Electric pole quality determination method, device, equipment, medium and program product
The pole quality evaluation model is generated through combined empowerment method and simulation technology, which solves the problem that traditional methods are difficult to accurately evaluate the state of reinforced concrete poles, and achieves the efficiency and accuracy of pole quality evaluation, providing science for the power transmission and distribution network Maintenance basis.
Patent Information
- Application Number
- CN202410995995.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-08
AI Technical Summary
The traditional method of reinforced concrete pole status evaluation depends on preset index system and empirical judgment, which is difficult to accurately reflect the actual status of the pole, and the detection method is slow, so the degree of damage of the pole cannot be determined in time and accurately, and it cannot meet the power transmission and distribution network pairing. Quick assessment of pole damage.
The weight grading table is redefined through the combined empowerment method, a pole quality evaluation model is generated, and a pole quality evaluation sample is generated using simulation technology. The model is trained to improve the evaluation accuracy, and the quality level of the pole is determined based on the evaluation results.
It improves the accuracy and efficiency of pole quality evaluation, provides a scientific and effective basis for the maintenance and management of poles, and improves the reliability of circuit operation in the power transmission and distribution network.
Smart Images

Figure CN118917734A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power transmission and transformation project quality detection, and in particular to a method, device, equipment, medium and program product for determining the quality of an electric pole. Background Art
[0002] In the power transmission and distribution network, reinforced concrete poles are key facilities, and their structural integrity and safety are crucial to ensure the reliable operation of transmission lines. During long-term service, poles may suffer from cracks and steel corrosion due to factors such as environmental erosion and material aging, which will reduce their bearing capacity and increase the risk of failure. Therefore, accurate status assessment and damage detection of reinforced concrete poles have extremely important engineering application value.
[0003] So far, the traditional reinforced concrete pole status assessment method mainly relies on the preset indicator system and empirical judgment, which is difficult to accurately reflect the actual status of the pole. In particular, considering the differences in soil chloride ion content, pole concrete strength, steel bar type, etc. in different regions, the accuracy and applicability of traditional methods are seriously challenged. In addition, the existing reinforced concrete pole detection methods are slow and cannot intuitively derive the specific operating status of reinforced concrete poles, which makes it difficult to meet the needs of timely and accurate determination of the degree of damage of reinforced concrete poles in power transmission and distribution networks. Summary of the invention
[0004] The present invention provides a method, device, equipment, medium and program product for determining the quality of electric poles. The weight grading table based on a preset indicator system and empirical judgment is redefined through a combined weighting method, and the training of an electric pole quality assessment model is completed based on the electric pole quality assessment samples generated by the redefined weight grading table, so that the trained electric pole quality assessment model can more accurately assess the degree of damage of the electric pole to be inspected, and complete the quality determination of the electric pole to be inspected based on the assessment results, thereby improving the assessment efficiency and accuracy of the electric pole quality assessment and providing a scientific and effective basis for the maintenance and management of the electric poles.
[0005] In a first aspect, an embodiment of the present invention provides a method for determining the quality of a pole, comprising:
[0006] Obtain damage status information of the pole to be inspected;
[0007] Input the damage status information into the pre-trained pole quality assessment model to determine the quality loss score of the pole to be inspected;
[0008] Determine the quality grade of the pole to be inspected based on the quality loss score and the pre-configured quality grading standard table;
[0009] Among them, the pole quality assessment model is trained based on the pole quality assessment samples generated by simulation; the labels of the pole quality assessment samples are the scores of the damage corresponding to the pole quality assessment samples based on the weight classification table redefined based on the combined weighting method.
[0010] In a second aspect, an embodiment of the present invention further provides a device for determining the quality of a pole, comprising:
[0011] An information acquisition module is used to obtain damage status information of the pole to be detected;
[0012] A loss score determination module is used to input the damage status information into the pre-trained pole quality assessment model to determine the quality loss score of the pole to be inspected;
[0013] A quality grade determination module is used to determine the quality grade of the pole to be inspected according to the quality loss score and a pre-configured quality grading standard table;
[0014] Among them, the pole quality assessment model is trained based on the pole quality assessment samples generated by simulation; the labels of the pole quality assessment samples are the scores of the damage corresponding to the pole quality assessment samples based on the weight classification table redefined based on the combined weighting method.
[0015] In a third aspect, an embodiment of the present invention further provides a pole quality determination device, the pole quality determination device comprising:
[0016] at least one processor; and a memory communicatively coupled to the at least one processor;
[0017] The memory stores a computer program executable by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can implement the pole quality determination method of any embodiment of the present invention.
[0018] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the pole quality determination method of any embodiment of the present invention.
[0019] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which is used to execute the pole quality determination method of any embodiment of the present invention when executed by a processor.
