Corrosion assessment method and device for offshore booster station transformer

Abstract

The invention provides a corrosion evaluation method and device for a transformer of an offshore booster station, and relates to the technical field of transformer detection of the offshore booster station. The method comprises the following steps: carrying out data fusion on data of a plurality of sensors of a transformer to obtain an n * m fusion data matrix; performing feature extraction on each sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each sensor; and determining the corrosion risk category of the transformer according to the sensor feature vector corresponding to each sensor and the reference sensor feature vectors of the plurality of corrosion risk categories. According to the invention, data fusion is carried out on multiple sensor data, feature extraction is carried out based on the fused data matrix, and potential association relationships among different sensor data are mined. And the corrosion risk category of the transformer is determined by integrating the preliminary assessment of the corrosion risk by the feature vector of each sensor, so that the corrosion risk of the offshore booster station transformer can be assessed more comprehensively and accurately.

Description

Technical Field

[0001] The present disclosure relates to the technical field of transformer detection for offshore booster stations, and in particular to a corrosion assessment method and device for offshore booster station transformers. Background Art

[0002] Offshore booster stations are facilities built in the ocean to increase the voltage of electricity such as wind power generation. The environment in which the transformers in offshore booster stations are located is characterized by high humidity, high salt fog, strong winds, etc. Therefore, the transformers are susceptible to corrosion in the harsh marine environment, which poses a serious threat to the safe operation and service life of the transformers. Traditional single sensor monitoring methods, such as using only humidity sensors or gas sensors, cannot fully reflect the complex conditions of the corrosive environment. Some multi-sensor monitoring systems have problems with simple data fusion and poor coordination, making it difficult to give full play to the advantages of multiple sensors. Summary of the invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, the first embodiment of the present disclosure proposes a corrosion assessment method for an offshore booster station transformer, comprising the following steps:

[0005] Acquire multiple sensor data of the transformer based on multiple sensors;

[0006] Performing data fusion on the multiple sensor data to obtain an n×m fusion data matrix; wherein n is the number of sensors, and m is the number of sampling points of each sensor data;

[0007] Perform feature extraction on each of the sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each of the sensors;

[0008] The corrosion risk category of the transformer is determined according to the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of each of the plurality of corrosion risk categories.

[0009] In some embodiments of the present disclosure, feature extraction is performed on each of the sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each of the sensors, including: determining the Pearson correlation coefficient between different sensors according to the fusion data matrix; determining the covariance matrix of the fusion data matrix according to the Pearson correlation coefficient; and calculating the eigenvector of the covariance matrix to obtain a sensor feature vector corresponding to each of the sensors.

[0010] In some embodiments of the present disclosure, determining the corrosion risk category of the transformer based on the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of each of the corrosion risk categories includes: determining the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of each of the corrosion risk categories; determining the corrosion risk category of the transformer based on the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of each of the corrosion risk categories.

[0011] In some embodiments of the present disclosure, the corrosion risk category of the transformer is determined based on the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of the multiple corrosion risk categories, including: for each of the sensor feature vectors, determining the corrosion risk category identification data of the sensor feature vector based on the corrosion risk category corresponding to the reference sensor feature vector having the smallest distance to the sensor feature vector; performing weighted sum processing on the corrosion risk category identification data of each of the multiple sensor feature vectors to obtain first corrosion risk category identification data; comparing the first corrosion risk category identification data with the identification data ranges corresponding to each of the multiple corrosion risk categories, and determining the corrosion risk category corresponding to the identification data range within which the first corrosion risk category identification data falls as the corrosion risk category of the transformer.

[0012] The second aspect of the present disclosure provides a corrosion assessment device for an offshore booster station transformer, comprising:

[0013] A first acquisition module, configured to acquire a plurality of sensor data of the transformer based on a plurality of sensors;

[0014] A second acquisition module is used to perform data fusion on the multiple sensor data to obtain an n×m fusion data matrix; wherein n is the number of sensors, and m is the number of sampling points of each sensor data;

[0015] A third acquisition module is used to extract features from each of the sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each of the sensors;

[0016] The determination module is used to determine the corrosion risk category of the transformer according to the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of each of the multiple corrosion risk categories.

