Compressed air energy storage system turbine equipment fault diagnosis and analysis method

Abstract

The invention relates to a compressed air energy storage system turbine equipment fault diagnosis and analysis method, which comprises the following steps: acquiring a plurality of key operation data of a turbine unit under different working conditions, and carrying out feature extraction and correlation analysis operation on the key operation data to obtain standard classification data; determining safe operation intervals and fault probability thresholds of the turbine unit under different working conditions, and constructing a corresponding fault ontology model based on the plurality of key operation data; the fault ontology model is converted into a corresponding BN diagnosis model according to the safe operation interval, the BN diagnosis model is trained through standard classification data to generate a fault diagnosis model, and fault information of the compressed air energy storage system turbine unit under different working conditions is diagnosed through the fault diagnosis model in the online detection stage. Therefore, the problems that according to an existing compressed air energy storage system turbine equipment fault diagnosis method, the phenomena of misjudgment and the like are likely to happen when a unit operates under variable working conditions, and the reliability of fault diagnosis is low are solved.

Description

Technical Field

[0001] The present application relates to the field of new energy technologies, and in particular to a method for diagnosing and analyzing faults of turbine equipment in a compressed air energy storage system. Background Art

[0002] Compressed Air Energy Storage (CAES) is an efficient and sustainable energy storage method, widely used in renewable energy power systems, and has great potential in ensuring grid stability and peak-to-valley shifting. As the core equipment of the compressed air energy storage system, the turboexpander converts the internal energy of compressed air into mechanical energy, thereby driving the generator to work and output electrical energy. Its performance directly affects the efficiency and reliability of the entire system.

[0003] The compressed air energy storage system has significant working condition diversity in the actual operation process, which is mainly reflected in the following aspects:

[0004] 1. Sliding pressure operation conditions:

[0005] The pressure of the gas storage reservoir changes continuously during the charging and discharging process, resulting in dynamic changes in the turbine inlet pressure. The system needs to maintain stable operation under variable pressure and variable flow conditions. Since pressure changes will cause fluctuations in turbine load and efficiency, the equipment needs to adapt to wide-range operating conditions.

[0006] 2. Series-parallel switching conditions:

[0007] The system switches the series and parallel modes of the turbine units according to load demand. During the switching process, changes in the system configuration will cause sudden changes in flow distribution, which will further lead to significant changes in pressure distribution and may cause pressure fluctuations. The switching transient process will produce impact loads on the equipment.

[0008] 3. Air supply operation conditions:

[0009] During the continuous discharge of the system, the operation of supplementing compressed air to maintain the pressure of the gas storage reservoir will cause fluctuations in system parameters. Specifically, the gas replenishment process causes dynamic changes in the pressure and temperature of the gas storage reservoir. The amount of supplemented air directly affects the turbine inlet parameters. At the same time, the mixing of the supplemented compressed air and the working fluid in the gas storage reservoir will cause temperature stratification. These characteristics make the operating characteristics of the system under the gas replenishment operating condition more complex, increasing the difficulty of fault diagnosis. Higher requirements.

[0010] The above special operating conditions bring new challenges to fault diagnosis: the dynamic changes of operating parameters increase the difficulty of fault feature extraction, and the operating condition switching process may trigger false alarms and multi-condition coupling effects, making the fault mode more complicated. The traditional single operating condition diagnosis method is difficult to adapt to the operating characteristics of the CAES system. Therefore, it is urgent to establish a fault diagnosis method that can effectively cope with the special operating conditions of the CAES system.

[0011] The Bayesian Network (BN) diagnostic model can handle this complexity and uncertainty very well, because the compressed air energy storage system turbine unit will generate a large amount of historical data during operation, including normal operation data and fault data. The Bayesian diagnostic model can learn from this data and continuously improve the accuracy of fault diagnosis. However, due to the variable operating conditions of the compressed air energy storage system, the complexity and uncertainty of the turbine unit failure are greatly increased, making the model prone to misjudgment when the unit is operating under variable conditions.

[0012] In summary, the existing fault diagnosis method for turbine equipment in compressed air energy storage systems is prone to misjudgment when the unit is operating under variable conditions, which makes the reliability of fault diagnosis low and needs to be solved urgently. Summary of the invention

[0013] The present application provides a method for diagnosing and analyzing faults of turbine equipment in a compressed air energy storage system, so as to solve the problem that the existing method for diagnosing faults of turbine equipment in a compressed air energy storage system is prone to misjudgment when the unit is operating under variable operating conditions, resulting in low reliability of fault diagnosis.

[0014] A first aspect of the present application provides a method for fault diagnosis and analysis of turbine equipment in a compressed air energy storage system, which is applied to an offline training stage and includes the following steps: collecting a plurality of key operating data of a preset turbine unit under different operating conditions, and performing feature extraction and correlation analysis operations on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data; determining a safe operating range and a fault probability threshold of the turbine unit under different operating conditions, and constructing a corresponding fault ontology model based on the plurality of key operating data; converting the fault ontology model into a corresponding BN diagnostic model according to the safe operating range, and training the BN diagnostic model through the standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different operating conditions in the online detection stage.

[0015] Optionally, in one embodiment of the present application, the collecting of multiple key operating data of a preset turbine unit under different operating conditions, and performing feature extraction and correlation analysis operations on the multiple key operating data to obtain standard classification data corresponding to the multiple key operating data, includes: arranging the multiple key operating data into multiple key operating data sets, wherein the multiple key operating data sets include a turbine inlet and outlet temperature data set, a pressure data set and an impeller speed data set; performing correlation analysis on the turbine inlet and outlet temperature data set, the pressure data set and the impeller speed data set to identify data features corresponding to the turbine inlet and outlet temperature, pressure and impeller speed when the turbine unit is working under variable operating conditions; performing data cleaning and normalization operations on the multiple key operating data data sets according to the data features to obtain standard classification data corresponding to the multiple key operating data.

[0016] Optionally, in one embodiment of the present application, converting the fault ontology model into a corresponding BN diagnostic model according to the safe operating range includes: converting the fault ontology model into a corresponding BN structure according to a preset model conversion rule; determining a fault judgment standard corresponding to the turbine unit based on a preset plurality of key performance parameters of the turbine unit; performing an expert judgment operation on the plurality of key performance parameters based on the BN structure, the fault judgment standard and the safe operating range to obtain an expert judgment result corresponding to each of the plurality of key performance parameters; performing fuzzification processing on the expert judgment result to obtain a fuzzy number corresponding to the expert judgment result, and performing conversion and defuzzification operations on the fuzzy number to construct a BN diagnostic model corresponding to the BN structure.

