A method and system for intelligent diagnosis and rectification of off-line test of power plant fire-resistant oil

Abstract

The application discloses a kind of power plant fire-resistant oil offline test intelligent diagnosis and rectification method and system, comprising: collecting fire-resistant oil offline test data, unit operation parameter and oil product use information, with standard threshold comparison and divide oil quality abnormal grade;Based on operating experience, historical data and fault case, abnormal reason feature library is constructed, and the degradation root is identified and sorted by multidimensional correlation analysis;According to abnormal grade and root cause, generate graded rectification measures, form standardized disposal scheme;After rectification, retest verification effect, qualified then archive optimization, unqualified then iterative processing.The application realizes fire-resistant oil quality abnormal intelligent diagnosis and closed-loop rectification, solves the problems such as experience dependence, disposal lag, non-uniform standard in traditional manual mode, improves the efficiency and reliability of power plant chemical supervision, and guarantees the safe and stable operation of unit.

Description

Technical Field

[0001] This invention belongs to the field of intelligent monitoring technology for fire-resistant oil, and relates to a method and system for intelligent diagnosis and rectification of fire-resistant oil in power plants after offline testing. Background Technology

[0002] Fire-resistant oil is the core medium for ensuring the reliable operation of the regulating system of power plant turbine generator units, and its quality directly affects the safety and stability of the unit. Currently, power plants generally use periodic sampling and offline laboratory testing for oil quality monitoring. After the testing is completed, technicians rely on their experience to conduct oil quality analysis, anomaly identification, and rectification plan formulation. The entire process is highly dependent on manual operation. This traditional model has significant technical shortcomings: after the oil quality test results are issued, the time for manually investigating the causes of deterioration and formulating rectification measures is long, and the pace of action lags behind the rate of oil deterioration, which can easily aggravate oil damage and increase the probability of failures such as jamming of regulating components. At the same time, there is a lack of unified diagnostic and rectification standards, the judgment results are highly subjective and biased, and the rectification measures given are generally applicable but not specific enough to effectively solve practical problems. In addition, there is a lack of systematic correlation and intelligent connection between offline test data, causes of oil deterioration, and treatment measures, which cannot form a complete closed loop of analysis and treatment, making it difficult to achieve data-driven accurate diagnosis and efficient rectification, thus restricting the efficiency and reliability of chemical monitoring of fire-resistant oil in power plants. Summary of the Invention

[0003] The purpose of this invention is to solve the problems in the existing technology of power plant fire-resistant oil offline testing and supervision, such as reliance on manual experience, delayed diagnosis and treatment, lack of standardized diagnosis and rectification logic, and insufficient closed-loop data management. The invention provides an intelligent diagnosis and rectification method and system for power plant fire-resistant oil offline testing.

[0004] To achieve the above objectives, the present invention employs the following technical solution: A method for intelligent diagnosis and rectification of fire-resistant oil in power plants after offline testing includes: Collect offline test data of fire-resistant oil, unit operating parameters and oil usage information, and compare the offline test data of fire-resistant oil with standard thresholds to determine the qualified status of indicators. Based on the unqualified indicators, classify the oil quality abnormality level to form a diagnostic grading basis. Based on the operating experience of fire-resistant oil in power plants, historical test data, failure cases and oil usage information, a mapping relationship between the non-compliance indicators of fire-resistant oil and the causes of deterioration is preset, and a standardized abnormal cause feature library is constructed. Based on diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information, the abnormal cause feature library is called to conduct multi-dimensional correlation analysis to identify and rank the root causes of oil quality deterioration. Based on the root causes of oil quality deterioration and the diagnostic and grading criteria, graded rectification measures are generated, implementation priorities and treatment requirements are determined, and standardized treatment plans are obtained. The power plant system was rectified based on the standardized treatment plan. Offline samples of fire-resistant oil were collected again for testing, and the rectification effect was compared. If the rectification was qualified, the case was archived and the diagnostic logic was optimized. If the rectification was not qualified, iterative analysis and rectification were carried out until the rectification requirements were met.

[0005] A further improvement of the present invention is that: Furthermore, the offline test data for the fire-resistant oil includes moisture content, acid value, particulate contamination level, volume resistivity, sludge content, and flash point; the unit operating parameters include unit load, operating time, and oil temperature setpoint; the oil usage information includes the fire-resistant oil usage time and refueling records; wherein, the flash point refers to the lowest temperature at which a combustible mixture formed by mixing oil vapor and air can instantly ignite upon encountering an ignition source under specified test conditions.

[0006] Furthermore, the process of comparing the offline test data of fire-resistant oil with standard thresholds to determine the qualification status of the indicators, and classifying the oil quality abnormality level based on the non-qualified indicators, forms a diagnostic grading basis. Specifically, the offline test data of fire-resistant oil is compared with the standard thresholds one by one. When the offline test data of fire-resistant oil does not exceed the standard threshold, the offline test data of fire-resistant oil is considered qualified; when the offline test data of fire-resistant oil exceeds the standard threshold, the offline test data of fire-resistant oil is considered unqualified; and the oil quality abnormality level is automatically classified according to the number of non-qualified indicators and the degree of exceeding the standard.

