Cable aging assessment determination system and method based on sample data

Abstract

The embodiment of the invention discloses a cable aging assessment determination system and method based on sample data, and the method comprises the steps: obtaining the performance information of each sample cable under different environment factor information, types, service life and service time, and determining the aging assessment value of the sample cable based on the performance information, determining a training data set according to the aging evaluation value, the environmental factor information, the type, the service life and the service duration of each sample cable, performing training based on the training data set and a pre-training model to obtain a cable aging evaluation model, and obtaining the environmental factor information, the type, the service life and the service duration of a to-be-evaluated cable, and determining input data according to the environmental factor information, the type, the service life and the service duration of the to-be-evaluated cable, and inputting the input data into the cable aging evaluation model to obtain an aging evaluation result. According to the scheme, aging evaluation is carried out on the cable through the sample data, cable aging evaluation can be efficiently and accurately realized, and the method is simple and easy to implement and low in labor cost.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of cable technology, and more particularly to a system and method for determining cable aging assessment based on sample data. Background Art

[0002] Cable aging refers to the phenomenon that the insulation and protective layers of the cable are affected by external environmental factors, mechanical damage, chemical corrosion, long-term overload operation and other factors for a long time, resulting in the decline of its insulation performance and the loss of its protective function. Cable aging is a gradual process, which not only affects the service life of the cable, but also may bring safety hazards. After the cable ages to a certain extent, its insulation performance decreases and it is easy to cause a short circuit, especially in dry, cold and humid weather conditions. Although the appearance of the wire is intact, the insulation performance has been reduced. When moisture penetrates into the metal conductor, a short circuit may occur, causing a fire or electric shock accident. In addition, cable aging may lead to a decrease in the efficiency of power transmission and distribution, affect the stable operation of the power system, and cause inconvenience to industrial production and daily life.

[0003] In the existing cable aging assessment methods, aging is usually assessed based on the cable's service life, type, etc., or on-site inspections are conducted to confirm the aging situation. This assessment method has low assessment accuracy and efficiency, and is less applicable to field conditions that are difficult to observe. Summary of the invention

[0004] The embodiments of the present invention provide a cable aging assessment determination system and method based on sample data, which solves the problems of low assessment accuracy and efficiency in existing cable aging assessment technologies, and poor applicability to field conditions that are difficult to observe. It can efficiently and accurately implement cable aging degree assessment, is simple and easy to implement, and has low labor costs.

[0005] In a first aspect, an embodiment of the present invention provides a cable aging assessment determination method based on sample data, comprising:

[0006] Acquire the performance information of each sample cable under different environmental factor information, types, service life and service time, and determine the aging assessment value of each sample cable based on the performance information;

[0007] Determine a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and usage duration, and perform model training based on the training data set and a preset pre-trained model to obtain a trained cable aging assessment model;

[0008] The environmental factor information, type, service life and usage duration of the cable to be evaluated are obtained, input data is determined according to the environmental factor information, type, service life and usage duration of the cable to be evaluated, and the input data is input into the cable aging assessment model for aging assessment to obtain an aging assessment result of the cable to be evaluated.

[0009] Optionally, the performance information includes a plurality of different types of performance change data, and determining the aging assessment value of each sample cable based on the performance information includes:

[0010] Aging assessment standard information corresponding to each different type of performance change data is determined respectively, and an aging assessment value of each sample cable is determined based on the performance change data and the aging assessment standard information.

[0011] Optionally, the performance change data includes a performance degradation percentage, the aging assessment standard information includes a standard aging assessment value corresponding to a unit degradation percentage, and determining the aging assessment value of each sample cable based on the performance change data and the aging assessment standard information includes:

[0012] The performance degradation percentage is divided by the unit degradation percentage and multiplied by the corresponding standard aging assessment value to obtain the aging assessment value to be integrated, the preset weights of each different type of performance change data are determined, the aging assessment value to be integrated is multiplied by the corresponding preset weights and superimposed to obtain the aging assessment value of the sample cable.