[0017] In some embodiments of the present disclosure, the third acquisition module is specifically used to: determine the Pearson correlation coefficient between different sensors based on the fusion data matrix; determine the covariance matrix of the fusion data matrix based on the Pearson correlation coefficient; calculate the eigenvector of the covariance matrix to obtain the sensor eigenvector corresponding to each sensor.

[0018] In some embodiments of the present disclosure, the determination module is specifically used to: determine the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of the multiple corrosion risk categories; determine the corrosion risk category of the transformer based on the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of the multiple corrosion risk categories.

[0019] In some embodiments of the present disclosure, the determination module is specifically used to: for each of the sensor feature vectors, determine the corrosion risk category identification data of the sensor feature vector according to the corrosion risk category corresponding to the reference sensor feature vector having the smallest distance to the sensor feature vector; perform weighted sum processing on the corrosion risk category identification data of each of the multiple sensor feature vectors to obtain first corrosion risk category identification data; compare the first corrosion risk category identification data with the identification data ranges corresponding to each of the multiple corrosion risk categories, and determine the corrosion risk category corresponding to the identification data range within which the first corrosion risk category identification data falls as the corrosion risk category of the transformer.

[0020] A third aspect of the present disclosure provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0021] The memory stores computer-executable instructions;

[0022] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0023] The fourth aspect of the present disclosure provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0024] The corrosion assessment method for offshore substation transformers provided by the present disclosure is based on the cooperation and collaboration of multiple sensors to jointly conduct real-time and continuous observation and data collection of offshore substation transformers, perform data fusion on multiple sensor data, perform feature extraction based on the fused data matrix, and mine the potential correlation between different sensor data. By combining the preliminary assessment of the corrosion risk of each sensor feature vector and determining the corrosion risk category of the transformer, the corrosion risk of the offshore substation transformer can be assessed more comprehensively and accurately.

[0025] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] Figure 1 A schematic flow chart of a corrosion assessment method for an offshore booster station transformer provided by an embodiment of the present disclosure;

[0028] Figure 2 A schematic diagram of a corrosion assessment device for an offshore booster station transformer provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] Embodiments of the present disclosure are described in detail below, examples of which 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 disclosure, and should not be construed as limiting the present disclosure.

[0030] Specifically, the corrosion assessment method and device for offshore booster station transformer according to the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0031] Figure 1 The present invention provides a flow chart of a corrosion assessment method for an offshore booster station transformer provided by an embodiment of the present invention. Figure 1 As shown, the corrosion assessment method for offshore substation transformer may include the following steps:

[0032] Step 101: Acquire multiple sensor data of a transformer based on multiple sensors.

[0033] Optionally, in the embodiment of the present disclosure, the sensors may include gas sensors, humidity sensors, temperature sensors, electrochemical sensors and image sensors, and the setting positions of multiple sensors may also be optimized to comprehensively reflect the environmental information of the offshore substation transformer.

[0034] Among them, the gas sensor is used to detect the concentration of corrosive gases such as hydrogen sulfide (HS), sulfur dioxide (SO), and hydrogen chloride (HCl) in the environment where the transformer is located. It can be based on the gas diffusion model (Fick's law where J is the diffusion flux, D is the diffusion coefficient, C is the gas concentration, and x is the position) to determine the optimal installation position of the gas sensor on the transformer housing, especially at the sealing interface, valve accessories, etc. where gas leakage and accumulation are prone to occur.

[0035] Humidity sensor: measures the humidity of the environment where the transformer is located.

