Generator health state assessment method and device, electronic equipment and storage medium

Abstract

The invention discloses a health state evaluation method and device of a generator, electronic equipment and a storage medium, and the method comprises the steps: obtaining the real-time monitoring quantity, the periodic monitoring quantity and the offline test monitoring quantity of the generator, and obtaining evaluation data; performing discrimination processing on the evaluation data and the attribute information of the generator by using the data type corresponding to the at least one evaluation dimension to obtain a feature state quantity of the at least one evaluation dimension; performing category statistics on the feature state quantity of the at least one evaluation dimension to obtain a category ratio result of each evaluation dimension; and determining a health state evaluation result of the generator based on the category proportion result of each evaluation dimension. Through the technical scheme of the embodiment of the invention, the integrity and comprehensiveness of the evaluation result are improved, and the accuracy of the evaluation result is further improved.

Description

Technical Field

[0001] The present invention relates to the field of generator technology, and in particular to a method, apparatus, electronic device and storage medium for assessing the health status of a generator. Background Technology

[0002] Hydrogen-cooled generators, as key equipment in large thermal power plants and some nuclear power plants, occupy a central position in power generation. With their efficient cooling methods and reliable performance, they can efficiently convert other forms of energy into electrical energy, providing stable and continuous power support to the power grid. Their operating status directly affects the power plant's generation efficiency, power quality, and security. Therefore, assessing the health status of hydrogen-cooled generators is of paramount importance for ensuring the safe and stable operation of the power system and improving energy utilization efficiency.

[0003] Currently, generator health status assessment methods mainly rely on real-time monitoring data. While these methods have relatively low implementation complexity, they struggle to comprehensively reflect the generator's overall condition under different operating conditions and testing scenarios. This results in insufficient completeness and comprehensiveness of the health status assessment results, which can easily lead to misjudgments of the condition or missed faults.

[0004] Therefore, there is an urgent need to propose a new method to solve the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for assessing the health status of a generator, which can improve the completeness and comprehensiveness of the assessment results, thereby improving the accuracy of the assessment results.

[0006] In a first aspect, embodiments of the present invention provide a method for assessing the health status of a generator, the method comprising:

[0007] The real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator are obtained to obtain evaluation data;

[0008] Using the data type corresponding to at least one evaluation dimension, the evaluation data and attribute information of the generator are processed to obtain the feature state quantity of at least one evaluation dimension.

[0009] Perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension;

[0010] The health status evaluation result of the generator is determined based on the category proportion results of each evaluation dimension.

[0011] The technical solution of this invention first acquires real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain evaluation data. This avoids the one-sidedness of evaluation caused by relying solely on one type of data (e.g., real-time data alone cannot detect mechanical hazards under shutdown conditions). It comprehensively reflects the overall status of the generator under different operating conditions and testing scenarios, thus ensuring the integrity and comprehensiveness of the evaluation data, avoiding single data blind spots, and providing complete data support for subsequent dimensional evaluations, ensuring that no key indicators are omitted in the health status assessment. Next, using the data type corresponding to at least one evaluation dimension, the generator's evaluation data and attribute information are processed to obtain characteristic state quantities for at least one evaluation dimension. This avoids bias caused by using unrelated data for discrimination, ensuring that the discrimination of each evaluation dimension is based on "targeted data," reducing the probability of misjudgment, and thus improving the accuracy of subsequent evaluations. Finally, the characteristic state quantities of at least one evaluation dimension are statistically analyzed to obtain the category proportion results for each evaluation dimension, providing a data foundation for obtaining the generator's health status evaluation results. Finally, based on the category proportions of each evaluation dimension, the generator's health status evaluation result is determined, achieving a comprehensive assessment of the generator. On the one hand, this avoids the limitations of relying solely on a single indicator, making the health status evaluation result more closely reflect reality; on the other hand, it transforms the qualitative description of the generator's health status into quantitative data, clearly presenting the generator's health level in various aspects. This quantitative analysis reduces the interference of subjective judgment, making the evaluation results more objective and accurate. Therefore, the technical solution of this invention solves the problem in the prior art where the evaluation results are incomplete and incomplete due to the inability to fully reflect the generator's comprehensive status under different operating conditions and testing scenarios, leading to misjudgments of status or missed faults.

[0012] Secondly, embodiments of the present invention also provide a generator health status assessment device, the device comprising:

[0013] The acquisition module is used to acquire real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain evaluation data.

[0014] The discrimination module is used to discriminate the evaluation data and attribute information of the generator using the data type corresponding to at least one evaluation dimension, and obtain the feature state quantity of at least one evaluation dimension.

[0015] The statistics module is used to perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension.

[0016] The determination module is used to determine the health status evaluation result of the generator based on the category proportion results of each evaluation dimension.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0018] At least one processor; and a memory communicatively connected to said at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the health status assessment method for the generator described in any of the first aspects.

[0020] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, implement the health status assessment method for any of the generators described in the first aspect.

[0021] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the generator health status assessment device, or it may be packaged separately from the processor of the generator health status assessment device; this application does not impose any limitations on this.

[0022] The descriptions of the second, third, and fourth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects described in the second, third, and fourth aspects can be referenced to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0023] In this application, the name of the aforementioned generator health status assessment device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0024] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating a method for assessing the health status of a generator, as provided in an embodiment of the present invention;

[0027] Figure 2 A flowchart of another generator health status assessment method provided in an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of the structure of a generator health status assessment device provided in an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0030] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0031] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0032] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0033] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0034] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc. Moreover, without conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0035] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0036] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0037] Figure 1 This is a flowchart illustrating a generator health status assessment method provided in an embodiment of the present invention. This embodiment is applicable to situations requiring generator health status assessment. The method can be executed by a generator health status assessment device, which can be implemented in software and / or hardware. For example, the device can be integrated into an electronic device. (Reference) Figure 1 The generator health status assessment method in this embodiment specifically includes the following steps:

[0038] Step 110: Obtain the real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain the evaluation data.

