Method, device and equipment for evaluating state of transformer through subjective and objective combination
By combining power user feedback and objective evaluation, the subjective and objective evaluation score of the transformer is calculated, which solves the problem of inaccurate judgment in the existing technology, and achieves a more accurate and efficient transformer status evaluation.
Patent Information
- Application Number
- CN202410970635.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-12
AI Technical Summary
The prior art relies too much on manual experience when judging the transformer state, resulting in inaccurate and one-sided judgments, and is unable to take into account both the technical specifications and the subjective perspective of electricity users.
By obtaining feedback information from electricity users and objective evaluation scores, combining classification models and factor weights, the subjective evaluation scores are calculated, and the objective and subjective evaluation scores are combined to determine the transformer status.
It improves the accuracy and efficiency of transformer status judgment, takes into account technical specifications and subjective feedback from power users, and provides a more comprehensive status evaluation.
Smart Images

Figure CN118940147A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to the technical field of transformers, and in particular, to a method, device and apparatus for evaluating a transformer status by combining subjective and objective means. Background Art
[0002] With the development of technology and the improvement of people's living standards, various electrified equipment has been popularized and the scale of the power grid has been expanding. The power system has begun to develop in the direction of large capacity and ultra-high voltage. Transformers are one of the core equipment in the power system. Transformers are responsible for energy transmission and conversion. The status of the transformer, such as the health status, is related to the stability of the entire power grid.
[0003] At present, thresholds are usually set for various electrical parameters of the transformer (such as voltage, current, capacity load rate and station area loss) based on manual experience, and the electrical parameters of the transformer during operation are compared with the corresponding thresholds to determine the status of the transformer.
[0004] However, this method of determining the transformer status by threshold comparison only judges the transformer status from the perspective of a technician, resulting in an inaccurate and overly one-sided transformer status. Summary of the invention
[0005] The embodiments of the present invention provide a method, device and equipment for evaluating the status of a transformer by combining subjective and objective factors, so as to judge the status of the transformer from both the objective perspective of technical specifications and the subjective perspective of electricity users, thereby accurately and conveniently determining the target transformer status of the target transformer, thereby improving the efficiency and accuracy of determining the target transformer status.
[0006] In a first aspect, an embodiment of the present invention provides a method for evaluating a transformer status by combining subjective and objective methods, comprising:
[0007] Obtaining target power consumption feedback information of power users for a target transformer and an objective evaluation score corresponding to the target transformer;
[0008] Determine a subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights;
[0009] Based on the objective evaluation score and the subjective evaluation score, a target transformer state corresponding to the target transformer is determined.
[0010] Optionally, the method further includes: obtaining candidate corpora related to electricity consumption recently published by electricity users based on preset channels; determining target corpora corresponding to the target transformer based on the target transformer identifier and the candidate corpora, and determining target electricity consumption feedback information based on the target corpora.
[0011] Optionally, the method also includes: inputting each target corpus in the target electricity consumption feedback information into the target classification model in turn for classification, and obtaining the target probability that each target corpus belongs to each influencing factor; for each influencing factor, based on the target probability, determining the average probability corresponding to each target corpus under the current influencing factor, and determining the average probability as the factor evaluation score corresponding to the current influencing factor; based on each of the factor evaluation scores and preset factor weights, determining the subjective evaluation score corresponding to the target transformer.
[0012] Optionally, the method further includes: multiplying each factor evaluation score by a preset factor weight corresponding to the factor evaluation score to obtain a weighted factor evaluation score corresponding to each influencing factor; and adding the weighted factor evaluation scores corresponding to each influencing factor to obtain a subjective evaluation score corresponding to the target transformer.
[0013] Optionally, the method further includes: performing weighted summation of the objective evaluation score and the subjective evaluation score to obtain a target evaluation score; and determining a target transformer state corresponding to the target transformer based on the target evaluation score and a preset mapping table.
[0014] Optionally, the method also includes: obtaining multiple electrical parameters of the target transformer within a preset time period; determining an index evaluation score corresponding to each electrical parameter based on each electrical parameter and a preset index threshold corresponding to the electrical parameter, and determining an objective evaluation score corresponding to the target transformer based on each of the index evaluation scores.