[0036] Temperature sensor: monitors the ambient temperature of the transformer and the operating temperature of the transformer. Through heat exchange analysis (heat exchange formula Q = hAΔT, where Q is the heat exchange amount, h is the heat transfer coefficient, A is the heat transfer area, and ΔT is the temperature difference), the locations around the transformer where there may be large temperature differences and humidity changes can be optimized, such as heat sinks and vents, to ensure comprehensive perception of environmental conditions.

[0037] Electrochemical sensor: measures the electrochemical parameters of transformer metal parts, such as potential, current, etc. Electrochemical sensors can be directly installed on the surface of metal parts of transformers. Where J is current density, I is current, and A is cross-sectional area) or on the surface of metal parts susceptible to electrochemical corrosion to increase the density of electrochemical sensors.

[0038] Image sensor: Capture the appearance image of the transformer to observe signs of surface corrosion, such as rust spots, coating peeling, etc. It should be noted that the sensor data collected by the image sensor can be the brightness value of multiple pixels in the appearance image. The image sensor can be set at multiple angles such as horizontal, vertical and tilted to obtain a comprehensive image of the transformer appearance.

[0039] In some embodiments of the present disclosure, multiple sensors collect data at a set frequency, transmit the data to a data processing center in real time through wired or wireless communication, and use a reliable communication protocol to ensure the accuracy and integrity of the data. A time synchronization mechanism and coordination sequence are established, and each sensor works together according to a predetermined time and sequence to avoid conflicts and omissions in data collection.

[0040] Step 102: perform data fusion on the data of multiple sensors to obtain an n×m fusion data matrix, where n is the number of sensors and m is the number of sampling points of each sensor data.

[0041] It should be noted that the multiple sensor data are obtained by preprocessing the collected raw data. Assume that the raw data collected by n sensors are X1, X2, ..., X n , where the raw data collected by the i-th sensor is Xˊ i ={xˊ i1 ,xˊ i2 ,…,xˊ im}. m is the number of sampling points. The original data is processed for missing values ​​by using methods such as mean filling and linear difference, and the data after missing value filling is processed by Z-score standardization to obtain the i-th sensor data X i ={x i1 ,x i2 ,…,x im}. Perform data-level fusion on multiple sensor data to obtain an n×m fusion data matrix Where n is the number of sensors, and m is the number of sampling points of each sensor data.

[0042] Since the fused data matrix includes multiple sensor data, feature extraction of the fused data matrix can reflect the relationship between different sensor dimensions. By observing the size of the correlation coefficient and the degree of deviation between the data points in the fused data matrix and the mean, and analyzing the data, the following conclusions can be verified:

[0043] (1) Data from different gas sensors can complement each other. High concentrations of HS may indicate that severe corrosion is occurring, while low concentrations of SO detected at the same time may indicate a different type or source of corrosion.

[0044] (2) Humidity data combined with data from gas sensors can more accurately determine the possibility and severity of corrosion. In conditions of high humidity and the presence of corrosive gases, the risk of corrosion increases significantly.

[0045] (3) High temperature and high humidity environment, coupled with the presence of corrosive gases, means a very high risk of corrosion. Combining environmental parameters such as gas, humidity and temperature can provide a deeper understanding of the mechanism and progression of corrosion.

[0046] (4) Combined with quantitative data from other sensors, it provides intuitive evidence for corrosion assessment. The severe rust spots observed in the image correspond to high concentrations of corrosive gases and adverse environmental conditions, which can more conclusively indicate the severity of corrosion.

[0047] Step 103 , extracting features from each sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each sensor.

[0048] In some embodiments of the present disclosure, the Pearson correlation coefficient between different sensors can be determined based on the fusion data matrix. Determine the covariance matrix of the fused data matrix based on the Pearson correlation coefficient Calculate the eigenvalues ​​and eigenvectors of the covariance matrix, extract the principal components, and obtain the sensor eigenvector F corresponding to each sensor i ={f i1 ,f i2 ,…,f ik}. The sensor feature vector F i The relationship between the sensor data of the i-th sensor and the multiple sensor data can be indicated.

