductivity is 0.15 µs / cm, when the fluctuation rate of hydrogen conductivity is between 0.08 and 0.10, the weight of hydrogen conductivity is multiplied by a coefficient of 0.10 / 0.15. The time of influence is determined by the proportion of time occupied by each data point to the maximum value. By incorporating the time and range of data fluctuations into the evaluation system, it can be shown that the degree of influence of data being equally qualified or unqualified is different, avoiding the bias caused by relying on a single standard to judge the pass rate.
[0032] In this embodiment of the application, the influence weight of each monitoring parameter in the chemical monitoring data is determined according to the indicator type of the chemical monitoring indicator, including: inputting the indicator type of the chemical monitoring indicator into the target evaluation model, and the target evaluation model outputting the influence weight of each monitoring parameter in the chemical monitoring data, wherein the target evaluation model is trained and generated based on the historical operating data of the thermal power plant, the indicator type of each chemical monitoring indicator and the influence weight of each monitoring parameter. It is understood that the embodiments of this application can input the index type of chemical monitoring indicators into the target evaluation model, and the model outputs the influence weight of each monitoring parameter, so as to realize the scientific and objective generation of influence weights, get rid of subjective experience dependence, improve the power plant adaptability and personalization level of the weight system, and make the overall evaluation more accurate and objective.
[0033] Specifically, the training process of the target evaluation model: (1) Training data includes historical chemical monitoring data, equipment operation and status data, and standard and threshold data. Among them, historical chemical monitoring data includes: online instrument data accumulated over many years (such as pH, conductivity, dissolved oxygen, iron, copper, chloride ions, oleic acid value, etc.) and laboratory test data (with timestamps). Equipment operation and status data includes: equipment maintenance records (such as scaling rate, corrosion depth, and salt accumulation during boiler tube cutting inspection), unplanned shutdown or fault records (such as leakage events caused by corrosion), chemical cleaning cycle and cleaning agent dosage, and operating parameters such as unit load, number of start-ups and shutdowns, and running time.
[0034] (2) Since the influencing weights are latent variables, training labels need to be constructed indirectly through observable device states. Common methods include: 1) Construct continuous labels based on the degree of equipment deterioration: For example, define "corrosion impact intensity" = corrosion rate in a certain period of time × average chloride ion exceedance multiple in that period of time, and "scaling impact intensity" = scaling rate × iron content exceedance integral. These impact intensities can be used as target impact values of monitoring parameters to infer their proper weights.
[0035] 2) Construct classification labels based on events: If a condenser leak occurs in a certain month, it is marked as "high corrosion risk"; if the boiler cleaning cycle is shortened, it is marked as "high scaling risk"; the model can be trained as a classification model, and the output parameters are weighted distribution under different risk levels.
[0036] (3) Input features include: index type, parameter name, parameter basic attributes, historical statistical features, system context features and feature crossover. Among them, index type: such as "corrosion", "scaling", "oil quality-cleanliness" etc. (can be encoded as unique heat vector or embedded vector); parameter name: such as "feed water chloride ion", "steam iron" etc.; parameter basic attributes: such as detection frequency, standard limit, measurement unit; historical statistical features: such as the average value, exceedance rate, volatility, trend slope of the parameter in the past N months, etc.; system context features: such as unit type, water source type, whether fine treatment is in operation, etc.; feature crossover: construct crossover features such as "index type × parameter" and "parameter × unit" to improve the model's expressive ability.
[0037] (4) Divide the above training data into training set and validation set, and use the training dataset to train the target evaluation model until the validation target training evaluation model meets the training requirements and then stop training.
[0038] In this embodiment of the application, the influence weight of the corresponding monitoring parameter is corrected based on the sampled value of each monitoring parameter in the chemical monitoring data, including: obtaining the fluctuation range and fluctuation duration of the sampled value of each monitoring parameter; querying the first mapping table using the fluctuation range and fluctuation duration as indexes to obtain the correction coefficient of the corresponding monitoring parameter; and correcting the influence weight based on the correction coefficient.
[0039] The first mapping table can be set according to requirements without specific limitations.
[0040] It is understood that, according to the embodiments of this application, the corresponding correction coefficient can be obtained by querying a preset first mapping table based on the fluctuation range and fluctuation duration of the sampled values of each monitoring parameter in the chemical monitoring data, and the influence weight can be corrected according to the correction coefficient, so as to realize the dynamic and contextual adjustment of the influence weight and improve the engineering interpretability and controllability of the evaluation system.