[0039] Specifically, a generator refers to a mechanical device that converts other forms of energy (such as mechanical energy, thermal energy, hydropower, etc.) into electrical energy. For example, a generator can be a water-hydrogen-cooled generator, a fully hydrogen-cooled generator, etc. Real-time monitoring data refers to data continuously collected from parameters generated during generator operation via sensors and other monitoring equipment. This data reflects the generator's current instantaneous operating status, such as real-time voltage, current, speed, and temperature. Periodic monitoring data refers to data periodically collected from specific generator parameters at preset fixed time intervals (such as one hour, three hours, one day, etc.). This data is used to track the generator's state change trends within a certain period, such as periodically measured insulation resistance and vibration amplitude. Offline test monitoring data refers to monitoring data obtained through specialized testing methods when the generator is shut down. This data is typically used for in-depth testing of key generator components or performance, such as winding DC resistance test data and withstand voltage test data. Evaluation data refers to the data set used to assess the generator's health status, compiled by summarizing the real-time monitoring data, periodic monitoring data, and offline test monitoring data.

[0040] In practice, real-time monitoring data can be acquired using sensors installed on the generator. Then, from a database storing periodic monitoring data, the periodic monitoring data closest in time to the real-time data acquisition time is selected. Simultaneously, from a database storing offline test monitoring data, the offline test monitoring data closest in time to the real-time monitoring data acquisition time is selected. Finally, the evaluation data is obtained by summarizing the real-time monitoring data, periodic monitoring data, and offline test monitoring data.

[0041] In this embodiment, the above steps can avoid the one-sidedness of evaluation caused by relying on only one type of data (such as the inability to discover mechanical hazards in the shutdown state using only real-time data), and comprehensively reflect the overall status of the generator under different operating conditions and testing scenarios. This ensures the integrity and comprehensiveness of the evaluation data, avoids blind spots in single data, and provides complete data support for subsequent dimensional evaluations, ensuring that no key indicators are omitted in the health status assessment.

[0042] Step 120: Using the data type corresponding to at least one evaluation dimension, perform discrimination processing on the generator's evaluation data and attribute information to obtain the feature state quantity of at least one evaluation dimension.

[0043] Specifically, evaluation dimensions refer to the different angles or aspects used to assess the health status of a generator. For example, evaluation dimensions can include electrical performance, mechanical performance, thermal performance, stator, rotor, and auxiliary system dimensions. The data type corresponding to an evaluation dimension refers to the data category required for that dimension when assessing the generator's health status. Attribute information refers to the inherent characteristics or parameters related to the generator itself. For example, attribute information can include the generator's model, rated power, years of operation, manufacturer, and historical fault records. Characteristic state quantities refer to the features that, after discrimination processing, can characterize the generator's state or performance on a certain evaluation dimension. For example, characteristic state quantities can be categorized as "normal," "abnormal," and "severe," such as stator winding temperature - abnormal, rotor dynamic balance amplitude - severe.

[0044] In practical implementation, at least one evaluation dimension can be determined first based on actual conditions or needs [such as stator dimension (focusing on stator winding insulation, temperature, and voltage distribution), rotor dimension (focusing on rotor winding short circuits, dynamic balance, and excitation current)]. Then, for each determined evaluation dimension, the correspondence table between evaluation dimensions and data types is queried to determine the data type corresponding to that evaluation dimension. Next, data that perfectly matches the aforementioned data type is selected from the generator's evaluation data to obtain the feature data for that evaluation dimension. Then, the initial judgment threshold corresponding to the feature data of that evaluation dimension is updated using the generator's attribute information to obtain the target judgment threshold corresponding to that feature data. For example, the attribute information and the initial judgment threshold corresponding to the feature data can be substituted into a pre-determined update formula to calculate the target judgment threshold corresponding to the feature data. The pre-determined update formula is determined after analyzing a large amount of historical operating data and fault case data of similar generators.

[0045] Finally, according to the predetermined judgment rules, combined with the data type of the feature data and the target judgment threshold, the feature data is processed to obtain the feature state quantity of the current evaluation dimension. The correspondence table between evaluation dimensions and data types is set in advance according to the actual situation or needs.

[0046] In this embodiment, the above steps can avoid bias caused by using unrelated data for judgment, ensure that the judgment of each evaluation dimension is based on "targeted data", reduce the probability of misjudgment, and thus improve the accuracy of subsequent evaluation.

[0047] Step 130: Perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension.

[0048] Specifically, the category proportion results for each evaluation dimension refer to the distribution ratio of different categories in each evaluation dimension.

[0049] In practice, for each evaluation dimension's feature state quantity, it can be classified and statistically analyzed according to its corresponding category (such as normal, abnormal, severe, etc.), and the quantity of each category is recorded. Then, the ratio of the quantity of each category to the total number of feature state quantities under that dimension is calculated to obtain the category proportion result for that evaluation dimension. For example, if the current evaluation dimension is divided into normal, abnormal, and severe categories, with 50 feature state quantities for the normal category, 30 for the abnormal category, and 20 for the severe category, and the total number of feature state quantities under this dimension is 100, then the category proportion result for the current evaluation dimension is 50% normal, 30% abnormal, and 20% severe.

[0050] In this embodiment, the above steps provide a data foundation for obtaining the generator's health status evaluation results.