[0015] Optionally, the method also includes: obtaining historical electricity consumption feedback information of electricity users; clustering historical corpus based on the historical electricity consumption feedback information to determine corpus clusters; determining influencing factors that have a dependency relationship with the transformer based on the corpus clusters, and configuring a target classification model based on the influencing factors; comparing the importance of factors based on each of the influencing factors to determine a preset factor weight corresponding to each influencing factor.
[0016] In a second aspect, an embodiment of the present invention further provides a device for evaluating a transformer state by combining subjective and objective means, the device comprising:
[0017] An information acquisition module, used to obtain target power consumption feedback information of the power user for the target transformer and an objective evaluation score corresponding to the target transformer;
[0018] A subjective evaluation score determination module, used to determine the subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights;
[0019] A target transformer state determination module is used to determine a target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score.
[0020] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:
[0021] one or more processors;
[0022] A memory for storing one or more programs;
[0023] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for evaluating the transformer status by combining subjective and objective means as provided in any embodiment of the present invention.
[0024] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for evaluating a transformer state by combining subjective and objective means as provided in any embodiment of the present invention.
[0025] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the method for evaluating a transformer state by combining subjective and objective means as provided in any embodiment of the present invention.
[0026] The technical solution of the embodiment of the present invention obtains the target power consumption feedback information of the power user for the target transformer and the objective evaluation score corresponding to the target transformer; determines the subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights; determines the target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score, thereby achieving the judgment of the transformer state from both the objective perspective of the technical specifications and the subjective perspective of the power user, and then accurately and conveniently determining the target transformer state of the target transformer, thereby improving the efficiency and accuracy of determining the target transformer state.
[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0029] Figure 1 This is a flow chart of a method for evaluating transformer status by combining subjective and objective means provided in Embodiment 1 of the present invention;
[0030] Figure 2 This is a flow chart of a method for evaluating transformer status by combining subjective and objective means provided in Embodiment 2 of the present invention;
[0031] Figure 3 is an example diagram of the relative importance of an influencing factor involved in the second embodiment of the present invention;
[0032] Figure 4 is an example diagram of a judgment matrix involved in the second embodiment of the present invention;
[0033] Figure 5 It is a structural schematic diagram of a device for evaluating transformer status by combining subjective and objective means provided in Embodiment 3 of the present invention;
[0034] Figure 6 It is a structural schematic diagram of an electronic device for implementing the method for evaluating transformer status by combining subjective and objective means according to an embodiment of the present invention. DETAILED DESCRIPTION
[0035] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0037] Embodiment 1
[0038] Figure 1A flowchart of a method for subjectively and objectively evaluating transformer status is provided for the first embodiment of the present invention. This embodiment is applicable to the case of determining the target transformer status corresponding to the target transformer. The method can be performed by a device for subjectively and objectively evaluating transformer status. The device for subjectively and objectively evaluating transformer status can be implemented in the form of hardware and / or software. The device for subjectively and objectively evaluating transformer status can be configured in an electronic device. Figure 1 As shown, the method includes:
[0039] S110, obtaining target power consumption feedback information of the power user for the target transformer and an objective evaluation score corresponding to the target transformer.
[0040] The target transformer may refer to a transformer whose transformer status is to be determined. The target transformer may be any transformer in the power system. The target power consumption feedback information may refer to the power consumption experience feedback information of the power user for the target transformer. The objective evaluation score may be a score of the health of the transformer determined from an objective perspective of the technical specifications.
[0041] Specifically, target power consumption feedback information of power users for a target transformer is obtained from the collected power consumption experience feedback information of power users, and an objective evaluation score corresponding to a predetermined target transformer is obtained.
[0042] For example, supervised training can be performed on a time series scoring model based on deep learning, such as a long short-term memory network (LSTM). The electrical parameters of the target transformer during operation are organized into a time series, and the time series is input into a pre-trained scoring model for scoring to obtain an objective evaluation score corresponding to the target transformer.
[0043] On the basis of the above technical scheme, "obtaining target electricity consumption feedback information from electricity users for a target transformer" may include: obtaining candidate corpus related to electricity consumption recently published by electricity users based on preset channels; determining the target corpus corresponding to the target transformer based on the target transformer identifier and the candidate corpus, and determining the target electricity consumption feedback information based on the target corpus.
[0044] The corpus to be selected may refer to the corpus after data preprocessing. Data preprocessing may include but is not limited to data cleaning, word segmentation and deletion of stop words. Data cleaning may include but is not limited to deduplication, alignment and deletion.
