A comprehensive evaluation method for the operation of power generation equipment based on multiple indicators

Abstract

The present invention discloses a comprehensive evaluation method for the operation of power generation equipment based on multiple indicators, which relates to the technical field of equipment operation evaluation. The method includes: monitoring the operation of power generation equipment to obtain a set of equipment operation parameters; building a comprehensive evaluation index list; synchronizing multiple evaluation indicators to a mathematical analysis model for quantitative evaluation, generating multiple indicator quantitative evaluation results, and determining the comprehensive evaluation results of the operation; generating feedback evaluation suggestions, performing optimization, and generating a comprehensive evaluation optimization index list; establishing a regular evaluation mechanism, and performing a comprehensive intelligent evaluation of the operation of power generation equipment based on operation tracking data. The present invention solves the technical problem that the prior art is not comprehensive and accurate in the evaluation of the operation of power generation equipment, resulting in unstable equipment operation and low operating efficiency, and achieves the technical effect of realizing a comprehensive and accurate evaluation of the operation of power generation equipment and improving equipment reliability and operating efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation evaluation, and in particular to a comprehensive evaluation method for the operation of power generation equipment based on multiple indicators. Background Art

[0002] With the rapid development of the electric power industry, power generation equipment has become increasingly complex, and it is essential to conduct a comprehensive and accurate evaluation of its operation. Traditional power generation equipment evaluation methods often rely on the subjective judgment and experience of experts, which are highly subjective and have large deviations. In addition, when there are too many evaluation indicators, the evaluation process becomes complicated and time-consuming, increasing the difficulty and cost of the evaluation. At the same time, the operating status of power generation equipment is affected by many factors, such as environmental factors and the skill level of operators. Traditional evaluation methods are difficult to fully consider these factors, resulting in the accuracy and reliability of the evaluation results being affected.

[0003] The existing technology has the technical problem that the evaluation of the operation of power generation equipment is not comprehensive and accurate enough, resulting in unstable operation of the equipment and low operating efficiency. Summary of the invention

[0004] The present application provides a comprehensive evaluation method for the operation of power generation equipment based on multiple indicators, which is used to solve the technical problem in the prior art that the evaluation of the operation of power generation equipment is not comprehensive and accurate enough, resulting in unstable equipment operation and low operating efficiency.

[0005] In view of the above problems, the present application provides a comprehensive evaluation method for the operation of power generation equipment based on multiple indicators, the method comprising:

[0006] Perform operation monitoring on power generation equipment to obtain a set of equipment operation parameters; construct a comprehensive evaluation index list based on the equipment operation parameter set, wherein the comprehensive evaluation index list includes multiple evaluation indicators; synchronize the multiple evaluation indicators to a mathematical analysis model for quantitative evaluation to generate multiple indicator quantitative evaluation results, perform comprehensive analysis based on the multiple indicator quantitative evaluation results, and determine a comprehensive operation evaluation result; generate feedback evaluation suggestions based on the comprehensive operation evaluation result, optimize the comprehensive evaluation index list according to the feedback evaluation suggestions, and generate a comprehensive evaluation optimization index list; establish a regular evaluation mechanism based on the comprehensive evaluation optimization index list to continuously track power generation equipment, and perform a comprehensive and intelligent evaluation of the operation of power generation equipment according to the operation tracking data.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Monitor the operation of power generation equipment and obtain the equipment operation parameter set; build a comprehensive evaluation index list based on the equipment operation parameter set; synchronize multiple evaluation indicators to the mathematical analysis model for quantitative evaluation, generate multiple indicator quantitative evaluation results, conduct comprehensive analysis based on multiple indicator quantitative evaluation results, and determine the operation comprehensive evaluation results; generate feedback evaluation suggestions based on the operation comprehensive evaluation results, perform optimization, and generate a comprehensive evaluation optimization index list; establish a regular evaluation mechanism based on the comprehensive evaluation optimization index list to continuously track the power generation equipment, and conduct a comprehensive intelligent evaluation of the operation of the power generation equipment based on the operation tracking data. The technical effect of achieving a comprehensive and accurate evaluation of the operation of the power generation equipment and improving the reliability and operation efficiency of the equipment has been achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a method for comprehensively evaluating the operation of power generation equipment based on multiple indicators provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of a flow chart of multiple evaluation indicators of a comprehensive evaluation method for the operation of power generation equipment based on multiple indicators provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The present application provides a comprehensive evaluation method for the operation of power generation equipment based on multiple indicators, which is used to solve the technical problem in the prior art that the evaluation of the operation of power generation equipment is not comprehensive and accurate enough, resulting in unstable equipment operation and low operating efficiency.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] Example

[0015] like Figure 1 As shown, the present application provides a comprehensive evaluation method for the operation of power generation equipment based on multiple indicators, the method comprising:

[0016] Step S100: monitor the operation of power generation equipment and obtain a set of equipment operation parameters.

[0017] Specifically, in order to obtain the equipment operation parameter set, first clarify the scope of monitoring in the power generation equipment, including the generator body (stator temperature and winding condition, rotor speed and excitation system parameters), steam turbine or water turbine (steam pressure and temperature, speed of thermal power generation steam turbine, guide vane opening, runner speed, water flow and pressure of hydropower generation water turbine) and transformer (oil temperature, oil level, winding temperature) and other key components, select appropriate monitoring equipment and sensors, such as thermocouples and thermal resistors for temperature measurement, strain gauge and capacitive pressure sensors for pressure monitoring, photoelectric and magnetoelectric speed sensors for speed measurement, current transformers and voltage transformers for current and voltage conversion. Through these sensors and equipment, the key parts of the power generation equipment are monitored in real time, and the operating parameters of various aspects such as temperature, pressure, speed, current, voltage, etc. are collected, and finally integrated into the equipment operation parameter set, providing reliable basic data support for subsequent evaluation and analysis.

[0018] Step S200: constructing a comprehensive evaluation index list based on the equipment operation parameter set, wherein the comprehensive evaluation index list includes multiple evaluation indexes.

[0019] Specifically, the equipment operation parameter set is carefully analyzed to distinguish equipment operation status parameters (temperature, pressure, vibration, etc., which reflect the physical state of the equipment. For example, the temperature of different components can reflect the heating condition, the pressure will affect the output power and efficiency of the equipment, and the abnormal vibration indicates problems such as loose or worn components) and equipment operation performance parameters (such as output power reflects the power generation capacity, voltage and current are related to power quality and equipment failure, and power factor reflects the power utilization efficiency). The equipment operation efficiency is calculated based on these parameters. There are different calculation methods for different types of power generation equipment. For example, thermal power generation equipment is often calculated based on the thermal efficiency formula (the ratio of the output power of the generator to the heat energy released by fuel combustion), and hydropower generation equipment is calculated based on the hydropower generation efficiency formula (the ratio of the output power of the generator to the water energy contained in the water flow). Then, the equipment operation status parameters, equipment operation performance parameters, and the calculated equipment operation efficiency are used as classification dimensions, and multiple hierarchical structures are constructed based on these dimensions, such as a top-level structure reflecting the overall performance of the equipment, an intermediate hierarchical structure containing different parameter categories, and a bottom-level structure specific to each parameter. Finally, multiple evaluation indicators are determined based on these carefully constructed multi-level structures. These evaluation indicators cover all aspects of equipment operation, comprehensively and accurately evaluate the operating status of power generation equipment from different angles, provide strong support for subsequent equipment management and optimization, and promptly discover potential problems and optimize operation and maintenance strategies.

[0020] Step S300: synchronizing the multiple evaluation indicators to a mathematical analysis model for quantitative evaluation, generating multiple indicator quantitative evaluation results, performing comprehensive analysis based on the multiple indicator quantitative evaluation results, and determining an operation comprehensive evaluation result.