[0007] Furthermore, the oil quality anomaly levels include: general anomaly, important anomaly, and emergency anomaly; the general anomaly is a slight exceedance of a single indicator; the important anomaly is a severe exceedance of a single indicator; the emergency anomaly is a severe exceedance of 2-3 indicators; the slight exceedance is an exceedance value greater than the standard threshold but not exceeding the first threshold; the severe exceedance is an exceedance value greater than the first threshold; wherein, the first threshold is greater than the standard threshold.

[0008] Furthermore, based on the power plant's experience in operating fire-resistant oil, historical test data, failure cases, and oil usage information, a mapping relationship between unqualified fire-resistant oil indicators and deterioration causes is preset, and a standardized abnormal cause feature library is constructed. Specifically, combining the fire-resistant oil deterioration mechanism, power plant operating experience, historical test data, failure cases, and oil usage information, a mapping relationship between unqualified indicators such as moisture, acid value, particulate contamination degree, volume resistivity, sludge / colloid precipitation, and flash point and their corresponding deterioration causes is preset, and unit operating parameters and fire-resistant oil usage time are associated with deterioration causes to obtain a standardized abnormal cause feature library.

[0009] Furthermore, the correlation between unit operating parameters, fire-resistant oil usage time and deterioration causes is as follows: unit operating parameters directly cause or accelerate the occurrence of deterioration causes; the longer the fire-resistant oil usage time is, the greater the probability of deterioration. Furthermore, the mapping relationship between the preset moisture content, acid value, particulate contamination, volume resistivity, sludge / colloid precipitation, and flash point non-compliance indicators and their corresponding deterioration causes is as follows: abnormal moisture content is associated with cooler leakage, breather failure, moisture introduced during oil replenishment, moisture released from diatomaceous earth, improper sampling sealing, and moisture introduced by the resin filter element; abnormal acid value is associated with excessive moisture triggering hydrolysis, excessively high oil temperature accelerating oxidation, incorrect oil replenishment or contamination, long-term lack of regeneration and purification, and catalytic oxidation by metal particles; abnormal particulate size is associated with impurities generated by component wear, filter element failure, and improper maintenance. Abnormalities include: oil contamination, scale and flaking of electric heaters, and welding residue; abnormal volume resistivity is caused by excessive moisture, increased acid value generating conductive impurities, oil deterioration producing conductive products, or contamination by other conductive media; abnormal sludge / colloid precipitation is caused by long-term aging of fire-resistant oil, accumulation of deterioration products from hydrolysis and oxidation, synergistic effects of multiple indicators exceeding standards, improper oil replenishment, oil incompatibility, or long-term high oil temperature accelerating precipitation; abnormal flash point is caused by oxidation and deterioration of fire-resistant oil producing light components, mixing with low flash point oil, mixing with flammable impurities, or cracking due to long-term high-temperature operation.

[0010] Furthermore, based on the diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information, a multi-dimensional correlation analysis is performed using an anomaly cause feature library to identify and rank the root causes of oil quality deterioration. Specifically, the diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information are matched and compared with the preset mapping relationship between non-compliant indicators and deterioration causes in the anomaly cause feature library. Through multi-parameter correlation analysis, 1 to 3 of the most likely root causes of oil quality deterioration are selected, and the root causes of oil quality deterioration are ranked according to indicator matching degree, operating condition adaptability, impact contribution, and case similarity. Among them, the higher the degree of fit between indicator matching degree, operating condition adaptability, impact contribution, and case similarity with the deterioration inducing factor, the higher the probability of the deterioration cause occurring, and the higher the ranking. When there are complex anomalies with multiple indicators exceeding the standard at the same time, a weighted analysis algorithm is used to determine the dominant cause with the greatest impact on oil quality deterioration.

[0011] Furthermore, the index matching degree is the degree of matching between the cause of degradation and the current exceeding index and the magnitude of index exceeding the standard. The more matching items there are and the more the exceeding characteristics match the degradation mechanism, the higher the probability. The operating condition adaptability refers to the degree of correlation and fit between the cause of deterioration and the unit's operating parameters and the service life of fire-resistant oil. The more the operating status and oil service life match the conditions for the occurrence of the deterioration cause, the higher the probability of the corresponding cause. The contribution rate of the impact is the proportion of the combined impact of the deterioration cause on the current multiple abnormal indicators. The stronger the driving effect on oil quality deterioration and the wider the scope of the impact, the higher the probability. The case similarity refers to the degree of similarity between the current abnormal scenario and historical failure cases, as well as the test data of similar equipment. The higher the frequency of the deterioration cause in similar scenarios, the higher the probability.

