Gas turbine generator state monitoring method, device and equipment and storage medium

Abstract

The invention provides a gas turbine generator state monitoring method, device and equipment and a storage medium, and the method comprises the steps: obtaining the electrical monitoring data of a gas turbine generator in a current time period; performing clustering analysis on the electrical monitoring data to obtain the current working condition of the gas turbine generator; based on the current working condition and the data state characteristics of the electrical monitoring data, obtaining a current health index sequence of the gas turbine generator in the current time period; performing prediction based on the current health index sequence to obtain a predicted health index sequence in a future time period; and performing state monitoring on the gas turbine generator based on the current health index sequence and the predicted health index sequence. According to the technical scheme, the accuracy of monitoring the health state of the gas turbine generator can be improved.

Description

Technical Field

[0001] This application relates to the field of gas turbine generator monitoring technology, and in particular to a gas turbine generator condition monitoring method, device, equipment and storage medium. Background Technology

[0002] The gas turbine generator is the core of a gas turbine power generation system, and its operating status directly affects the system's safety and economy. Currently, monitoring of gas turbine generators relies on periodic maintenance, fixed threshold alarms, and human experience, which suffers from problems such as delayed response, high false alarm rates, and inability to provide early warnings. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in the related art.

[0004] In a first aspect, this application proposes a method for condition monitoring of a gas turbine generator. The method includes: acquiring electrical monitoring data of the gas turbine generator in the current time period; performing cluster analysis on the electrical monitoring data to obtain the current operating condition of the gas turbine generator; acquiring a current health indicator sequence of the gas turbine generator in the current time period based on the current operating condition and the data state characteristics of the electrical monitoring data; making predictions based on the current health indicator sequence to obtain a predicted health indicator sequence for future time periods; and performing condition monitoring of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence.

[0005] In one implementation, the step of performing cluster analysis on the electrical monitoring data to obtain the current operating condition of the gas turbine generator includes: extracting features from the electrical monitoring data to obtain operating condition feature parameters; obtaining feature vectors based on the operating condition feature parameters; obtaining the distances between the feature vectors and a plurality of preset cluster centers; wherein each cluster center corresponds to an operating condition; and obtaining the current operating condition based on the distances between the feature vectors and each cluster center.

[0006] In one implementation, obtaining the current health indicator sequence of the gas turbine generator within the current time period based on the data state characteristics of the current operating condition and the electrical monitoring data includes: obtaining a target health status assessment model corresponding to the current operating condition from multiple candidate health status assessment models; wherein different candidate health status assessment models correspond to different operating conditions, and each candidate health status assessment model is trained from the operating data of the corresponding operating condition; inputting the electrical monitoring data into the target health status assessment model to obtain an initial health indicator sequence; obtaining the reconstruction error of the target health status assessment model; and adjusting the initial health indicator sequence based on the reconstruction error to obtain the current health indicator sequence.

[0007] In one implementation, the step of monitoring the state of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence includes: acquiring statistical characteristics of the current health indicator sequence; setting at least one level early warning threshold based on the statistical characteristics; and monitoring the state of the gas turbine generator based on the predicted health indicator sequence and the at least one level early warning threshold.

[0008] In one implementation, the step of monitoring the state of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence includes: performing risk mapping based on the current health indicator sequence to obtain a fault risk function; predicting a risk critical time based on the fault risk function and the predicted health indicator sequence; obtaining a predicted equipment lifespan based on the risk critical time; and determining the current state of the gas turbine generator based on the current health indicator sequence and the predicted equipment lifespan.

[0009] In one implementation, the method further includes: obtaining an anomaly scoring model corresponding to the current operating condition; inputting the electrical monitoring data into the anomaly scoring model to obtain basic anomaly scores for each moment within the current time period; performing sliding window analysis on the basic anomaly scores for each moment within the current time period to obtain weight values ​​corresponding to each moment within the current time period; performing weighted processing on the basic anomaly scores based on the weight values ​​to obtain a comprehensive anomaly index for each moment within the current time period; and determining the data anomaly moments within the current time period based on the comprehensive anomaly index.