[0017] The second aspect of the present application provides a method for fault diagnosis and analysis of a turbine device of a compressed air energy storage system, which is applied to the online diagnosis stage and includes the following steps: collecting a plurality of current key operating data of a turbine generator set of a target compressed air energy storage system under different operating conditions, and constructing a system operation data set corresponding to the plurality of current key operating data; inputting the system operation data set into a pre-trained fault diagnosis model, and combining it with a preset safe operating range to generate a fault probability corresponding to the turbine generator set of the target compressed air energy storage system, and comparing the fault probability with a preset fault probability threshold to obtain a fault comparison result, and performing corresponding fault handling operations according to the fault comparison result, wherein the fault diagnosis model is obtained by training a BN diagnosis model obtained by converting a preset fault ontology model using a plurality of key operating data of the turbine unit under preset different operating conditions.

[0018] Optionally, in one embodiment of the present application, the collecting of multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions and constructing a system operation data set corresponding to the multiple current key operating data include: deploying the fault diagnosis model in the target compressed air energy storage system turbine generator set, and collecting multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions; performing feature extraction and correlation analysis operations on the multiple current key operating data to divide each of the multiple current key operating data into a corresponding system operation data set, wherein the system operation data set includes a preset turbine inlet and outlet temperature fault diagnosis data set, a pressure fault diagnosis data set, and an impeller speed fault diagnosis data set.

[0019] Optionally, in one embodiment of the present application, the system operation data set is input into a pre-trained fault diagnosis model, and combined with a preset safe operating range to generate a fault probability corresponding to the target compressed air energy storage system turbine generator set, and the fault probability is compared with a preset fault probability threshold to obtain a fault comparison result, and corresponding fault handling operations are performed according to the fault comparison result, including: determining whether the current key operating data in the system operation data set is within the preset safe operating range; if the current key operating data is within the safe operating range, determining that the target compressed air energy storage system turbine generator set does not have a fault corresponding to the current key operating data; if the current key operating data is not within the safe operating range, determining that the target compressed air energy storage system turbine generator set has a fault corresponding to the current key operating data, and generating the fault diagnosis model through the fault diagnosis model. The fault probability corresponding to the current key operating data, and the fault diagnosis information corresponding to the fault is obtained; the fault probability is compared with the fault probability threshold, and when the fault probability is less than or equal to the fault probability threshold, the fault corresponding to the turbine generator set of the target compressed air energy storage system is processed through the fault diagnosis information, and when the fault type in the fault diagnosis information meets the preset major fault type requirement, the fault warning function of the turbine generator set of the target compressed air energy storage system is triggered; when the fault probability is greater than the fault probability threshold, the fault corresponding to the turbine generator set of the target compressed air energy storage system is processed through the fault diagnosis information, and the fault warning function is triggered at the same time; the fault diagnosis information is input into a preset fault optimization database to optimize the fault diagnosis model through the fault optimization database, and the target compressed air energy storage system turbine generator set is fault diagnosed through the optimized fault diagnosis model.

[0020] The third aspect of the present application provides a device for fault diagnosis and analysis of turbine equipment in a compressed air energy storage system, which is applied to an offline training stage, and includes: an analysis module for collecting a plurality of key operating data of a preset turbine unit under different operating conditions, and performing feature extraction and correlation analysis operations on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data; a modeling module for determining a safe operating range and a fault probability threshold of the turbine unit under different operating conditions, and constructing a corresponding fault ontology model based on the plurality of key operating data; a training module for converting the fault ontology model into a corresponding BN diagnostic model according to the safe operating range, and training the BN diagnostic model through the standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different operating conditions in the online detection stage.

[0021] Optionally, in one embodiment of the present application, the analysis module includes: a sorting unit, used to sort the multiple key operating data into multiple key operating data data sets, wherein the multiple key operating data data sets include a turbine inlet and outlet temperature data set, a pressure data set and an impeller speed data set; an extraction unit, used to perform correlation analysis on the turbine inlet and outlet temperature data set, the pressure data set and the impeller speed data set to identify data features corresponding to the turbine inlet and outlet temperature, pressure and impeller speed when the turbine unit is operating under variable operating conditions; a preprocessing unit, used to perform data cleaning and normalization operations on the multiple key operating data data sets according to the data features to obtain standard classification data corresponding to the multiple key operating data.

[0022] Optionally, in one embodiment of the present application, the training module includes: a conversion unit, used to convert the fault ontology model into a corresponding BN structure according to a preset model conversion rule; a determination unit, used to determine the fault judgment standard corresponding to the turbine unit based on a preset plurality of key performance parameters of the turbine unit; an expert judgment unit, used to perform expert judgment operations on the plurality of key performance parameters based on the BN structure, the fault judgment standard and the safe operating range to obtain an expert judgment result corresponding to each of the plurality of key performance parameters; a fuzzification unit, used to perform fuzzification processing on the expert judgment result to obtain a fuzzy number corresponding to the expert judgment result, and perform conversion and defuzzification operations on the fuzzy number to construct a BN diagnostic model corresponding to the BN structure.

[0023] The fourth aspect of the present application provides a compressed air energy storage system turbine equipment fault diagnosis and analysis device, which is used in the online diagnosis stage, including: an acquisition module, which is used to collect multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions, and construct a system operation data set corresponding to the multiple current key operating data; a diagnosis module, which is used to input the system operation data set into a pre-trained fault diagnosis model, and combine it with a preset safe operating range to generate a fault probability corresponding to the target compressed air energy storage system turbine generator set, and compare the fault probability with a preset fault probability threshold to obtain a fault comparison result, and perform corresponding fault processing operations according to the fault comparison result, wherein the fault diagnosis model is obtained by training a BN diagnosis model obtained by converting a preset fault ontology model based on multiple key operating data of the turbine unit under preset different operating conditions.

[0024] Optionally, in one embodiment of the present application, the acquisition module includes: a deployment unit, used to deploy the fault diagnosis model in the target compressed air energy storage system turbine generator set, and collect multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions; a division unit, used to perform feature extraction and correlation analysis operations on the multiple current key operating data to divide each of the multiple current key operating data into a corresponding system operation data set, wherein the system operation data set includes a preset turbine inlet and outlet temperature fault diagnosis data set, a pressure fault diagnosis data set, and an impeller speed fault diagnosis data set.