[0020] The embodiments of the present invention provide a method, device, equipment, medium and program product for determining the quality of electric poles, which obtains the damage status information of the electric poles to be detected; inputs the damage status information into a pre-trained electric pole quality assessment model to determine the quality loss score of the electric poles to be detected; and determines the quality grade of the electric poles to be detected based on the quality loss score and a pre-configured quality grading standard table; wherein the electric pole quality assessment model is trained based on the electric pole quality assessment samples generated by simulation; the labels of the electric pole quality assessment samples are the scores of the damage corresponding to the electric pole quality assessment samples based on the weight grading table redefined based on the combined weighting method. By adopting the above technical scheme, simulation technology is used to generate electric poles with different damage conditions as electric pole quality assessment samples, and a weight grading table is obtained by redefining the existing damage weight evaluation table based on the manually set indicator system and experience judgment setting based on the combined weighting method, so as to score the damage conditions corresponding to the electric pole quality assessment samples more accurately and without human influence, and obtain electric pole quality assessment samples that can be used for model training. Then, the pole quality assessment model is trained through pole quality assessment samples, and when the pole to be inspected needs to be inspected, the damage status information of the pole to be inspected is input into the pole quality assessment model to determine the quality loss score, and then the quality grade of the pole to be inspected is obtained based on the determined quality loss score. Since the pre-trained pole quality assessment model is trained based on pole quality assessment samples constructed based on a redefined weight grading table that does not rely on manual judgment, the trained pole quality assessment model can more accurately assess the degree of damage of the pole to be inspected, and complete the quality determination of the pole to be inspected based on the assessment results, which improves the assessment efficiency and accuracy of pole quality assessment and provides a scientific and effective basis for the maintenance and management of poles.
[0021] 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
[0022] 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.
[0023] Figure 1 A flowchart of a method for determining the quality of a pole provided in the first embodiment of the present invention;
[0024] Figure 2 A flowchart of a method for determining the quality of a pole provided in the second embodiment of the present invention;
[0025] Figure 3 An example diagram of a process for combining and weighting each simulated pole according to each shear stress and each bending moment to determine a redefined weight classification table provided in the second embodiment of the present invention;
[0026] Figure 4 A schematic diagram of the structure of a pole quality determination device provided in Embodiment 3 of the present invention;
[0027] Figure 5 This is a schematic structural diagram of a pole quality determination device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0028] 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.
[0029] 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.
[0030] Embodiment 1
[0031] Figure 1 This is a flowchart of a pole quality determination method provided in the first embodiment of the present invention. The embodiment of the present invention can be applied to determine the corrosion and fracture conditions of reinforced concrete poles in the power transmission and distribution network, so as to evaluate their structural integrity and safety. The pole quality determination method can be executed by a pole quality determination device, which can be implemented by software and / or hardware, and the pole quality determination device can be configured in a pole quality determination device. Optionally, the pole quality determination device can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.
[0032] like Figure 1 As shown, a method for determining the quality of a pole provided by an embodiment of the present invention specifically includes the following steps:
[0033] S101. Obtain damage status information of a pole to be inspected.
[0034] In this embodiment, the pole to be inspected can be specifically understood as a reinforced concrete pole in the power transmission and distribution network that needs to be inspected for steel corrosion and cracking to assess whether its quality can meet the operation requirements of the transmission line. The damage status information can be specifically understood as information that intuitively reflects the external and internal damage of the pole to be inspected. For example, the damage status information may include the depth of transverse corrosion and the length of longitudinal corrosion of the steel bars inside the pole to be inspected, and the presence of cracks on the outside of the pole to be inspected.
[0035] Specifically, in order to ensure the safe operation of the power transmission and distribution network, it is necessary to regularly monitor the damage of reinforced concrete poles in the power transmission and distribution network to determine whether the reinforced concrete poles can meet the requirements of safe operation of the power transmission and distribution network in the presence of damage. At this time, the reinforced concrete poles that need to be monitored for damage can be determined as the poles to be detected, and when it is necessary to monitor them, the damage status information related to the external and internal damage of the poles to be detected can be obtained from both external and internal perspectives.
[0036] S102: Input the damage status information into a pre-trained pole quality assessment model to determine the quality loss score of the pole to be inspected.
[0037] Among them, the pole quality assessment model is trained based on the pole quality assessment samples generated by simulation; the labels of the pole quality assessment samples are the scores of the damage corresponding to the pole quality assessment samples based on the weight classification table redefined based on the combined weighting method.
[0038] In this embodiment, the pole quality assessment model can be specifically understood as a neural network model for scoring and predicting the quality loss corresponding to the damage status information based on the features in the input damage status information. The quality loss score can be specifically understood as a quantitative value used to describe the corrosion and cracking of the pole to be tested, which causes its quality deviation relative to the safe operating state. The pole quality assessment sample can be specifically understood as a sample used to train the pole quality assessment model, which may include the damage status information of the pole generated by simulation for input into the untrained pole quality assessment model, and the score given after the quality loss assessment of the damage status information based on the weight classification table redefined by the combined weighting method, which is used as the pole quality assessment sample label. The weight classification table can be specifically understood as a table containing the evaluation criteria, scores and weights of the required evaluation features that are considered to be more important for the pole quality assessment after the index selection and redefined by the combined weighting method.