[0010] Secondly, this application proposes a gas turbine generator condition monitoring device, the device comprising: an acquisition module for acquiring electrical monitoring data of the gas turbine generator in the current time period; a first processing module for performing cluster analysis on the electrical monitoring data to obtain the current operating condition of the gas turbine generator; a second processing module for acquiring a current health indicator sequence of the gas turbine generator in the current time period based on the current operating condition and the data state characteristics of the electrical monitoring data; a third processing module for making predictions based on the current health indicator sequence to obtain a predicted health indicator sequence for future time periods; and a fourth processing module for performing condition monitoring of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence.

[0011] In one implementation, the first processing module can be used to: extract features from the electrical monitoring data to obtain operating condition feature parameters; obtain feature vectors based on the operating condition feature parameters; obtain the distances between the feature vectors and a plurality of preset cluster centers; wherein each cluster center corresponds to an operating condition; and obtain the current operating condition based on the distances between the feature vectors and each cluster center.

[0012] In one implementation, the second processing module can be used to: obtain a target health status assessment model corresponding to the current operating condition from multiple candidate health status assessment models; wherein different candidate health status assessment models correspond to different operating conditions, and each candidate health status assessment model is trained from the operating data of the corresponding operating condition; input the electrical monitoring data into the target health status assessment model to obtain an initial health indicator sequence; obtain the reconstruction error of the target health status assessment model; and adjust the initial health indicator sequence based on the reconstruction error to obtain the current health indicator sequence.

[0013] In one implementation, the fourth processing module can be used to: acquire the statistical characteristics of the current health indicator sequence; set at least one level early warning threshold based on the statistical characteristics; and perform status monitoring on the gas turbine generator based on the predicted health indicator sequence and the at least one level early warning threshold.

[0014] In one implementation, the fourth processing module can be used to: perform risk mapping based on the current health indicator sequence to obtain a fault risk function; predict a risk critical time based on the fault risk function and the predicted health indicator sequence; obtain a predicted equipment lifespan based on the risk critical time; and determine the current state of the gas turbine generator based on the current health indicator sequence and the predicted equipment lifespan.

[0015] In one implementation, the device further includes a fifth processing module, which can be used to: acquire the anomaly scoring model corresponding to the current operating condition; input the electrical monitoring data into the anomaly scoring model to obtain the basic anomaly scores at each time point within the current time period; perform sliding window analysis on the basic anomaly scores at each time point within the current time period to obtain the weight values ​​corresponding to each time point within the current time period; perform weighted processing on the basic anomaly scores based on the weight values ​​to obtain the comprehensive anomaly index at each time point within the current time period; and determine the data anomaly time within the current time period based on the comprehensive anomaly index.

[0016] Thirdly, this application proposes an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the gas turbine generator condition monitoring method as described in the first aspect.

[0017] Fourthly, this application proposes a storage medium storing instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect.

[0018] Fifthly, this application proposes a program product comprising at least one of a program and instructions, wherein when the program and instructions are executed by an electronic device, they implement the steps of the method described in the first aspect.

[0019] The gas turbine generator condition monitoring method, apparatus, equipment, and storage medium provided in this application can determine the current operating condition of the gas turbine generator based on electrical monitoring data of the gas turbine generator in the current time period, determine a health index sequence of the gas turbine generator based on the current operating condition, and then predict a health index sequence based on the current health index sequence. Based on the current health index sequence and the predicted health index sequence, the condition of the gas turbine generator can be monitored. This improves the accuracy of gas turbine generator health status monitoring.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0022] Figure 1 This is a flowchart illustrating a gas turbine generator condition monitoring method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating another gas turbine generator condition monitoring method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating another gas turbine generator condition monitoring method provided in the embodiments of this application; Figure 4 This is a flowchart illustrating another gas turbine generator condition monitoring method provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of a gas turbine generator condition monitoring device provided in an embodiment of this application; Figure 6 This is a schematic diagram of another gas turbine generator condition monitoring device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The following describes a gas turbine generator condition monitoring method and apparatus according to embodiments of this application with reference to the accompanying drawings.