[0025] Optionally, in one embodiment of the present application, the diagnosis module includes: a judgment unit, used to judge whether the current key operating data in the system operation data set is within a preset safe operating range; a first judgment unit, used to judge that if the current key operating data is within the safe operating range, the target compressed air energy storage system turbine generator set does not have a fault corresponding to the current key operating data; a second judgment unit, used to judge that if the current key operating data is not within the safe operating range, the target compressed air energy storage system turbine generator set has a fault corresponding to the current key operating data, and generate a fault probability corresponding to the current key operating data through the fault diagnosis model, and obtain fault diagnosis information corresponding to the fault; a comparison unit, used to compare the fault probability with the fault probability threshold value, when the fault probability is less than or equal to the fault probability threshold, the fault corresponding to the target compressed air energy storage system turbine generator set is processed through the fault diagnosis information, and when the fault type in the fault diagnosis information meets the preset major fault type requirement, the fault warning function of the target compressed air energy storage system turbine generator set is triggered; a trigger unit, used to process the fault corresponding to the target compressed air energy storage system turbine generator set through the fault diagnosis information when the fault probability is greater than the fault probability threshold, and trigger the fault warning function at the same time; an optimization unit, used to input the fault diagnosis information into a preset fault optimization database, so as to optimize the fault diagnosis model through the fault optimization database, and perform fault diagnosis on the target compressed air energy storage system turbine generator set through the optimized fault diagnosis model.

[0026] The fifth aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for fault diagnosis and analysis of turbine equipment of a compressed air energy storage system as described in the above embodiment.

[0027] The sixth aspect of the present application provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the above-mentioned method for diagnosing and analyzing faults of turbine equipment in a compressed air energy storage system.

[0028] Therefore, the embodiments of the present application have the following beneficial effects:

[0029] The embodiment of the present application can collect multiple key operating data of the preset turbine unit under different working conditions, and perform feature extraction and correlation analysis operations on the multiple key operating data to obtain standard classification data corresponding to the multiple key operating data; determine the safe operating range and fault probability threshold of the turbine unit under different working conditions, and build a corresponding fault ontology model based on multiple key operating data; convert the fault ontology model into a corresponding BN diagnosis model according to the safe operating range, and train the BN diagnosis model through standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different working conditions in the online detection stage. The present application can not only accurately describe the uncertainty of the fault of the turbine unit when the turbine unit is running under variable working conditions, but also continuously optimize the fault cases to improve the reliability of the fault diagnosis of the turbine unit, and provide support for the stable operation of the turbine unit. Thus, the existing fault diagnosis method of the turbine equipment of the compressed air energy storage system is solved, which is prone to misjudgment when the unit is running under variable working conditions, resulting in low reliability of fault diagnosis.

[0030] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0032] Figure 1 A flowchart of a method for diagnosing and analyzing a fault of a turbine device of a compressed air energy storage system applied in an offline training phase according to an embodiment of the present application;

[0033] Figure 2 A flowchart of a method for diagnosing and analyzing a fault of a turbine device of a compressed air energy storage system applied in an online diagnosis phase according to an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a network structure of a hierarchical BN diagnostic model based on working condition identification provided by an embodiment of the present application;

[0035] Figure 4 A flowchart of operating condition identification and hierarchical diagnosis of a compressed air energy storage system provided for one embodiment of the present application;

[0036] Figure 5 This is an example diagram of a fault diagnosis and analysis device for a turbine device of a compressed air energy storage system applied in an offline training phase according to an embodiment of the present application;

[0037] Figure 6This is an example diagram of a fault diagnosis and analysis device for a turbine device of a compressed air energy storage system applied in an online diagnosis stage according to an embodiment of the present application;

[0038] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0039] Among them, 10-a compressed air energy storage system turbine equipment fault diagnosis and analysis device applied in the offline training stage, 20-a compressed air energy storage system turbine equipment fault diagnosis and analysis device applied in the online diagnosis stage; 101-analysis module, 102-modeling module, 103-training module; 201-acquisition module, 202-diagnosis module; 701-memory, 702-processor, 703-communication interface. DETAILED DESCRIPTION

[0040] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0041] The following describes the fault diagnosis and analysis method of the turbine equipment of the compressed air energy storage system of the embodiment of the present application with reference to the accompanying drawings. In response to the problems mentioned in the above background technology, the present application provides a method for fault diagnosis and analysis of the turbine equipment of the compressed air energy storage system, in which multiple key operating data of the turbine unit under different operating conditions are collected, and feature extraction and correlation analysis operations are performed on them to obtain standard classification data; the current operating condition type of the compressed air energy storage system is identified, including typical operating conditions such as sliding pressure operation, series-parallel switching and air supply operation; corresponding characteristic parameters and diagnostic criteria are selected based on the operating condition type; the safe operating range and fault probability threshold of the turbine unit under different operating conditions are determined, and based on multiple key operating data, a corresponding fault ontology model is constructed; the fault ontology model is converted into a corresponding BN diagnostic model according to the safe operating range, and the BN diagnostic model is trained through standard classification data to generate a fault diagnosis model, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different operating conditions in the online detection stage. In particular, a characteristic parameter set based on the pressure change rate is established for the sliding pressure condition, a characteristic parameter set based on the flow distribution and pressure distribution is established for the series-parallel switching condition, and a characteristic parameter set based on the air supply volume and temperature is established for the air supply condition, so as to achieve accurate diagnosis of various special conditions. In this way, the existing fault diagnosis method of the turbine equipment of the compressed air energy storage system is solved, such as the phenomenon that the fault diagnosis is prone to misjudgment when the unit is running under variable conditions, resulting in low reliability of fault diagnosis.

[0042] Specifically, Figure 1A flow chart of a method for diagnosing and analyzing faults of turbine equipment in a compressed air energy storage system applied in an offline training phase provided in an embodiment of the present application.

[0043] like Figure 1 As shown, the compressed air energy storage system turbine equipment fault diagnosis and analysis method includes the following steps:

[0044] In step S101, a plurality of key operating data of a preset turbine unit under different operating conditions are collected, and feature extraction and correlation analysis operations are performed on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data.

[0045] The embodiments of the present application can first collect multiple key operating data of the turbine unit under different operating conditions, and perform feature extraction and correlation analysis on the data, thereby realizing data classification.

[0046] Optionally, in one embodiment of the present application, multiple key operating data of a preset turbine unit under different operating conditions are collected, and feature extraction and correlation analysis operations are performed on the multiple key operating data to obtain standard classification data corresponding to the multiple key operating data, including: arranging the multiple key operating data into multiple key operating data sets, wherein the multiple key operating data sets include a turbine inlet and outlet temperature data set, a pressure data set, and an impeller speed data set; performing correlation analysis on the turbine inlet and outlet temperature data set, the pressure data set, and the impeller speed data set to identify data features corresponding to the turbine inlet and outlet temperature, pressure, and impeller speed when the turbine unit is working under variable operating conditions; performing data cleaning and normalization operations on the multiple key operating data data sets according to the data features to obtain standard classification data corresponding to the multiple key operating data.