[0051] Step 140: Determine the health status evaluation result of the generator based on the category proportion results of each evaluation dimension.

[0052] Specifically, the health status evaluation result refers to the conclusion obtained after comprehensively evaluating the overall health status of the generator based on the category proportion results of each evaluation dimension. For example, the health status evaluation result can be "healthy", "sub-healthy", "mildly abnormal", "fault", etc., among which "fault" has a higher degree of abnormality than "mildly abnormal".

[0053] In practice, the health score for each evaluation dimension can be calculated first. The specific calculation formula is: Dimension Health Score = (Normal Percentage × Preset Normal Quantitative Score) + (Abnormal Percentage × Preset Abnormal Quantitative Score) + (Severe Percentage × Preset Severe Quantitative Score). For example, if the category percentage of the current evaluation dimension is 50% normal, 30% abnormal, and 20% severe, and the preset normal quantitative score is 100, the preset abnormal quantitative score is 50, and the preset severe quantitative score is 0, then the current dimension health score is 65.

[0054] If there are more than one evaluation dimension, the weight of each dimension should be determined in advance based on the actual situation or needs. Then, the overall health score is calculated using the formula "dimension score × dimension weight". For example, if the evaluation dimensions include stator dimension, rotor dimension, and auxiliary system dimension, and the stator dimension score is 65, the rotor dimension score is 72.5, and the auxiliary system dimension score is 95, with corresponding weights of 0.4, 0.4, and 0.2 respectively, then the overall health score is 65 × 0.4 + 72.5 × 0.4 + 95 × 0.2 = 74. If there is only one evaluation dimension, then the health score of the current dimension is the overall health score.

[0055] Finally, based on the pre-set "health score and health level" correspondence standard, the health status evaluation result of the generator is determined. For example, the corresponding standard is: when the overall health score is in the range of [80-100], the evaluation result is "healthy"; when it is in the range of [60-80), the evaluation result is "sub-healthy"; when it is in the range of [40-60), the evaluation result is "mildly abnormal"; and when it is in the range of [0-40), the evaluation result is "faulty". If the overall health score is 74, which is in the range of [60-80), then the health status evaluation result of the generator is "sub-healthy".

[0056] In this embodiment, the above steps achieve a comprehensive evaluation of the generator: on the one hand, it avoids the limitations of relying solely on a single indicator, making the health status evaluation results more consistent with reality; on the other hand, it transforms the qualitative description of the generator's health status into quantitative data, clearly presenting the health level of various aspects of the generator. This quantitative analysis reduces the interference of subjective judgment, making the evaluation results more objective and accurate.

[0057] The generator health status assessment method provided in this invention first acquires real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain assessment data. This avoids the one-sidedness of assessment caused by relying solely on one type of data (e.g., real-time data alone cannot detect mechanical hazards under shutdown conditions). It comprehensively reflects the overall status of the generator under different operating conditions and testing scenarios, thus ensuring the integrity and comprehensiveness of the assessment data, avoiding single data blind spots, and providing complete data support for subsequent dimensional evaluations, ensuring that no key indicators are omitted in the health status assessment. Next, using the data type corresponding to at least one evaluation dimension, the generator's assessment data and attribute information are processed to obtain characteristic state quantities for at least one evaluation dimension. This avoids bias caused by using unrelated data for discrimination, ensuring that the discrimination of each evaluation dimension is based on "targeted data," reducing the probability of misjudgment, and thus improving the accuracy of subsequent assessments. Finally, the characteristic state quantities of at least one evaluation dimension are statistically analyzed to obtain the category proportion results for each evaluation dimension, providing a data foundation for obtaining the generator's health status assessment results. Finally, based on the category proportions of each evaluation dimension, the generator's health status evaluation result is determined, achieving a comprehensive assessment of the generator. On the one hand, this avoids the limitations of relying solely on a single indicator, making the health status evaluation result more closely reflect reality; on the other hand, it transforms the qualitative description of the generator's health status into quantitative data, clearly presenting the generator's health level in various aspects. This quantitative analysis reduces the interference of subjective judgment, making the evaluation results more objective and accurate. Therefore, the technical solution of this invention solves the problem in the prior art where the evaluation results are incomplete and incomplete due to the inability to fully reflect the generator's comprehensive status under different operating conditions and testing scenarios, leading to misjudgments of status or missed faults.

[0058] Figure 2 A flowchart illustrating another method for assessing the health status of a generator provided in this embodiment of the invention is shown. This embodiment is a further specification based on the above embodiments. In this embodiment, the method may further include:

[0059] Step 210: Obtain the real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain the evaluation data.

[0060] Further, step 210 may specifically include: obtaining the real-time monitoring data of the generator; selecting the periodic monitoring data with the smallest difference between timestamps from the periodic monitoring data database based on the timestamps of the real-time monitoring data to obtain the periodic monitoring data; selecting the offline test monitoring data with the smallest difference between timestamps from the offline test monitoring data database based on the timestamps of the real-time monitoring data to obtain the offline test monitoring data; and summarizing the real-time monitoring data, periodic monitoring data, and offline test monitoring data to obtain the evaluation data.

[0061] In practice, the generator's real-time monitoring data can be acquired first through sensors installed on the generator. Next, the timestamps are extracted from the real-time monitoring data. Then, the periodic monitoring data with the smallest difference between its timestamp and the acquired timestamp is selected from the periodic monitoring data database to obtain the periodic monitoring data; simultaneously, the offline test monitoring data with the smallest difference between its timestamp and the acquired timestamp is selected from the offline test monitoring data database to obtain the offline test monitoring data. Finally, the real-time monitoring data, periodic monitoring data, and offline test monitoring data are summarized to obtain the evaluation data.