[0049] Step 104: Determine the corrosion risk category of the transformer according to the sensor feature vector corresponding to each sensor and the reference sensor feature vectors of each of the multiple corrosion risk categories.

[0050] It should be noted that the reference sensor feature vectors of the multiple corrosion risk categories are determined based on a large amount of multi-sensor historical data. The multi-sensor historical data has the same sensor type and sensor quantity as the multi-sensor data. In one implementation, the multi-sensor historical data can be operated from step 101 to step 103, and feature fusion and feature extraction can be performed on the multi-sensor historical data to obtain the corresponding historical sensor feature vectors. The historical sensor feature vectors are classified by identifying the hidden patterns or rules in the data through classification algorithms, pattern recognition, clustering algorithms, etc., and the corrosion risk categories of each type are determined based on the actual corrosion risk corresponding to the multi-sensor historical data, such as normal corrosion risk, mild corrosion risk, moderate corrosion risk, and severe corrosion risk, and the correlation between the specific transformer environmental conditions and the corrosion risk categories is established.

[0051] Alternatively, a linear discriminant analysis method can be used to find the projection direction ω, which maximizes the variance of different categories after projection, and then perform classification analysis. The projection direction can be obtained by solving the following optimization problem: Where SB is the between-class scatter matrix and SW is the within-class scatter matrix.

[0052] After classifying the historical sensor feature vectors and dividing them into corrosion risk categories, the center point of the historical sensor feature vector in each corrosion risk category can be determined as the reference sensor feature vector of each corrosion risk category.

[0053] Optionally, in some embodiments of the present disclosure, the distance between each sensor feature vector and the reference sensor feature vectors of the respective corrosion risk categories can be calculated. The corrosion risk category of the transformer is determined by the distance between the sensor feature vector corresponding to each sensor and the reference sensor feature vectors of the respective corrosion risk categories. If the corrosion risk category is a preset alarm category, the transformer can be warned, and then corresponding protective measures, maintenance actions or further monitoring strategies can be taken according to the corrosion risk category of the transformer.

[0054] In a possible implementation, for each sensor feature vector, the corrosion risk category identification data of the sensor feature vector is determined according to the corrosion risk category corresponding to the reference sensor feature vector with the smallest distance from the sensor feature vector. The corrosion risk category identification data of each of the multiple sensor feature vectors are weighted summed to obtain the first corrosion risk category identification data. That is, the sensor feature vector of each sensor first independently makes a preliminary assessment of the corrosion risk, and the corrosion risks of multiple sensors are fused at the decision level to obtain the corrosion risk assessment result of the transformer. The first corrosion risk category identification data is compared with the identification data ranges corresponding to each of the multiple corrosion risk categories, and the corrosion risk category corresponding to the identification data range into which the first corrosion risk category identification data falls is determined as the corrosion risk category of the transformer.

[0055] Among them, different corrosion risk categories correspond to different corrosion risk category identification data, and different corrosion risk categories correspond to different identification data ranges. The corrosion risk category identification data is used to determine the corrosion risk category corresponding to each sensor feature vector, and the identification data range is used to determine the corrosion risk category of the transformer according to the first corrosion risk category identification data. For example, the higher the corrosion risk, the larger the corrosion risk category identification data corresponding to the corrosion risk category, and the larger the value in the identification data range. Assuming that the corrosion risk categories include normal corrosion risk, mild corrosion risk, moderate corrosion risk, and severe corrosion risk, the corrosion risk category identification data of normal corrosion risk, mild corrosion risk, moderate corrosion risk, and severe corrosion risk can be set to 0, 1, 2, and 3 respectively, and the same applies to the identification data range.