[0012] Furthermore, the generation of graded rectification measures based on the root causes of oil quality deterioration and diagnostic grading criteria, the determination of implementation priorities and treatment requirements, and the acquisition of standardized treatment plans are specifically as follows: matching targeted rectification measures based on the root causes of deterioration, and classifying mandatory and recommended items according to the oil quality anomaly level; determining the rectification implementation priority, rectification time limit, and safe treatment requirements according to the severity of the anomaly level and the weight of the deterioration impact; and integrating the rectification measures, priorities, and treatment requirements to form a standardized treatment plan. Based on the root cause of deterioration and the determined level of oil quality abnormality, corrective measures are generated corresponding to each cause of deterioration. These corrective measures are divided into mandatory items and recommended items, specifically: If the moisture content exceeds the standard, the mandatory steps are to start the vacuum oil filter for vacuum dehydration, repair the cooler leaks, and replace the desiccant. The recommended steps are to standardize the sampling process, check the condition of the ion exchange resin regeneration filter element, and replace it promptly if any abnormalities are found. For excessive acid values, mandatory steps include regeneration and deacidification, and controlling oil temperature to 40-55℃; recommended steps include a thorough cleaning of the fuel system and timely replacement of worn parts. For cases where particle size exceeds the standard, mandatory steps include replacing the filter element, performing full system filtration, and cleaning worn parts; recommended steps include optimizing maintenance procedures, establishing a regular filter element replacement mechanism, and replacing filters promptly based on operating time and filtration effectiveness. If the resistivity is too low, the essential steps are to remove conductive impurities, treat the moisture and acid value simultaneously, and replace the fire-resistant oil. Recommended steps include regularly testing the resistivity of the fire-resistant oil and establishing a record of resistivity change trends; and avoiding contact between the fire-resistant oil and other conductive media to prevent cross-contamination. For excessive sludge and gum content, the mandatory steps are to filter out deterioration products, clean the system, and replace the fire-resistant oil; the recommended steps are to optimize oil temperature control and strictly verify the brand and quality standard of the oil when adding oil. The essential steps to reduce flash point are to investigate the source of contamination, replace contaminated oil, and avoid high-temperature operation; recommended steps include strengthening the storage management of fire-resistant oils, regularly testing flash point indicators, and establishing an early warning mechanism for flash point changes.

[0013] A smart diagnostic and remediation system for offline testing of fire-resistant oil in power plants, comprising: The comparison module collects offline test data of fire-resistant oil, unit operating parameters and oil usage information, and compares the offline test data of fire-resistant oil with standard thresholds to determine the qualified status of the indicators. Based on the unqualified indicators, the oil quality abnormality level is divided to form a diagnostic grading basis. The module is designed based on the power plant's experience in operating fire-resistant oil, historical test data, failure cases, and oil usage information. It pre-defines the mapping relationship between the non-compliance indicators of fire-resistant oil and the causes of deterioration, and builds a standardized feature library of abnormal causes. The identification module, based on diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information, calls the abnormal cause feature library to perform multi-dimensional correlation analysis, identify and sort the root causes of oil quality deterioration; The acquisition module generates graded rectification measures based on the root causes of oil quality deterioration and diagnostic grading criteria, determines the execution priority and disposal requirements, and acquires standardized disposal plans. The detection module is used to rectify the power plant system based on a standardized treatment plan. It re-collects offline test samples of fire-resistant oil for testing and compares the rectification effect. If the rectification is qualified, the case is archived and the diagnostic logic is optimized. If the rectification is unqualified, iterative analysis and rectification are carried out until the rectification requirements are met.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention achieves accurate determination of oil quality status through data collection, threshold comparison, and anomaly classification. It constructs a standardized anomaly cause feature library to establish a mapping relationship between indicators and the root causes of deterioration. Relying on multi-dimensional correlation analysis and weighting algorithms, it quickly locates and sorts the root causes. It generates graded rectification plans according to the anomaly level and the root cause of deterioration, forming a closed-loop handling process. This effectively solves the problems of traditional manual diagnosis, such as reliance on experience, low efficiency, strong subjectivity, and delayed handling. It realizes intelligent diagnosis and standardized rectification of fire-resistant oil quality anomalies, ensuring the safe and stable operation of steam turbine generator sets. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating an intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants, according to the present invention. Figure 2 This is a schematic diagram of the structure of an intelligent diagnosis and rectification system for offline testing of fire-resistant oil in power plants according to the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0018] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0019] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0020] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0021] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0022] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0023] The present invention will now be described in further detail with reference to the accompanying drawings: See Figure 1 This invention discloses a method for intelligent diagnosis and rectification of fire-resistant oil in power plants after offline testing, including: S101 collects offline test data of fire-resistant oil, unit operating parameters and oil usage information, and compares the offline test data of fire-resistant oil with standard thresholds to determine the qualified status of indicators. Based on the unqualified indicators, the oil quality abnormality level is classified to form a diagnostic grading basis. The offline test data for the fire-resistant oil includes moisture content, acid value, particulate contamination level, volume resistivity, sludge content, and flash point; the unit operating parameters include unit load, operating time, and oil temperature setpoint; and the oil usage information includes the fire-resistant oil usage time and refueling records.