[0045] Specifically, the electricity-related corpus published by electricity users is collected from preset channels such as user complaint tickets, power grid forums, and local life community websites, and these corpus are preprocessed to obtain candidate corpus. Users do not necessarily comment on transformers directly, but when users evaluate electricity consumption, they mostly comment on transformers indirectly. It is necessary to count the corpus belonging to the target transformer from all candidate corpus. For example, the geographic location can be used as the target transformer identifier for screening, and the target corpus belonging to the target transformer is composed of the target electricity feedback information.
[0046] Based on the above technical solution, "obtaining the objective evaluation score corresponding to the target transformer" may include: obtaining multiple electrical parameters of the target transformer within a preset time period; determining the indicator evaluation score corresponding to each electrical parameter based on each electrical parameter and the preset indicator threshold corresponding to the electrical parameter, and determining the objective evaluation score corresponding to the target transformer based on each indicator evaluation score.
[0047] Among them, electrical parameters may refer to parameters that need to be monitored during transformer operation. Electrical parameters may include but are not limited to voltage, current, capacity load rate and station area loss. The preset indicator threshold may be a parameter value corresponding to normal operation pre-set according to the technical specifications of the transformer. The indicator evaluation score may refer to the degree to which each electrical parameter meets the technical specifications.
[0048] Specifically, multiple parameter values of each electrical parameter of the target transformer monitored within a preset time period are obtained, and each parameter value is compared with a preset index threshold corresponding to the corresponding electrical parameter, the number of parameter values falling within the preset index threshold is divided by the total number of parameters corresponding to the electrical parameter to obtain a division result, and the division result is determined as the index evaluation score of the corresponding electrical parameter, and the weighted sum of each index evaluation score is performed to determine the objective evaluation score corresponding to the target transformer.
[0049] S120: Determine a subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and preset factor weights.
[0050] The target classification model may be a multi-classification classification model. For example, the target classification model may be a large language model (LLaMA). The preset factor weight may refer to the weight corresponding to each influencing factor when calculating the subjective evaluation score. The subjective evaluation score may refer to the score of the transformer health determined from the subjective perspective of the electricity user.
[0051] Specifically, the target power consumption feedback information is input into the target classification model for classification, and each classification result is weighted and summed with the preset factor weights corresponding to the influencing factors of each classification result to determine the subjective evaluation score corresponding to the target transformer.
[0052] S130. Determine a target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score.
[0053] The target transformer state may refer to the health status of the target transformer, which may reflect whether the transformer can work normally and whether it needs maintenance.
[0054] Specifically, the objective evaluation score and the subjective evaluation score are compared, the evaluation score with a larger score is selected, and based on the corresponding relationship between the evaluation score and the preset transformer state and score, the transformer state corresponding to the evaluation score is determined, and the transformer state is determined as the target transformer state corresponding to the target transformer.
[0055] On the basis of the above technical solution, "determining the target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score" may include: weighted summing the objective evaluation score and the subjective evaluation score to obtain the target evaluation score; determining the target transformer state corresponding to the target transformer based on the target evaluation score and a preset mapping table.
[0056] The target evaluation score may refer to an evaluation score corresponding to the transformer determined from both an objective perspective of technical specifications and a subjective perspective of electricity users. The preset mapping table may include a mapping relationship between the target evaluation score and the target transformer state.
[0057] Specifically, the weighted sum of the objective evaluation score and the subjective evaluation score may be performed using the following formula.
[0058]
[0059] Among them, Score is the target evaluation score, subjectivity is the subjective evaluation score, Objective is the objective evaluation score, α and β are weights, and α+β=1. The target evaluation score is used to determine the target transformer state corresponding to the target evaluation score from the preset mapping table, thereby obtaining the target transformer state corresponding to the target transformer.
[0060] It should be noted that since the subjective evaluation of the health status of the transformer by the electricity user is a negative score, while the objective evaluation of the health status of the transformer using electrical parameters is a positive score, it is necessary to normalize the objective evaluation score and the subjective evaluation score to obtain the target evaluation score of the transformer.
[0061] The technical solution of the embodiment of the present invention obtains the target power consumption feedback information of the power user for the target transformer and the objective evaluation score corresponding to the target transformer; determines the subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights; determines the target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score, thereby achieving the judgment of the transformer state from both the objective perspective of the technical specifications and the subjective perspective of the power user, and then accurately and conveniently determining the target transformer state of the target transformer, thereby improving the efficiency and accuracy of determining the target transformer state.