[0056] As an example, for a certain sensor feature vector, among the distances to the reference sensor feature vectors of multiple corrosion risk categories, the distance between the sensor feature vector and the reference sensor feature vector corresponding to the moderate corrosion risk is the smallest, and the corrosion risk category identification data of the sensor feature vector can be determined to be 2. Thus, the corrosion risk category identification data of each sensor feature vector is obtained, and then the weighted summation of the corrosion risk category identification data of each of the multiple sensor feature vectors can be performed based on the weight of each sensor through the following formula to obtain the first corrosion risk category identification data:

[0057]

[0058] Where F is the first corrosion risk category identification data, n is the number of sensors, ω i is the weight of the i-th sensor, S i is the corrosion risk category identification data of the i-th sensor. Optionally, the weight of each sensor can be set to the same value, or can be set according to actual conditions. For example, in the corrosion monitoring of the metal material part of the transformer, more attention is paid to the influence of humidity on the corrosion risk, and the weight of the humidity sensor can be increased.

[0059] By implementing the disclosed embodiments, multiple sensors cooperate with each other to jointly conduct real-time and continuous observation and data collection of offshore substation transformers, perform data fusion on multiple sensor data, perform feature extraction based on the fused data matrix, and explore the potential correlation between different sensor data. By combining the preliminary assessment of the corrosion risk of each sensor feature vector and determining the corrosion risk category of the transformer, the corrosion risk of the offshore substation transformer can be assessed more comprehensively and accurately.

[0060] Figure 2 Schematic diagram of a corrosion assessment device for an offshore booster station transformer provided by an embodiment of the present disclosure. Figure 2 As shown, the corrosion assessment device for offshore booster station transformer includes: a first acquisition module 201 , a second acquisition module 202 , a third acquisition module 203 and a determination module 204 .

[0061] Among them, the first acquisition module 201 is used to obtain multiple sensor data of the transformer based on multiple sensors.

[0062] The second acquisition module 202 is used to perform data fusion on multiple sensor data to obtain an n×m fusion data matrix, where n is the number of sensors and m is the number of sampling points of each sensor data.

[0063] The third acquisition module 203 is used to extract features from each sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each sensor.

[0064] The determination module 204 is used to determine the corrosion risk category of the transformer according to the sensor feature vector corresponding to each sensor and the reference sensor feature vectors of each of the multiple corrosion risk categories.

[0065] In some embodiments of the present disclosure, the third acquisition module 203 is specifically used to: determine the Pearson correlation coefficient between different sensors based on the fused data matrix; determine the covariance matrix of the fused data matrix based on the Pearson correlation coefficient; calculate the eigenvector of the covariance matrix to obtain the sensor eigenvector corresponding to each sensor.

[0066] In some embodiments of the present disclosure, the determination module 204 is specifically used to: determine the distance between the sensor feature vector corresponding to each sensor and the reference sensor feature vectors of multiple corrosion risk categories; determine the corrosion risk category of the transformer based on the distance between the sensor feature vector corresponding to each sensor and the reference sensor feature vectors of multiple corrosion risk categories.

[0067] In some embodiments of the present disclosure, the determination module 204 is specifically used to: for each sensor feature vector, determine the corrosion risk category identification data of the sensor feature vector according to the corrosion risk category corresponding to the reference sensor feature vector having the smallest distance to the sensor feature vector; perform weighted sum processing on the corrosion risk category identification data of each of the multiple sensor feature vectors to obtain first corrosion risk category identification data; compare the first corrosion risk category identification data with the identification data ranges corresponding to each of the multiple corrosion risk categories, and determine the corrosion risk category corresponding to the identification data range within which the first corrosion risk category identification data falls as the corrosion risk category of the transformer.

[0068] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0069] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0070] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0071] In order to implement the above embodiments, the present disclosure also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0072] In the description of the aforementioned embodiments, 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 disclosure. 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 more 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, unless they are contradictory.

[0073] 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 the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0074] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional 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 disclosure belong.

[0075] 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 the 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 more wires (electronic device), 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, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0076] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: 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.

[0077] 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.

[0078] In addition, each functional unit in each embodiment of the present disclosure 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.