[0024] The process of comparing offline test data of fire-resistant oil with standard thresholds to determine the pass / fail status of indicators, and classifying oil quality anomalies based on the number of non-compliant indicators, forms a diagnostic grading basis. Specifically, the offline test data of fire-resistant oil is compared with standard thresholds one by one. When the offline test data of fire-resistant oil does not exceed the standard threshold, the offline test data of fire-resistant oil is considered qualified; when the offline test data of fire-resistant oil exceeds the standard threshold, the offline test data of fire-resistant oil is considered unqualified. The oil quality anomaly level is automatically classified according to the number of non-compliant indicators and the degree of exceedance. The oil quality anomaly levels include: general anomaly, important anomaly, and emergency anomaly; a general anomaly is a slight exceedance of a single indicator; an important anomaly is a severe exceedance of a single indicator; an emergency anomaly is a severe exceedance of 2-3 indicators; a slight exceedance is an exceedance value greater than the standard threshold but not exceeding a first threshold; a severe exceedance is an exceedance value greater than the first threshold; wherein, the first threshold is greater than the standard threshold.

[0025] S102, based on the operating experience of fire-resistant oil in power plants, historical test data, failure cases and oil usage information, preset the mapping relationship between the non-conforming indicators of fire-resistant oil and the causes of deterioration, and build a standardized abnormal cause feature library. Combining the degradation mechanism of fire-resistant oil, power plant operation experience, historical test data, failure cases and oil usage information, the mapping relationship between unqualified indicators such as moisture, acid value, particulate contamination, volume resistivity, sludge / colloid precipitation, and flash point and the corresponding degradation causes is preset. The unit operating parameters and the service life of fire-resistant oil are also correlated with the degradation causes to obtain a standardized abnormal cause feature library.

[0026] The association between unit operating parameters, fire-resistant oil usage time, and deterioration causes is as follows: unit operating parameters directly cause or accelerate deterioration causes; the longer the fire-resistant oil usage time, the greater the probability of deterioration.

[0027] The mapping relationship between the preset moisture content, acid value, particulate contamination, volume resistivity, sludge / colloid precipitation, flash point failure indicators and their corresponding causes of deterioration is as follows: When the moisture content is abnormal, i.e. the humidity is not less than 1000 mg / L, the corresponding causes include leakage of fire-resistant fuel cooler, failure of desiccant in fuel tank breather leading to air moisture intrusion, water mixed in during fuel replenishment, incomplete drying of diatomaceous earth used for acid filtration releasing moisture, improper sealing during sampling causing secondary pollution, and improper use of ion exchange resin regeneration filter element introducing moisture. When the acid value is abnormal, i.e. greater than 0.15 mg KOH / g, the corresponding causes include hydrolysis chain reaction of fire-resistant oil (triggered by excessive moisture), local oil temperature too high (>60℃) accelerating oxidation, incorrect oil type or oil contamination, oil not regenerated and purified for a long time, and aggravated oxidation reaction catalyzed by metal wear particles. When the particulate contamination level is abnormal, i.e., the particulate contamination level is greater than level 6, the corresponding causes include: wear of unit components (oil motor O-ring, EH oil pump) producing rubber or metal particles; failure of oil filtration device (filter element blockage or puncture); improper maintenance operation (incomplete cleaning of oil system pipelines, sealing pipelines with rags to introduce impurities); failure to perform sludge precipitation test before oil replenishment leading to mixed oil contamination; scaling and carbonization on the surface of electric heater producing carbide peeling off; and residual welding slag due to failure to perform argon arc welding with argon protection during oil pipe welding. When the volume resistivity is abnormal, that is, when the volume resistivity is less than 6.0 × 10⁻⁶ at 20℃. 9 The corresponding reasons include excessive moisture, increased acid value leading to hydrolysis of fire-resistant oil producing acidic substances, oil deterioration generating conductive impurities, and fire-resistant oil being contaminated by other conductive media. When sludge / colloid precipitation is abnormal, the corresponding causes include long-term aging of fire-resistant oil, accumulation of deterioration products from hydrolysis and oxidation reactions, synergistic effect of excessive particle size and moisture, improper oil replenishment leading to oil incompatibility, and long-term high oil temperature accelerating the precipitation of deterioration products. When the flash point is abnormal, i.e. the temperature is less than 235℃, the corresponding causes include the oxidation and deterioration of the fire-resistant oil to produce light components, the mixing of other oils with low flash points, the mixing of flammable impurities in the oil, and the cracking of the oil due to long-term high-temperature operation. At the same time, the unit's operating parameters, the service life of fire-resistant oil, and the causes of deterioration are correlated to improve the accuracy of cause matching.