[0062] In addition, to avoid interference from abnormal data, after obtaining the periodic monitoring volume and the offline test monitoring volume, the data can be verified according to the preset verification rules (such as the periodic monitoring volume must be within the range of "historical similar data ±20%" and the offline test monitoring volume must meet the industry standard threshold). If it does not meet the verification rules, it is determined to be abnormal data. At this time, the mean of the most recent multiple sets (such as 3 sets) of valid data of this parameter can be called to calculate the mean and the mean can be used to replace the abnormal data.

[0063] In this embodiment, the above steps can avoid analytical bias caused by "time misalignment", ensure data "timeliness matching", enhance the correlation value of evaluation data, and thus improve the accuracy of subsequent evaluation results.

[0064] Step 211: Using the data type corresponding to at least one evaluation dimension, perform discrimination processing on the generator's evaluation data and attribute information to obtain the feature state quantity of at least one evaluation dimension.

[0065] Further, step 211 may specifically include: for the current evaluation dimension, filtering the generator's evaluation data based on the data type corresponding to the current evaluation dimension to obtain the feature data of the current evaluation dimension; updating the initial judgment threshold corresponding to the feature data using the generator's attribute information to obtain the target judgment threshold corresponding to the feature data; and performing judgment processing on the feature data using the data type of the feature data and the target judgment threshold to obtain the feature state quantity of the current evaluation dimension.

[0066] Specifically, data type refers to the specific monitoring parameter type corresponding to the evaluation dimension. For example, the data type corresponding to the stator dimension could be stator winding temperature, stator insulation resistance, stator voltage distribution, etc.; the data type corresponding to the rotor dimension could be rotor excitation current, rotor dynamic balance amplitude, etc. Feature data refers to data selected from the evaluation data that perfectly matches the data type corresponding to the current evaluation dimension. For example, when the current evaluation dimension is the stator dimension, data such as "stator winding temperature 90℃" and "stator insulation resistance 800 megohms" selected from the evaluation data are feature data for the stator dimension. Initial judgment threshold refers to a general judgment standard pre-set for a certain data type based on actual conditions (such as international standards, national standards, industry standards, etc.) or needs. For example, the initial judgment threshold for stator winding temperature could be the standard limit for stator winding temperature specified in the industry standard (85℃). Target judgment threshold refers to the threshold obtained after updating the initial judgment threshold by combining generator attribute information, a judgment standard that better reflects the actual situation of the equipment.

[0067] In practice, for the current evaluation dimension, data with the same data type as the corresponding data type in the generator's evaluation data can be filtered out to obtain the feature data for the current evaluation dimension. Then, the generator's attribute information and the initial judgment threshold corresponding to the feature data are input into a pre-trained threshold update model to obtain the target judgment threshold corresponding to the feature data. The threshold update model refers to the model trained using the historical attribute information of each generator, the initial judgment threshold corresponding to historical feature data, and the target judgment threshold corresponding to these historical feature data as training data.

[0068] Finally, according to the predetermined judgment rules, the feature data is processed by combining the data type and target judgment threshold to obtain the feature state quantity of the current evaluation dimension. For example, if the feature data of the current evaluation dimension includes stator winding temperature (data type) with a specific value of 90 degrees Celsius and a corresponding target judgment threshold of 85 degrees Celsius, and bearing vibration amplitude (data type) with a specific value of 0.3 mm and a corresponding target judgment threshold of 0.1 mm, according to the judgment rules: if the data value of the feature data does not exceed the target judgment threshold, it is normal; if the data value exceeds the target judgment threshold, and the data type is predefined as "exceeding the limit does not directly affect the operation of the equipment", it is abnormal; if the data value exceeds the target judgment threshold, and the data type is predefined as "exceeding the limit will directly affect the operation of the equipment", it is severe; then the feature state quantity of the current evaluation dimension can be determined as stator winding temperature - abnormal, bearing vibration amplitude - severe.

[0069] In this embodiment, the above steps can avoid interference from irrelevant information and improve the targeting of the assessment; optimize the judgment criteria by combining individual differences of equipment and improve the accuracy of the assessment; and build standardized assessment logic to ensure the traceability of results, thereby improving the standardization of management.

[0070] Furthermore, before updating the initial judgment threshold corresponding to the feature data using the generator's attribute information to obtain the target judgment threshold corresponding to the feature data, the process further includes: determining whether the generator has a peak-shaving record; if so, determining the generator's peak-shaving frequency based on the generator's peak-shaving record; updating the initial judgment threshold corresponding to the feature data based on the generator's peak-shaving frequency to obtain the target judgment threshold corresponding to the feature data; if not, triggering the execution of updating the initial judgment threshold corresponding to the feature data using the generator's attribute information to obtain the target judgment threshold corresponding to the feature data.

[0071] Specifically, peak shaving records refer to the historical records of generator operations during operation that adjust power output in response to grid load fluctuations (such as increasing output during peak hours and decreasing output during off-peak hours). Peak shaving frequency refers to the frequency with which a generator performs peak shaving tasks within a certain period of time, based on statistics from peak shaving records. For example, peak shaving frequency can be the number of times a generator performs peak shaving operations per unit of time (such as daily, weekly, monthly, quarterly, etc.), or the proportion of peak shaving operations to total operating time. It is a core indicator reflecting the frequency of generator power fluctuations.

[0072] In practice, before updating the initial judgment threshold corresponding to the feature data using the generator's attribute information to obtain the target judgment threshold, a search can be performed in the database storing generator peak-shaving records to determine whether the generator has peak-shaving records. If they exist, the generator's peak-shaving frequency is determined based on the generator's peak-shaving records. For example, the peak-shaving frequency can be obtained by counting the total number of peak-shaving operations in the past three months and then dividing it by the total number of operating days in that period; or by calculating the proportion of peak-shaving operating time to total operating time.