[0079] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. A corrosion assessment method for offshore booster station transformer, characterized in that: The following steps are involved: Acquire multiple sensor data of the transformer based on multiple sensors; Performing data fusion on the multiple sensor data to obtain an n×m fusion data matrix; wherein n is the number of sensors, and m is the number of sampling points of each sensor data; Perform feature extraction on each of the sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each of the sensors; The corrosion risk category of the transformer is determined according to the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of each of the plurality of corrosion risk categories.

2. The method according to claim 1, characterized in that The step of extracting features from each sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each sensor includes: Determine the Pearson correlation coefficient between different sensors according to the fused data matrix; Determine the covariance matrix of the fused data matrix according to the Pearson correlation coefficient; The eigenvector of the covariance matrix is ​​calculated to obtain a sensor eigenvector corresponding to each of the sensors.

3. The method according to claim 1, characterized in that: The step of determining the corrosion risk category of the transformer according to the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of the respective corrosion risk categories includes: determining a distance between a sensor feature vector corresponding to each of the sensors and a reference sensor feature vector of each of the plurality of corrosion risk categories; The corrosion risk category of the transformer is determined according to the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of the multiple corrosion risk categories.

4. The method according to claim 3, characterized in that The step of determining the corrosion risk category of the transformer according to the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of the plurality of corrosion risk categories includes: For each of the sensor feature vectors, determining the corrosion risk category identification data of the sensor feature vector according to the corrosion risk category corresponding to the reference sensor feature vector having the smallest distance to the sensor feature vector; Performing weighted sum processing on the corrosion risk category identification data of each of the plurality of sensor feature vectors to obtain first corrosion risk category identification data; The first corrosion risk category identification data is compared with the identification data ranges corresponding to each of the multiple corrosion risk categories, and the corrosion risk category corresponding to the identification data range within which the first corrosion risk category identification data falls is determined as the corrosion risk category of the transformer.

5. A corrosion assessment device for offshore booster station transformer, characterized in that: include: A first acquisition module, configured to acquire a plurality of sensor data of the transformer based on a plurality of sensors; A second acquisition module is used to perform data fusion on the multiple sensor data to obtain an n×m fusion data matrix; wherein n is the number of sensors, and m is the number of sampling points of each sensor data; A third acquisition module is used to extract features from each of the sensor data according to the fusion data matrix to obtain a sensor feature vector corresponding to each of the sensors; The determination module is used to determine the corrosion risk category of the transformer according to the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of each of the multiple corrosion risk categories.

6. The device according to claim 5, characterized in that The third acquisition module is specifically used for: Determine the Pearson correlation coefficient between different sensors according to the fused data matrix; Determine the covariance matrix of the fused data matrix according to the Pearson correlation coefficient; The eigenvector of the covariance matrix is ​​calculated to obtain a sensor eigenvector corresponding to each of the sensors.

7. The device according to claim 5, characterized in that The determination module is specifically used for: determining a distance between a sensor feature vector corresponding to each of the sensors and a reference sensor feature vector of each of the plurality of corrosion risk categories; The corrosion risk category of the transformer is determined according to the distance between the sensor feature vector corresponding to each of the sensors and the reference sensor feature vectors of the multiple corrosion risk categories.

8. The device according to claim 7, characterized in that The determination module is specifically used for: For each of the sensor feature vectors, determining the corrosion risk category identification data of the sensor feature vector according to the corrosion risk category corresponding to the reference sensor feature vector having the smallest distance to the sensor feature vector; Performing weighted sum processing on the corrosion risk category identification data of each of the plurality of sensor feature vectors to obtain first corrosion risk category identification data; The first corrosion risk category identification data is compared with the identification data ranges corresponding to each of the multiple corrosion risk categories, and the corrosion risk category corresponding to the identification data range within which the first corrosion risk category identification data falls is determined as the corrosion risk category of the transformer.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 4 when executed by a processor.

Images