[0028] S103, based on diagnostic grading criteria, offline test data of fire-resistant oil and unit operation information, calls the abnormal cause feature library to perform multi-dimensional correlation analysis, identify and sort the root causes of oil quality deterioration; The diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information are matched and compared with the pre-set mapping relationship between unqualified indicators and deterioration causes in the abnormal cause feature database. Through multi-parameter correlation analysis, 1 to 3 of the most likely root causes of oil quality deterioration are selected, and the root causes of oil quality deterioration are ranked according to indicator matching degree, operating condition adaptability, impact contribution, and case similarity. Among them, the higher the degree of fit between indicator matching degree, operating condition adaptability, impact contribution, and case similarity with the deterioration inducing factors, the higher the probability of the deterioration cause occurring, and the higher the ranking. When there are complex anomalies with multiple indicators exceeding the standard at the same time, a weighted analysis algorithm is used to determine the dominant cause with the greatest impact on oil quality deterioration.

[0029] The indicator matching degree refers to the degree of matching between the cause of degradation and the current exceeding indicators and the magnitude of the exceeding indicators. The more matching items and the more consistent the exceeding characteristics with the degradation mechanism, the higher the probability. The operating condition adaptability degree refers to the degree of correlation and fit between the cause of degradation and the unit operating parameters and the service life of fire-resistant oil. The more the operating status and oil service life match the conditions for the occurrence of the degradation cause, the higher the probability. The influence contribution degree refers to the proportion of the comprehensive influence of the degradation cause on the current multiple abnormal indicators. The stronger the driving effect on oil quality degradation and the wider the scope of influence, the higher the probability. The case similarity degree refers to the degree of similarity between the current abnormal scenario and historical failure cases and test data of similar equipment. The higher the frequency of the degradation cause in similar scenarios, the higher the probability. S104, Based on the root causes of oil quality deterioration and the diagnostic and grading criteria, generate graded rectification measures, determine the implementation priority and treatment requirements, and obtain standardized treatment plans; Based on the root cause of deterioration and the determined level of oil quality abnormality, corrective measures are generated corresponding to each cause of deterioration. The corrective measures are divided into mandatory items and recommended items. At the same time, the execution priority, rectification time limit and operation precautions are marked according to the level of abnormality, thus forming a fire-resistant oil quality treatment plan.

[0030] When moisture content exceeds the standard, the mandatory steps are: starting a vacuum oil filter (with a matching diatomaceous earth desiccant filter element) for deep dehydration; checking for leaks in the fire-resistant oil cooler, locating the leak using a pressure test and repairing it; and replacing the desiccant in the fuel tank breather. Recommended steps include: standardizing the sampling process, ensuring the sampling bottle is sealed without damage and free of residual moisture; checking the condition of the ion exchange resin regeneration filter element and replacing it immediately if any abnormalities are found; and optimizing the EH system seal to prevent moisture intrusion.

[0031] When the acid value exceeds the standard, the mandatory steps are to start the fire-resistant oil regeneration device (ion exchange resin column) for deacidification and decolorization; adjust the oil temperature of the fire-resistant oil system to ensure that the oil temperature is controlled between 40 and 55 degrees Celsius, and avoid local oil temperatures exceeding 60 degrees Celsius. Recommended steps include: thoroughly cleaning the fire-resistant oil system during maintenance to remove carbon deposits, sludge, and other deterioration products; standardizing the oil replenishment process, verifying the oil brand before replenishment to ensure compatibility with the original fire-resistant oil, and conducting offline testing after replenishment; checking for metal wear on the unit, and replacing worn parts promptly to reduce catalytic oxidation by metal particles.

[0032] When particulate contamination levels exceed standards, mandatory steps include checking for damage or malfunction of the precision filter, replacing the precision filter element if necessary, starting the oil filter machine for full system circulation filtration, and adding an external filtration system if necessary. During maintenance, a comprehensive inspection of the fuel system pipelines, fuel actuator, and fuel pump should be conducted, replacing worn O-rings, seals, and other vulnerable components, and cleaning scale and carbon deposits from the electric heater surface to prevent carbon deposits from flaking off and contaminating the fuel. Recommendations include optimizing maintenance procedures, prohibiting the use of rags to block pipelines, conducting sludge precipitation tests and particle size analysis on new fuel before adding it, using argon arc welding with argon protection for oil pipe welding to avoid weld slag residue, and establishing a regular filter element replacement mechanism, replacing filters promptly based on operating time and filtration effectiveness.