[0025] Figure 1 This is a flowchart illustrating a gas turbine generator condition monitoring method provided in an embodiment of this application. Figure 1 As shown, the method may include, but is not limited to, the following steps: S101: Obtain electrical monitoring data of the gas turbine generator during the current time period.

[0026] For example, electrical monitoring data of a gas turbine generator is acquired over a period of time, ending at the current time.

[0027] In the embodiments of this application, the electrical monitoring data includes at least one of the following: power, voltage, current, speed, and temperature.

[0028] S102: Perform cluster analysis on electrical monitoring data to obtain the current operating condition of the gas turbine generator.

[0029] For example, after standardizing the electrical monitoring data of the gas turbine generator, a preset clustering algorithm (e.g., K-Means clustering) is used to divide the standardized data into different clusters, and then the current operating condition is determined by matching the features of each cluster with the features corresponding to the preset operating conditions.

[0030] In one implementation, the above-mentioned cluster analysis of electrical monitoring data to obtain the current operating condition of the gas turbine generator may include the following steps: extracting features from the electrical monitoring data to obtain operating condition feature parameters; obtaining feature vectors based on the operating condition feature parameters; obtaining the distance between the feature vectors and multiple preset cluster centers; wherein each cluster center corresponds to an operating condition; and obtaining the current operating condition based on the distance between the feature vectors and each cluster center.

[0031] In the embodiments of this application, the above-mentioned operating conditions include at least one of the following: shutdown state, startup process, low load operation, high load operation, and shutdown.

[0032] For example, based on the preprocessed electrical monitoring data of the gas turbine generator, the active power sliding average, speed fluctuation coefficient, and load change rate are extracted as the current feature vector; a preset algorithm is used to cluster the historical feature data to obtain the cluster centers corresponding to different operating conditions; the distance between the current feature vector and each cluster center is calculated, and the operating condition category with the closest distance is taken as the target operating condition.

[0033] S103: Based on the data status characteristics of the current operating conditions and electrical monitoring data, obtain the current health index sequence of the gas turbine generator in the current time period.

[0034] For example, electrical monitoring data is processed to obtain data features that can reflect the status of the gas turbine generator equipment. These data features are then analyzed in conjunction with the current operating conditions to obtain the current health indicator sequence of the gas turbine generator in the current time period.

[0035] In the embodiments of this application, the above-mentioned data features include at least one of the following: effective vibration value, temperature difference, and current imbalance.

[0036] S104: Based on the current health indicator sequence, make predictions to obtain the predicted health indicator sequence for future periods.

[0037] For example, a pre-trained Long Short-Term Memory (LSTM) network is used to model and predict health indicator sequences to obtain predicted health indicator sequences for future periods.

[0038] In one embodiment of this application, historical health operation data can be extracted from the historical operation data of the gas turbine generator, and the historical health index sequence corresponding to the historical health operation data can be obtained. The historical health operation data and the corresponding historical health index sequence are used as sample data to train the long short-term memory network, and the mean squared error is used as the loss function for optimization during the training process.

[0039] S105: Based on the current health indicator sequence and the predicted health indicator sequence, perform condition monitoring on the gas turbine generator.

[0040] For example, a warning threshold, an alarm threshold, and an emergency alarm threshold are preset. If the current health indicator is lower than the warning threshold but higher than the alarm threshold, and the duration reaches a preset first duration, a yellow warning is triggered. If the current health indicator is lower than the alarm threshold but higher than the emergency threshold, and the duration reaches a preset second duration, an orange alarm is triggered, where the second duration is shorter than the first duration. If the current health indicator is lower than the emergency alarm threshold, a red emergency alarm is immediately triggered, and the on-duty personnel are notified in real time via SMS, telephone, or other communication methods.