[0013] Optionally, determining the training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life, and usage duration includes:

[0014] The sample input data is determined according to the environmental factor information, type, service life and usage time of each sample cable, the aging assessment value of each sample cable is correspondingly determined as the sample output data associated with the sample input data, and the sample input data and the sample output data are determined as a training data set.

[0015] Optionally, the environmental factor information includes multiple environmental factors and corresponding environmental factor values, and the determining of sample input data according to the environmental factor information, type, service life and service time of each sample cable includes:

[0016] Determine the preset interval associated with the corresponding environmental factor into which each environmental factor value of the sample cable falls, and superimpose the factor evaluation values ​​corresponding to the preset interval into which each environmental factor value falls to obtain the environmental comprehensive evaluation value of the corresponding sample cable;

[0017] The comprehensive environmental assessment value, type, service life and usage duration of each sample cable are determined as sample input data.

[0018] Optionally, the performing model training based on the training data set and a preset pre-trained model to obtain a trained cable aging assessment model includes:

[0019] Inputting the sample input data in the training data set into the preset pre-training model for prediction to obtain a corresponding predicted aging assessment value, and comparing the predicted aging assessment value with the sample output data in the training data set to obtain a corresponding difference value;

[0020] The preset pre-trained model is adjusted based on the difference value to obtain a trained cable aging assessment model.

[0021] Optionally, the adjusting the preset pre-trained model based on the difference value to obtain a trained cable aging assessment model includes:

[0022] The parameters of the preset pre-trained model are adjusted according to the difference value, and the sample input data in the training data set is input into the adjusted preset pre-trained model for prediction again, until the difference value is less than the preset standard value, it is determined that the training of the preset pre-trained model is completed and determined as the cable aging assessment model.

[0023] In a second aspect, an embodiment of the present invention further provides a cable aging assessment and determination system based on sample data, comprising:

[0024] An acquisition module is used to acquire performance information of each sample cable under different environmental factor information, types, service life and service time;

[0025] An aging assessment value determination module, configured to determine an aging assessment value of each sample cable based on the performance information;

[0026] A training data determination module, used to determine a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and service time;

[0027] A model training module, used for performing model training based on the training data set and a preset pre-training model to obtain a trained cable aging assessment model;

[0028] The acquisition module is also used to obtain environmental factor information, type, service life and service time of the cable to be evaluated;

[0029] An input data determination module, used to determine input data according to the environmental factor information, type, service life and service time of the cable to be evaluated;

[0030] The aging assessment module is used to input the input data into the cable aging assessment model to perform aging assessment to obtain an aging assessment result of the cable to be assessed.

[0031] In a third aspect, an embodiment of the present invention further provides a cable aging evaluation and determination device based on sample data, the device comprising:

[0032] one or more processors;

[0033] a storage device for storing one or more programs,

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the cable aging evaluation determination method based on sample data described in an embodiment of the present invention.

[0035] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer executable instructions, which, when executed by a computer processor, are used to execute the cable aging assessment determination method based on sample data described in an embodiment of the present invention.

[0036] In an embodiment of the present invention, the performance information of each sample cable under different environmental factor information, types, service life and service time is obtained, the aging assessment value of each sample cable is determined based on the performance information, a training data set is determined according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and service time, model training is performed based on the training data set and a preset pre-trained model to obtain a trained cable aging assessment model, the environmental factor information, type, service life and service time of the cable to be evaluated is obtained, input data is determined according to the environmental factor information, type, service life and service time of the cable to be evaluated, and the input data is input into the cable aging assessment model to perform aging assessment to obtain the aging assessment result of the cable to be evaluated. This solution performs aging assessment on the cable through sample data, solves the problems of low assessment accuracy and efficiency in the existing cable aging assessment technology, and poor applicability to field conditions that are difficult to observe, and can efficiently and accurately realize cable aging assessment, is simple and easy to implement, and has low labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flow chart of a cable aging assessment determination method based on sample data provided by an embodiment of the present invention;

[0038] Figure 2 A flowchart of another cable aging assessment determination method based on sample data provided by an embodiment of the present invention;

[0039] Figure 3 A flowchart of another cable aging assessment determination method based on sample data provided by an embodiment of the present invention;

[0040] Figure 4 A flowchart of another cable aging assessment determination method based on sample data provided by an embodiment of the present invention;

[0041] Figure 5 A module structure block diagram of a cable aging assessment and determination system based on sample data provided by an embodiment of the present invention;

[0042] Figure 6 A schematic diagram of the structure of a cable aging assessment and determination device based on sample data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention, rather than to limit the embodiments of the present invention. It is also necessary to explain that, for ease of description, only parts related to the embodiments of the present invention are shown in the accompanying drawings, rather than all structures.