[0073] Next, the generator's peak-shaving frequency and the initial judgment threshold corresponding to the feature data can be input into a pre-trained peak-shaving update threshold model to obtain the target judgment threshold corresponding to the feature data. If the target threshold does not exist, the generator's attribute information is used to directly update the initial judgment threshold corresponding to the feature data to obtain the target judgment threshold. The peak-shaving update threshold model refers to a model trained using machine learning algorithms (such as linear regression, gradient boosting trees, etc.) with the historical peak-shaving frequencies and historical feature data of different generators as input, and the target judgment threshold obtained after manual verification or actual operation verification of these historical feature data as the output label.

[0074] In this embodiment, the above steps achieve differentiated threshold updates, which can take into account the evaluation needs of different operating scenarios and ensure that the thresholds under different operating scenarios can reflect the true health tolerance of the unit, thereby improving the accuracy of subsequent characteristic data determination.

[0075] Step 212: Perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension.

[0076] Step 213: Determine the health status evaluation result of the generator based on the category proportion results of each evaluation dimension.

[0077] Furthermore, when there are at least two evaluation dimensions, the health status evaluation result of the generator is determined based on the category proportion results of each evaluation dimension, including: for the current evaluation dimension, if the proportion of normal categories in the category proportion results of the current evaluation dimension is greater than a first preset threshold, then the evaluation result of the current evaluation dimension is determined to be healthy; if the proportion of normal categories in the category proportion results of the current evaluation dimension is not greater than the first preset threshold but greater than the second preset threshold, and the proportion of abnormal categories is not greater than the third preset threshold but greater than the fourth preset threshold, then the evaluation result of the current evaluation dimension is determined to be sub-healthy; if the proportion of normal categories in the category proportion results of the current evaluation dimension is not greater than the second preset threshold but greater than the fifth preset threshold, and the proportion of abnormal categories is not greater than the sixth preset threshold but greater than the third preset threshold, then the evaluation result of the current evaluation dimension is determined to be slightly abnormal; otherwise, the evaluation result of the current evaluation dimension is determined to be faulty; the evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions is determined as the health status evaluation result of the generator.

[0078] Specifically, the first, second, third, fourth, fifth, and sixth preset thresholds refer to fixed percentage values ​​pre-set according to actual conditions or needs, used to classify the health level of a single evaluation dimension. The order is: First Threshold Preset Threshold > Second Threshold Preset Threshold > Fifth Threshold Preset Threshold > Sixth Threshold Preset Threshold > Third Threshold Preset Threshold > Fourth Threshold Preset Threshold. Processing priority refers to the order of emergency handling for the four evaluation results: "Healthy," "Sub-healthy," "Mild Abnormality," and "Fault," with priority from highest to lowest as: "Fault" > "Mild Abnormality" > "Sub-healthy" > "Healthy." The evaluation result of the current evaluation dimension refers to the health level corresponding to that dimension, derived by comparing its category proportion with each preset threshold, including the four categories of "Healthy," "Sub-healthy," "Mild Abnormality," and "Fault."

[0079] In practice, for any evaluation dimension, the evaluation result is determined according to the following rules based on the proportion of its status categories: If the proportion of normal categories > the first preset threshold (e.g., 99%), the evaluation result of this dimension is determined to be healthy. If the proportion of normal categories ≤ the first threshold (99%) and > the second threshold (e.g., 90%), and the proportion of abnormal categories ≤ the third threshold (e.g., 10%) and > the fourth threshold (e.g., 0%), the evaluation result of this dimension is determined to be sub-healthy, meaning that the equipment can operate but there are a few abnormal indicators that need attention (e.g., regular inspections, data tracking, etc.). If the proportion of normal categories ≤ the second threshold (90%) and > the fifth threshold (e.g., 80%), and the proportion of abnormal categories ≤ the sixth threshold (e.g., 20%) and > the third threshold (e.g., 10%), the evaluation result of this dimension is determined to be slightly abnormal, meaning that the equipment needs to be monitored (although it does not directly cause a shutdown, it has a potential impact on operational safety or stability, and the equipment needs to be operated under enhanced monitoring). If none of the above conditions are met, the evaluation result of this dimension is determined to be faulty, meaning that the equipment cannot operate.

[0080] Finally, the evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions is determined as the generator's health status evaluation result. For example, if the evaluation result of one dimension is sub-healthy and the evaluation result of the other dimension is faulty, then the generator's health status evaluation result is faulty.

[0081] In this embodiment, the above steps achieve hierarchical and accurate judgment, avoiding misjudgment of health status; at the same time, it covers multi-dimensional features, overcoming the limitations of single-dimensional evaluation; in addition, by focusing on key risks through the "priority principle", it avoids decision-making hesitation caused by the mixture of multi-dimensional results, which can help staff quickly identify core issues, prioritize the allocation of resources to solve high-risk hidden dangers, reduce unplanned equipment downtime, and thus improve operation and maintenance efficiency.

[0082] Furthermore, before determining the evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions as the health status evaluation result of the generator, the process further includes: determining whether there are dimension weights corresponding to at least two evaluation dimensions; if so, weighting the evaluation results of at least two evaluation dimensions based on the dimension weights of at least two evaluation dimensions to obtain the health status evaluation result of the generator; if not, determining the evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions as the health status evaluation result of the generator.

[0083] Specifically, dimensional weights refer to numerical values ​​that are pre-set according to actual conditions or needs to reflect the importance of different evaluation dimensions in generator health assessment.