[0039] Specifically, the damage status information of the pole to be inspected is input into the pre-trained pole quality assessment model. The pole quality assessment model first extracts features of the damage status information, and based on the extracted features, a quantitative prediction is made on the corrosion and cracking of the pole to be inspected, which leads to quality loss relative to the safe operating state. The output result of the pole quality assessment model is determined as the quality loss score of the pole to be inspected.
[0040] S103: Determine the quality grade of the electric pole to be inspected according to the quality loss score and a pre-configured quality grading standard table.
[0041] In this embodiment, the quality grading standard table can be specifically understood as a table that is preset according to actual conditions and is used to reflect the corresponding relationship between the quality loss score and the quality grade related to the operable state of the pole.
[0042] Specifically, the quality loss score is matched with the score interval corresponding to each quality grade in the preconfigured quality grade standard table, and the quality grade corresponding to the successfully matched score interval is determined as the quality grade of the pole to be inspected.
[0043] The technical solution of this embodiment is to obtain the damage status information of the pole to be detected; input the damage status information into the pre-trained pole quality assessment model to determine the quality loss score of the pole to be detected; determine the quality grade of the pole to be detected based on the quality loss score and the pre-configured quality grading standard table; wherein the pole quality assessment model is trained based on the pole quality assessment samples generated by simulation; the label of the pole quality assessment sample is the score of the damage corresponding to the pole quality assessment sample based on the weight grading table redefined based on the combined weighting method. By adopting the above technical solution, simulation technology is used to generate poles with different damage conditions as pole quality assessment samples, and the weight grading table is obtained by redefining the existing damage weight evaluation table based on the artificially set indicator system and experience judgment based on the combined weighting method, so as to score the damage corresponding to the pole quality assessment sample more accurately and without human influence, and obtain the pole quality assessment sample that can be used for model training. Then, the pole quality assessment model is trained through pole quality assessment samples, and when the pole to be inspected needs to be inspected, the damage status information of the pole to be inspected is input into the pole quality assessment model to determine the quality loss score, and then the quality grade of the pole to be inspected is obtained based on the determined quality loss score. Since the pre-trained pole quality assessment model is trained based on pole quality assessment samples constructed based on a redefined weight grading table that does not rely on manual judgment, the trained pole quality assessment model can more accurately assess the degree of damage of the pole to be inspected, and complete the quality determination of the pole to be inspected based on the assessment results, which improves the assessment efficiency and accuracy of pole quality assessment and provides a scientific and effective basis for the maintenance and management of poles.
[0044] Embodiment 2
[0045] Figure 2A flowchart of a pole quality determination method provided in the second embodiment of the present invention is provided. The embodiment of the present invention is further optimized on the basis of the above-mentioned optional technical solutions. A plurality of simulated poles with different degrees of damage are simulated and generated according to a preset steel bar corrosion state set and a preset crack state set, and the shear stress and bending moment of each simulated pole are simulated. Combination weighting without human influence is performed based on the shear stress and bending moment of each simulated pole, that is, after the subjective weight in the combination weighting method is determined in a way that does not rely on human experience, the weight grading table used to evaluate the pole quality is redefined, and then a pole quality assessment sample is constructed based on the redefined weight grading table and the simulated pole, and the pole quality assessment model is trained through the pole quality assessment sample. The quality assessment score output by the pole quality assessment model is made to be a more accurate score that does not rely on human experience, and then the quality grade of the pole to be tested is determined by relying on the quality loss score, which improves the assessment efficiency and accuracy of the pole quality assessment, makes the quality grade based on the maintenance and management of the pole more scientific, and improves the reliability of circuit operation in the power transmission and distribution network.
[0046] like Figure 2 As shown, a method for determining the quality of a pole provided by an embodiment of the present invention specifically includes the following steps:
[0047] S201. Generate at least two simulated poles with different damage degrees according to a preset steel bar corrosion state set and a preset crack state set, and determine the shear stress and bending moment of each simulated pole.
[0048] In this embodiment, the preset steel bar corrosion state set can be specifically understood as a set of multiple pre-determined steel bar corrosion conditions according to the different angles of corrosion conditions that may occur in the steel bars in the reinforced concrete pole. Optionally, the preset steel bar corrosion state set may include the remaining effective cross-sectional area of the steel bar, the corrosion length, the number of steel bars, the buried depth of the steel bar and the uniformity of steel bar corrosion, and each preset steel bar corrosion state can be assigned different values, such as the corrosion length can be set to different length values, etc., and the embodiment of the present invention does not limit this. The preset crack state set can be specifically understood as a set of crack presentation states of different lengths, widths and extension modes that may appear after the concrete shell in the reinforced concrete pole cracks. Optionally, the preset crack state set may include transverse cracks, longitudinal cracks and mesh cracks, and the maximum length and width of the above-mentioned types of cracks can be set differently according to actual conditions, and the embodiment of the present invention does not limit this. Shear stress can be specifically understood as the force that interacts between the internal parts of the pole when it is deformed due to external factors, which is used to resist the external factors and try to restore the pole from the position after deformation to the position before deformation. Bending moment can be specifically understood as an internal torque generated by the force in the pole.