[0044] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and or or" in the specification and claims represents at least one of the connected objects, and the character "or" generally indicates that the objects associated before and after are in an "or" relationship.

[0045] The cable aging assessment determination method based on sample data provided in the embodiment of the present application can be applied to the cable aging degree assessment scenario. The cable aging assessment determination method based on sample data provided in the embodiment of the present application, the execution subject of each step can be a computer device, which refers to any electronic device with data calculation, processing and storage capabilities, such as mobile phones, PCs (Personal Computers), tablet computers and other terminal devices, and can also be servers and other devices, which are not limited in the embodiment of the present application.

[0046] Figure 1 A flow chart of a cable aging evaluation determination method based on sample data provided by an embodiment of the present invention, such as Figure 1 As shown, specifically including:

[0047] Step S101, obtaining performance information of each sample cable under different collected environmental factor information, types, service life and service time, and determining an aging assessment value of each sample cable based on the performance information.

[0048] Among them, the environmental factor information can be the relevant data information of the surrounding environment of the cable, the type can be classified according to the structure, material, purpose and performance characteristics of the cable, the service life is used to characterize the length of time that the cable can be used normally, the service time is used to characterize the length of time from the installation and start of operation of the cable to the current time, the sample cable is used to characterize the cable actually observed or investigated in the study, the performance information is used to characterize the data information of the relevant performance of the cable, and the aging evaluation value is used to characterize the result of the quantitative evaluation of the cable aging phenomenon. Through the performance information of each sample cable under different environmental factor information, types, service years and service time, the aging evaluation of each sample cable is performed to obtain the corresponding aging evaluation value. In one embodiment, a plurality of different types of performance change values ​​of each sample cable under different environmental factor information, types, service years and service time are obtained, and each performance change value of the sample cable is substituted into the preset aging evaluation value calculation formula to obtain the aging evaluation value. Optionally, the performance information includes a plurality of different types of performance change data, and a method for determining the aging evaluation value can be: respectively determine the aging evaluation standard information corresponding to each different type of performance change data, and determine the aging evaluation value of each sample cable based on the performance change data and the aging evaluation standard information. By evaluating the aging of the sample cables based on their performance changes and aging evaluation standards, the aging evaluation values ​​of the sample cables can be made more reasonable and accurate, thus providing accurate reference data for subsequent aging evaluations of actual cables.

[0049] Step S102: determining a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and usage duration, and performing model training based on the training data set and a preset pre-trained model to obtain a trained cable aging assessment model.

[0050] Among them, the training data set is a data set used to train the machine learning model, which contains various sample data used to train the model. The preset pre-trained model refers to a model pre-trained on a large data set, which usually performs well on certain general tasks and can be used as the starting point for subsequent specific tasks, and is adapted and optimized by transfer learning or fine-tuning. The cable aging assessment model is used to characterize the model for aging assessment of cables, and the output data is the aging assessment result of the cable. In one embodiment, the aging assessment values ​​of all sample cables and the corresponding environmental factor information, type, service life and usage time are sorted to obtain a training data set for model training, and the preset pre-trained model is trained according to the training data set to obtain a trained cable aging assessment model. Optionally, a method for determining a training data set can be: determine sample input data according to the environmental factor information, type, service life and usage time of each sample cable, determine the aging assessment value of each sample cable as the sample output data associated with the sample input data, and determine the sample input data and the sample output data as the training data set. By sorting out the sample data of the sample cable to obtain a training data set, the model can learn the laws and characteristics of cable aging. Optionally, a model training method may be: inputting sample input data in a training data set into a preset pre-trained model for prediction to obtain a corresponding predicted aging assessment value, comparing the predicted aging assessment value with the sample output data in the training data set to obtain a corresponding difference value, and adjusting the preset pre-trained model based on the difference value to obtain a trained cable aging assessment model. The trained cable aging assessment model obtained by model training with the training data set and the preset pre-trained model can simplify the subsequent actual cable aging assessment and ensure the accuracy of the cable aging assessment results.