[0062] Embodiment 2
[0063] Figure 2 This is a flowchart of a method for evaluating transformer status by combining subjective and objective evaluation provided in the second embodiment of the present invention. Based on the above embodiment, this embodiment describes in detail the process of determining the subjective evaluation score corresponding to the target transformer. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 2 As shown, the method includes:
[0064] S210: Obtain target power consumption feedback information of the power user for the target transformer and an objective evaluation score corresponding to the target transformer.
[0065] S220: Input each target corpus in the target electricity consumption feedback information into the target classification model in sequence for classification, and obtain the target probability that each target corpus belongs to each influencing factor.
[0066] The target classification model can be used to determine the probability that the input data belongs to each influencing factor. The influencing factor can refer to a factor that affects the state of the transformer. For example, the influencing factor can include but is not limited to (voltage / current) stability, noise, maintenance, temperature and fault.
[0067] Specifically, each target corpus in the target electricity consumption feedback information is sequentially input into the target classification model for classification, and the target probability that each target corpus belongs to each influencing factor is sequentially obtained based on the output of the target classification model.
[0068] S230: For each influencing factor, based on the target probability, determine the average probability corresponding to each target corpus under the current influencing factor, and determine the average probability as the factor evaluation score corresponding to the current influencing factor.
[0069] Each target material has a corresponding target probability for different influencing factors. The average probability may refer to the average value of the target probabilities corresponding to all target materials under the influencing factors. The factor evaluation score may refer to the degree of influence of the influencing factors on the transformer state.
[0070] Specifically, the target probabilities corresponding to each target corpus under the influencing factor are averaged to determine the average probability corresponding to each target corpus under the influencing factor, and the average probability is determined as the factor evaluation score corresponding to the influencing factor.
[0071] S240: Determine a subjective evaluation score corresponding to the target transformer based on the evaluation scores of each factor and the preset factor weights.
[0072] Specifically, each factor evaluation score is weighted and multiplied by the preset factor weight corresponding to the influencing factor of the factor evaluation score to obtain a multiplication result. The multiplication results corresponding to all influencing factors are added together to determine the subjective evaluation score corresponding to the target transformer.
[0073] On the basis of the above technical solution, "determining the subjective evaluation score corresponding to the target transformer based on the evaluation scores of each factor and the preset factor weights" may include: multiplying each factor evaluation score by the preset factor weight corresponding to the factor evaluation score to obtain the weighted factor evaluation score corresponding to each influencing factor; adding the weighted factor evaluation scores corresponding to each influencing factor to obtain the subjective evaluation score corresponding to the target transformer.
[0074] Among them, the preset factor weight can be understood as the importance of the influencing factor to the transformer status judgment.
[0075] S250: Determine a target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score.
[0076] The technical solution of the embodiment of the present invention is to input each target corpus in the target electricity consumption feedback information into the target classification model for classification in turn, and obtain the target probability of each target corpus belonging to each influencing factor, and then use the target probability of each target corpus under each influencing factor to perform mean processing to obtain the factor evaluation score corresponding to each influencing factor, and then based on each factor evaluation score and preset factor weights, accurately determine the subjective evaluation score corresponding to the target transformer from the subjective perspective of the electricity user, and further determine the accuracy of the target transformer status.
[0077] On the basis of the above technical solution, determining the preset factor weights and the influencing factors in the target classification model may include: obtaining historical electricity consumption feedback information from electricity users; clustering the historical corpus in the historical electricity consumption feedback information to determine the corpus clusters; based on the corpus clusters, determining the influencing factors that have a dependency relationship with the transformer, and configuring the target classification model based on the influencing factors; comparing the importance of each influencing factor to determine the preset factor weight corresponding to each influencing factor.
[0078] Among them, for electricity users, it is difficult to quantitatively evaluate the health status of the services provided by the transformer. Therefore, the hierarchical analysis method can be used to evaluate the health status of the transformer. The hierarchical analysis method is a decision analysis method that combines qualitative and quantitative methods to solve complex problems with multiple objectives. After determining the influencing factors of the goal achievement, they are compared two by two, and finally the most advantageous factors are determined. This method can better solve those problems that are difficult to quantify. The hierarchical analysis method divides the decision-making goals, the factors to be considered (decision criteria) and the decision-making objects into the decision-making layer, the criterion layer and the solution layer according to their mutual relationship. Decision-making layer: the purpose of decision-making, the problem to be solved - evaluate the health status of the transformer. Criteria layer: the influencing factors considered, the decision criteria - the influencing factors related to the health status of the transformer selected based on the user's electricity experience. Solution layer: alternative solutions when making decisions - the score indicating the health status of the transformer, etc.