[0084] In practice, before determining the highest-priority evaluation result from at least two evaluation dimensions as the generator's health status evaluation result, a search can be performed in the database storing dimension weights to determine if corresponding dimension weights exist for these at least two evaluation dimensions. If they exist, the evaluation results for at least two evaluation dimensions are weighted based on their respective weights to obtain the generator's health status evaluation result. Specifically, the qualitative results of each evaluation dimension can be converted into quantifiable values ​​(e.g., healthy = 100 points, sub-healthy = 80 points, slightly abnormal = 60 points, faulty = 0 points). Then, preset dimension weights are extracted, and the product of each dimension's evaluation result value and its corresponding weight is calculated. All products are then summed to obtain a comprehensive value reflecting the generator's overall health status. Finally, based on the range of the comprehensive score, it is mapped back to the qualitative evaluation results (e.g., above 90 points indicates healthy, 70-90 points indicates sub-healthy, 50-70 points indicates slightly abnormal, and below 50 points indicates faulty), which is the generator's health status evaluation result. If it does not exist, the evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions will be directly determined as the health status evaluation result of the generator.

[0085] In this embodiment, the above steps can increase the proportion of key dimension evaluation results in the overall conclusion, prevent minor abnormalities (or healthy status) in secondary dimensions from obscuring the true condition of key dimensions, and make the final evaluation results more consistent with the actual health logic of the generator, thereby improving the practical applicability of the evaluation scheme.

[0086] Step 214: Generate a maintenance report for the generator based on the health status assessment results.

[0087] Specifically, a maintenance report refers to a report generated based on the results of a health status assessment, which proposes maintenance recommendations and solutions for the current health problems and potential risks of the generator. For example, a maintenance report may include the generator's health status assessment results, abnormal monitoring data, and the corresponding maintenance measures and plans.

[0088] In practice, after obtaining the health status evaluation results, a preset maintenance report template (containing report number, generator basic information, health status analysis, maintenance suggestions, generation time, etc.) can be called, and the corresponding content can be automatically filled in according to the template structure, thereby quickly generating a generator maintenance report.

[0089] In this embodiment, the above steps generate targeted maintenance plans, significantly improving operational efficiency. Simultaneously, the report helps staff clearly trace the basis for determining when maintenance is needed, avoiding deviations in maintenance direction due to a lack of transparency and ensuring that every operational decision is supported by clear data.

[0090] Step 215: Send the maintenance report to the staff's terminal.

[0091] Specifically, the staff's terminal refers to the electronic device used by the staff that can receive maintenance reports, such as a mobile phone, computer, or tablet.

[0092] In practice, after receiving the maintenance report, it can be accurately sent to the staff's terminal through built-in system push, instant messaging tool push, or email push.

[0093] In this embodiment, the above steps not only ensure the timeliness of maintenance response and reduce the risk of fault escalation, but also lower the information acquisition threshold and improve operation and maintenance efficiency. At the same time, they ensure the accuracy of information transmission and effectively avoid deviations that may result from manual relaying.

[0094] The generator health status assessment method provided in this invention first acquires real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain assessment data. This avoids the one-sidedness of assessment caused by relying on only one type of data, comprehensively reflecting the overall status of the generator under different operating conditions and testing scenarios, thus ensuring the integrity and comprehensiveness of the assessment data, avoiding blind spots in single data sets, and providing complete data support for subsequent dimensional evaluations, ensuring that no key indicators are omitted in the health status assessment. Next, using the data type corresponding to at least one evaluation dimension, the generator's assessment data and attribute information are processed to obtain the characteristic state quantities of at least one evaluation dimension. This avoids bias caused by using unrelated data for discrimination, ensuring that the discrimination of each evaluation dimension is based on "targeted data," reducing the probability of misjudgment, and thus improving the accuracy of subsequent assessments. Afterwards, the characteristic state quantities of at least one evaluation dimension are statistically analyzed to obtain the category proportion results of each evaluation dimension, providing a data foundation for obtaining the generator's health status assessment results. Then, based on the category proportion results of each evaluation dimension, the generator's health status assessment result is determined, realizing a comprehensive assessment of the generator and making the health status assessment results more consistent with the actual situation. Based on the health status evaluation results, a generator maintenance report is generated, enabling the creation of targeted maintenance plans and significantly improving operation and maintenance efficiency. Simultaneously, this report helps staff clearly trace the basis for determining the need for maintenance, avoiding deviations in maintenance direction due to information asymmetry and ensuring that every operation and maintenance decision is supported by clear data. Finally, sending the maintenance report to staff terminals not only ensures the timeliness of maintenance response and reduces the risk of fault escalation but also lowers the information access barrier and improves operation and maintenance efficiency. Furthermore, it ensures the accuracy of information transmission, effectively avoiding deviations that may result from manual relaying. Therefore, the technical solution of this invention solves the problem in existing technologies where the evaluation results are incomplete and incomplete due to the inability to comprehensively reflect the generator's overall status under different operating conditions and testing scenarios, leading to misjudgments of status or missed faults.

[0095] Figure 3 This is a schematic diagram of a generator health status assessment device provided in an embodiment of the present invention. This device belongs to the same inventive concept as the generator health status assessment method in the above embodiments. For details not described in detail in the embodiments of the generator health status assessment device, please refer to the embodiments of the generator health status assessment method described above.

[0096] like Figure 3 As shown, the device includes:

[0097] The acquisition module 310 is used to acquire the real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain evaluation data;

[0098] The discrimination module 320 is used to discriminate the evaluation data and attribute information of the generator using the data type corresponding to at least one evaluation dimension, and obtain the feature state quantity of at least one evaluation dimension.