[0047] It should be noted that, in the embodiment of the present application, monitoring equipment can be deployed in the turbine unit to collect key data of the turbine unit of the compressed air energy storage system under different working conditions for a long time, and the inlet and outlet temperatures, pressures and impeller speeds of each level of turbines can be sorted into three data sets to obtain multiple key operating data data sets such as the turbine inlet and outlet temperature data set, the pressure data set and the impeller speed data set; secondly, the embodiment of the present application can process the data and extract the time domain characteristics of each data set. On this basis, the three input signals are correlated and analyzed to identify the changes between the turbine inlet and outlet temperatures, pressure and impeller speed under different working conditions, and the three groups of input data features when the turbine is working under variable working conditions are identified. The above features are extracted and fed back to the original data set. At this time, the abnormal part of the data when the system is working normally under variable working conditions can be eliminated (i.e., data cleaning operation); thereafter, the embodiment of the present application can normalize the three types of feature data to the [0, 1] interval to obtain standard classification data corresponding to multiple key operating data.

[0048] Therefore, the embodiments of the present application collect and classify data when the turbine unit is operating under rated conditions and variable conditions, thereby providing reliable data support for the subsequent BN diagnostic model construction and training.

[0049] In step S102, the safe operation range and fault probability threshold of the turbine unit under different operating conditions are determined, and a corresponding fault ontology model is constructed based on multiple key operation data.

[0050] In step S103, the fault ontology model is converted into a corresponding BN diagnostic model according to the safe operating range, and the BN diagnostic model is trained by standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different operating conditions in the online detection stage.

[0051] Furthermore, the embodiment of the present application also needs to set corresponding safe operating ranges and fault probability thresholds for various fault characteristics under different operating conditions based on expert experience, establish a fault entity model, and convert it into a BN diagnosis model. At the same time, the BN diagnosis model is trained through standard classification data until a fault diagnosis model for the turbine unit is generated, thereby effectively ensuring the realization of the fault diagnosis model's real-time diagnosis function of the compressed air energy storage system turbine unit faults under different operating conditions.

[0052] Optionally, in one embodiment of the present application, the fault ontology model is converted into a corresponding BN diagnostic model according to the safe operating range, including: converting the fault ontology model into a corresponding BN structure according to a preset model conversion rule; determining the fault judgment criteria corresponding to the turbine unit based on a plurality of preset key performance parameters of the turbine unit; performing expert judgment operations on the plurality of key performance parameters based on the BN structure, the fault judgment criteria and the safe operating range to obtain an expert judgment result corresponding to each of the plurality of key performance parameters; performing fuzzification processing on the expert judgment results to obtain a fuzzy number corresponding to the expert judgment result, and performing conversion and defuzzification operations on the fuzzy number to construct a BN diagnostic model corresponding to the BN structure.

[0053] It should be noted that the embodiments of the present application can establish a fault ontology model through the fault information (fault type, fault symptoms) reflected by the collected multiple key performance parameters of the turbine unit, and convert the fault ontology model into a BN structure through three model conversion rules: determining node variables, determining directed edges, and determining node variable states; secondly, the embodiments of the present application can set fault judgment criteria based on key performance parameters such as the efficiency, output power, and expansion ratio of the turbine unit, and obtain corresponding expert judgment results by having experts perform semantic judgments on the probability of occurrence of turbine unit failures.

[0054] Specifically, the embodiments of the present application can determine the safe operation threshold of each key performance parameter under different operating conditions. If it exceeds the safe operation threshold, it is considered abnormal. When most parameters are normal, but there are some marginal values ​​or slight non-critical deviations, the failure probability is defined as "low"; key performance parameters such as speed, expansion ratio, etc. exceed the normal range, but will not cause serious impact on the unit in the short term, then it is defined as the failure probability "medium"; when the key performance parameters seriously deviate from the normal range and immediate measures need to be taken to prevent the fault from worsening, it is defined as the failure probability "high".

[0055] Furthermore, the embodiments of the present application can introduce weights to synthesize the evaluation results of multiple experts, and fuzzify the expert evaluation results through triangular (or trapezoidal) fuzzy numbers; then use the left and right fuzzy sorting method to convert the fuzzy numbers, and perform defuzzification operations to obtain specific fuzzy probability values, thereby constructing the final BN diagnostic model.

[0056] Finally, the embodiments of the present application may input the above normalized three types of feature data (ie, standard classification data) into the BN diagnosis model to train the BN diagnosis model.

[0057] Therefore, the embodiments of the present application can well handle the complexity and uncertainty of the failure of the turbine generator set of the compressed air energy storage system, so that the operating parameters of the turbine unit of the compressed air energy storage system under different operating conditions can be identified and the failure probability can be calculated, and continuous optimization based on failure cases can be carried out to improve the reliability of fault diagnosis.

[0058] According to the method for fault diagnosis and analysis of turbine equipment of compressed air energy storage system applied to offline training stage proposed in the embodiment of the present application, multiple key operating data of preset turbine units under different working conditions are collected, and feature extraction and correlation analysis operations are performed on multiple key operating data to obtain standard classification data corresponding to multiple key operating data; the safe operating range and fault probability threshold of the turbine unit under different working conditions are determined, and the corresponding fault ontology model is constructed based on multiple key operating data; the fault ontology model is converted into the corresponding BN diagnosis model according to the safe operating range, and the BN diagnosis model is trained by standard classification data until the fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different working conditions in the online detection stage. This application can not only accurately describe the uncertainty of the fault of the turbine unit when it is running under variable working conditions, but also can improve the reliability of fault diagnosis of the turbine unit through continuous optimization of fault cases, and provide support for the stable operation of the turbine unit.

[0059] Figure 2 A flow chart of a method for diagnosing and analyzing faults of turbine equipment in a compressed air energy storage system applied in the online diagnosis stage provided in an embodiment of the present application.

[0060] like Figure 2 As shown, the compressed air energy storage system turbine equipment fault diagnosis and analysis method includes the following steps:

[0061] In step S201, a plurality of current key operating data of the turbine generator set of the target compressed air energy storage system under different operating conditions are collected, and a system operating data set corresponding to the plurality of current key operating data is constructed.

[0062] During the online diagnosis stage, the embodiments of the present application can deploy monitoring equipment and data acquisition systems in actual compressed air energy storage system turbine generator sets to collect real-time operating data of the target compressed air energy storage system turbine generator sets under different operating conditions.