[0021] Specifically, first, data preparation and model selection, collect and organize data of multiple evaluation indicators, which cover various key aspects of power generation equipment, such as power generation efficiency, reliability, safety, maintainability, etc. According to the characteristics of the data and the needs of the evaluation, select the appropriate mathematical analysis model (hierarchical analysis method, fuzzy comprehensive evaluation method). Quantitative evaluation process, for each evaluation indicator, according to its own characteristics and definition, convert it into a quantifiable value or level. For example, for power generation efficiency, a quantitative efficiency value can be determined by the ratio of actual power generation to theoretical maximum power generation; for reliability, a reliability index can be calculated based on data such as the equipment's trouble-free operation time and the number of failures. In the quantification process, it is necessary to refer to industry standards, historical data or expert experience to determine the rules and methods of quantification. All evaluation indicator data are input into the mathematical analysis model for processing, and the model will evaluate and calculate each indicator according to the preset algorithms and rules. After obtaining the quantitative evaluation results of multiple indicators, a comprehensive analysis is required. This step aims to integrate the evaluation results of each independent indicator into a comprehensive evaluation result that fully reflects the operating status of the power generation equipment. The final comprehensive operation evaluation result can be a specific value, or a grade or classification. This result should be able to intuitively reflect the operating status and performance level of the power generation equipment. At the same time, the results need to be interpreted and analyzed to provide a basis for subsequent decision-making and improvement. If the comprehensive evaluation results are not ideal, it is necessary to further analyze which indicators have problems, find out the root causes of the problems, and formulate corresponding improvement measures, such as adjusting equipment operating parameters, strengthening maintenance, and carrying out technical transformation, to provide strong support for equipment management and optimization.

[0022] Step S400: generating feedback evaluation suggestions based on the operation comprehensive evaluation results, optimizing the comprehensive evaluation index list according to the feedback evaluation suggestions, and generating a comprehensive evaluation optimization index list.

[0023] Specifically, the comprehensive evaluation results of operation are analyzed. After the comprehensive evaluation results of operation are obtained, they are first analyzed in depth. The comprehensive evaluation results of operation are presented in numerical form, such as a score between 0 and 100. Different score intervals are set to represent different operating status levels. For example, 80 points or more are excellent, 60 to 80 points are good, 40 to 60 points are general, and 40 points or less are poor. According to the comprehensive evaluation results of operation, find out the problems and advantages in the operation of power generation equipment. For example, if the power generation efficiency index score is low, it means that there are problems with the energy conversion efficiency of the equipment, and it is necessary to further check the operating parameters, energy input and output of the equipment, etc.; if the reliability index score is low, it means that the equipment frequently fails, and it is necessary to analyze the cause of the failure, such as equipment aging, improper maintenance or external environmental factors. At the same time, for indicators with higher scores, it is also necessary to analyze and summarize their successful experiences so as to maintain and strengthen these advantages in the subsequent optimization process. Based on the analysis of problems and advantages, specific feedback evaluation suggestions are generated. For indicators with problems, targeted improvement measures are proposed. For example, if the power generation efficiency is low, it is recommended to check whether there is leakage in the energy input pipeline of the equipment, adjust the operating parameters of the equipment to improve the energy conversion efficiency, and regularly maintain and service the equipment to reduce energy loss. If there are problems with the safety indicators, such as multiple safety accidents or frequent triggering of safety protection devices, it is recommended to strengthen the safety protection measures of the equipment, provide safety training for operators, and regularly inspect and maintain safety equipment. Evaluate the existing comprehensive evaluation indicator list, conduct a comprehensive evaluation of the existing comprehensive evaluation indicator list, and analyze the rationality, accuracy and importance of each indicator. For example, some indicators are difficult to accurately measure or obtain data in actual operation, or have a large correlation with other indicators, resulting in information redundancy; the importance of some indicators has changed with the technical upgrade of the equipment or the change of the operating environment. According to the feedback evaluation suggestions and the re-evaluation of the indicators, adjust the weight of the indicators in the comprehensive evaluation indicator list. If an indicator shows a very important impact in the comprehensive evaluation results of the operation, then increase its weight appropriately; conversely, if the impact of an indicator is relatively small, reduce its weight. According to the actual operation of the power generation equipment and the feedback evaluation suggestions, consider whether it is necessary to add new evaluation indicators or delete some indicators that are no longer applicable. For example, if a new key factor of the equipment is found to have a significant impact on the operating status during operation, but the factor is not included in the existing comprehensive evaluation index list, then you can consider adding the corresponding index. On the other hand, if a certain indicator has been difficult to measure accurately in actual operation or its contribution to the comprehensive evaluation results is very small, you can consider deleting it from the comprehensive evaluation index list. After adjusting the comprehensive evaluation index list, optimizing the weights, and possibly adding or removing indicators, a new comprehensive evaluation optimization index list is generated.This list should reflect the operating status of power generation equipment in a more scientific and reasonable manner, and provide more accurate and effective guidance for subsequent equipment evaluation and management. Through the above steps, the comprehensive evaluation index list can be continuously optimized and improved according to the comprehensive evaluation results of operation, ensuring that the evaluation system is always adapted to the actual operating conditions of power generation equipment, and providing strong support for improving the operating efficiency and reliability of equipment.

[0024] Step S500: Establish a regular evaluation mechanism based on the comprehensive evaluation optimization index list to continuously track the power generation equipment, and conduct a comprehensive and intelligent evaluation of the operation status of the power generation equipment based on the operation tracking data.

[0025] Specifically, a regular evaluation mechanism is established based on the comprehensive evaluation optimization index list. When determining the evaluation cycle, it is necessary to comprehensively consider factors such as the characteristics, importance, and actual operation requirements of the power generation equipment. For example, key equipment requires a shorter evaluation cycle. Then, a detailed evaluation plan is formulated to clarify the evaluation time, participating personnel and required resources, as well as the method and frequency of data collection. At the same time, a reliable data storage and management system is established to ensure the security, integrity, accuracy and timeliness of the data. In the continuous tracking process, online monitoring equipment is used to obtain equipment operation status data in real time, and manual inspections and records are combined to supplement comprehensive information. Then, after the operation tracking data is collected, based on these data and the optimized index list, the various performance and operating parameters of the equipment are comprehensively considered, and the operation of the power generation equipment is comprehensively and deeply analyzed and evaluated from multiple angles, and finally an objective and accurate comprehensive intelligent evaluation result is obtained, so as to timely discover problems and potential risks in equipment operation, and provide a strong basis for equipment optimization adjustment and maintenance decisions.

[0026] In one possible implementation, Figure 2 As shown, step S200 also includes:

[0027] Step S210: parse the device operation parameter set to obtain device operation status parameters and device operation performance parameters.

[0028] Step S220: Calculate and obtain the equipment operation efficiency based on the equipment operation status parameters and the equipment operation performance parameters.

[0029] Step S230: Using the equipment operation status parameters, the equipment operation performance parameters, and the equipment operation efficiency as classification dimensions, multiple hierarchical structures are constructed based on the classification dimensions.

[0030] Step S240: determining the multiple evaluation indicators according to the multiple hierarchical structures.