[0079] The various influencing factors of the criterion layer in the hierarchical analysis method are often formulated by experts, but it is difficult for electricity users to directly give the influencing factors for evaluating the health status of the transformer, which is not conducive to characterizing the electricity consumption experience of electricity users. Therefore, natural language can be used to analyze the user's electricity consumption experience of the transformer, so as to fit the influencing factors given by electricity users to evaluate the health status of the transformer.
[0080] Specifically, the historical electricity consumption feedback information of electricity users is obtained, and the historical corpus in the historical electricity consumption feedback information is clustered using the k-means clustering algorithm (k-means) to obtain k corpus clusters. In each corpus cluster, the dependency relationship between each keyword in the corpus and the transformer is analyzed. If the keyword has a dependency relationship with the transformer, such as (voltage / current) stability, noise, maintenance, temperature, fault, etc., the frequency of the keyword is counted, and the m keywords with the highest frequency are selected to form a phrase. The phrases in each corpus cluster are intersected, and the keywords in the intersection are set as the criterion layer in the hierarchical analysis method, that is, the influencing factors. The target classification model is configured based on the influencing factors.
[0081] Among them, the judgment matrix is compared with each other, so the relative scale is used in the comparison to minimize the difficulty of comparing the influencing factors of different natures and improve the accuracy. The relative importance of the influencing factors in the judgment matrix is given by Santy's 1-9 scaling method, such as Figure 3 shown.
[0082] Specifically, take five influencing factors as an example. C1, C2, C3, C4, and C5 correspond to the five influencing factors of the criterion layer, namely (voltage / current) stability, noise, maintenance, temperature, and fault. The judgment matrix is as follows: Figure 4 shown.
[0083] Exemplarily, in order to compare the relative importance of different influencing factors, a general two-way sentiment analysis classification model, such as GLU-CNN, Attention-BiLSTM, etc., can be trained using historical corpus. Since most of the corpus belongs to negative emotions and a small part of the corpus belongs to positive emotions, the classification model is trained with negative emotions as positive samples and positive emotions as negative samples. When preparing to compare the relative importance between influencing factors C1 and C2, in the k corpus clusters, the cluster M with the highest frequency when influencing factor C1 is used as a keyword is selected, and the cluster N with the highest frequency when influencing factor C2 is used as a keyword is selected. All corpora in clusters M and cluster N are input into the pre-training model (BERT) to encode the vector of the corpus. For the corpus containing influencing factor C1 in cluster M, the attention mechanism (Self-Attention) is used to encode the vector of the corpus again while increasing the attention of influencing factor C1, so as to increase the weight of influencing factor C1 in the corpus. For the corpus containing the influencing factor C2 in cluster N, the attention mechanism (Self-Attention) is used to re-encode the vector of the corpus while increasing the attention to the influencing factor C2, so as to increase the weight of the influencing factor C2 in the corpus. In cluster M, the vectors of each corpus are input into the classification model of the two-way sentiment analysis to obtain the sentiment score of each corpus, and the average of the sentiment scores is calculated to obtain the overall score of cluster M. In cluster N, the vectors of each corpus are input into the classification model of the two-way sentiment analysis to obtain the sentiment score of each corpus, and the average of the sentiment scores is calculated to obtain the overall score of cluster N. If the overall score of cluster M is higher than that of cluster N, it means that the influencing factor C1 is more important than the influencing factor C2. At this time, the overall score of cluster M is subtracted from the overall score of cluster N to obtain the score difference, and the score difference is proportionally mapped to [1,9] to determine the preset factor weight corresponding to each influencing factor, and select the relative importance with the closest score difference.
[0084] The following is an embodiment of a device for subjectively and objectively evaluating a transformer state provided by an embodiment of the present invention. The device and the method for subjectively and objectively evaluating a transformer state in the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the device for subjectively and objectively evaluating a transformer state, reference can be made to the embodiment of the method for subjectively and objectively evaluating a transformer state in the above-mentioned embodiments.