[0049] Specifically, in order to realize the training of the pole quality assessment model, it is necessary to construct training samples for training the pole quality assessment model based on poles with different damage conditions. The more damage conditions included in the training samples, the more accurate the quality loss scores of different damage conditions determined by the trained pole quality assessment model. Therefore, before training the pole quality assessment model, different steel corrosion states and crack states can be selected from the preset steel corrosion state set and the preset crack state set for combination, so as to simulate different types of damage that may occur in the poles in real situations through combination, and then simulate poles of different types and degrees of damage under each combination through simulation, and obtain the corresponding simulated poles, as well as the shear stress and bending moment of each simulated pole when it has its corresponding type of damage.
[0050] S202, combining and weighting each simulated pole according to each shear stress and each bending moment, and determining a redefined weight classification table.
[0051] Specifically, the subjective weights corresponding to different simulated poles are determined according to the bending moment of each simulated pole, and the objective weights corresponding to different simulated poles are jointly determined according to the shear stress and bending moment of each simulated pole. Then, the subjective weight and objective weight of each simulated pole are integrated to achieve combined weighting, and weights and scores are assigned to various characteristics that may affect the quality assessment of the poles to generate a redefined weight classification table.
[0052] Optional, Figure 3 The second embodiment of the present invention provides a flow chart of combining and weighting each simulated pole according to each shear stress and each bending moment to determine a redefined weight classification table, such as Figure 3 As shown, the following steps may be specifically included:
[0053] S2021. Input each bending moment into a preset clustering model for clustering, and determine the subjective weight of each simulated pole.
[0054] In this embodiment, the preset clustering model can be specifically understood as a model pre-selected according to actual conditions, which is used to cluster different simulated poles, so as to assign the same subjective weight to simulated poles with similar damage states. Optionally, the preset clustering model can be a self-organizing map neural network model (Self-Organizing Map, SOM), which realizes the clustering of each simulated pole based on bending moment by a mechanism based on a competitive learning network.
[0055] Exemplarily, each bending moment is input into a preset clustering model for clustering, and the subjective weight of each simulated pole is determined, which can be achieved in the following manner:
[0056] Each bending moment is input into the preset clustering model, and clustering is performed after feature selection using L1 norm regularization; the subjective weight of each simulated pole is determined according to the weight corresponding to each cluster.
[0057] Specifically, each bending moment is input into the preset clustering model, and L1 norm regularization is used to select features. Since L1 norm regularization will impose the same penalty on all weights, that is, regardless of the size of the parameters in the preset clustering model, they will be punished with the same intensity. Based on the above processing, the smaller weights will become 0 after being punished, that is, after L1 norm regularization, the values of a large number of model parameters become 0 or approach 0, and these parameters will not appear in the final model, thereby achieving the effect of feature selection. Then, the preset clustering model after feature selection can be used to automatically cluster the input bending moments to form several clusters. Then, the subjective weight of each simulated pole can be determined as the weight corresponding to the cluster in which it is located, so that the degree of influence of the subjective judgment of the decision maker on the determined subjective weight is reduced, avoiding the possibility of affecting the final analysis result due to deviations or inconsistencies in the judgment of the decision maker.
[0058] In the embodiment of the present invention, since the factors affecting the state of reinforced concrete poles are terminal, and the process and mechanism of instability of reinforced concrete poles are also very complex, selecting the correct evaluation index is a very critical step in judging reinforced concrete poles, and the selection of the index will have a decisive impact on the prediction results. The combined weighting method is better at analyzing single factor evaluation. When analyzing multiple factors, such as complex interactions and correlations between multiple factors, relying solely on the combined weighting method to determine may not be able to fully reflect the comprehensive impact of each factor on the decision. At the same time, since the results of the combined weighting method may be affected by the subjective judgment of the subjective decision maker, if the judgment of the decision maker is biased or inconsistent, it may affect the final analysis results. Therefore, in this scheme, a preset clustering model is used to cluster the bending moment in the main influencing factors when the reinforced concrete pole falls, and the weights obtained by clustering are used to replace the subjective weights in the combined weighting method to reduce the impact of the decision maker's judgment bias on the accuracy of the analysis results of the combined weighting method. At the same time, the screening of evaluation indicators is realized based on L1 norm regularization, so that the evaluation indicators finally used for pole quality determination are scientific and representative.
[0059] S2022. Determine the objective weight of each simulated pole based on the pre-acquired normal bending strength, normal shear stress, most unfavorable bending strength and most unfavorable shear stress, as well as each shear stress and each bending moment.
[0060] In this embodiment, the normal bending strength can be specifically understood as the bending strength that the pole can withstand under lossless normal operation, which is calculated based on the geographical location of the pole to be tested, the local wind speed, the gravity of the ground wire and other related parameters. It is also the maximum bending moment that the pole can withstand under lossless normal operation. The normal shear stress can be specifically understood as the shear stress value that the pole can withstand under lossless normal operation, which is calculated based on the geographical location of the pole to be tested, the local wind speed, the gravity of the ground wire and other related parameters. The most unfavorable bending strength can be specifically understood as the maximum bending moment that the pole can withstand when the most unfavorable situation occurs at the geographical location of the pole to be tested. The most unfavorable shear stress can be specifically understood as the maximum shear stress that the pole can withstand when the most unfavorable situation occurs at the geographical location of the pole to be tested.