[0041] In some embodiments, an interactive interface can be provided through terminal devices or other monitoring devices, and the interface can be visualized with corresponding colors to facilitate maintenance personnel to quickly identify and perform corresponding handling operations.

[0042] By implementing the embodiments of this application, the current operating condition of the gas turbine generator can be determined based on the electrical monitoring data of the gas turbine generator in the current time period. A health index sequence for the gas turbine generator can then be determined based on the current operating condition. A predicted health index sequence can then be predicted based on the current health index sequence. Finally, the condition of the gas turbine generator can be monitored based on both the current and predicted health index sequences. This improves the accuracy of health status monitoring of the gas turbine generator.

[0043] In some embodiments, a suitable neural network model can be selected based on the current operating conditions to obtain the current health indicator sequence. For example, please refer to [link to example]. Figure 2 , Figure 2 This is a flowchart illustrating another gas turbine generator condition monitoring method provided in an embodiment of this application. Figure 2 As shown, the method may include, but is not limited to, the following steps: S201: Obtain electrical monitoring data of the gas turbine generator during the current time period.

[0044] In the embodiments of this application, step S201 can be implemented in any of the ways described in the embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0045] S202: Perform cluster analysis on electrical monitoring data to obtain the current operating condition of the gas turbine generator.

[0046] In the embodiments of this application, step S202 can be implemented in any of the ways described in the embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0047] S203: Obtain the target health status assessment model corresponding to the current working condition from multiple candidate health status assessment models.

[0048] In the embodiments of this application, different candidate health status assessment models correspond to different working conditions, and each candidate health status assessment model is trained from the operating data of the corresponding working condition.

[0049] In the embodiments of this application, the above-mentioned health status assessment model can be a deep belief network (DBN).

[0050] For example, based on the pre-established one-to-one mapping relationship between working conditions and health status assessment models, a target health status assessment model that is suitable for the current working condition is matched from multiple candidate health status assessment models that have been pre-trained.

[0051] S204: Input electrical monitoring data into the target health status assessment model to obtain an initial health indicator sequence.

[0052] S205: Obtain the reconstruction error of the target health status assessment model.

[0053] For example, the numerical deviation between the original real-time features of the input target health status assessment model and the reconstructed features output by the model is obtained as the reconstruction error.

[0054] S206: Adjust the initial health indicator sequence based on the reconstruction error to obtain the current health indicator sequence.

[0055] For example, the initial health indicator sequence is adaptively adjusted according to a preset correction strategy based on the magnitude of the reconstruction error. For instance, the larger the reconstruction error, the greater the downward correction of the initial health indicators; the smaller the reconstruction error, the smaller the correction of the initial health indicator sequence; when the reconstruction error is within a preset normal range, no adjustment is made to the initial health indicator sequence.

[0056] S207: Based on the current health indicator sequence, make predictions to obtain the predicted health indicator sequence for future periods.

[0057] In the embodiments of this application, step S207 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not be described in detail.

[0058] S208: Based on the current health indicator sequence and the predicted health indicator sequence, perform condition monitoring on the gas turbine generator.

[0059] In the embodiments of this application, step S208 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not be described in detail.

[0060] By implementing the embodiments of this application, a target health status assessment model corresponding to the current operating condition can be obtained from multiple candidate health status assessment models. Based on the target health status assessment model, a predicted health indicator sequence for future periods can be obtained. Therefore, based on the current health indicator sequence and the predicted health indicator sequence, the condition of the gas turbine generator can be monitored. By matching the operating condition with the health status assessment model, the accuracy of gas turbine generator condition monitoring is improved.

[0061] In some embodiments, an early warning threshold can be set based on the current health indicator sequence to monitor the status based on the numerical relationship between the early warning threshold and the predicted health indicator sequence. For example, please refer to [link to example]. Figure 3 , Figure 3 This is a flowchart illustrating another gas turbine generator condition monitoring method provided in this application. Figure 3 As shown, the method may include, but is not limited to, the following steps: S301: Obtain electrical monitoring data of the gas turbine generator during the current time period.