[0031] Specifically, the equipment operation parameter set containing data such as voltage stability, current change, power factor, temperature monitoring, pressure monitoring, flow monitoring, vibration and noise is obtained. For voltage stability, relevant data is obtained by analyzing the voltage fluctuation and the degree of deviation from the rated voltage over a period of time; for current change, the current change trend over time and its peak and valley values ​​need to be monitored; the power factor is calculated using the corresponding power factor measurement instrument or algorithm; temperature monitoring can be achieved with the help of temperature sensors, which are installed in key parts of the equipment to collect temperature data in real time; pressure monitoring also relies on pressure sensors, which are placed at appropriate pressure measurement points to obtain pressure values; flow monitoring uses flow sensors to measure the flow data of fluids for equipment involving fluids; vibration and noise can use vibration sensors and noise sensors to collect information such as vibration frequency, amplitude, and noise intensity during equipment operation. Then, these collected data are classified and processed. Data such as temperature, pressure, vibration and noise are classified as equipment operating status parameters because they directly reflect the physical state and operating environment of the equipment, while data such as voltage stability, current change, power factor, flow monitoring, etc. are classified as equipment operating performance parameters because they are closely related to the equipment's power generation efficiency, energy conversion capacity, and contribution to the power grid. Through such data collection and classification processing, it is possible to obtain equipment operating status parameters and equipment operating performance parameters from the equipment operating parameter set, laying the foundation for subsequent calculation and analysis work.

[0032] The equipment operation efficiency is derived from the equipment operation state parameters and equipment operation performance parameters, both of which play an important role. Equipment operation state parameters, such as temperature and pressure, can show the physical environment and internal working conditions of the equipment during operation. The power, current, voltage, etc. in the equipment operation performance parameters are directly related to the energy conversion and output of the equipment. For example, for common power generation equipment, the energy conversion efficiency method is usually used for calculation. The equipment operation efficiency is equal to the output power divided by the input power multiplied by 100%. Among them, the output power is obtained from the power data in the equipment operation performance parameters, such as the output power of the generator, while the calculation of the input power is relatively complicated. For example, for thermal power generation equipment, the input power involves the energy input of the fuel; for hydropower generation equipment, the input power is related to the energy input of the water flow. In this process, the temperature and pressure in the equipment operation state parameters also play a role, because they affect the energy transfer and conversion efficiency, and then affect the calculation of the input power. For different types of power generation equipment, the calculation method will be adjusted according to their own working principles and characteristics. For example, for wind power generation equipment, factors such as wind speed and wind direction will affect the efficiency of the equipment, so these factors need to be considered during calculation. For solar power generation equipment, light intensity, operating temperature of solar panels, etc. are also factors that cannot be ignored, and they will also have an effect on the calculation of equipment efficiency. In summary, the calculation of equipment operating efficiency is a complex process that integrates multiple parameters and factors. By using equipment operating status parameters and equipment operating performance parameters, the equipment operating efficiency can be evaluated more accurately.

[0033] The significance and interrelationship of the three classification dimensions of equipment operation status parameters, equipment operation performance parameters and equipment operation efficiency are clarified. Equipment operation status parameters describe the current physical condition and operation environment of the equipment, such as temperature reflects whether it is overheated, pressure shows the internal condition, and vibration and noise indicate the status of mechanical components; equipment operation performance parameters reflect the energy conversion and output capacity of the equipment and its contribution to the external system, such as power, current, voltage, power factor, etc.; equipment operation efficiency is a comprehensive indicator calculated based on the first two, reflecting the overall performance of equipment energy conversion and utilization. Then start to build a hierarchical structure. The first layer is the overall equipment operation evaluation, which is the most macro summary. The second layer is divided into equipment operation status evaluation, equipment operation performance evaluation and equipment operation efficiency evaluation according to the classification dimensions. The equipment operating status assessment is based on the equipment operating status parameters, and is subdivided into sub-assessments such as temperature, pressure, vibration and noise; the equipment operating performance assessment is based on the equipment operating performance parameters, and includes assessments of power, current, voltage, power factor and other aspects; the equipment operating efficiency assessment focuses on the analysis of the equipment operating efficiency itself, and further subdivides the levels according to the numerical range and grade standards of specific parameters, forming an assessment structure with clear levels and interrelated aspects from macro to micro, so as to comprehensively and systematically evaluate the operation of the power generation equipment.

[0034] The evaluation indicators are determined based on the multiple hierarchical structures constructed previously. First, for the hierarchical structure of equipment operation status evaluation, in terms of temperature, evaluation indicators such as whether the temperature is within the normal working range and whether the temperature change rate is abnormal can be set according to different temperature ranges; for pressure, indicators such as whether the pressure is stable in a reasonable range and whether the pressure fluctuation amplitude exceeds the standard are set; for vibration and noise, evaluation indicators such as whether the vibration frequency is within the allowable range and whether the noise intensity is too high to affect the environment are set. Secondly, for the equipment operation performance evaluation level, in terms of power, indicators such as whether the output power meets the design requirements and how the power stability is determined; for current and voltage, indicators such as whether the current and voltage are balanced and whether the current and voltage fluctuations are within the specified range are set; for power factor, indicators such as whether the power factor meets the requirements of the power grid are set. Finally, for the equipment operation efficiency evaluation level, the main evaluation indicators can include whether the equipment operation efficiency meets the expected standards and the level of operation efficiency compared with the same type of equipment. By extracting key information from different hierarchical structures in this way, a series of targeted and systematic evaluation indicators are determined. These indicators can comprehensively and accurately reflect the operation status and performance of power generation equipment in different aspects, and provide specific measurement basis for subsequent comprehensive evaluation.

[0035] In a possible implementation, step S300 further includes:

[0036] Step S310: constructing a mathematical analysis model based on the multiple evaluation indicators and the evaluation target of the power generation equipment, wherein the mathematical analysis model comprises a data input layer, a quantitative evaluation layer, an evaluation test layer, and a data output layer.

[0037] Step S320: constructing a first evaluation matrix based on the multiple evaluation indicators.

[0038] Step S330: Mapping the first evaluation matrix to the quantitative evaluation layer through the data input layer to perform single-index quantitative evaluation and generate a single-index quantitative evaluation result.

[0039] Step S340: input the single indicator quantitative evaluation result to the evaluation test layer, and when the test passes, start the data output layer to output the multiple indicator quantitative evaluation results.

[0040] Step S350: performing weight assignment based on the quantitative evaluation results of the multiple indicators to determine multiple weight coefficients.

[0041] Step S360: Analyze the quantitative evaluation results of the multiple indicators according to the multiple weight coefficients to generate the comprehensive operation evaluation indicator.

[0042] Specifically, we first determine the mathematical model based on the hierarchical analysis method. At the data input stage, we need to comprehensively collect various evaluation index data related to power generation equipment. We collect evaluation index data such as temperature (stator, rotor, bearing, etc.), pressure (oil pressure, air pressure, etc.), power (input, output), vibration (amplitude, frequency), operation time, and fault history of power generation equipment, remove abnormal data, and unify the data collection frequency.

[0043] To construct a hierarchical model, we first need to make it clear that the evaluation goal is to evaluate the comprehensive performance or operating status of the power generation equipment. This is the highest level, the overall target level. The middle criterion level is composed of multiple evaluation indicators, such as temperature, pressure, power, vibration, etc. These indicators are independent of each other, but they all have an impact on the overall evaluation of the power generation equipment. The lowest level of the solution level is the specific power generation equipment or the different operating conditions of the equipment, such as multiple power generation equipment of the same model, or the operating conditions of the same equipment under different loads and different environmental conditions.