[0063] Optionally, in one embodiment of the present application, multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions are collected, and a system operation data set corresponding to multiple current key operating data is constructed, including: deploying a fault diagnosis model in the target compressed air energy storage system turbine generator set, and collecting multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions; performing feature extraction and correlation analysis operations on the multiple current key operating data to divide each of the multiple current key operating data into a corresponding system operation data set, wherein the system operation data set includes a preset turbine inlet and outlet temperature fault diagnosis data set, a pressure fault diagnosis data set, and an impeller speed fault diagnosis data set.

[0064] During the actual implementation process, the embodiments of the present application can integrate the pre-trained BN diagnostic model, that is, the fault diagnosis model, into the monitoring system server of the target compressed air energy storage system turbine generator set, and deploy the monitoring equipment and data acquisition system in the actual compressed air energy storage system turbine generator set to collect multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions.

[0065] Afterwards, the embodiments of the present application can perform the above-mentioned feature extraction and correlation analysis and other operations on multiple current key operating data, and divide each current key operating data into corresponding system operating data sets such as turbine inlet and outlet temperature fault diagnosis data set, pressure fault diagnosis data set and impeller speed fault diagnosis data set.

[0066] Therefore, the embodiment of the present application ensures the accuracy and reliability of fault diagnosis of the turbine generator set of the target compressed air energy storage system by real-time collection of the current key operating data of the turbine generator set of the target compressed air energy storage system and corresponding processing thereof.

[0067] In step S202, the system operation data set is input into the fault diagnosis model, and combined with the preset safe operation range, the fault probability corresponding to the turbine generator set of the target compressed air energy storage system is generated, and the fault probability is compared with the preset fault probability threshold to obtain a fault comparison result, and the corresponding fault processing operation is performed according to the fault comparison result, wherein the fault diagnosis model is obtained by training the BN diagnosis model obtained by converting the preset fault ontology model with multiple key operation data of the turbine unit under different preset working conditions, wherein the network structure of the hierarchical BN diagnosis model based on working condition recognition is as follows: Figure 3 shown.

[0068] Furthermore, the embodiments of the present application may integrate the fault diagnosis model into the detection system server, and input the system operation data set into the fault diagnosis model to calculate the failure probability of the turbine generator set of the target compressed air energy storage system. When the failure probability exceeds the set failure probability threshold, the system alarm is triggered; finally, the embodiments of the present application may record the fault case related information in the database to optimize the fault diagnosis model and improve the fault diagnosis process.

[0069] Optionally, in one embodiment of the present application, the system operation data set is input into the fault diagnosis model, and combined with the preset safe operation range to generate the fault probability corresponding to the target compressed air energy storage system turbine generator set, and the fault probability is compared with the preset fault probability threshold to obtain a fault comparison result, and the corresponding fault handling operation is performed according to the fault comparison result, including: judging whether the current key operation data in the system operation data set is within the preset safe operation range; if the current key operation data is within the safe operation range, it is judged that the target compressed air energy storage system turbine generator set does not have the fault corresponding to the current key operation data; if the current key operation data is not within the safe operation range, it is judged that the target compressed air energy storage system turbine generator set has the fault corresponding to the current key operation data, and generates through the fault diagnosis model. The fault probability corresponding to the current key operating data is obtained, and the fault diagnosis information corresponding to the fault is obtained; the fault probability and the fault probability threshold are compared, and when the fault probability is less than or equal to the fault probability threshold, the fault corresponding to the turbine generator set of the target compressed air energy storage system is processed through the fault diagnosis information, and when the fault type in the fault diagnosis information meets the preset major fault type requirement, the fault warning function of the turbine generator set of the target compressed air energy storage system is triggered; when the fault probability is greater than the fault probability threshold, the fault corresponding to the turbine generator set of the target compressed air energy storage system is processed through the fault diagnosis information, and the fault warning function is triggered at the same time; the fault diagnosis information is input into a preset fault optimization database to optimize the fault diagnosis model through the fault optimization database, and the target compressed air energy storage system turbine generator set is fault diagnosed through the optimized fault diagnosis model.

[0070] Specifically, the embodiments of the present application can calculate the failure probability corresponding to the turbine generator set of the target compressed air energy storage system according to the safe operating range and failure probability threshold set in the above-mentioned offline training stage.

[0071] For example, when setting up a diagnosis for an out-of-control overspeed fault through a fault diagnosis model, the embodiment of the present application can set different safe operating ranges for the speeds under rated conditions and variable conditions. When the input data is processed and classified as rated conditions, the fault diagnosis model will call the safe operating range set under the rated conditions to diagnose the out-of-control overspeed fault. When the speed is outside the safe operating range, the probability of an out-of-control overspeed fault is calculated through the fault diagnosis model, and a fault probability threshold is defined. When the fault probability exceeds the set fault probability threshold, a system alarm is triggered; when the fault probability is lower than the fault probability threshold, the fault diagnosis model determines that the probability of an out-of-control overspeed fault in the target compressed air energy storage system turbine generator set is low, and the fault diagnosis model will actively adjust the speed through the feedback link. Based on the characteristics of the compressed air energy storage system turbine unit, for certain special major fault types, such as shaft breakage, a lower safe operating range and fault probability threshold are set separately. Even if the fault probability calculated by the fault diagnosis model is low, an alarm will be triggered immediately.

[0072] Finally, the embodiments of the present application can record the relevant information of the fault diagnosis, such as the fault time, fault type and symptoms, the fault probability output by the model and the corresponding measures taken, in the fault database to optimize the model and improve the fault diagnosis process.

[0073] Therefore, the embodiments of the present application can greatly reduce the probability of misjudgment of turbine unit faults in a compressed air energy storage system under various operating conditions such as variable operating conditions, and improve the accuracy and reliability of turbine unit fault diagnosis.

[0074] In summary, this application particularly considers the operating characteristics of the compressed air energy storage system during actual operation. The system mainly operates under three typical operating conditions: sliding pressure operation, series-parallel switching, and air supply operation. Figure 4 shown.

[0075] Among them, the sliding pressure operation condition refers to the process in which the gas storage pressure continues to change with the energy release process, and the system gradually decreases from the initial pressure p to the minimum working pressure pmin. In this process, the relationship between the turbine inlet pressure pin and the gas storage pressure ps can be expressed as:

[0076] pin=ηps

[0077] Where η is the pipeline pressure loss coefficient.

[0078] The series-parallel switching condition means that the system adjusts the operation mode of the turbine unit according to the load demand. During the switching process, the change in system configuration causes a sudden change in flow distribution, and the pressure ratio π and flow G of each stage of the turbine change dynamically.