[0061] Specifically, based on the normal bending strength, normal shear stress, most unfavorable bending strength and most unfavorable shear stress obtained in advance, the benchmark of bending strength and shear stress that the pole to be tested can withstand at its geographical location can be determined. Each simulated pole is a simulation of the state that the pole can present corresponding to a combination of steel bar corrosion state and crack state. The corresponding shear stress and bending moment can be understood as the maximum bending moment and maximum shear stress that the pole can withstand in the presence of corresponding types of damage. The difference relative to the benchmark can be considered as damage to the ability to withstand bending moment and shear stress due to damage, and the corresponding objective weight can be determined for the simulated pole based on the difference, so as to reflect the impact of the corresponding damage situation of the simulated pole on the quality of the pole through the objective weight.
[0062] Optionally, the objective weight of each simulated pole is determined according to the pre-acquired normal bending strength, normal shear stress, most unfavorable bending strength and most unfavorable shear stress, as well as each shear stress and each bending moment, which can be specifically achieved through the following steps:
[0063] 1) The difference between the normal bending strength and the most unfavorable bending strength obtained in advance is determined as the bending strength reference value.
[0064] 2) The difference between the normal shear stress and the most unfavorable shear stress obtained in advance is determined as the shear stress reference value.
[0065] 3) For each simulated pole, the difference between the shear stress corresponding to the simulated pole and the shear stress reference value is determined as the shear stress variation, and the difference between the bending moment corresponding to the simulated pole and the bending strength reference value is determined as the bending moment variation.
[0066] 4) The objective weight of the simulated pole is determined according to the ratio of the shear stress change to the shear stress reference value, the ratio of the bending moment change to the bending strength reference value, and the corresponding relationship of the preset proportion weights.
[0067] Specifically, the difference between the normal bending strength obtained in advance and the most unfavorable bending strength is determined as the bending strength reference value for determining the bending moment loss of the simulated pole; the difference between the normal shear stress obtained in advance and the most unfavorable shear stress is determined as the shear stress reference value for determining the shear stress loss of the simulated pole. Furthermore, for each simulated pole, the difference between its corresponding shear stress and the shear stress reference value is determined as the shear stress change, and the difference between its corresponding bending moment and the bending strength reference value is determined as the bending moment change. The shear stress change can be considered as the amount of shear stress loss that the pole can withstand due to the damage to the simulated pole, corresponding to the damage state; the bending moment change can be considered as the amount of bending moment loss that the pole can withstand due to the damage to the simulated pole, corresponding to the damage state. Furthermore, the correspondence between the proportion of shear stress loss and the proportion of bending moment loss and the objective weight can be determined in advance according to the actual situation, and a preset proportion-weight correspondence can be constructed. Then, the ratio of the shear stress change to the shear stress benchmark value and the ratio of the bending moment change to the bending strength benchmark value of each simulated pole are substituted in turn to obtain the objective weight of the corresponding simulated pole in the combined weighting method.
[0068] S2023. Assign weights and scores to the subjective weight, objective weight, steel corrosion state and crack state of each simulated pole, to each preset steel corrosion state in the preset steel corrosion state set, and to each preset crack state in the preset crack state set, and determine a redefined weight grading table.
[0069] Specifically, since each simulated electric pole corresponds to a different combination of steel bar corrosion states and crack states, after clarifying the subjective weight and objective weight of each simulated electric pole, the subjective weight and objective weight corresponding to each preset steel bar corrosion state in the preset steel bar corrosion state set, as well as the subjective weight and objective weight corresponding to each preset crack state in the preset crack state set can be determined. After comprehensive analysis and combined weighting, weights and scores can be assigned to each preset steel bar corrosion state and each preset crack state. The final weights and scores can be expressed in a tabular form to be determined as a redefined weight classification table.
[0070] Exemplarily, the redefined weight classification table in the embodiment of the present invention can be represented by the following table:
[0071]
[0072]
[0073] S203: Score the damage status information of each simulated pole using a redefined weight classification table, and use each score as a label for the corresponding damage status information.
[0074] Specifically, for each simulated pole, the information related to the scoring content in the redefined weight classification table in its damage status information can be extracted in turn, and the weights and scores corresponding to the evaluation content can be determined according to the corresponding evaluation standards, and then each weight is multiplied by the score and summed up to obtain a score for the damage status of the simulated pole, and then the score can be used as a label for its corresponding damage status information, so that the combination of the damage status information and the label can be determined as a pole quality assessment sample.
[0075] For example, assuming that the length and width of the crack of the shell of the simulated pole are 50mm and 1mm respectively, the crack state of the simulated pole can be considered as a longitudinal crack. Substituting it into the redefined weight classification table, the score related to the crack state can be obtained as 10*0.05=0.5. Assuming that the remaining effective cross-sectional area of the steel bars of the simulated pole is 75%, the corrosion length is 120mm, the number of steel bars is consistent with the involved number, and the buried depth of the steel bars is less than 30% of the protective layer thickness, the above evaluation contents are respectively substituted into the redefined weight classification table, and the score related to the corrosion state of the steel bars can be obtained as
[0076] 10*0.55+4*0.1+0*0.2+7*0.05=6.25. Accordingly, the score corresponding to the simulated pole damage status information is 6.25+0.5=6.75.