[0044] Constructing the judgment matrix: For each evaluation indicator in the criterion layer, it is necessary to judge their relative importance to the overall goal based on expert experience or historical data, and use the 1-9 scale method to quantify this importance comparison. For example, 1 means that two indicators are equally important, 3 means that one indicator is slightly more important than the other, 5 means obviously important, 7 means strongly important, 9 means extremely important, and 2, 4, 6, and 8 are the intermediate values ​​of the above adjacent judgments. Then construct the judgment matrix based on these comparison results. For example, assuming that there are four evaluation indicators, temperature (T), pressure (P), power (W), and vibration (V), if it is believed that temperature is slightly more important than pressure, temperature is obviously more important than power, temperature is strongly more important than vibration, pressure is slightly more important than power, pressure is slightly more important than vibration, and power is slightly more important than vibration, then the corresponding judgment matrix can be constructed. Calculate the maximum eigenvalue, consistency index, and consistency ratio of the judgment matrix. If the ratio is less than 0.1, the consistency is acceptable, otherwise it needs to be readjusted. For the judgment matrix that passes the consistency test, calculate the eigenvector to determine the weight of each indicator. Evaluation and testing layer: In this layer, the results obtained from the quantitative evaluation layer need to be tested and verified to ensure the accuracy and reliability of the evaluation results. The cross-validation method is used to divide the data into multiple subsets, one for training the model and the other for testing the performance of the model. Through multiple cross-validations, a relatively stable and reliable evaluation result is obtained. The errors found during the test are analyzed to determine whether the errors are caused by data problems, model structure problems or other reasons. If it is a model problem, the model needs to be adjusted and optimized, such as re-adjusting the judgment matrix or modifying the weight calculation method.

[0045] The data output layer is responsible for outputting the results of the evaluation and testing in a suitable form. It can be in numerical form, directly outputting the quantified evaluation score, such as the comprehensive performance score of the equipment between 0-100. It can also be in the form of grades, such as excellent, good, qualified, unqualified, etc., so that users can intuitively understand the operating status of the equipment. The output results are explained and illustrated so that users can clearly understand the meaning and value of the evaluation results so as to make corresponding decisions, such as whether the equipment needs to be maintained, upgraded or replaced.

[0046] Identify multiple evaluation indicators of power generation equipment, such as temperature indicators that reflect thermal status (including the temperature of stators, rotors, bearings, etc.), pressure indicators that reflect the status of fluid or gas systems (such as oil pressure, air pressure), power indicators that measure power generation capacity and energy consumption (including input and output power), and vibration indicators that reveal the status of mechanical structures (covering amplitude, frequency, etc.). Then collect data for these indicators, obtain real-time physical parameters through sensor measurements, extract electrical parameters and operating information from the equipment control system records, and refer to historical data and empirical data. Then use the evaluation indicators as the rows of the matrix, the time points or operating conditions as the columns, and fill the corresponding collected data into the corresponding positions of the matrix in turn, so as to construct the first evaluation matrix, which provides a clear and structured data set for subsequent analysis and evaluation, and helps to accurately evaluate the operating status of power generation equipment.

[0047] The data input layer plays a key role as a bridge for data transmission. It receives the constructed first evaluation matrix, which contains data of multiple evaluation indicators at different time points or working conditions. When the data enters the quantitative evaluation layer through the data input layer, the quantitative evaluation layer begins to perform quantitative evaluation for each individual evaluation indicator. For example, for the temperature indicator, the normal range of temperature and the quantitative scores corresponding to different intervals are pre-set. If the temperature value at a certain moment is within the normal range, a corresponding higher quantitative score is given according to the established rules; if it exceeds the normal range, the quantitative score is reduced according to certain standards based on the degree of excess. For example, for the stator temperature of the generator, the normal operating temperature range is [40℃, 60℃]. When the temperature is 50℃, 8 points (out of 10 points) may be given, and when the temperature reaches 70℃, 4 points are given. Similar operations are performed for pressure indicators. For power indicators, quantification can be performed based on the rated power of the equipment and the ratio of the actual output power to the rated power. If the actual output power is close to or reaches a higher proportion of the rated power, a higher quantitative evaluation result is given; conversely, if the actual output power is far lower than the rated power or fluctuates greatly, the quantitative score is reduced. For example, 9 points are given when the output power of the generator reaches more than 80% of the rated power, and 5 points are given when the output power is less than 50%. For vibration indicators, quantification is performed based on the amplitude, frequency and other characteristics of the vibration and its allowable range. Higher scores are given within the allowable vibration range, and when the vibration exceeds the allowable range, points are deducted according to the degree of excess. For example, for a rotating equipment, 8 points are given when the vibration amplitude is within [0.1mm, 0.3mm], and only 4 points are given when the vibration amplitude reaches 0.5mm. After quantitative analysis of each evaluation indicator under different conditions, the quantitative evaluation results of each evaluation indicator are finally generated. These results can be expressed in numerical form, providing basic data support for subsequent comprehensive evaluation and decision-making.

[0048] The quantitative evaluation results of a single indicator enter the evaluation test layer from the quantitative evaluation layer. Here, the evaluation test layer will strictly review aspects such as data rationality (such as checking whether the temperature is within a reasonable numerical range to avoid abnormal values), consistency and correlation between indicators (such as the temperature should change reasonably when the power increases to prevent contradictions), and comparison with historical and standard data (if the current vibration evaluation results deviate too much from the previous trend, analysis is required). Once these results pass the test and show that they are reasonable, accurate and reliable, the data output layer will be activated, and then the quantitative evaluation results of these multiple indicators that have been tested will be output, providing strong data support for subsequent analysis and decision-making.

[0049] The key link is to allocate weights based on the quantitative evaluation results of multiple indicators, because different evaluation indicators have different degrees of influence on the overall operating status and evaluation objectives of power generation equipment. For example, temperature anomalies directly affect the insulation performance and service life of the equipment, pressure anomalies affect the mechanical structure stability of the equipment, power reflects the power generation efficiency and energy utilization of the equipment, and vibration anomalies indicate that the equipment has hidden mechanical failures. In order to accurately reflect the relative importance of each indicator in the comprehensive evaluation, it is necessary to determine a reasonable weight coefficient. The hierarchical analysis method is used to first stratify the evaluation problems, such as the target layer (comprehensive evaluation of power generation equipment), the criterion layer (various evaluation indicators), and the solution layer (power generation equipment or operation scenarios). Then, the indicators are compared pairwise based on historical experience to determine their relative importance, and a judgment matrix is ​​constructed. The weight coefficient of each indicator is then obtained through mathematical calculation, so that the final comprehensive evaluation results are more in line with the actual situation and needs, providing strong support for the accurate evaluation of the operating status of power generation equipment.

[0050] Multiple weight coefficients are determined in the previous steps, and they reflect the relative importance of each evaluation index in the comprehensive evaluation. For example, if the weight coefficient of a certain index is large, it means that the index has a more critical impact on the operating status of the power generation equipment. For multiple index quantitative evaluation results, these are the data obtained after quantitative analysis of each evaluation index in the previous steps, and they present the status of each index at different time points or working conditions in the form of specific numerical values ​​or levels. Then, the analysis process is to combine the quantitative evaluation results of each index with its corresponding weight coefficient. Specifically, it is through certain mathematical operations, usually weighted summation. For example, if there are four evaluation indicators of temperature, pressure, power, and vibration, and their quantitative evaluation results are T, P, W, and V respectively, and the corresponding weight coefficients are α, β, γ, and δ respectively, then the comprehensive evaluation index of operation can be expressed as: comprehensive evaluation index = α×T+β×P+γ×W+δ×V. In this process, the quantitative evaluation results of each index are enlarged or reduced accordingly according to its weight coefficient. This ensures that important indicators play a greater role in the comprehensive evaluation, while the influence of relatively less important indicators is relatively small. The final generated comprehensive operation evaluation index is a value or level that can comprehensively and comprehensively reflect the operating status of power generation equipment. It takes into account multiple factors and overcomes the limitations of single indicator evaluation. Through this comprehensive evaluation index, users can more intuitively and accurately understand the overall operating status of power generation equipment, providing a strong basis for equipment management and maintenance decisions. For example, if the value of the comprehensive evaluation index is high, it means that the equipment is in good operating condition; if the value is low or has dropped significantly, it indicates that the equipment is faulty or needs maintenance and improvement.