[0079] The air replenishment operating condition refers to the operating state in which when the pressure of the gas storage reservoir drops to the set value ps_set, compressed air needs to be added to the gas storage reservoir to maintain the system pressure, and the air replenishment process causes system parameter fluctuations.

[0080] For the above three typical working conditions, this application establishes a corresponding characteristic parameter system. Under the sliding pressure operating condition, the pressure change characteristic coefficient Kp and the flow characteristic coefficient KG are defined as shown in the following formula:

[0081] Kp=(dp / dt) / (dp / dt)rated

[0082] KG=(G√T / p) / (G√T / p)rated

[0083] Among them, the subscript rated represents the rated operating condition parameters. At the same time, this application introduces the modified speed coefficient Kn=n / √T to characterize the speed change characteristics. Based on these characteristic parameters, the safe operation range criterion under sliding pressure conditions is established:

[0084] 0.8≤Kp≤1.2

[0085] 0.85≤KG≤1.15

[0086] 0.95≤Kn≤1.05

[0087] Under the series-parallel switching condition, the flow distribution coefficient KF and the pressure distribution coefficient Kπ are defined as shown in the following formula:

[0088] KF=Gi / ΣGi(i=1,2,...,n, n is the number of parallel units)

[0089] Kπ=(πi-πi+1) / πrated

[0090] Where πi is the pressure ratio of the i-th stage. The dynamic characteristics of the switching process are described by the characteristic time τ = t / trated. The parameter fluctuation caused by the change of system configuration must satisfy:

[0091] |ΔKF|≤5%

[0092] |ΔKπ|≤8%

[0093] 0.8≤τ≤1.2

[0094] Under the air supply operation condition, the system performance is characterized by the air supply flow ratio Ks and the pressure recovery coefficient Kr:

[0095] Ks = Gs / Gn (Gs is the air supply flow, Gn is the rated flow)

[0096] Kr = (p-pmin) / (pmax-pmin)

[0097] The safe operation requirements under this condition are:

[0098] 0≤Ks≤0.3

[0099] Kr≥0.85

[0100] The fault diagnosis model constructed in the present application adopts a hierarchical structure. The operating condition identification layer determines the current operating condition based on the above-mentioned characteristic parameters; the parameter characteristic layer calculates the characteristic parameters corresponding to each operating condition and compares them with the safe operating range; the fault diagnosis layer calculates the fault probability based on the Bayesian network, and the conditional probability table of the network node is obtained by training with historical data under different operating conditions; when a certain characteristic parameter exceeds the safe operating range, the system enters the fault diagnosis state, and the model outputs the fault type and fault probability.

[0101] In particular, during the working condition switching process, the present application may adopt a dynamic threshold strategy to modify the criterion of the safe operating range to:

[0102] [X]min(1-ε)≤X≤[X]max(1+ε)

[0103] Among them, X is the characteristic parameter, ε is the margin coefficient considering the dynamic process, which is usually 0.1-0.2; this strategy effectively reduces the misdiagnosis rate during the working condition switching process.

[0104] According to the fault diagnosis and analysis method for turbine equipment of compressed air energy storage system applied to the online diagnosis stage proposed in the embodiment of the present application, multiple current key operating data of the turbine generator set of the target compressed air energy storage system under different working conditions are collected, and a system operation data set corresponding to multiple current key operating data is constructed; the system operation data set is input into the pre-trained fault diagnosis model, and combined with the preset safe operation range, to generate the fault probability corresponding to the turbine generator set of the target compressed air energy storage system, and the fault probability is compared with the preset fault probability threshold to obtain the fault comparison result, and the corresponding fault processing operation is performed according to the fault comparison result, wherein the fault diagnosis model is obtained by training the BN diagnosis model obtained by converting the preset fault ontology model with multiple key operating data of the turbine set under different preset working conditions. The present application can not only accurately describe the uncertainty of the fault of the turbine set when it is running under variable working conditions, but also can improve the reliability of the fault diagnosis of the turbine set through continuous optimization of fault cases, and provide support for the stable operation of the turbine set.

[0105] Secondly, the compressed air energy storage system turbine equipment fault diagnosis and analysis device proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0106] Figure 5 It is a block diagram of a compressed air energy storage system turbine equipment fault diagnosis and analysis device applied to an offline training stage according to an embodiment of the present application.

[0107] like Figure 5 As shown, the compressed air energy storage system turbine equipment fault diagnosis and analysis device 10 applied in the offline training stage includes: an analysis module 101, a modeling module 102 and a training module 103.

[0108] The analysis module 101 is used to collect a plurality of key operating data of a preset turbine unit under different operating conditions, and perform feature extraction and correlation analysis operations on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data.

[0109] The modeling module 102 is used to determine the safe operating range and fault probability threshold of the turbine unit under different operating conditions, and to construct a corresponding fault ontology model based on multiple key operating data.

[0110] The training module 103 is used to convert the fault entity model into a corresponding BN diagnosis model according to the safe operating range, and train the BN diagnosis model through standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different operating conditions during the online detection stage.

[0111] Optionally, in one embodiment of the present application, the analysis module 101 includes: a sorting unit, an extraction unit and a preprocessing unit.

[0112] The sorting unit is used to sort the multiple key operating data into multiple key operating data data sets, wherein the multiple key operating data data sets include a turbine inlet and outlet temperature data set, a pressure data set and an impeller speed data set.

[0113] The extraction unit is used to perform correlation analysis on the turbine inlet and outlet temperature data set, the pressure data set and the impeller speed data set to identify the data features corresponding to the turbine inlet and outlet temperature, pressure and impeller speed when the turbine unit is working under variable conditions.

[0114] The preprocessing unit is used to perform data cleaning and normalization operations on multiple key operation data sets according to data characteristics to obtain standard classification data corresponding to the multiple key operation data.

[0115] Optionally, in one embodiment of the present application, the training module 103 includes: a conversion unit, a determination unit, an expert judgment unit and a fuzzification unit.

[0116] The conversion unit is used to convert the fault ontology model into a corresponding BN structure according to a preset model conversion rule.

[0117] The determination unit is used to determine the fault judgment criteria corresponding to the turbine unit based on a plurality of preset key performance parameters of the turbine unit.

[0118] The expert evaluation unit is used to perform expert evaluation operations on multiple key performance parameters based on the BN structure, fault evaluation criteria and safe operation range, so as to obtain an expert evaluation result corresponding to each of the multiple key performance parameters.