[0099] The statistics module 330 is used to perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results of each evaluation dimension.

[0100] The determination module 340 is used to determine the health status evaluation result of the generator based on the category proportion results of each evaluation dimension.

[0101] Based on the above embodiments, the discrimination module 320 is specifically used for:

[0102] For the current evaluation dimension, the evaluation data of the generator is filtered based on the data type corresponding to the current evaluation dimension to obtain the feature data of the current evaluation dimension;

[0103] The initial judgment threshold corresponding to the feature data is updated using the attribute information of the generator to obtain the target judgment threshold corresponding to the feature data;

[0104] The feature data is processed using the data type and target judgment threshold to obtain the feature state quantity of the current evaluation dimension.

[0105] Based on the above embodiments, the device further includes:

[0106] The peak shaving judgment module is used to determine whether the generator has a peak shaving record before updating the initial judgment threshold corresponding to the feature data using the attribute information of the generator to obtain the target judgment threshold corresponding to the feature data; if it exists, the peak shaving frequency of the generator is determined based on the peak shaving record of the generator; the initial judgment threshold corresponding to the feature data is updated based on the peak shaving frequency of the generator to obtain the target judgment threshold corresponding to the feature data; if it does not exist, the module triggers the execution of updating the initial judgment threshold corresponding to the feature data using the attribute information of the generator to obtain the target judgment threshold corresponding to the feature data.

[0107] Based on the above embodiments, when there are at least two evaluation dimensions, the determining module 340 is specifically used for:

[0108] For the current evaluation dimension, if the proportion of the normal category in the category proportion results of the current evaluation dimension is greater than the first preset threshold, then the evaluation result of the current evaluation dimension is determined to be healthy.

[0109] If the proportion of normal categories in the current evaluation dimension is not greater than the first preset threshold but greater than the second preset threshold, and the proportion of abnormal categories is not greater than the third preset threshold but greater than the fourth preset threshold, then the evaluation result of the current evaluation dimension is determined to be sub-healthy; the first preset threshold is greater than the second preset threshold; the third preset threshold is greater than the fourth preset threshold.

[0110] If the proportion of normal categories in the current evaluation dimension is not greater than the second preset threshold but greater than the fifth preset threshold, and the proportion of abnormal categories is not greater than the sixth preset threshold but greater than the third preset threshold, then the evaluation result of the current evaluation dimension is determined to be slightly abnormal; the second preset threshold is greater than the fifth preset threshold; the sixth preset threshold is greater than the third preset threshold; the fifth preset threshold is greater than the sixth preset threshold.

[0111] Otherwise, the evaluation result for the current evaluation dimension is determined to be a fault;

[0112] The evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions is determined as the health status evaluation result of the generator.

[0113] Based on the above embodiments, the device further includes:

[0114] The weighting determination module is used to determine whether there are dimension weights corresponding to the at least two evaluation dimensions before determining the evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions as the health status evaluation result of the generator; if there are, the evaluation results of the at least two evaluation dimensions are weighted based on the dimension weights of the at least two evaluation dimensions to obtain the health status evaluation result of the generator; if there are no, the evaluation result with the highest processing priority among the evaluation results of the at least two evaluation dimensions is determined as the health status evaluation result of the generator.

[0115] Based on the above embodiments, the acquisition module 310 is specifically used for:

[0116] Obtain real-time monitoring data of the generator;

[0117] Based on the timestamp of the real-time monitoring quantity, the periodic monitoring quantity with the smallest difference between the timestamp and the timestamp is selected from the periodic monitoring quantity database to obtain the periodic monitoring quantity.

[0118] Based on the timestamp of the real-time monitoring quantity, the offline test monitoring quantity with the smallest difference between the timestamp and the real timestamp is selected from the offline test monitoring quantity database to obtain the offline test monitoring quantity;

[0119] The evaluation data is obtained by summing the real-time monitoring data, the periodic monitoring data, and the offline test monitoring data.

[0120] Based on the above embodiments, the device further includes:

[0121] The generation module is used to determine the health status evaluation result of the generator based on the category proportion results of each evaluation dimension, generate a maintenance report of the generator based on the health status evaluation result, and send the maintenance report to the staff's terminal.

[0122] The generator health status assessment device provided in the embodiments of the present invention can execute the generator health status assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0123] It is worth noting that in the embodiments of the above-mentioned generator health status assessment device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0124] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0125] like Figure 4 As shown, electronic device 4 is represented in the form of a general-purpose computing electronic device. The components of electronic device 4 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0126] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0127] Electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0128] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0129] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0130] Electronic device 4 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 4, and / or with any device that enables electronic device 4 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, electronic device 4 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 4 As shown, network adapter 20 communicates with other modules of electronic device 4 via bus 18. It should be understood that, although... Figure 4Not shown, it can be combined with electronic device 4 to use other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0131] Processing unit 16 executes various functional applications and page displays by running programs stored in system memory 28, such as implementing the generator health status assessment method provided in this embodiment of the invention, which includes:

[0132] The real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator are obtained to obtain evaluation data;

[0133] Using the data type corresponding to at least one evaluation dimension, the evaluation data and attribute information of the generator are processed to obtain the feature state quantity of at least one evaluation dimension.

[0134] Perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension;

[0135] The health status evaluation result of the generator is determined based on the category proportion results of each evaluation dimension.

[0136] Of course, those skilled in the art will understand that the processor can also implement the technical solution of the generator health status assessment method provided in any embodiment of the present invention.

[0137] This invention provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements, for example, the generator health status assessment method provided in this invention, the method comprising:

[0138] The real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator are obtained to obtain evaluation data;

[0139] Using the data type corresponding to at least one evaluation dimension, the evaluation data and attribute information of the generator are processed to obtain the feature state quantity of at least one evaluation dimension.