[0051] In a possible implementation, step S400 further includes:

[0052] Step S410: Analyze the comprehensive evaluation results of the operation and arrange them in ascending order according to the scores to obtain a contribution degree sequence.

[0053] Step S420: extracting the evaluation index corresponding to the first-rank contribution based on the contribution sequence for evaluation, and adding the evaluation index corresponding to the first-rank contribution to the feedback evaluation suggestion according to the contribution evaluation result.

[0054] Step S430: reducing the dimension of the first evaluation matrix according to the feedback evaluation suggestions to generate a second evaluation matrix.

[0055] Step S440: screening and optimizing the multiple evaluation indicators in the comprehensive evaluation indicator list according to the second evaluation matrix to generate multiple screened and optimized evaluation indicators.

[0056] Step S450: generating the comprehensive evaluation optimization index list based on the multiple screening optimization evaluation indexes.

[0057] Specifically, the comprehensive evaluation results of operation usually include a comprehensive score of power generation equipment based on multiple evaluation indicators. These scores are arranged in ascending order to obtain a contribution sequence. After the ascending order, the indicators with lower scores mean that the negative impact on the comprehensive evaluation results is relatively large, and their contribution is low; while the indicators with higher scores have a greater positive impact on the comprehensive evaluation results, and their contribution is relatively high.

[0058] The contribution sequence reflects the different degrees of influence of each evaluation index on the comprehensive evaluation result. When starting to process this step, we will first go deep into the contribution sequence to accurately extract the evaluation index corresponding to the first-order contribution. For example, in the evaluation scenario of power generation equipment, it is assumed that temperature, pressure, power, vibration and some other evaluation indicators together constitute the comprehensive evaluation system. After a series of calculations and analyses to obtain the contribution sequence, if it is found that the vibration index is ranked in the first-order contribution position, this means that in the current evaluation system, the vibration index has the most critical impact on the comprehensive evaluation result. Then enter the comprehensive evaluation stage of the vibration index. In terms of data accuracy, carefully check the working status of the vibration sensor to confirm whether it has problems such as failure or aging, because the abnormality of the sensor causes the collected vibration data to be inaccurate. At the same time, observe the change trend of the vibration data recorded at different time points, such as whether the vibration amplitude has an unreasonable sudden increase or decrease at different stages of equipment operation. If abnormal mutations or fluctuations are found, it is necessary to further explore the cause. If after the above comprehensive and detailed evaluation, it is determined that there are indeed problems with the vibration index, and these problems have a significant adverse impact on the comprehensive evaluation results, such as causing a decrease in the comprehensive evaluation score, misjudgment of the equipment operating status, etc., then the vibration index will be added to the feedback evaluation suggestions. The feedback evaluation suggestions can be a detailed report that clearly explains the problems with the vibration index, possible causes, and specific impacts on the comprehensive evaluation results, providing a clear and powerful basis and direction for the subsequent improvement and optimization of the indicator and the entire evaluation system, making the evaluation and management of power generation equipment more scientific, accurate and reliable.

[0059] Feedback evaluation suggestions play a key guiding role. They are formed through in-depth analysis of the contribution sequence and comprehensive evaluation of the corresponding evaluation indicators, and clearly point out which evaluation indicators have problems and the direction that needs to be improved. The first evaluation matrix contains the data of the initial multiple evaluation indicators in different situations. When the dimensionality reduction is performed according to the feedback evaluation suggestions, the first evaluation matrix will be screened and adjusted. If some evaluation indicators have data problems, such as inaccurate and unstable data, or highly overlapping and redundant with other indicators, or the contribution to the comprehensive evaluation results is very small or even has a negative effect, these indicators will be removed from the matrix or merged and simplified, and finally a new second evaluation matrix will be generated. Compared with the first evaluation matrix, the second evaluation matrix is ​​more streamlined and effective, removing unnecessary dimensions and information interference, and can more accurately reflect the key operating conditions and evaluation information of power generation equipment, providing a clearer and more targeted data basis for subsequent evaluation and analysis.

[0060] Taking the second evaluation matrix after dimensionality reduction as an important basis, the comprehensive evaluation index list originally contains multiple evaluation indicators for evaluating power generation equipment. These indicators have some problems before optimization. First, based on the data in the second evaluation matrix, the correlation between the indicators is analyzed. When it is found that some indicators are highly correlated, such as temperature and power have a strong correlation under certain circumstances, the more critical indicators or indicators with better data quality will be retained and redundant indicators will be removed. Secondly, combined with the characteristics and needs of the actual operation of the power generation equipment, the importance of each indicator to the operating status and performance of the equipment is evaluated. For example, the power indicator is usually directly related to the power generation capacity of the equipment. The key indicators will be retained first and the relatively minor indicators will be screened. Finally, a data quality review will be conducted. If a certain indicator data has a large number of missing, outliers or large fluctuations and is difficult to repair, such as temperature sensor failure causing unreliable temperature data, it will be considered to be removed from the comprehensive evaluation index list. After such a screening and optimization process, multiple screening and optimization evaluation indicators are finally generated. These indicators can more accurately and effectively reflect the operating status of the equipment and provide strong support for subsequent more accurate comprehensive evaluation.

[0061] After a series of steps, multiple screening optimization evaluation indicators are obtained. These indicators are retained from the initial numerous evaluation indicators through a rigorous screening and optimization process. They have higher accuracy, stronger pertinence and closer correlation with the operating conditions of power generation equipment. The process of generating a comprehensive evaluation optimization indicator list is as follows: these screening optimization evaluation indicators are sorted and classified. According to the different aspects of equipment operation reflected by the indicators, such as equipment performance, reliability, safety, etc., the indicators are classified and arranged. Then, detailed descriptions and annotations are added to each indicator, including the definition of the indicator, measurement method, normal range, and its importance and role in the comprehensive evaluation. This makes the comprehensive evaluation optimization indicator list clearer and easier to understand, and convenient for users to understand and apply. For example, if the screening optimization evaluation indicators include optimized temperature indicators, pressure indicators, and power indicators, the specific meaning of each indicator will be clearly stated in the comprehensive evaluation optimization indicator list. For example, the temperature indicator may refer to the temperature of the key parts of the generator stator. The measurement method is through a specific temperature sensor. The normal working range is within a certain temperature range. It is of great significance to judge the thermal state and insulation performance of the equipment in the comprehensive evaluation. The final generated comprehensive evaluation optimization indicator list is a more scientific, reasonable and effective evaluation system. It can more accurately reflect the actual operating conditions of power generation equipment, provide strong support and guidance for comprehensive evaluation, fault diagnosis, maintenance decisions and performance improvement of equipment, help users manage and maintain power generation equipment more efficiently, and improve the operating efficiency and reliability of equipment.

[0062] In a possible implementation, step S430 further includes:

[0063] Step S431: constructing a preset evaluation conflict interval based on the feedback evaluation suggestion.

[0064] Step S432: Calculate and obtain the distribution probability of a plurality of evaluation index data in the first evaluation matrix and preset evaluation index data within a preset evaluation conflict interval, and obtain an evaluation index distribution probability lattice.

[0065] Step S433: constructing a lattice similarity probability distribution function, performing dimensionality reduction processing on the lattice distribution of the evaluation index distribution probability lattice, and generating a distribution probability lattice dimensionality reduction result.

[0066] Step S434: constructing the second evaluation matrix based on the distribution probability lattice dimensionality reduction result.