[0062] In the embodiments of this application, step S301 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not be described in detail.

[0063] S302: Perform cluster analysis on electrical monitoring data to obtain the current operating condition of the gas turbine generator.

[0064] In the embodiments of this application, step S302 can be implemented in any of the ways described in the embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0065] S303: Based on the data status characteristics of the current operating conditions and electrical monitoring data, obtain the current health index sequence of the gas turbine generator in the current time period.

[0066] In the embodiments of this application, step S303 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not be described in detail.

[0067] S304: Based on the current health indicator sequence, make predictions to obtain the predicted health indicator sequence for future periods.

[0068] In the embodiments of this application, step S304 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not be described in detail.

[0069] S305: Obtain the statistical characteristics of the current health indicator sequence.

[0070] In the embodiments of this application, the statistical characteristics of the current health indicator sequence include at least one of the following: mean and standard deviation.

[0071] S306: Set at least one level of early warning threshold based on statistical characteristics.

[0072] For example, taking statistical characteristics including mean and standard deviation as an example, a two-level warning threshold, including a first warning threshold and a second warning threshold, can be set based on the mean and standard deviation. The first-level warning threshold can be expressed as: P1=μ k1σ The second-level warning threshold can be expressed as: P2=μ k2σ Where P1 is the first-level warning threshold, P2 is the second-level warning threshold, μ is the mean, σ is the standard deviation, k1 and k2 are calculation coefficients, and k2 > k1 > 0.

[0073] S307: Monitor the condition of gas turbine generators based on predicted health indicator sequences and at least a first-level early warning threshold.

[0074] For example, the predicted health indicator sequence is compared one by one with the first-level warning threshold and the second-level warning threshold. When the predicted health indicator at any time is lower than the first-level warning threshold but higher than the second-level warning threshold, the first-level warning is triggered. When the predicted indicator is lower than the second-level warning threshold, the second-level warning is triggered.

[0075] In one alternative implementation, the changing trend of the predicted health indicator sequence can also be obtained, and a deterioration warning can be issued if the predicted health indicator continues to decline.

[0076] By implementing the embodiments of this application, at least one early warning threshold can be set based on the health indicator sequence for the current time period. Based on the predicted health indicator sequence and the at least one early warning threshold, the state of the gas turbine generator at future times can be predicted, thereby ensuring the continuous and stable operation of the gas turbine generator.

[0077] In some embodiments, the predicted lifespan of a gas turbine generator can be monitored using both the current health indicator sequence and the predicted health indicator sequence. As an example, please refer to... Figure 4 , Figure 4 This is a flowchart illustrating another gas turbine generator condition monitoring method provided in this application. Figure 4 As shown, the method may include, but is not limited to, the following steps: S401: Obtain electrical monitoring data of the gas turbine generator during the current time period.

[0078] In the embodiments of this application, step S401 can be implemented in any of the ways described in the embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0079] S402: Perform cluster analysis on electrical monitoring data to obtain the current operating condition of the gas turbine generator.

[0080] In the embodiments of this application, step S402 can be implemented in any of the ways described in the embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0081] S403: Based on the data status characteristics of the current operating conditions and electrical monitoring data, obtain the current health index sequence of the gas turbine generator in the current time period.

[0082] In the embodiments of this application, step S403 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not be described in detail.

[0083] S404: Based on the current health indicator sequence, make predictions to obtain the predicted health indicator sequence for future periods.

[0084] In the embodiments of this application, step S404 can be implemented in any of the ways described in the embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0085] S405: Perform risk mapping based on the current health indicator sequence to obtain the fault risk function.

[0086] For example, the Weibull proportional hazards model is used, with the current health indicator sequence as the core input variable, so as to quantify and map the health indicator values ​​into failure risk probabilities, thereby obtaining the failure risk function of the gas turbine generator.