[0041] In step S103, the impact score of the corresponding chemical monitoring index on the thermal power plant is calculated by weighting the sampled value and influence weight of each parameter in the chemical monitoring data. Based on the impact score of each chemical monitoring index and the current operating data of the thermal power plant, an operation assessment report of the thermal power plant is generated. It is understood that the embodiments of this application can perform weighted calculations based on the sampled values of each parameter in the chemical monitoring data and the dynamically corrected influence weights to obtain the influence scores of each chemical monitoring index. Combined with the current operating data of the thermal power plant, a comprehensive operation assessment report is generated to achieve quantitative comprehensive evaluation of multi-source data fusion, improve the sensitivity and accuracy of the scoring results, and achieve precise location of the root cause of the problem.
[0042] In this embodiment of the application, an operation assessment report for the thermal power plant is generated based on the impact score of each chemical monitoring indicator and the current operating data of the thermal power plant. This includes: if the impact score of any chemical monitoring indicator exceeds the target safety threshold, an operation assessment report for the thermal power plant is generated based on the impact score of the chemical monitoring indicator and the current operating data of the thermal power plant, and a risk marker is generated based on the impact score of the chemical monitoring indicator that exceeds the target safety threshold. The target safety threshold can be set according to actual needs, without specific limitations.
[0043] It is understood that, based on the impact score of each chemical monitoring indicator and the current operating data of the thermal power plant, this application embodiment can automatically generate an operation assessment report and generate risk markers for the exceeding items when any impact score is detected to exceed the target safety threshold, thereby achieving accurate and graded risk identification and alarm triggering, and improving processing efficiency through risk marker visualization.
[0044] According to the chemical monitoring data processing method for thermal power plants proposed in this application, the sampled values of each monitoring parameter in the chemical monitoring data are extracted. The influence weight of each monitoring parameter in the chemical monitoring data is determined according to the indicator type of the chemical monitoring index. The influence weight of the corresponding monitoring parameter is corrected according to the sampled values of each monitoring parameter in the chemical monitoring data. The dynamic weight correction improves risk sensitivity and significantly enhances the ability to capture hidden risks. According to the sampled values and influence weights of each parameter in the chemical monitoring data, the influence score of the corresponding chemical monitoring index on the thermal power plant is calculated by weighting. According to the influence score of each chemical monitoring index and the current operating data of the thermal power plant, an operation assessment report of the thermal power plant is generated, which improves the diagnostic accuracy and subsequent processing efficiency.
[0045] The method for processing chemical monitoring data in thermal power plants according to this application will be described in detail below with reference to specific embodiments: (1) Scientifically classify and define different types of indicator data. Water quality indicators include scaling and corrosion indicators, while oil quality indicators include cleanliness and system operation indicators. Scaling indicators primarily determine the presence of scaling tendency within the system, including feedwater conductivity and hydrogen conductivity; feedwater pH value, feedwater iron, copper, and silicon content; steam iron, copper, and silicon content; and boiler water phosphate ion (PO43-) content, silicon content, and conductivity. Corrosion indicators assess the risk of equipment corrosion, such as condensate hydrogen conductivity, feedwater pH value, feedwater chloride ion concentration, feedwater dissolved oxygen content, steam hydrogen conductivity, and chloride ion concentration. Cleanliness indicators measure the cleanliness of the system and may include particulate matter content and mechanical impurities in the oil. System operation indicators determine whether the system is overheating, such as chemical change products in the oil at specific temperatures, like the oil's acid value and resistivity.
[0046] (2) Assign values to the equipment and system based on the influence of each indicator, and reflect their importance in the comprehensive evaluation in the form of weights. The impact of each indicator is assessed using experimental data, historical operational data, and expert experience. The impact index is generally set between 0 and 1. The closer the index is to 1, the higher the importance of the indicator.
[0047] Specifically, for the key indicators reflecting scaling trends in the water-steam system, the iron content in the feedwater has the largest weight (0.40), followed by the hydrogen conductivity of the feedwater (0.25), the pH value of the feedwater (0.20), and the hydrogen conductivity of the steam (0.15). Among the corrosion impact indices, the chloride ion content in the feedwater (0.5), the pH value of the feedwater (0.4), and the hydrogen conductivity of the feedwater (0.10) are the most important.
[0048] Dynamic adjustment: The impact index will be adjusted accordingly based on the fluctuation range of the indicator. For example, if the pass rate of hydrogen conductivity is 0.15µs / cm, when the fluctuation rate of hydrogen conductivity is between 0.08 and 0.10, the weight of hydrogen conductivity will be multiplied by a coefficient of 0.10 / 0.15. The impact time is determined by the ratio of the time occupied by each data point to the maximum value. (3) Using the given assigned indicators and real-time collected data, a comprehensive evaluation is conducted to obtain the impact score of the thermal power plant on the current state of the system. The system acquires the latest chemical monitoring data from various sensors or laboratory analytical equipment. The data should include timestamps to ensure timeliness.