[0085] Embodiment 3
[0086] Figure 5 This is a schematic diagram of the structure of a device for evaluating transformer status by combining subjective and objective means provided in the third embodiment of the present invention. Figure 5 As shown, the device includes: an information acquisition module 510 , a subjective evaluation score determination module 520 and a target transformer state determination module 530 .
[0087] Among them, the information acquisition module 510 is used to obtain the target power consumption feedback information of the power user for the target transformer and the objective evaluation score corresponding to the target transformer; the subjective evaluation score determination module 520 is used to determine the subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights; the target transformer state determination module 530 is used to determine the target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score.
[0088] The technical solution of the embodiment of the present invention obtains the target power consumption feedback information of the power user for the target transformer and the objective evaluation score corresponding to the target transformer; determines the subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights; determines the target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score, thereby achieving the judgment of the transformer state from both the objective perspective of the technical specifications and the subjective perspective of the power user, and then accurately and conveniently determining the target transformer state of the target transformer, thereby improving the efficiency and accuracy of determining the target transformer state.
[0089] Based on the above technical solution, the information acquisition module 510 may include:
[0090] The submodule for obtaining the candidate corpus is used to obtain the candidate corpus related to electricity consumption recently published by electricity users based on preset channels;
[0091] The target power consumption feedback information determination submodule is used to determine the target corpus corresponding to the target transformer based on the target transformer identifier and the corpus to be selected, and to determine the target power consumption feedback information based on the target corpus.
[0092] Based on the above technical solution, the subjective evaluation score determination module 520 may include:
[0093] The target probability determination submodule is used to input each target corpus in the target electricity consumption feedback information into the target classification model in turn for classification, and obtain the target probability that each target corpus belongs to each influencing factor;
[0094] The factor evaluation score determination submodule is used to determine the average probability corresponding to each target corpus under the current influencing factor based on the target probability for each influencing factor, and determine the average probability as the factor evaluation score corresponding to the current influencing factor;
[0095] The subjective evaluation score determination submodule is used to determine the subjective evaluation score corresponding to the target transformer based on the evaluation scores of various factors and preset factor weights.
[0096] On the basis of the above technical solution, the subjective evaluation score determination submodule is specifically used for: multiplying each factor evaluation score by the preset factor weight corresponding to the factor evaluation score to obtain the weighted factor evaluation score corresponding to each influencing factor; adding the weighted factor evaluation scores corresponding to each influencing factor to obtain the subjective evaluation score corresponding to the target transformer.
[0097] Based on the above technical solution, the target transformer state determination module 530 is specifically used to: perform weighted summation of the objective evaluation score and the subjective evaluation score to obtain the target evaluation score; and determine the target transformer state corresponding to the target transformer based on the target evaluation score and the preset mapping table.
[0098] Based on the above technical solution, the information acquisition module 510 may include:
[0099] An electrical parameter acquisition submodule is used to acquire various electrical parameters of a target transformer within a preset time period;
[0100] The objective evaluation score determination submodule is used to determine the index evaluation score corresponding to each electrical parameter based on each electrical parameter and the preset index threshold value corresponding to the electrical parameter, and determine the objective evaluation score corresponding to the target transformer based on each index evaluation score.
[0101] On the basis of the above technical solution, the device also includes:
[0102] An information determination module, used to determine the preset factor weights and influencing factors in the target classification model;
[0103] The information determination module is specifically used to: obtain historical electricity consumption feedback information from electricity users; cluster the historical corpus in the historical electricity consumption feedback information to determine the corpus clusters; based on the corpus clusters, determine the influencing factors that have a dependency relationship with the transformer, and configure the target classification model based on the influencing factors; compare the importance of factors based on each influencing factor, and determine the preset factor weight corresponding to each influencing factor.
[0104] The device for subjectively and objectively evaluating the transformer state provided by the embodiment of the present invention can execute the method for subjectively and objectively evaluating the transformer state provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method for subjectively and objectively evaluating the transformer state.
[0105] It is worth noting that in the above-mentioned embodiment of combining subjective and objective evaluation of the transformer status, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0106] Embodiment 4
[0107] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0108] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0109] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0110] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for combining subjective and objective evaluation of the transformer state.
[0111] In some embodiments, the method for subjectively and objectively combining the evaluation of the transformer state can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for subjectively and objectively combining the evaluation of the transformer state described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for subjectively and objectively combining the evaluation of the transformer state in any other appropriate manner (for example, by means of firmware).