[0033] When the volume resistivity exceeds the standard, the mandatory steps are to start the fire-resistant oil regeneration device to remove conductive impurities and acidic degradation products from the oil; check the moisture and acid value indicators, and simultaneously address issues of excessive moisture and rising acid value; replace the contaminated fire-resistant oil (if the resistivity remains consistently low, a partial or complete oil change is necessary). Recommended steps include regularly testing the resistivity of the fire-resistant oil and establishing a record of resistivity changes; avoiding contact between the fire-resistant oil and other conductive media to prevent cross-contamination.

[0034] When sludge / gum levels are excessive, the mandatory steps are to activate the fire-resistant fuel regeneration device to filter and remove sludge, gum, and other deterioration products; during maintenance, thoroughly clean the fire-resistant fuel system tank and pipelines to remove attached sludge deposits; if sludge precipitation is severe, perform a partial or complete fuel change. Recommended steps include optimizing fuel temperature control to reduce the precipitation of deterioration products; when adding fuel, strictly verify the fuel brand and quality standards to prevent incompatible fuels from being mixed in.

[0035] When the flash point exceeds the limit, the mandatory steps are to immediately check whether low-flash-point oil or flammable impurities have been mixed into the fire-resistant oil. If contamination is found, the contaminated fire-resistant oil must be replaced immediately. Inspect components such as the electric heater and pipelines of the fire-resistant oil system to prevent prolonged high temperatures from causing oil decomposition. Start the oil filter to remove light, deteriorated components from the oil. Recommended steps include strengthening the storage management of fire-resistant oil to avoid mixing with low-flash-point oil; regularly testing flash point indicators and establishing a flash point change early warning mechanism; and optimizing the heat dissipation design of the fire-resistant oil system to ensure the oil temperature remains stable within a reasonable range. Simultaneously, the system automatically marks the rectification priority, rectification deadline, and precautions during the rectification process, adapting to the actual needs of offline monitoring in power plants.

[0036] S105. Based on the standardized handling plan, rectify the power plant system, re-collect offline test samples of fire-resistant oil for testing, and compare the rectification effect; if the rectification is qualified, archive the case and optimize the diagnostic logic; if the rectification is unqualified, iterate the analysis and rectification until the rectification requirements are met.

[0037] See Figure 2 This invention discloses an intelligent diagnostic and remediation system for offline testing of fire-resistant oil in power plants, comprising: The comparison module collects offline test data of fire-resistant oil, unit operating parameters and oil usage information, and compares the offline test data of fire-resistant oil with standard thresholds to determine the qualified status of the indicators. Based on the unqualified indicators, the oil quality abnormality level is divided to form a diagnostic grading basis. The module is designed based on the power plant's experience in operating fire-resistant oil, historical test data, failure cases, and oil usage information. It pre-defines the mapping relationship between the non-compliance indicators of fire-resistant oil and the causes of deterioration, and builds a standardized feature library of abnormal causes. The identification module, based on diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information, calls the abnormal cause feature library to perform multi-dimensional correlation analysis, identify and sort the root causes of oil quality deterioration; The acquisition module generates graded rectification measures based on the root causes of oil quality deterioration and diagnostic grading criteria, determines the execution priority and disposal requirements, and acquires standardized disposal plans. The detection module is used to rectify the power plant system based on a standardized treatment plan. It re-collects offline test samples of fire-resistant oil for testing and compares the rectification effect. If the rectification is qualified, the case is archived and the diagnostic logic is optimized. If the rectification is unqualified, iterative analysis and rectification are carried out until the rectification requirements are met.

[0038] This invention provides a terminal device. The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the various method embodiments described above. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the various device embodiments described above.

[0039] The computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention.

[0040] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0041] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0042] The memory can be used to store the computer program and / or module. The processor implements various functions of the terminal device by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory.

[0043] If the modules / units integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0044] The above are merely preferred embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent diagnosis and rectification of fire-resistant oil in power plants after offline testing, characterized in that, include: Collect offline test data of fire-resistant oil, unit operating parameters and oil usage information, and compare the offline test data of fire-resistant oil with standard thresholds to determine the qualified status of indicators. Based on the unqualified indicators, classify the oil quality abnormality level to form a diagnostic grading basis. Based on the operating experience of fire-resistant oil in power plants, historical test data, failure cases and oil usage information, a mapping relationship between the non-compliance indicators of fire-resistant oil and the causes of deterioration is preset, and a standardized abnormal cause feature library is constructed. Based on diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information, the abnormal cause feature library is called to conduct multi-dimensional correlation analysis to identify and rank the root causes of oil quality deterioration. Based on the root causes of oil quality deterioration and the diagnostic and grading criteria, graded rectification measures are generated, implementation priorities and treatment requirements are determined, and standardized treatment plans are obtained. The power plant system was rectified based on the standardized treatment plan. Offline samples of fire-resistant oil were collected again for testing, and the rectification effect was compared. If the rectification was qualified, the case was archived and the diagnostic logic was optimized. If the rectification was not qualified, iterative analysis and rectification were carried out until the rectification requirements were met.

2. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 1, characterized in that, The offline test data for the fire-resistant oil includes moisture content, acid value, particulate contamination level, volume resistivity, sludge content, and flash point; the unit operating parameters include unit load, operating time, and oil temperature setpoint; the oil usage information includes the fire-resistant oil usage time and refueling records; wherein, the flash point refers to the lowest temperature at which a combustible mixture formed by mixing oil vapor and air can instantly ignite upon contact with an ignition source under specified test conditions.

3. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 2, characterized in that, The process of comparing offline test data of fire-resistant oil with standard thresholds to determine the pass / fail status of indicators, and classifying oil quality abnormalities based on the non-passing indicators, forms a diagnostic grading basis. Specifically, the offline test data of fire-resistant oil is compared with the standard thresholds one by one. When the offline test data of fire-resistant oil does not exceed the standard threshold, the offline test data of fire-resistant oil is considered to be passable; when the offline test data of fire-resistant oil exceeds the standard threshold, the offline test data of fire-resistant oil is considered to be non-passable; and the oil quality abnormality level is automatically classified according to the number of non-passing indicators and the degree of exceeding the standard.

4. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 3, characterized in that, The oil quality anomaly levels include: general anomaly, important anomaly, and emergency anomaly; the general anomaly is a slight exceedance of a single indicator; the important anomaly is a severe exceedance of a single indicator; the emergency anomaly is a severe exceedance of 2-3 indicators; the slight exceedance is an exceedance value greater than the standard threshold but not exceeding the first threshold; the severe exceedance is an exceedance value greater than the first threshold; wherein, the first threshold is greater than the standard threshold.

5. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 4, characterized in that, Based on the power plant's experience in operating fire-resistant oil, historical test data, failure cases, and oil usage information, a mapping relationship between unqualified fire-resistant oil indicators and deterioration causes is preset, and a standardized abnormal cause feature library is constructed. Specifically, by combining the fire-resistant oil deterioration mechanism, power plant operating experience, historical test data, failure cases, and oil usage information, a mapping relationship is preset between unqualified indicators such as moisture, acid value, particulate contamination degree, volume resistivity, sludge / colloid precipitation, and flash point and their corresponding deterioration causes. The unit operating parameters and fire-resistant oil usage time are also correlated with the deterioration causes to obtain a standardized abnormal cause feature library.

6. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 5, characterized in that, The correlation between unit operating parameters, fire-resistant oil usage time and deterioration causes is as follows: unit operating parameters directly cause or accelerate the occurrence of deterioration causes; the longer the fire-resistant oil usage time is, the greater the probability of deterioration. The mapping relationship between the preset indicators of moisture content, acid value, particulate contamination, volume resistivity, sludge / colloid precipitation, and flash point non-compliance and their corresponding causes of deterioration is as follows: Abnormal moisture content is associated with cooler leaks, breather failure, moisture introduced during oil replenishment, moisture released from diatomaceous earth, improper sampling sealing, and moisture introduced by the resin filter element; abnormal acid value is associated with excessive moisture triggering hydrolysis, excessively high oil temperature accelerating oxidation, incorrect oil replenishment or contamination, long-term lack of regeneration and purification, and catalytic oxidation by metal particles; abnormal particulate matter is associated with impurities generated by component wear, filter element failure, and improper maintenance. Oil contamination, scale and peeling from electric heaters, and welding residue; abnormal volume resistivity is caused by excessive moisture, increased acid value generating conductive impurities, oil deterioration producing conductive products, or contamination by other conductive media; abnormal sludge / colloid precipitation is caused by long-term aging of fire-resistant oil, accumulation of deterioration products from hydrolysis and oxidation, synergistic effect of multiple indicators exceeding the standard, improper oil replenishment, oil incompatibility, or long-term high oil temperature accelerating precipitation; abnormal flash point is caused by oxidation and deterioration of fire-resistant oil producing light components, mixing with low flash point oil, mixing with flammable impurities, or cracking due to long-term high-temperature operation.

7. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 6, characterized in that, The process involves using diagnostic grading criteria, offline testing data of fire-resistant oil, and unit operation information to call upon an anomaly cause feature library for multi-dimensional correlation analysis to identify and rank the root causes of oil quality deterioration. Specifically, this involves matching and comparing the diagnostic grading criteria, offline testing data of fire-resistant oil, and unit operation information with the preset mapping relationship between non-compliant indicators and deterioration causes in the anomaly cause feature library; through multi-parameter correlation analysis, selecting 1 to 3 of the most likely root causes of oil quality deterioration, and ranking the root causes of oil quality deterioration based on indicator matching degree, operating condition adaptability, impact contribution, and case similarity. The higher the degree of matching between indicators, working conditions, impact contribution, and case similarity with the deterioration cause, the higher the probability of the deterioration cause occurring, and the higher its ranking. When there are complex anomalies with multiple indicators exceeding the standard at the same time, a weighted analysis algorithm is used to determine the dominant cause with the greatest impact on oil quality deterioration.

8. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 7, characterized in that, The matching degree of the indicators refers to the degree of matching between the cause of degradation and the current exceeding indicators and the extent of exceeding the standards. The more matching items there are and the more the exceeding characteristics match the degradation mechanism, the higher the probability of the corresponding result. The operating condition adaptability refers to the degree of correlation and fit between the cause of deterioration and the unit's operating parameters and the service life of fire-resistant oil. The more the operating status and oil service life match the conditions for the occurrence of the deterioration cause, the higher the probability of the corresponding cause. The contribution rate of the impact is the proportion of the combined impact of the deterioration cause on the current multiple abnormal indicators. The stronger the driving effect on oil quality deterioration and the wider the scope of the impact, the higher the probability. The case similarity refers to the degree of similarity between the current abnormal scenario and historical failure cases, as well as the test data of similar equipment. The higher the frequency of the deterioration cause in similar scenarios, the higher the probability.

9. The intelligent diagnosis and rectification method for offline testing of fire-resistant oil in power plants according to claim 8, characterized in that, The process involves generating graded rectification measures based on the root causes and diagnostic grading criteria of oil quality deterioration, determining implementation priorities and handling requirements, and obtaining standardized handling plans. Specifically, this includes: matching targeted rectification measures based on the root causes of deterioration, classifying mandatory and recommended items according to the oil quality anomaly level; determining the rectification implementation priority, rectification time limit, and safe handling requirements according to the severity of the anomaly level and the weight of the deterioration impact; and integrating the rectification measures, priorities, and handling requirements to form a standardized handling plan. Based on the root cause of deterioration and the determined level of oil quality abnormality, corrective measures are generated corresponding to each cause of deterioration. These corrective measures are divided into mandatory items and recommended items, specifically: If the moisture content exceeds the standard, the mandatory steps are to start the vacuum oil filter for vacuum dehydration, repair the cooler leaks, and replace the desiccant. The recommended steps are to standardize the sampling process, check the condition of the ion exchange resin regeneration filter element, and replace it promptly if any abnormalities are found. For excessive acid values, mandatory steps include regeneration and deacidification, and controlling oil temperature to 40-55℃; recommended steps include a thorough cleaning of the fuel system and timely replacement of worn parts. For cases where particle size exceeds the standard, mandatory steps include replacing the filter element, performing full system filtration, and cleaning worn parts; recommended steps include optimizing maintenance procedures, establishing a regular filter element replacement mechanism, and replacing filters promptly based on operating time and filtration effectiveness. If the resistivity is too low, the essential steps are to remove conductive impurities, treat the moisture and acid value simultaneously, and replace the fire-resistant oil. Recommended steps include regularly testing the resistivity of the fire-resistant oil and establishing a record of resistivity change trends; and avoiding contact between the fire-resistant oil and other conductive media to prevent cross-contamination. For excessive sludge and gum content, the mandatory steps are to filter out deterioration products, clean the system, and replace the fire-resistant oil; the recommended steps are to optimize oil temperature control and strictly verify the brand and quality standard of the oil when adding oil. The essential steps to reduce flash point are to investigate the source of contamination, replace contaminated oil, and avoid high-temperature operation; recommended steps include strengthening the storage management of fire-resistant oils, regularly testing flash point indicators, and establishing an early warning mechanism for flash point changes.

10. A smart diagnostic and remediation system for offline testing of fire-resistant oil in power plants, characterized in that, include: The comparison module collects offline test data of fire-resistant oil, unit operating parameters and oil usage information, and compares the offline test data of fire-resistant oil with standard thresholds to determine the qualified status of the indicators. Based on the unqualified indicators, the oil quality abnormality level is divided to form a diagnostic grading basis. The module is designed based on the power plant's experience in operating fire-resistant oil, historical test data, failure cases, and oil usage information. It pre-defines the mapping relationship between the non-compliance indicators of fire-resistant oil and the causes of deterioration, and builds a standardized feature library of abnormal causes. The identification module, based on diagnostic grading criteria, offline test data of fire-resistant oil, and unit operation information, calls the abnormal cause feature library to perform multi-dimensional correlation analysis, identify and sort the root causes of oil quality deterioration; The acquisition module generates graded rectification measures based on the root causes of oil quality deterioration and diagnostic grading criteria, determines the execution priority and disposal requirements, and acquires standardized disposal plans. The detection module is used to rectify the power plant system based on a standardized treatment plan. It re-collects offline test samples of fire-resistant oil for testing and compares the rectification effect. If the rectification is qualified, the case is archived and the diagnostic logic is optimized. If the rectification is unqualified, iterative analysis and rectification are carried out until the rectification requirements are met.

Images