[0087] S406: Based on the fault risk function and the predicted health indicator sequence, predict the critical time of risk.

[0088] For example, the predicted health indicators at each time point are substituted into the fault risk function to calculate the corresponding cumulative fault risk probability. When the cumulative fault risk probability reaches the preset critical value, that time point is the predicted risk critical time.

[0089] S407: Obtain equipment life prediction values ​​based on risk criticality time.

[0090] For example, the time difference between the current moment and the risk critical time is calculated and used as the predicted value of the remaining service life of the gas turbine generator.

[0091] S408: Determine the current status of the gas turbine generator based on the current health indicator sequence and equipment life prediction values.

[0092] For example, by comprehensively analyzing the current health indicator values ​​and the remaining service life, and based on preset grading rules, the equipment status of the gas turbine generator is divided into four levels: normal, attention, warning, and danger, thereby determining the current specific operating status of the equipment.

[0093] By implementing the embodiments of this application, risk mapping can be performed based on the current health indicator sequence to obtain a fault risk function. Then, based on the fault risk function and the predicted health indicator sequence, a predicted equipment lifespan value can be obtained. This allows for the determination of the current state of the gas turbine generator based on the current health indicator sequence and the predicted equipment lifespan value. This enables the prediction of the gas turbine generator's lifespan.

[0094] In some embodiments, the above method may further include the following steps: A1: Obtain the anomaly scoring model corresponding to the current working condition.

[0095] In the embodiments of this application, the above-mentioned anomaly scoring model can be a pre-trained isolated forest model.

[0096] In some embodiments, historical electrical monitoring data of different operating conditions under the healthy state of the gas turbine generator can be acquired, and the electrical monitoring data of each operating condition can be cleaned. For each operating condition, adaptation parameters such as the number of isolated trees in the isolated forest, the number of samples per tree, and the contamination rate can be set, and the above-mentioned historical electrical monitoring data corresponding to the operating condition can be used for unsupervised independent training to obtain the anomaly scoring model corresponding to the operating condition.

[0097] A2: Input electrical monitoring data into the anomaly scoring model to obtain the basic anomaly scores for each time period within the current time period.

[0098] A3: Perform a sliding window analysis on the basic anomaly scores at each time point within the current time period to obtain the corresponding weight values ​​at each time point within the current time period.

[0099] For example, based on a preset fixed sliding window length, the electrical monitoring data for the current time period is analyzed segment by segment. For the basic anomaly score within each sliding window, it is determined whether there are continuous multi-frame data fluctuations or single-point instantaneous changes. If there are continuous multi-frame data fluctuations, the weights corresponding to each time point of the data fluctuation are increased; if there is a single-point instantaneous change, only the weights corresponding to the time point of the change are increased, thereby obtaining the weight values ​​corresponding to each time point within the current time period.

[0100] A4: The basic anomaly scores are weighted based on the weight values ​​to obtain the comprehensive anomaly index for each moment in the current period.

[0101] A5: Determine the time of data anomalies within the current period based on the comprehensive anomaly index.

[0102] For example, if the comprehensive anomaly index at a certain moment is greater than or equal to a preset index threshold, then that moment is considered a data anomaly moment.

[0103] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a gas turbine generator condition monitoring device provided in an embodiment of this application. Figure 5 As shown, the device 500 includes: an acquisition module 501 for acquiring electrical monitoring data of a gas turbine generator in the current time period; a first processing module 502 for performing cluster analysis on the electrical monitoring data to obtain the current operating condition of the gas turbine generator; a second processing module 503 for acquiring the current health indicator sequence of the gas turbine generator in the current time period based on the data state characteristics of the current operating condition and the electrical monitoring data; a third processing module 504 for making predictions based on the current health indicator sequence to obtain a predicted health indicator sequence for future time periods; and a fourth processing module 505 for monitoring the status of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence.