[0119] The fuzzification unit is used to fuzzify the expert evaluation results to obtain the fuzzy numbers corresponding to the expert evaluation results, and to convert and defuzzify the fuzzy numbers to construct a BN diagnostic model corresponding to the BN structure.

[0120] According to the embodiment of the present application, the compressed air energy storage system turbine equipment fault diagnosis and analysis device applied to the offline training stage includes an analysis module for collecting a plurality of key operating data of a preset turbine unit under different working conditions, and performing feature extraction and correlation analysis operations on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data; a modeling module for determining the safe operating range and fault probability threshold of the turbine unit under different working conditions, and building a corresponding fault ontology model based on the plurality of key operating data; a training module for converting the fault ontology model into a corresponding BN diagnosis model according to the safe operating range, and training the BN diagnosis model through standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different working conditions in the online detection stage. The present application can not only accurately describe the uncertainty of the fault of the turbine unit when it is running under variable working conditions, but also can continuously optimize the fault cases to improve the reliability of the fault diagnosis of the turbine unit, and provide support for the stable operation of the turbine unit.

[0121] Figure 6 It is a block diagram of a fault diagnosis and analysis device for a turbine device of a compressed air energy storage system applied in an online diagnosis stage according to an embodiment of the present application.

[0122] like Figure 6 As shown, the compressed air energy storage system turbine equipment fault diagnosis and analysis device 20 applied in the online diagnosis stage includes: a collection module 201 and a diagnosis module 202.

[0123] Among them, the acquisition module 201 is used to collect multiple current key operating data of the turbine generator set of the target compressed air energy storage system under different operating conditions, and construct a system operation data set corresponding to multiple current key operating data.

[0124] The diagnostic module 202 is used to input the system operation data set into the pre-trained fault diagnosis model, and combine it with the preset safe operation range to generate the fault probability corresponding to the turbine generator set of the target compressed air energy storage system, and compare the fault probability with the preset fault probability threshold to obtain the fault comparison result, and perform corresponding fault processing operations according to the fault comparison result, wherein the fault diagnosis model is obtained by training the BN diagnosis model obtained by converting the preset fault ontology model through multiple key operation data of the turbine unit under different preset operating conditions.

[0125] Optionally, in one embodiment of the present application, the collection module 201 includes: a deployment unit and a division unit.

[0126] Among them, the deployment unit is used to deploy the fault diagnosis model in the target compressed air energy storage system turbine generator set, and collect multiple current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions.

[0127] A partitioning unit is used to perform feature extraction and correlation analysis operations on multiple current key operating data to partition each of the multiple current key operating data into a corresponding system operating data set, wherein the system operating data set includes a preset turbine inlet and outlet temperature fault diagnosis data set, a pressure fault diagnosis data set, and an impeller speed fault diagnosis data set.

[0128] Optionally, in one embodiment of the present application, the diagnosis module 202 includes: a judgment unit, a first judgment unit, a second judgment unit, a comparison unit, a trigger unit and an optimization unit.

[0129] The judging unit is used to judge whether the current key operating data in the system operating data set is within a preset safe operating range.

[0130] The first determination unit is used to determine that the target compressed air energy storage system turbine generator set does not have a fault corresponding to the current key operating data if the current key operating data is within a safe operating range.

[0131] The second determination unit is used to determine if the current key operating data is not within the safe operating range, then determine if the target compressed air energy storage system turbine generator set has a fault corresponding to the current key operating data, and generate a fault probability corresponding to the current key operating data through a fault diagnosis model, and obtain fault diagnosis information corresponding to the fault.

[0132] A comparison unit is used to compare the fault probability and the fault probability threshold. When the fault probability is less than or equal to the fault probability threshold, the fault corresponding to the turbine generator set of the target compressed air energy storage system is processed through the fault diagnosis information, and when the fault type in the fault diagnosis information meets the preset major fault type requirements, the fault warning function of the turbine generator set of the target compressed air energy storage system is triggered.

[0133] The trigger unit is used to process the fault corresponding to the turbine generator set of the target compressed air energy storage system through fault diagnosis information when the fault probability is greater than the fault probability threshold, and trigger the fault warning function at the same time.

[0134] The optimization unit is used to input the fault diagnosis information into a preset fault optimization database so as to optimize the fault diagnosis model through the fault optimization database, and perform fault diagnosis on the turbine generator set of the target compressed air energy storage system through the optimized fault diagnosis model.

[0135] It should be noted that the aforementioned explanation of the embodiment of the method for diagnosing and analyzing the faults of the turbine equipment of the compressed air energy storage system is also applicable to the device for diagnosing and analyzing the faults of the turbine equipment of the compressed air energy storage system of this embodiment, and will not be repeated here.

[0136] According to the embodiment of the present application, the compressed air energy storage system turbine equipment fault diagnosis and analysis device applied to the online diagnosis stage includes an acquisition module for collecting multiple current key operating data of the target compressed air energy storage system turbine generator set under different working conditions, and constructing a system operation data set corresponding to multiple current key operating data; a diagnosis module for inputting the system operation data set into a pre-trained fault diagnosis model, and combining the preset safe operation range to generate the fault probability corresponding to the target compressed air energy storage system turbine generator set, and comparing the fault probability with the preset fault probability threshold to obtain a fault comparison result, and performing corresponding fault processing operations according to the fault comparison result, wherein the fault diagnosis model is obtained by training the BN diagnosis model obtained by converting the preset fault ontology model with multiple key operating data of the turbine unit under different preset working conditions. The present application can not only accurately describe the uncertainty of the fault of the turbine unit when it is running under variable working conditions, but also can continuously optimize the fault cases to improve the reliability of the fault diagnosis of the turbine unit, and provide support for the stable operation of the turbine unit.

[0137] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0138] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0139] When the processor 702 executes the program, the compressed air energy storage system turbine equipment fault diagnosis and analysis method provided in the above embodiment is implemented.

[0140] Furthermore, the electronic device further comprises:

[0141] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0142] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0143] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0144] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0145] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0146] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0147] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for diagnosing and analyzing faults of turbine equipment in a compressed air energy storage system.

[0148] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0149] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0150] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0151] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0152] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0153] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0154] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0155] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for fault diagnosis and analysis of turbine equipment in a compressed air energy storage system, applied in an offline training phase, characterized in that: The following steps are involved: Collecting a plurality of key operating data of a preset turbine unit under different operating conditions, and performing feature extraction and correlation analysis operations on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data; Determining the safe operation range and fault probability threshold of the turbine unit under different operating conditions, and constructing a corresponding fault ontology model based on the multiple key operation data; The fault ontology model is converted into a corresponding BN diagnostic model according to the safe operating range, and the BN diagnostic model is trained by the standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different operating conditions during the online detection stage.