[0049] For each category's indicator, the actual measured value is multiplied by its corresponding influence index (weight), and then summed to obtain the total influence index for that category. The formula is as follows: Impact rating of thermal power plants = ,in, Let be the influence weight of the i-th indicator.
[0050] Based on the total impact results of each subcategory, a comprehensive analysis is conducted to obtain an overall health status assessment of the system. If a certain category has a high score in a particular subcategory, it may be necessary to strengthen management or maintenance in that area.
[0051] (4) Results diagnosis and feedback The calculated impact indices are transformed into actionable information to aid management and maintenance decisions. Indicator exceedance detection: When the calculated value of an indicator exceeds a pre-set safety threshold, the system triggers an alarm mechanism. The system summarizes the total impact index and key parameter changes for each category, generating periodic analysis reports. Reports include: the current status of each indicator, the impact index calculation results, explanations of abnormal situations, and recommended measures or maintenance plans. The impact index values are continuously optimized based on operational experience to ensure the evaluation model always matches actual operating conditions.
[0052] (5) As the system's service life, operating environment, or other external conditions change, the evaluation indicators and weights should be adjusted in a timely manner to improve the adaptability and accuracy of the evaluation model. Regular review mechanism: A comprehensive review of the impact index is conducted annually or quarterly, taking into account factors such as the introduction of new equipment, changes in the process flow, and analysis of historical failure data. Data analysis and feedback loop: Continuously optimize the evaluation model using real-time data and historical event records. Introduce machine learning algorithms to automatically adjust the weights of influencing indices, improving the accuracy of evaluation results.
[0053] In summary, this application can accurately identify potential problems, prevent equipment failures and corrosion, thereby extending equipment life and reducing maintenance costs; the energy-based data analysis reduces the need for manual inspections, improves overall operational speed and decision-making quality, and enhances operational efficiency; it is only applicable to thermal power plants, but can also be extended to industries such as heating and chemicals to meet diverse testing needs; by reducing processing and operating costs, this method has good economic viability. At the same time, reducing the environmental impact of equipment failures contributes to sustainable development.
[0054] Next, referring to the accompanying drawings, a chemical monitoring data processing device for thermal power plants according to an embodiment of this application is described.
[0055] Figure 2 This is a block diagram of a chemical monitoring data processing device for a thermal power plant according to an embodiment of this application.
[0056] like Figure 2 As shown, the chemical monitoring data processing device 10 for the thermal power plant includes: an acquisition module 100, an extraction module 200, and a calculation module 300.
[0057] The acquisition module 100 is used to acquire chemical monitoring indicators of thermal power plants and chemical monitoring data for each chemical monitoring indicator; the extraction module 200 is used to extract the sampled value of each monitoring parameter in the chemical monitoring data, determine the influence weight of each monitoring parameter in the chemical monitoring data according to the indicator type of the chemical monitoring indicator, and correct the influence weight of the corresponding monitoring parameter according to the sampled value of each monitoring parameter in the chemical monitoring data; the calculation module 300 is used to calculate the weighted impact score of the corresponding chemical monitoring indicator on the thermal power plant according to the sampled value and influence weight of each parameter in the chemical monitoring data, and generate an operation evaluation report of the thermal power plant according to the impact score of each chemical monitoring indicator and the current operation data of the thermal power plant.
[0058] According to the chemical monitoring data processing device for thermal power plants proposed in this application, the sampled values of each monitoring parameter in the chemical monitoring data are extracted. The influence weight of each monitoring parameter in the chemical monitoring data is determined according to the index type of the chemical monitoring index. The influence weight of the corresponding monitoring parameter is corrected according to the sampled values of each monitoring parameter in the chemical monitoring data. The dynamic weight correction improves risk sensitivity and significantly enhances the ability to capture hidden risks. According to the sampled values and influence weights of each parameter in the chemical monitoring data, the influence score of the corresponding chemical monitoring index on the thermal power plant is calculated by weighting. According to the influence score of each chemical monitoring index and the current operating data of the thermal power plant, an operation assessment report of the thermal power plant is generated, which improves the diagnostic accuracy and subsequent processing efficiency.
[0059] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 301, the processor 302, and the computer program stored on the memory 301 and capable of running on the processor 302.
[0060] When the processor 302 executes the program, it implements the chemical monitoring data processing method for thermal power plants provided in the above embodiments.
[0061] Furthermore, electronic devices also include: Communication interface 303 is used for communication between memory 301 and processor 302.