[0104] In one implementation, the first processing module 502 can be used to: extract features from electrical monitoring data to obtain operating condition feature parameters; obtain feature vectors based on the operating condition feature parameters; obtain the distance between the feature vectors and multiple preset cluster centers; wherein each cluster center corresponds to an operating condition; and obtain the current operating condition based on the distance between the feature vectors and each cluster center.

[0105] In one implementation, the second processing module 503 can be used to: obtain the target health status assessment model corresponding to the current operating condition from multiple candidate health status assessment models; wherein different candidate health status assessment models correspond to different operating conditions, and each candidate health status assessment model is trained from the operating data of the corresponding operating condition; input electrical monitoring data into the target health status assessment model to obtain an initial health indicator sequence; obtain the reconstruction error of the target health status assessment model; and adjust the initial health indicator sequence based on the reconstruction error to obtain the current health indicator sequence.

[0106] In one implementation, the fourth processing module 505 can be used to: acquire the statistical characteristics of the current health indicator sequence; set at least one level early warning threshold based on the statistical characteristics; and perform status monitoring on the gas turbine generator based on the predicted health indicator sequence and the at least one level early warning threshold.

[0107] In one implementation, the fourth processing module 505 can be used to: perform risk mapping based on the current health indicator sequence to obtain a fault risk function; predict the risk critical time based on the fault risk function and the predicted health indicator sequence; obtain the equipment life prediction value based on the risk critical time; and determine the current state of the gas turbine generator based on the current health indicator sequence and the equipment life prediction value.

[0108] In one implementation, the above-described apparatus further includes a fifth processing module. As an example, please refer to... Figure 6 , Figure 6 This is a schematic diagram of another gas turbine generator condition monitoring device provided in an embodiment of this application. Figure 6 As shown, the device 600 also includes a fifth processing module 606, which can be used to: acquire the anomaly scoring model corresponding to the current operating condition; input electrical monitoring data into the anomaly scoring model to obtain the basic anomaly scores at each time point within the current time period; perform sliding window analysis on the basic anomaly scores at each time point within the current time period to obtain the weight values ​​corresponding to each time point within the current time period; perform weighted processing on the basic anomaly scores based on the weight values ​​to obtain the comprehensive anomaly index at each time point within the current time period; and determine the data anomaly time within the current time period based on the comprehensive anomaly index. Among these, Figure 6 Modules 601-605 in Figure 5 Modules 501-505 in the series have the same structure and function.

[0109] The apparatus of this application embodiment can determine the current operating condition of the gas turbine generator based on electrical monitoring data of the gas turbine generator in the current time period, and then determine a health index sequence of the gas turbine generator based on the current operating condition. A predicted health index sequence is then predicted based on the current health index sequence, and the gas turbine generator's condition is monitored based on both the current and predicted health index sequences. This improves the accuracy of health status monitoring of the gas turbine generator.

[0110] It should be noted that the foregoing explanation of the gas turbine generator condition monitoring method embodiment also applies to the gas turbine generator condition monitoring device of this embodiment, and will not be repeated here.

[0111] To implement the above embodiments, this application also proposes an electronic device. Please see [link to relevant documentation]. Figure 7 , Figure 7 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 7 As shown, the electronic device 700 includes: a processor 701 and a memory 702 communicatively connected to the processor 701; the memory 702 stores computer execution instructions; the processor 701 executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0112] To implement the above embodiments, this application also proposes a storage medium storing instructions that, when executed on an electronic device, cause the electronic device to perform the methods provided in the foregoing embodiments.

[0113] To implement the above embodiments, this application also proposes a program product, including at least one of a program and instructions, wherein when the program and instructions are executed by an electronic device, they implement the steps of the method provided in the foregoing embodiments.

[0114] It should be noted that the acquisition, transmission, storage, use, and processing of data in this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0115] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0116] It is worth noting that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0117] In the description of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document is merely a description of the relationship between related objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone.