[0067] Specifically, feedback evaluation suggestions play a key guiding role. Since there is an antagonistic relationship between the evaluation indicators of power generation equipment, such as an increase in one indicator should be accompanied by a corresponding increase or decrease in another indicator, when this relationship is abnormal, it is necessary to construct a preset evaluation contradiction interval. For example, power and energy consumption should usually change synchronously. If an abnormality occurs, or the correlation between temperature and heat dissipation efficiency is unreasonable, the feedback evaluation suggestions will record these abnormal data and indicator trend contradictions. Contradictory indicators need to be retained because they are crucial for accurately verifying the accuracy of subsequent equipment operation, while those indicators with little correlation with other indicators are considered for dimensionality reduction. By analyzing this information in the feedback evaluation suggestions, the scope of possible data contradictions or anomalies is determined, and then a preset evaluation contradiction interval is constructed, laying the foundation for subsequent in-depth analysis of equipment operation status and optimization of the evaluation system.

[0068] The preset evaluation contradiction interval is a specific data range determined in the previous step according to the feedback evaluation suggestions, which demarcates the area where data contradictions or anomalies exist. The first evaluation matrix contains the original data of multiple evaluation indicators at different time points or working conditions. In this step, these data within the preset evaluation contradiction interval are analyzed. The preset evaluation indicator data are usually some reference values, which can be the average value of historical data, the value specified by the industry standard, the typical value of the normal operation of the equipment, etc. The process of calculating the distribution probability is as follows: for each data point of the evaluation indicator in the preset evaluation contradiction interval, calculate its distribution probability relative to the preset evaluation indicator data. This probability reflects the relative position and possibility of occurrence of the data point in the entire data distribution. For example, for the temperature indicator, if the preset evaluation indicator data is the historical average temperature, for a certain temperature value within the preset evaluation contradiction interval, the distribution probability of the temperature value in all possible temperature values ​​can be obtained by the probability calculation method (such as based on the probability model such as the normal distribution). These distribution probabilities are expressed in the form of a dot matrix to obtain the evaluation indicator distribution probability dot matrix. In this dot matrix, each point corresponds to the distribution probability of a data point of an evaluation indicator within a specific interval. The entire dot matrix presents a collection of distribution probability information of multiple evaluation indicators within a preset evaluation contradiction interval, providing an intuitive and detailed basic data structure for subsequent data analysis and processing.

[0069] Constructing the probability distribution function of the dot matrix similarity is a critical step. It is a tool used to quantify the similarity between different points in the probability matrix of the evaluation index distribution. Through it, we can deeply understand the distribution characteristics and internal structure of the dot matrix data, calculate the similarity between points based on the distribution probability value of the points and convert it into a probability distribution form. Then, dimensionality reduction is performed. Since the original evaluation index distribution probability matrix has a high dimension, data processing is complex and there is redundancy and noise, and dimensionality reduction can reduce dimensions, extract key information, and improve processing efficiency and accuracy. Using principal component analysis, based on the similarity and correlation between points determined by the dot matrix similarity probability distribution function, similar points are merged or compressed, and redundant information is removed to highlight the main structure and trend. The resulting distribution probability matrix dimensionality reduction result is in a low-dimensional space, which is more concise and compact than the original matrix, retains key information, and can more clearly reflect the data distribution law and trend, providing a more efficient and convenient basis for subsequent operations such as constructing the second evaluation matrix.

[0070] The dimensionality reduction result of the distribution probability lattice is a more refined result that better reflects the essential characteristics of the data after the previous complex data processing and analysis. It contains the key information extracted from the distribution probability lattice of the original evaluation index, and removes redundancy and noise through dimensionality reduction. When constructing the second evaluation matrix, the dimensionality reduction result of the distribution probability lattice will be fully utilized. First, the evaluation indexes are reviewed and screened based on the information retained in the dimensionality reduction result. Those indicators that are considered to have important contributions to the data distribution and characteristics during the dimensionality reduction process will be given priority to be retained in the second evaluation matrix. For example, if an evaluation index shows that its distribution probability has obvious discrimination and representativeness in the results after dimensionality reduction, then this index is more likely to be included in the new matrix. Secondly, for the retained evaluation indicators, according to the data distribution and probability information in the dimensionality reduction results, their weights and arrangements in the matrix are re-determined. The weight determination can be based on factors such as the data importance of the indicator after dimensionality reduction and the degree of influence on the overall data distribution. For example, if the distribution probability of an indicator after dimensionality reduction is concentrated in a specific key interval and is of great significance to the judgment of the equipment operation status, then it will be given a higher weight. Finally, the second evaluation matrix is ​​constructed by integrating the selected evaluation indicators and their corresponding weights and data information. Compared with the first evaluation matrix, this new matrix is ​​more optimized in data structure and information content, and can more accurately reflect the operating status and evaluation information of power generation equipment under specific circumstances, providing a more reliable basis for subsequent comprehensive evaluation and decision-making.

[0071] In a possible implementation, step S433 further includes:

[0072] L=∑ i ∑ j KL[P(x i|x j )||Q(z i |z j )]。

[0073] Among them, KL is a measure index representing the proximity between the lattice distribution of the evaluation index distribution probability lattice and the dimensionality-reduced lattice distribution of the evaluation index distribution probability lattice. Taking KL approaching 0 as a constraint condition for dimensionality reduction processing, L is the divergence representing the similarity between the lattice distribution of the evaluation index distribution probability lattice and the dimensionality-reduced lattice distribution of the evaluation index distribution probability lattice. P(x i |x j ) is the similarity probability regarding lattice x i and lattice x j in the dimensionality-reduced lattice distribution based on the evaluation index distribution probability lattice. Q(z i |z j ) is the similarity probability regarding lattice z i and lattice z j in the lattice distribution based on the evaluation index distribution probability lattice. (i, j) is any coordinate point in the first evaluation matrix, the value range of i is 0 < i < n, the value range of j is 0 < j < n, and n is the total number of coordinate points in the first evaluation matrix.

[0074] Specifically, KL in this function is a key index, which is used to measure the proximity between the original lattice distribution of the evaluation index distribution probability lattice and the lattice distribution after dimensionality reduction processing. To achieve effective dimensionality reduction, taking KL approaching 0 as a constraint condition means that in the dimensionality reduction process, efforts are made to make the dimensionality-reduced lattice distribution as close as possible to the original lattice distribution to retain the important features and information of the data. L represents the divergence of the similarity between the lattice distribution of the evaluation index distribution probability lattice and the dimensionality-reduced lattice distribution. The divergence can reflect the difference degree between two distributions and is used here to evaluate the similarity of the distributions before and after dimensionality reduction. P(x i |x j ) represents the similarity probability regarding lattice x i and lattice x j in the dimensionality-reduced lattice distribution based on the evaluation index distribution probability lattice. This probability reflects the similarity degree between these two lattices in the dimensionality-reduced lattice. Q(z i |z j ) represents the similarity probability regarding lattice z i and lattice z j in the lattice distribution based on the evaluation index distribution probability lattice. By comparing P(x i |x j ) and Q9z i |z j),it is possible to understand the change in the similarity of the dot matrix before and after dimensionality reduction. (i, j) is any coordinate point in the first evaluation matrix, where the value range of i is 0 < i < n, the value range of j is 0 < j < n, and n is the total number of coordinate points in the first evaluation matrix. Such a definition covers all points in the matrix, ensuring a comprehensive analysis and processing of the entire dot matrix. As described above, this function realizes the dimensionality reduction processing of the dot matrix distribution by calculating and comparing the similarity probabilities between the dot matrices in the evaluation index distribution probability dot matrix, providing an important basis for the subsequent construction of the second evaluation matrix.