[0112] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0113] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0114] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0115] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0116] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0117] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0118] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for evaluating the state of a transformer by combining subjective and objective means as provided in any embodiment of the present application.
[0119] In the process of implementation, the computer program product can be written in one or more programming languages or a combination thereof to perform the computer program code of the present invention, wherein the programming language includes an object-oriented programming language, such as Java, Smalltalk, C++, and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The program product and the method for evaluating the state of a transformer by combining subjectivity and objectivity disclosed in each embodiment of the present application belong to the same inventive concept, so it is not repeated here.
[0120] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0121] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for evaluating transformer status by combining subjective and objective factors, characterized in that: include: Obtaining target power consumption feedback information of power users for a target transformer and an objective evaluation score corresponding to the target transformer; Determine a subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights; Based on the objective evaluation score and the subjective evaluation score, a target transformer state corresponding to the target transformer is determined.
2. The method according to claim 1, characterized in that Obtain target power consumption feedback information from power users for target transformers, including: Based on the preset channels, the candidate corpus related to electricity consumption recently published by electricity users is obtained; Based on the target transformer identifier and the to-be-selected corpus, the target corpus corresponding to the target transformer is determined, and the target electricity consumption feedback information is determined based on the target corpus.
3. The method according to claim 1, characterized in that: The step of determining a subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights includes: Inputting each target corpus in the target electricity consumption feedback information into the target classification model in turn for classification, and obtaining the target probability that each target corpus belongs to each influencing factor; For each influencing factor, based on the target probability, determine the average probability corresponding to each target corpus under the current influencing factor, and determine the average probability as the factor evaluation score corresponding to the current influencing factor; Based on the evaluation scores of each factor and the preset factor weights, a subjective evaluation score corresponding to the target transformer is determined.
4. The method according to claim 3, characterized in that Determining the subjective evaluation score corresponding to the target transformer based on the evaluation scores of each factor and the preset factor weights includes: Multiply each factor evaluation score by the preset factor weight corresponding to the factor evaluation score to obtain a weighted factor evaluation score corresponding to each influencing factor; The weighted factor evaluation scores corresponding to each influencing factor are added together to obtain the subjective evaluation score corresponding to the target transformer.
5. The method according to claim 1, characterized in that The determining, based on the objective evaluation score and the subjective evaluation score, a target transformer state corresponding to the target transformer comprises: Performing a weighted summation of the objective evaluation score and the subjective evaluation score to obtain a target evaluation score; Based on the target evaluation score and a preset mapping table, a target transformer state corresponding to the target transformer is determined.
6. The method according to claim 1, characterized in that Obtaining an objective evaluation score corresponding to the target transformer, including: Obtain various electrical parameters of the target transformer within a preset time period; Based on each electrical parameter and a preset index threshold corresponding to the electrical parameter, an index evaluation score corresponding to each electrical parameter is determined, and based on each of the index evaluation scores, an objective evaluation score corresponding to the target transformer is determined.
7. The method according to claim 1, characterized in that Determine the preset factor weights and influencing factors in the target classification model, including: Obtain historical electricity consumption feedback information from electricity users; Performing clustering based on the historical corpus in the historical electricity consumption feedback information to determine a corpus cluster; Based on the corpus clusters, determining influencing factors having a dependency relationship with the transformer, and configuring a target classification model based on the influencing factors; A comparison of the importance of each of the influencing factors is performed to determine a preset factor weight corresponding to each influencing factor.
8. A device for evaluating transformer status by combining subjective and objective methods, characterized in that: The device comprises: An information acquisition module, used to obtain target power consumption feedback information of the power user for the target transformer and an objective evaluation score corresponding to the target transformer; A subjective evaluation score determination module, used to determine the subjective evaluation score corresponding to the target transformer based on the target power consumption feedback information, the target classification model and the preset factor weights; A target transformer state determination module is used to determine a target transformer state corresponding to the target transformer based on the objective evaluation score and the subjective evaluation score.
9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for evaluating the transformer status by combining subjective and objective means as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for evaluating transformer status by combining subjective and objective means as described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Distribution network accurate investment strategy method based on customer demands
CN110765268A
Distribution network equipment state evaluation method based on AHP-fuzzy comprehensive evaluation method
CN114399150A
Method and device for evaluating performance of low-voltage power distribution network
CN117875546A