[0140] Perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension;

[0141] The health status evaluation result of the generator is determined based on the category proportion results of each evaluation dimension.

[0142] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0143] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0144] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0145] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0146] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0147] Furthermore, the acquisition, storage, use, and processing of data in the technical solution of this invention all comply with relevant laws and regulations.

[0148] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for assessing the health status of a generator, characterized in that, The method includes: The real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator are obtained to obtain evaluation data; Using the data type corresponding to at least one evaluation dimension, the evaluation data and attribute information of the generator are processed to obtain the feature state quantity of at least one evaluation dimension. Perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension; The health status evaluation result of the generator is determined based on the category proportion results of each evaluation dimension.

2. The generator health status assessment method according to claim 1, characterized in that, Using the data type corresponding to at least one evaluation dimension, the evaluation data and attribute information of the generator are processed to obtain feature state quantities of at least one evaluation dimension, including: For the current evaluation dimension, the evaluation data of the generator is filtered based on the data type corresponding to the current evaluation dimension to obtain the feature data of the current evaluation dimension; The initial judgment threshold corresponding to the feature data is updated using the attribute information of the generator to obtain the target judgment threshold corresponding to the feature data; The feature data is processed using the data type and target judgment threshold to obtain the feature state quantity of the current evaluation dimension.

3. The generator health status assessment method according to claim 2, characterized in that, Before updating the initial judgment threshold corresponding to the feature data using the attribute information of the generator to obtain the target judgment threshold corresponding to the feature data, the method further includes: Determine whether the generator has a peak-shaving record; If it exists, the peak shaving frequency of the generator is determined based on the peak shaving record of the generator; the initial judgment threshold corresponding to the feature data is updated based on the peak shaving frequency of the generator to obtain the target judgment threshold corresponding to the feature data. If it does not exist, then the execution is triggered to update the initial judgment threshold corresponding to the feature data using the attribute information of the generator, so as to obtain the target judgment threshold corresponding to the feature data.

4. The generator health status assessment method according to claim 1, characterized in that, When there are at least two evaluation dimensions, the health status evaluation result of the generator is determined based on the category proportion results of each evaluation dimension, including: For the current evaluation dimension, if the proportion of the normal category in the category proportion results of the current evaluation dimension is greater than the first preset threshold, then the evaluation result of the current evaluation dimension is determined to be healthy. If the proportion of normal categories in the current evaluation dimension is not greater than the first preset threshold but greater than the second preset threshold, and the proportion of abnormal categories is not greater than the third preset threshold but greater than the fourth preset threshold, then the evaluation result of the current evaluation dimension is determined to be sub-healthy; the first preset threshold is greater than the second preset threshold; the third preset threshold is greater than the fourth preset threshold. If the proportion of normal categories in the current evaluation dimension is not greater than the second preset threshold but greater than the fifth preset threshold, and the proportion of abnormal categories is not greater than the sixth preset threshold but greater than the third preset threshold, then the evaluation result of the current evaluation dimension is determined to be slightly abnormal; the second preset threshold is greater than the fifth preset threshold; the sixth preset threshold is greater than the third preset threshold; the fifth preset threshold is greater than the sixth preset threshold. Otherwise, the evaluation result for the current evaluation dimension is determined to be a fault; The evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions is determined as the health status evaluation result of the generator.

5. The generator health status assessment method according to claim 4, characterized in that, Before determining the health status evaluation result of the generator by processing the evaluation results of at least two evaluation dimensions with the highest priority, the process further includes: Determine whether there are dimension weights corresponding to the at least two evaluation dimensions; If they exist, the evaluation results of the at least two evaluation dimensions are weighted based on the dimensional weights of the at least two evaluation dimensions to obtain the health status evaluation result of the generator. If it does not exist, the evaluation result with the highest processing priority among the evaluation results of at least two evaluation dimensions shall be determined as the health status evaluation result of the generator.

6. The generator health status assessment method according to claim 1, characterized in that, Acquire real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain evaluation data, including: Obtain real-time monitoring data of the generator; Based on the timestamp of the real-time monitoring quantity, the periodic monitoring quantity with the smallest difference between the timestamp and the timestamp is selected from the periodic monitoring quantity database to obtain the periodic monitoring quantity. Based on the timestamp of the real-time monitoring quantity, the offline test monitoring quantity with the smallest difference between the timestamp and the real timestamp is selected from the offline test monitoring quantity database to obtain the offline test monitoring quantity; The evaluation data is obtained by summing the real-time monitoring data, the periodic monitoring data, and the offline test monitoring data.

7. The generator health status assessment method according to claim 1, characterized in that, After determining the health status evaluation result of the generator based on the category proportion results of each evaluation dimension, the process also includes: A maintenance report for the generator is generated based on the health status evaluation results; The maintenance report is sent to the staff's terminal.

8. A health status assessment device for a generator, characterized in that, The device includes: The acquisition module is used to acquire real-time monitoring data, periodic monitoring data, and offline test monitoring data of the generator to obtain evaluation data. The discrimination module is used to discriminate the evaluation data and attribute information of the generator using the data type corresponding to at least one evaluation dimension, and obtain the feature state quantity of at least one evaluation dimension. The statistics module is used to perform category statistics on the feature state quantities of at least one evaluation dimension to obtain the category proportion results for each evaluation dimension. The determination module is used to determine the health status evaluation result of the generator based on the category proportion results of each evaluation dimension.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the generator health status assessment method according to any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the health status assessment method for the generator as described in any one of claims 1-7.

Images