[0062] The memory 301 is used to store computer programs that can run on the processor 302.
[0063] The memory 301 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
[0064] If the memory 301, processor 302, and communication interface 303 are implemented independently, then the communication interface 303, memory 301, and processor 302 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0065] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.
[0066] Processor 302 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0067] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed by a processor, implements the above-described chemical monitoring data processing method for thermal power plants.
[0068] This application also provides a computer program product, including a computer program or instructions, which, when executed, implement the above-described chemical monitoring data processing method for thermal power plants.
[0069] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0070] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0071] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0072] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0073] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
Claims
1. A method for processing chemical monitoring data in a thermal power plant, characterized in that, Includes the following steps: Obtain chemical monitoring indicators for thermal power plants and chemical monitoring data for each indicator; Extract the sampled value of each monitoring parameter in the chemical monitoring data, determine the influence weight of each monitoring parameter in the chemical monitoring data according to the index type of the chemical monitoring index, and correct the influence weight of the corresponding monitoring parameter according to the sampled value of each monitoring parameter in the chemical monitoring data; Based on the sampled value and influence weight of each parameter in the chemical monitoring data, the influence score of the corresponding chemical monitoring index on the thermal power plant is calculated by weighting. Based on the influence score of each chemical monitoring index and the current operating data of the thermal power plant, an operation assessment report of the thermal power plant is generated.
2. The method for processing chemical monitoring data in thermal power plants according to claim 1, characterized in that, The step of determining the influence weight of each monitoring parameter in the chemical monitoring data based on the index type of the chemical monitoring index includes: The index type of the chemical monitoring index is input into the target evaluation model, and the target evaluation model outputs the influence weight of each monitoring parameter in the chemical monitoring data. The target evaluation model is trained and generated based on the historical operating data of the thermal power plant, the index type of each chemical monitoring index, and the influence weight of each monitoring parameter.
3. The method for processing chemical monitoring data in thermal power plants according to claim 2, characterized in that, The step of adjusting the influence weight of the corresponding monitoring parameter based on the sampled value of each monitoring parameter in the chemical monitoring data includes: Obtain the fluctuation range and fluctuation duration of the sampled values for each supervision parameter; Using the fluctuation range and fluctuation duration as indexes, the first mapping table is queried to obtain the correction coefficients of the corresponding supervision parameters; The influence weights are adjusted according to the correction coefficients.
4. The method for processing chemical monitoring data in thermal power plants according to claim 1, characterized in that, Before acquiring chemical monitoring data for each chemical monitoring indicator, the process includes: Based on the physical damage mechanism of thermal equipment caused by chemical monitoring index data of thermal power plants, the chemical monitoring index of the thermal power plants is classified into at least one index type of chemical monitoring index.
5. The method for processing chemical monitoring data in thermal power plants according to claim 1, characterized in that, The index types include at least one of the following: water vapor index, scaling index, corrosion index, oil quality index, cleanliness index, and system operation index.
6. The method for processing chemical monitoring data in thermal power plants according to claim 1, characterized in that, The process of generating an operational assessment report for the thermal power plant based on the impact score of each chemical monitoring indicator and the current operating data of the thermal power plant includes: If the impact score of any chemical monitoring indicator exceeds the target safety threshold, an operation assessment report for the thermal power plant is generated based on the impact score of the chemical monitoring indicator and the current operating data of the thermal power plant, and a risk marker is generated based on the impact score of the chemical monitoring indicator that exceeds the target safety threshold.
7. A chemical monitoring data processing device for a thermal power plant, characterized in that, include: The acquisition module is used to acquire chemical monitoring indicators of thermal power plants and chemical monitoring data for each chemical monitoring indicator; An extraction module is used to extract the sampled value of each monitoring parameter in the chemical monitoring data, determine the influence weight of each monitoring parameter in the chemical monitoring data according to the index type of the chemical monitoring index, and correct the influence weight of the corresponding monitoring parameter according to the sampled value of each monitoring parameter in the chemical monitoring data. The calculation module is used to calculate the impact score of the corresponding chemical monitoring index on the thermal power plant based on the sampled value and impact weight of each parameter in the chemical monitoring data, and to generate an operation evaluation report of the thermal power plant based on the impact score of each chemical monitoring index and the current operation data of the thermal power plant.
8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the chemical monitoring data processing method for thermal power plants as described in any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement the chemical monitoring data processing method for thermal power plants as described in any one of claims 1-6.
10. A computer program product, characterized in that, The method includes a computer program, which, when executed by a processor, is used to implement the chemical monitoring data processing method for thermal power plants according to any one of claims 1-6.