[0077] S204: Determine each combination of damage status information and a corresponding label as a pole quality assessment sample, and train an initial pole quality assessment model based on each pole quality assessment sample to generate a pole quality assessment model.
[0078] In this embodiment, the initial pole quality assessment model can be specifically understood as a pole quality assessment model that has not been trained and adjusted for parameters, and its structure is completely consistent with the pole quality assessment model.
[0079] Specifically, each combination of damage status information and the corresponding label is determined as a pole quality assessment sample, and the training sample set composed of each pole quality assessment sample is input into the initial pole quality assessment model for training, and the weight parameters of each neural network layer of the initial pole quality assessment model are adjusted until the preset convergence conditions are met, and then the pole quality assessment model is generated.
[0080] It can be understood that the determined pole quality assessment samples can be divided into a training sample set and a test sample set, and the embodiment of the present invention is not limited to this.
[0081] It can be understood that S201-S204 can be executed only before the pole quality determination method is put into actual use, or can be executed periodically during the use of the pole quality determination method to determine and update the pole quality assessment model. The execution time of the above steps in the embodiment of the present invention is not limited.
[0082] S205. Perform magnetic flux leakage detection on the pole to be inspected to determine the steel bar corrosion status information.
[0083] Specifically, since the corrosion of steel bars in reinforced concrete poles is mainly reflected in the reduction of the effective cross-sectional area of the steel bars, the corrosion of the steel bars can be regarded as a reduction in diameter. The buried depth and corrosion condition of the steel bars in the poles to be tested can be measured by non-destructive testing equipment through the leakage magnetic detection method. During the detection process, the steel bars in the poles to be tested are tested using a magnetization source to generate internal and surrounding magnetic fields. When there are cracks or structural changes in the steel bars, the magnetization state of the steel bars will be destroyed, causing magnetic field distortion and forming a leakage magnetic field. Then, based on the changes in the surface magnetic field captured by the magnetic induction sensor, the steel bar corrosion status information including information such as the steel bar diameter, buried depth and effective cross-sectional area can be completed.
[0084] S206: Collect crack images of the pole to be inspected, perform denoising and feature extraction on the crack images, and determine crack status information.
[0085] Specifically, the image acquisition device is used to acquire images of areas where cracks may exist on the pole to be inspected, and the acquired images are divided to obtain a crack image containing only one crack. The crack image is then processed by histogram equalization, median filter denoising, contrast enhancement, binarization and binary filter denoising to achieve denoising and feature extraction of the crack image, and the maximum length and maximum width of the crack image are obtained. The crack status information of the pole to be inspected is determined based on the maximum length and maximum width.
[0086] It is understandable that S205 and S206 may be executed simultaneously or in any order, and the embodiment of the present invention is not limited to this.
[0087] S207: Determine the steel bar corrosion status information and the crack status information as damage status information of the pole to be detected.
[0088] S208: Input the damage status information into a pre-trained pole quality assessment model to determine the quality loss score of the pole to be inspected.
[0089] S209: Determine the quality grade of the electric pole to be inspected according to the quality loss score and a pre-configured quality grading standard table.
[0090] The technical solution of this embodiment simulates and generates multiple simulated poles with different degrees of damage based on a preset set of steel bar corrosion states and a preset set of crack states, and simulates the shear stress and bending moment of each simulated pole, and performs combined weighting without human influence based on the shear stress and bending moment of each simulated pole, that is, after the subjective weights in the combined weighting method are determined in a way that does not rely on human experience, the weight grading table used to evaluate the quality of the poles is redefined, and then a pole quality assessment sample is constructed based on the redefined weight grading table and the simulated poles, and the pole quality assessment model is trained through the pole quality assessment sample. The quality assessment score output by the pole quality assessment model is made to be a more accurate score that does not rely on human experience, and then the quality grade of the pole to be tested is determined by relying on the quality loss score, which improves the assessment efficiency and accuracy of the pole quality assessment, makes the quality grade based on the maintenance and management of the poles more scientific, and improves the reliability of circuit operation in the power transmission and distribution network.
[0091] Embodiment 3
[0092] Figure 4 A schematic diagram of the structure of a pole quality determination device provided in the third embodiment of the present invention is shown in FIG. Figure 4 As shown, the pole quality determination device includes an information acquisition module 31 , a loss score determination module 32 and a quality level determination module 33 .
[0093] Among them, the information acquisition module 31 is used to obtain the damage status information of the pole to be detected; the loss score determination module 32 is used to input the damage status information into the pre-trained pole quality assessment model to determine the quality loss score of the pole to be detected; the quality grade determination module 33 is used to determine the quality grade of the pole to be detected according to the quality loss score and the pre-configured quality grading standard table; wherein the pole quality assessment model is trained based on the pole quality assessment sample generated by simulation; the label of the pole quality assessment sample is the score of the damage corresponding to the pole quality assessment sample based on the weight grading table redefined based on the combined weighting method.