[0051] Step S103: Obtain environmental factor information, type, service life and usage duration of the cable to be evaluated, determine input data according to the environmental factor information, type, service life and usage duration of the cable to be evaluated, and input the input data into the cable aging assessment model to perform aging assessment to obtain an aging assessment result of the cable to be evaluated.

[0052] The cable to be evaluated is used to characterize the actual cable waiting for aging evaluation. The input data may be data input into the cable aging evaluation model. After the model training is performed based on the training data set and the preset pre-training model to obtain the trained cable aging evaluation model, the environmental factor information, type, service life and service time of the current cable to be evaluated are obtained, and the environmental factor information, type, service life and service time of the cable to be evaluated are further sorted to obtain the input data of the cable aging evaluation model, and the input data is input into the cable aging evaluation model to obtain the output result as the aging evaluation result of the cable to be evaluated. In one embodiment, the environmental factor information of the cable to be evaluated includes multiple environmental factors and corresponding environmental factor values. A method for determining the input data may be: determining the preset interval associated with the corresponding environmental factor in which each environmental factor value of the cable to be evaluated falls, superimposing the factor evaluation values ​​corresponding to the preset interval in which each environmental factor value falls to obtain the environmental comprehensive evaluation value of the cable to be evaluated, and determining the environmental comprehensive evaluation value, type, service life and service time of the cable to be evaluated as the sample input data. An exemplary example may be that the type of cable a to be evaluated is model A, the service life is 30 years, the service time is 5 years, the environmental factor information of cable a to be evaluated includes temperature, humidity, and wind force, and the corresponding temperature value, humidity value, and wind force value are 30°C, 40%, and level 2, respectively. The preset intervals associated with temperature are (0°C, 10°C], (10°C, 20°C], (20°C, 30°C], and (30°C, 40°C]; the preset intervals associated with humidity are (0%, 30%], (30%, 60%], and (60%, 100%]; the preset intervals associated with wind force are (0, level 2], (2 level, level 4], and (4 level, level 6]; the interval in which the temperature value of cable a to be evaluated falls is (20°C, 30°C], and the corresponding temperature evaluation value is 0.75; the interval in which the humidity value of cable a to be evaluated falls is (30%, 60%], and the corresponding humidity evaluation value is 0.5; The humidity value falls into the interval of (0, 2 levels], and the corresponding humidity assessment value is 0.2, then the comprehensive environmental assessment value of the cable a to be evaluated is 1.45, 1.45, model A, 30 years, and 5 years are determined as input data and input into the cable aging assessment model, and the aging assessment value of the cable a to be evaluated is 30%. In another embodiment, the environmental factor information of the cable to be evaluated includes multiple environmental factors and corresponding environmental factor values, one environmental factor corresponds to a cable aging assessment model, one environmental factor of the cable to be evaluated and the corresponding environmental factor value, type, service life, and usage time are determined as the input data of the corresponding cable aging assessment model, the input data is input into the corresponding cable aging assessment model to obtain the aging assessment value to be calculated corresponding to each environmental factor, the aging assessment value to be calculated is multiplied by the preset weight of the corresponding environmental factor and superimposed to obtain the aging assessment value of the cable to be evaluated.

[0053] From the above, it can be seen that the performance information of each sample cable under different environmental factor information, types, service life and service time collected is obtained, and the aging assessment value of each sample cable is determined based on the performance information. The training data set is determined according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and service time. The model training is performed based on the training data set and the preset pre-training model to obtain a trained cable aging assessment model, and the environmental factor information, type, service life and service time of the cable to be evaluated are obtained. The input data is determined according to the environmental factor information, type, service life and service time of the cable to be evaluated. The input data is input into the cable aging assessment model to perform aging assessment to obtain the aging assessment result of the cable to be evaluated. This solution performs aging assessment on the cable through sample data, which solves the problems of low assessment accuracy and efficiency in the existing cable aging assessment technology, and poor applicability to field conditions that are difficult to observe. It can efficiently and accurately realize cable aging assessment, is simple and easy, and has low labor costs.