[0075] In a possible implementation manner, step S500 further includes:

[0076] Step S510: Determine the evaluation period according to the type and quantity of power generation equipment.

[0077] Step S520: Integrate according to the evaluation period in combination with the comprehensive evaluation optimization index list to construct the regular evaluation mechanism.

[0078] Step S530: Activate the regular evaluation mechanism based on the evaluation period to continuously track the data of the power generation equipment according to the comprehensive evaluation optimization index list, and generate the operation tracking data.

[0079] Specifically, determining the evaluation period is a key decision-making process. First, the type of power generation equipment needs to be considered. For different types of power generation equipment, there may be differences in their performance characteristics, operation stability, and maintenance requirements. For example, some large generator sets require a longer operation time to accumulate sufficient data for accurate evaluation, while some small auxiliary equipment can be evaluated in a shorter cycle. Second, the quantity of power generation equipment also affects the evaluation period. If the quantity of power generation equipment is large, in order to ensure effective monitoring and management of each equipment, more frequent evaluations are required to timely discover potential problems. On the contrary, if the quantity of equipment is small, the evaluation period can be appropriately shortened to reduce unnecessary resource consumption. By comprehensively considering the type and quantity of power generation equipment, through the analysis of historical data, the suggestions of equipment manufacturers, and the summary of actual operation experience, a suitable evaluation period is determined. This period should be able to ensure the timely discovery of potential problems of the equipment without evaluating too frequently, resulting in waste of resources.

[0080] According to the determined evaluation cycle, it is organically integrated with the comprehensive evaluation optimization index list to build a regular evaluation mechanism. First, the specific time interval and frequency of the evaluation cycle are clarified, such as once a week, once a day, etc. Then, the indicators in the comprehensive evaluation optimization index list are matched with the evaluation cycle to determine which indicators need to be monitored and evaluated in each evaluation cycle. For example, if the evaluation cycle is once a week, and the comprehensive evaluation optimization index list includes indicators such as equipment operating efficiency, energy consumption, and failure rate, then data collection and analysis will be performed on these indicators in the weekly regular evaluation. In the process of building a regular evaluation mechanism, detailed evaluation processes and methods need to be formulated, including determining the method and time of data collection, the method of data processing and analysis, and the generation and reporting of evaluation results. At the same time, the responsibilities and division of labor of relevant departments and personnel in the regular evaluation should be clarified to ensure the smooth progress of the evaluation work. Through such integration and construction, the regular evaluation mechanism can systematically monitor and evaluate power generation equipment continuously, timely discover problems and potential risks in equipment operation, and provide strong support for the optimized operation and maintenance of equipment.

[0081] When the set evaluation cycle is reached, the regular evaluation mechanism will be automatically activated. This mechanism will continuously track the data of the power generation equipment according to the requirements of the comprehensive evaluation optimization index list. During the data tracking process, the relevant data of the power generation equipment will be collected in real time, and these data correspond to the various indicators in the comprehensive evaluation optimization index list. For example, if the list includes indicators such as temperature, pressure, and power of the equipment, these parameters will be monitored and recorded in real time. Through continuous data tracking, the operating status information of the power generation equipment in different time periods can be obtained, and this information will be sorted and analyzed to generate operation tracking data. The operation tracking data reflects the operating trends and changes of the power generation equipment. It can help relevant personnel to promptly discover possible problems or abnormal conditions of the equipment. For example, if the data of a certain indicator suddenly fluctuates abnormally, or continuously deviates from the normal range, it can be detected in time through the operation tracking data, and corresponding measures can be taken to deal with it. By activating the regular evaluation mechanism based on the evaluation cycle, the power generation equipment is continuously tracked and the operation tracking data is generated, which provides an important basis for the subsequent comprehensive and intelligent evaluation of the operation of the power generation equipment.

[0082] In a possible implementation, step S530 further includes:

[0083] Step S531: Retrieve the operating sequence of the power generation equipment, and when the operating sequence is in the evaluation cycle, activate the periodic evaluation mechanism.

[0084] Step S532: Continuously track the data of the power generation equipment through the periodic evaluation mechanism to generate an operation data tracking trajectory.

[0085] Step S533: determine whether the operation data tracking trajectory is in a preset operation range. If the operation data tracking trajectory is not in the preset operation range, generate a deviation mark, and obtain the deviation difference of the operation data tracking trajectory according to the deviation mark analysis.

[0086] Step S534: When the deviation difference is greater than or equal to a preset deviation threshold, an alarm instruction is generated and the alarm instruction is added to the operation tracking data.

[0087] Specifically, first obtain the operating sequence information of the power generation equipment. The operating sequence records the operating status and related parameters of the power generation equipment at different time points. Then, compare the current operating sequence with the set evaluation cycle. The evaluation cycle is determined based on factors such as the type and quantity of the power generation equipment and actual needs, and is used to determine the time interval for regular evaluation of the equipment. If the current operating sequence is within the evaluation cycle, it means that it is time to evaluate the power generation equipment. At this time, the regular evaluation mechanism will be activated to start the collection, analysis and evaluation of various data of the power generation equipment. In this way, it can ensure that the power generation equipment is evaluated regularly at the appropriate time, and problems or potential risks of the equipment can be discovered in time, so that corresponding measures can be taken for maintenance and improvement to ensure the stable operation of the power generation equipment.

[0088] Once the periodic evaluation mechanism is activated, it will start to continuously track the data of the power generation equipment and monitor the various operating parameters of the power generation equipment in real time, such as voltage, current, power, temperature, pressure, etc. During the monitoring process, these data are recorded in chronological order to generate an operation data tracking trajectory, which can intuitively show the changes in the operating status of the power generation equipment over a period of time. For example, through the operation data tracking trajectory, you can see the fluctuations in the power of the power generation equipment in different time periods, or whether the temperature gradually increases or decreases within the normal range. The generated operation data tracking trajectory provides an important basis for subsequent analysis and judgment. Through the analysis of the trajectory, abnormal conditions in the operation of the equipment, such as sudden power drop, abnormal temperature increase, etc., can be discovered in time, so that appropriate measures can be taken to deal with them and ensure the safe and stable operation of the power generation equipment.

[0089] The operation data tracking trajectory is compared with the preset operation range. The preset operation range is a range set according to the normal operating status and performance parameters of the power generation equipment, representing the range in which the equipment should operate under ideal conditions. Each data point in the operation data tracking trajectory is checked one by one to determine whether they fall within the preset operation range. If all data points in the operation data tracking trajectory are within the preset operation range, it means that the operation status of the equipment is normal and there is no abnormality. However, if it is found that some or all of the data points in the operation data tracking trajectory are not within the preset operation range, it means that there is a problem with the operation status of the equipment, and a deviation mark will be generated. Once the deviation mark is generated, the deviation of the operation data tracking trajectory will be further analyzed based on this mark, and the deviation difference between the operation data tracking trajectory and the preset operation range will be calculated. This deviation difference can reflect the degree to which the operation status of the equipment deviates from the normal range. For example, if the preset operation range is a temperature between 50℃ and 80℃, and a data point in the operation data tracking trajectory shows a temperature of 90℃, then the deviation difference is 90℃ minus 80℃, that is, 10℃. By analyzing the deviation difference, the system can more accurately understand the degree of abnormality in the equipment's operating status, providing an important basis for subsequent processing and decision-making.