[0094] The technical solution of the embodiment of the present invention uses simulation technology to generate poles with different damage conditions as pole quality assessment samples, and based on the combined weighting method, the existing damage weight evaluation table based on the manually set indicator system and the experience judgment setting is redefined to obtain a weight grading table, and the damage conditions corresponding to the pole quality assessment samples are scored more accurately and without human influence, so as to obtain pole quality assessment samples that can be used for model training. Then, the pole quality assessment model is trained through the pole quality assessment samples, and when it is necessary to perform quality inspection on the pole to be inspected, the obtained damage state information of the pole to be inspected is input into the pole quality assessment model to determine the quality loss score, and then the quality grade of the pole to be inspected is obtained according to the determined quality loss score. Since the pre-trained pole quality assessment model is obtained by training the pole quality assessment sample constructed based on the redefined weight grading table that does not rely on manual judgment, the trained pole quality assessment model can more accurately evaluate the degree of damage of the pole to be inspected, and complete the quality determination of the pole to be inspected based on the evaluation results, thereby improving the evaluation efficiency and accuracy of the pole quality assessment, and providing a scientific and effective basis for the maintenance and management of the pole.
[0095] Optionally, the information acquisition module 31 includes:
[0096] A corrosion information acquisition unit is used to perform magnetic flux leakage detection on the pole to be detected and determine the steel bar corrosion status information;
[0097] The crack information acquisition unit is used to collect crack images of the pole to be detected, and to perform denoising and feature extraction on the crack images to determine the crack status information.
[0098] The damage information determination unit is used to determine the steel bar corrosion state information and crack state information as the damage state information of the pole to be detected.
[0099] Optionally, the pole quality determination device further includes: a model training module, which is used to:
[0100] Before obtaining the damage state information of the pole to be detected, at least two simulated poles with different damage degrees are simulated and generated according to a preset steel bar corrosion state set and a preset crack state set, and the shear stress and bending moment of each simulated pole are determined;
[0101] Combine and weight each simulated pole according to each shear stress and each bending moment, and determine the redefined weight classification table;
[0102] The damage status information of each simulated pole is scored respectively through a redefined weight classification table, and each score is used as a label of the corresponding damage status information;
[0103] A combination of each damage status information and a corresponding label is determined as a pole quality assessment sample, and an initial pole quality assessment model is trained based on each pole quality assessment sample to generate a pole quality assessment model.
[0104] Optionally, each simulated pole is weighted according to each shear stress and each bending moment to determine a redefined weight classification table, including:
[0105] Input each bending moment into the preset clustering model for clustering, and determine the subjective weight of each simulated pole;
[0106] According to the normal bending strength, normal shear stress, most unfavorable bending strength and most unfavorable shear stress, as well as each shear stress and each bending moment obtained in advance, the objective weight of each simulated pole is determined;
[0107] The subjective weight, objective weight, steel corrosion state and crack state of each simulated pole are weighted and scored to each preset steel corrosion state in the preset steel corrosion state set and each preset crack state in the preset crack state set, and a redefined weight grading table is determined.
[0108] Optionally, each bending moment is input into a preset clustering model for clustering to determine the subjective weight of each simulated pole, including:
[0109] Each bending moment is input into the preset clustering model and clustered after feature selection using L1 norm regularization;
[0110] Determine the subjective weight of each simulated pole according to the weight corresponding to each cluster;
[0111] Among them, the preset clustering model is a self-organizing map neural network model.
[0112] Optionally, the objective weight of each simulated pole is determined based on the pre-acquired normal bending strength, normal shear stress, most unfavorable bending strength and most unfavorable shear stress, as well as each shear stress and each bending moment, including:
[0113] The difference between the normal bending strength obtained in advance and the most unfavorable bending strength is determined as the bending strength reference value;
[0114] The difference between the normal shear stress obtained in advance and the most unfavorable shear stress is determined as the shear stress reference value;
[0115] For each simulated pole, the difference between the shear stress corresponding to the simulated pole and the shear stress reference value is determined as the shear stress variation, and the difference between the bending moment corresponding to the simulated pole and the bending strength reference value is determined as the bending moment variation;
[0116] The objective weight of the simulated pole is determined according to the ratio of the change in shear stress to the reference value of shear stress, the ratio of the change in bending moment to the reference value of bending strength, and the corresponding relationship of preset proportion weights.
[0117] The pole quality determination device provided in the embodiment of the present invention can execute the pole quality determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0118] Embodiment 4
[0119] Figure 5 A schematic diagram of the structure of a pole quality determination device provided in Embodiment 4 of the present invention. The pole quality determination device 40 may be 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 pole quality determination device 40 may also represent various forms of mobile devices, such as personal digital assistants, 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 claimed herein.
[0120] like Figure 5 As shown, the pole quality determination device 40 includes at least one processor 41, and a memory connected to the at least one processor 41 in communication, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the pole quality determination device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.