2. The method according to claim 1, characterized in that The collecting of a plurality of key operating data of a preset turbine unit under different working conditions, and performing feature extraction and correlation analysis operations on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data, includes: Arrange the plurality of key operating data into a plurality of key operating data data sets, wherein the plurality of key operating data data sets include a turbine inlet and outlet temperature data set, a pressure data set, and an impeller speed data set; performing correlation analysis on the turbine inlet and outlet temperature data set, the pressure data set and the impeller speed data set to identify data features corresponding to the turbine inlet and outlet temperature, pressure and impeller speed when the turbine unit is operating under variable operating conditions; Data cleaning and normalization operations are performed on the multiple key operation data sets according to the data features to obtain standard classification data corresponding to the multiple key operation data.

3. The method according to claim 2, characterized in that The converting the fault ontology model into a corresponding BN diagnosis model according to the safe operation range includes: Convert the fault ontology model into a corresponding BN structure according to a preset model conversion rule; Determining a fault judgment criterion corresponding to the turbine unit based on a plurality of preset key performance parameters of the turbine unit; Based on the BN structure, the fault judgment standard and the safe operation range, an expert judgment operation is performed on the multiple key performance parameters to obtain an expert judgment result corresponding to each of the multiple key performance parameters; The expert evaluation result is fuzzified to obtain a fuzzy number corresponding to the expert evaluation result, and the fuzzy number is converted and defuzzified to construct a BN diagnostic model corresponding to the BN structure.

4. A method for fault diagnosis and analysis of turbine equipment in a compressed air energy storage system, applied in the online diagnosis stage, characterized in that: The following steps are involved: Collecting a plurality of current key operating data of the turbine generator set of the target compressed air energy storage system under different operating conditions, and constructing a system operating data set corresponding to the plurality of current key operating data; The system operation data set is input into a pre-trained fault diagnosis model, and combined with a preset safe operation range to generate a fault probability corresponding to the turbine generator set of the target compressed air energy storage system, and the fault probability is compared with a preset fault probability threshold to obtain a fault comparison result, and corresponding fault handling operations are performed according to the fault comparison result, wherein the fault diagnosis model is obtained by training a BN diagnosis model obtained by converting a preset fault ontology model using multiple key operation data of the turbine unit under preset different operating conditions.

5. The method according to claim 4, characterized in that The collecting of a plurality of current key operating data of the turbine generator set of the target compressed air energy storage system under different operating conditions and constructing a system operating data set corresponding to the plurality of current key operating data include: Deploy the fault diagnosis model in the target compressed air energy storage system turbine generator set, and collect a plurality of current key operating data of the target compressed air energy storage system turbine generator set under different operating conditions; Feature extraction and correlation analysis operations are performed on the multiple current key operating data to divide each of the multiple current key operating data into a corresponding system operating data set, wherein the system operating data set includes a preset turbine inlet and outlet temperature fault diagnosis data set, a pressure fault diagnosis data set, and an impeller speed fault diagnosis data set.

6. The method according to claim 4, characterized in that The system operation data set is input into a pre-trained fault diagnosis model, and combined with a preset safe operation range to generate a fault probability corresponding to the turbine generator set of the target compressed air energy storage system, and the fault probability is compared with a preset fault probability threshold to obtain a fault comparison result, and a corresponding fault handling operation is performed according to the fault comparison result, including: Determining whether the current key operating data in the system operating data set is within a preset safe operating range; If the current key operating data is within the safe operating range, it is determined that the target compressed air energy storage system turbine generator set does not have a fault corresponding to the current key operating data; If the current key operating data is not within the safe operating range, it is determined that the target compressed air energy storage system turbine generator set has a fault corresponding to the current key operating data, and the fault probability corresponding to the current key operating data is generated through the fault diagnosis model, and the fault diagnosis information corresponding to the fault is obtained; Compare the fault probability with the fault probability threshold, and when the fault probability is less than or equal to the fault probability threshold, process the fault corresponding to the turbine generator set of the target compressed air energy storage system through the fault diagnosis information, and when the fault type in the fault diagnosis information meets the preset major fault type requirement, trigger the fault warning function of the turbine generator set of the target compressed air energy storage system; When the fault probability is greater than the fault probability threshold, the fault corresponding to the turbine generator set of the target compressed air energy storage system is processed through the fault diagnosis information, and the fault warning function is triggered at the same time; The fault diagnosis information is input into a preset fault optimization database to optimize the fault diagnosis model through the fault optimization database, and the fault diagnosis of the target compressed air energy storage system turbine generator set is performed through the optimized fault diagnosis model.

7. A compressed air energy storage system turbine equipment fault diagnosis and analysis device, used in the offline training stage, characterized in that: include: An analysis module, used for collecting a plurality of key operating data of a preset turbine unit under different working conditions, and performing feature extraction and correlation analysis operations on the plurality of key operating data to obtain standard classification data corresponding to the plurality of key operating data; A modeling module, used to determine the safe operation range and fault probability threshold of the turbine unit under different operating conditions, and to construct a corresponding fault ontology model based on the multiple key operation data; A training module is used to convert the fault entity model into a corresponding BN diagnostic model according to the safe operating range, and train the BN diagnostic model through the standard classification data until a fault diagnosis model of the turbine unit is generated, so as to use the fault diagnosis model to diagnose the fault information of the turbine unit of the compressed air energy storage system under different operating conditions during the online detection stage.

8. A compressed air energy storage system turbine equipment fault diagnosis and analysis device, used in the online diagnosis stage, characterized in that: include: A collection module, used to collect multiple current key operating data of the turbine generator set of the target compressed air energy storage system under different operating conditions, and construct a system operation data set corresponding to the multiple current key operating data; A diagnostic module is used to input the system operation data set into a pre-trained fault diagnosis model, and combine it with a preset safe operation range to generate a fault probability corresponding to the turbine generator set of the target compressed air energy storage system, and compare the fault probability with a preset fault probability threshold to obtain a fault comparison result, and perform corresponding fault processing operations according to the fault comparison result, wherein the fault diagnosis model is obtained by training a BN diagnostic model obtained by converting a preset fault ontology model based on multiple key operating data of the turbine unit under preset different operating conditions.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for diagnosing and analyzing faults of turbine equipment in a compressed air energy storage system as described in any one of claims 1 to 3 or any one of claims 4 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a method for diagnosing and analyzing faults of a turbine device in a compressed air energy storage system as described in any one of claims 1 to 3 or any one of claims 4 to 6.

Images