[0090] The deviation difference is judged. The preset deviation threshold is a critical value set according to the characteristics and operating requirements of the power generation equipment, which is used to determine whether the degree of deviation reaches the level that requires an alarm. If the deviation difference is greater than or equal to the preset deviation threshold, it means that the degree of deviation of the equipment's operating status from the normal range is serious, and there are potential faults or safety hazards. At this time, the system will generate an alarm instruction. The alarm instruction is a notification information used to remind relevant personnel that the equipment has an abnormal situation and needs to take timely measures to deal with it. The generated alarm instruction will be added to the operation tracking data for subsequent recording and analysis. By adding the alarm instruction to the operation tracking data, it can ensure that the relevant personnel can obtain the abnormal information of the equipment in a timely manner, and take corresponding measures according to the alarm instruction, such as equipment maintenance, adjustment of operating parameters, etc., to restore the normal operating state of the equipment and ensure the safe and stable operation of the power generation equipment.

[0091] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0093] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A comprehensive evaluation method for the operation of power generation equipment based on multiple indicators, characterized in that: The method comprises: Monitor the operation of power generation equipment and obtain the equipment operation parameter set; Building a comprehensive evaluation index list based on the equipment operation parameter set, wherein the comprehensive evaluation index list includes multiple evaluation indicators; Synchronizing the multiple evaluation indicators to a mathematical analysis model for quantitative evaluation, generating multiple indicator quantitative evaluation results, and performing comprehensive analysis based on the multiple indicator quantitative evaluation results to determine a comprehensive operation evaluation result; Generate feedback evaluation suggestions based on the operation comprehensive evaluation results, optimize the comprehensive evaluation index list according to the feedback evaluation suggestions, and generate a comprehensive evaluation optimization index list; Establishing a regular evaluation mechanism based on the comprehensive evaluation optimization index list to continuously track the power generation equipment, and conducting a comprehensive intelligent evaluation of the operation of the power generation equipment based on the operation tracking data; The step of generating feedback evaluation suggestions based on the operation comprehensive evaluation results, optimizing the comprehensive evaluation index list according to the feedback evaluation suggestions, and generating a comprehensive evaluation optimization index list includes: Constructing a first evaluation matrix based on the multiple evaluation indicators; Analyze the comprehensive evaluation results of the operation and arrange them in ascending order according to the scores to obtain a contribution degree sequence; Extracting the evaluation index corresponding to the first-order contribution based on the contribution sequence for evaluation, and adding the evaluation index corresponding to the first-order contribution to the feedback evaluation suggestion according to the contribution evaluation result; According to the feedback evaluation suggestions, the first evaluation matrix is ​​reduced in dimension to generate a second evaluation matrix; Screening and optimizing the multiple evaluation indicators in the comprehensive evaluation indicator list according to the second evaluation matrix to generate multiple screened and optimized evaluation indicators; Generate the comprehensive evaluation optimization index list based on the multiple screening optimization evaluation indexes; The first evaluation matrix is ​​reduced in dimension according to the feedback evaluation suggestion to generate a second evaluation matrix, the method comprising: Constructing a preset evaluation contradiction interval based on the feedback evaluation suggestion, wherein the preset evaluation contradiction interval refers to an area where data contradictions or anomalies exist; Calculate and obtain the distribution probability of a plurality of evaluation index data and preset evaluation index data in the first evaluation matrix within a preset evaluation contradiction interval, and obtain an evaluation index distribution probability lattice; Constructing a dot matrix similarity probability distribution function, performing dimensionality reduction processing on the dot matrix distribution of the evaluation index distribution probability dot matrix, and generating a distribution probability dot matrix dimensionality reduction result; The second evaluation matrix is ​​constructed based on the distribution probability lattice dimensionality reduction result.

2. A comprehensive evaluation method for the operation of power generation equipment based on multiple indicators as claimed in claim 1, characterized in that: The construction method of the plurality of evaluation indicators includes: Parse the equipment operation parameter set to obtain equipment operation status parameters and equipment operation performance parameters; Calculate and obtain the equipment operation efficiency based on the equipment operation status parameter and the equipment operation performance parameter; Using the equipment operation status parameter, the equipment operation performance parameter, and the equipment operation efficiency as classification dimensions, constructing multiple hierarchical structures based on the classification dimensions; The multiple evaluation indicators are determined according to the multiple hierarchical structures.

3. A comprehensive evaluation method for the operation of power generation equipment based on multiple indicators as claimed in claim 1, characterized in that: The method includes: synchronizing the multiple evaluation indicators to a mathematical analysis model for quantitative evaluation, generating multiple indicator quantitative evaluation results, performing comprehensive analysis based on the multiple indicator quantitative evaluation results, and determining a comprehensive operation evaluation result. Constructing a mathematical analysis model based on the multiple evaluation indicators and the evaluation target of the power generation equipment, wherein the mathematical analysis model comprises a data input layer, a quantitative evaluation layer, an evaluation test layer, and a data output layer; Constructing a first evaluation matrix based on the multiple evaluation indicators; Mapping the first evaluation matrix to the quantitative evaluation layer through the data input layer to perform single-indicator quantitative evaluation and generate a single-indicator quantitative evaluation result; Input the single indicator quantitative evaluation result to the evaluation test layer, and when the test passes, start the data output layer to output the multiple indicator quantitative evaluation results; Based on the quantitative evaluation results of the multiple indicators, weight allocation is performed to determine multiple weight coefficients; The quantitative evaluation results of the multiple indicators are analyzed according to the multiple weight coefficients to generate the comprehensive operation evaluation result.

4. A comprehensive evaluation method for the operation of power generation equipment based on multiple indicators as claimed in claim 1, characterized in that: The point matrix similarity probability distribution function is as follows: ； Among them, is a measure index for characterizing the proximity between the dot matrix distribution of the evaluation index distribution probability dot matrix and the dimensionality-reduced dot matrix distribution of the evaluation index distribution probability dot matrix. Let tend to 0 as a constraint condition for dimensionality reduction processing. is the divergence representing the similarity between the dot matrix distribution of the evaluation index distribution probability dot matrix and the dimensionality-reduced dot matrix distribution of the evaluation index distribution probability dot matrix. is the similarity probability based on the dimensionality-reduced dot matrix distribution of the evaluation index distribution probability dot matrix regarding the dot matrix and the dot matrix . is the similarity probability based on the dot matrix distribution of the evaluation index distribution probability dot matrix regarding the dot matrix and the dot matrix . (i, j) is any coordinate point in the first evaluation matrix, where the value range of i is 0 < i < n, the value range of j is 0 < j < n, and n is the total number of coordinate points in the first evaluation matrix.

5. A comprehensive evaluation method for the operation of power generation equipment based on multiple indicators as claimed in claim 1, characterized in that: Establishing the periodic evaluation mechanism to continuously track the power generation equipment includes: Determine the evaluation cycle based on the type and quantity of power generation equipment; Integrate the evaluation cycle and the comprehensive evaluation optimization index list to build the regular evaluation mechanism; The periodic evaluation mechanism is activated based on the evaluation cycle to continuously track the data of the power generation equipment according to the comprehensive evaluation optimization index list to generate the operation tracking data.

6. A method for comprehensive evaluation of power generation equipment operation based on multiple indicators as claimed in claim 5, characterized in that: The method includes: activating the periodic evaluation mechanism based on the evaluation cycle to continuously track the data of the power generation equipment according to the comprehensive evaluation optimization index list to generate the operation tracking data; Retrieving the operating time sequence of the power generation equipment, and activating the periodic evaluation mechanism when the operating time sequence is in the evaluation period; Continuously track the data of power generation equipment through the periodic evaluation mechanism to generate an operation data tracking trajectory; Determining whether the operation data tracking trajectory is in a preset operation interval, if the operation data tracking trajectory is not in the preset operation interval, generating a deviation mark, and obtaining a deviation difference of the operation data tracking trajectory according to the deviation mark; When the deviation difference is greater than or equal to a preset deviation threshold, an alarm instruction is generated and the alarm instruction is added to the operation tracking data.

Images