[0121] A number of components in the pole quality determination device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the pole quality determination device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0122] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 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 41 executes the various methods and processes described above, such as the pole quality determination method.
[0123] In some embodiments, the pole quality determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the computing power distribution device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the pole quality determination method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the pole quality determination method in any other appropriate manner (e.g., by means of firmware).
[0124] Optionally, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the pole quality determination method provided in any embodiment of the present invention.
[0125] 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.
[0126] 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.
[0127] 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.
[0128] In order to provide interaction with the user, the systems and techniques described herein can be implemented on a computing power distribution device, which has: 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 computing power distribution device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0129] 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.
[0130] 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.
[0131] 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.
[0132] 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 determining the quality of a pole, characterized in that: include: Obtain damage status information of the pole to be inspected; Inputting the damage status information into a pre-trained pole quality assessment model to determine the quality loss score of the pole to be inspected; Determining the quality grade of the pole to be inspected according to the quality loss score and a preconfigured quality grading standard table; The pole quality assessment model is trained based on pole quality assessment samples generated by simulation; the labels of the pole quality assessment samples are scores of damage corresponding to the pole quality assessment samples based on a weight grading table redefined based on a combined weighting method.
2. The method according to claim 1, characterized in that Before obtaining the damage status information of the pole to be detected, the method further includes: Simulating and generating at least two simulated poles with different damage degrees according to a preset steel bar corrosion state set and a preset crack state set, and determining the shear stress and bending moment of each of the simulated poles; Combining and weighting the simulated poles according to the shear stresses and the bending moments, and determining a redefined weight classification table; Scoring the damage status information of each simulated pole respectively through the redefined weight classification table, and using each score as a label of the corresponding damage status information; Each combination of the damage status information and the corresponding label is determined as a pole quality assessment sample, and an initial pole quality assessment model is trained based on each pole quality assessment sample to generate a pole quality assessment model.
3. The method according to claim 2, characterized in that The combining and weighting the simulated poles according to the shear stresses and the bending moments to determine a redefined weight classification table includes: Inputting each bending moment into a preset clustering model for clustering, and determining a subjective weight of each simulated pole; Determine the objective weight of each simulated pole according to the pre-acquired normal bending strength, normal shear stress, most unfavorable bending strength and most unfavorable shear stress, as well as each shear stress and each bending moment; The subjective weight, objective weight, steel corrosion state and crack state of each simulated pole are weighted and scored to each preset steel corrosion state in the preset steel corrosion state set and each preset crack state in the preset crack state set, and a redefined weight grading table is determined.
4. The method according to claim 3, characterized in that Determining the objective weight of each simulated pole according to the pre-acquired normal bending strength, normal shear stress, most unfavorable bending strength and most unfavorable shear stress, as well as each shear stress and each bending moment includes: The difference between the normal bending strength obtained in advance and the most unfavorable bending strength is determined as the bending strength reference value; The difference between the normal shear stress obtained in advance and the most unfavorable shear stress is determined as the shear stress reference value; For each simulated pole, the difference between the shear stress corresponding to the simulated pole and the shear stress reference value is determined as the shear stress variation, and the difference between the bending moment corresponding to the simulated pole and the bending strength reference value is determined as the bending moment variation; The objective weight of the simulated pole is determined according to the ratio of the shear stress change to the shear stress reference value, the ratio of the bending moment change to the bending strength reference value, and a preset proportion weight correspondence relationship.
5. The method according to claim 3, characterized in that: The step of inputting each bending moment into a preset clustering model for clustering to determine the subjective weight of each simulated pole includes: Inputting each of the bending moments into the preset clustering model, and performing clustering after performing feature selection using L1 norm regularization; Determine the subjective weight of each simulated pole according to the weight corresponding to each cluster; Wherein, the preset clustering model is a self-organizing map neural network model.
6. The method according to claim 1, characterized in that The step of obtaining the damage status information of the pole to be detected includes: Performing magnetic flux leakage detection on the pole to be detected to determine the steel bar corrosion status information; Collecting the crack image of the pole to be detected, and performing denoising and feature extraction on the crack image to determine the crack state information; The steel bar corrosion status information and the crack status information are determined as the damage status information of the pole to be detected.
7. A device for determining the quality of a pole, characterized in that: include: An information acquisition module is used to obtain damage status information of the pole to be detected; A loss score determination module, used for inputting the damage status information into a pre-trained pole quality assessment model to determine the quality loss score of the pole to be inspected; A quality grade determination module, used to determine the quality grade of the pole to be inspected according to the quality loss score and a preconfigured quality grading standard table; The pole quality assessment model is trained based on pole quality assessment samples generated by simulation; the labels of the pole quality assessment samples are scores of damage corresponding to the pole quality assessment samples based on a weight grading table redefined based on a combined weighting method.
8. A device for determining the quality of a pole, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the pole quality determination method according to any one of claims 1 to 6.
9. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the pole quality determination method according to any one of claims 1 to 6 when executed by a computer processor.
10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for determining the quality of a pole according to any one of claims 1 to 6 is implemented.