[0118] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0119] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0120] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0121] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0122] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0123] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0124] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0125] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for monitoring the condition of a gas turbine generator, characterized in that, include: Acquire electrical monitoring data of the gas turbine generator for the current time period; Cluster analysis is performed on the electrical monitoring data to obtain the current operating condition of the gas turbine generator; Based on the current operating conditions and the data status characteristics of the electrical monitoring data, the current health index sequence of the gas turbine generator in the current time period is obtained; Based on the current health indicator sequence, a predicted health indicator sequence for the future period is obtained. The gas turbine generator is monitored for its condition based on the current health indicator sequence and the predicted health indicator sequence.

2. The method according to claim 1, characterized in that, The step of performing cluster analysis on the electrical monitoring data to obtain the current operating condition of the gas turbine generator includes: Feature extraction is performed on the electrical monitoring data to obtain operating condition characteristic parameters; The feature vector is obtained based on the aforementioned operating condition characteristic parameters; Obtain the distance between the feature vector and a plurality of preset cluster centers; wherein each cluster center corresponds to a working condition; The current operating condition is obtained based on the distance between the feature vector and each of the cluster centers.

3. The method according to claim 1, characterized in that, The process of obtaining the current health indicator sequence of the gas turbine generator within the current time period based on the data status characteristics of the current operating conditions and the electrical monitoring data includes: From multiple candidate health status assessment models, the target health status assessment model corresponding to the current working condition is obtained; wherein, different candidate health status assessment models correspond to different working conditions, and each candidate health status assessment model is trained by the operating data of the corresponding working condition; The electrical monitoring data is input into the target health status assessment model to obtain an initial health indicator sequence; Obtain the reconstruction error of the target health status assessment model; The initial health indicator sequence is adjusted based on the reconstruction error to obtain the current health indicator sequence.

4. The method according to claim 1, characterized in that, The condition monitoring of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence includes: Obtain the statistical characteristics of the current health indicator sequence; At least one level of early warning threshold shall be set based on the aforementioned statistical characteristics; The gas turbine generator is monitored for its condition based on the predicted health indicator sequence and the at least one level early warning threshold.

5. The method according to claim 1, characterized in that, The condition monitoring of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence includes: Based on the current health indicator sequence, a risk mapping is performed to obtain a fault risk function; Based on the fault risk function and the predicted health indicator sequence, the risk critical time is predicted and obtained. Based on the aforementioned risk critical time, the predicted equipment lifespan is obtained; The current state of the gas turbine generator is determined based on the current health indicator sequence and the equipment life prediction value.

6. The method according to claim 1, characterized in that, The method further includes: Obtain the anomaly scoring model corresponding to the current operating condition; The electrical monitoring data is input into the anomaly scoring model to obtain the basic anomaly score for each moment within the current time period. A sliding window analysis is performed on the basic anomaly scores at each time point within the current time period to obtain the weight values ​​corresponding to each time point within the current time period. The basic anomaly score is weighted based on the weight value to obtain the comprehensive anomaly index for each moment in the current time period. The data anomaly moments within the current time period are determined based on the comprehensive anomaly index.

7. A gas turbine generator condition monitoring device, characterized in that, include: The acquisition module is used to acquire electrical monitoring data of the gas turbine generator during the current time period; The first processing module is used to perform cluster analysis on the electrical monitoring data to obtain the current operating condition of the gas turbine generator; The second processing module is used to obtain the current health index sequence of the gas turbine generator in the current time period based on the current operating conditions and the data status characteristics of the electrical monitoring data; The third processing module is used to make predictions based on the current health indicator sequence to obtain a predicted health indicator sequence for future periods. The fourth processing module is used to monitor the condition of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

9. A storage medium storing instructions, characterized in that, When the instructions are executed on an electronic device, the electronic device causes the electronic device to perform the method of any one of claims 1 to 6.

10. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the program or instructions is executed by an electronic device, it implements the steps of the method according to any one of claims 1 to 6.

Images