[0054] Figure 2 A flowchart of another cable aging evaluation determination method based on sample data provided by an embodiment of the present invention provides an optional specific method for determining the aging evaluation value of a sample cable, such as Figure 2 As shown, specifically including:

[0055] Step S201, obtain the performance information of each sample cable under different environmental factor information, types, service life and usage time, respectively determine the aging assessment standard information corresponding to each different type of performance change data, and determine the aging assessment value of each sample cable based on the performance change data and the aging assessment standard information.

[0056] Among them, the performance information includes multiple different types of performance change data, the performance change data is used to characterize the change of cable performance, and the aging assessment standard information is used to characterize the standard conditions for evaluating the aging phenomenon of the cable. A method for determining the aging assessment value may be: respectively determine the aging assessment standard information corresponding to each different type of performance change data, and determine the aging assessment value of each sample cable based on the performance change data and the aging assessment standard information. Optionally, the performance change data includes a performance degradation percentage, and the aging assessment standard information includes a standard aging assessment value corresponding to a unit degradation percentage. The performance degradation percentage may be a percentage of degradation of the cable performance value relative to the corresponding cable performance specification value. A method for determining the aging assessment value may be: divide the performance degradation percentage by the unit degradation percentage and multiply it with the corresponding standard aging assessment value to obtain an aging assessment value to be integrated, determine the preset weights of each different type of performance change data, multiply the aging assessment value to be integrated with the corresponding preset weights and superimpose them to obtain the aging assessment value of the sample cable. An exemplary example may be that the performance information of the sample cable a includes a heat resistance performance degradation percentage of 20%, an insulation performance degradation percentage of 10%, and a conductivity performance degradation percentage of 15%. The standard aging assessment value for a 1% decrease in heat resistance performance is 1%, the standard aging assessment value for a 1% decrease in insulation performance is 3%, and the standard aging assessment value for a 1% decrease in conductivity performance is 2%. The aging assessment value to be integrated for heat resistance performance is 20% (20*1%), the aging assessment value to be integrated for insulation performance is 30%, and the aging assessment value to be integrated for conductivity performance is 30%. The preset weights corresponding to heat resistance performance, insulation performance, and conductivity performance are 0.2, 0.5, and 0.3, respectively. The aging assessment value of the sample cable a is 28% (20%*0.2+30%*0.5+30%*0.3). In another embodiment, the performance degradation percentages of the sample cable are multiplied and superimposed with the corresponding preset weights to obtain the comprehensive performance degradation percentage of the sample cable. The aging assessment value of the sample cable is obtained by querying the preset aging assessment value mapping table according to the comprehensive performance degradation percentage.

[0057] Step S202: determining a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and usage duration, and performing model training based on the training data set and a preset pre-trained model to obtain a trained cable aging assessment model.

[0058] Step S203: Obtain environmental factor information, type, service life and usage duration of the cable to be evaluated, determine input data according to the environmental factor information, type, service life and usage duration of the cable to be evaluated, and input the input data into the cable aging assessment model to perform aging assessment to obtain an aging assessment result of the cable to be evaluated.

[0059] From the above, it can be seen that after obtaining the performance information of each sample cable under different environmental factor information, types, service life and service time, the aging assessment standard information corresponding to each different type of performance change data is determined respectively, and the aging assessment value of each sample cable is determined based on the performance change data and the aging assessment standard information. This solution performs aging assessment on the sample cable through the performance change of the sample cable and the aging assessment standard, which can make the aging assessment value of the sample cable more reasonable and accurate, and provide accurate reference data for the subsequent aging assessment of the actual cable.

[0060] Figure 3 A flowchart of another cable aging evaluation determination method based on sample data provided by an embodiment of the present invention provides an optional specific method for determining a training data set, such as Figure 3 As shown, specifically including:

[0061] Step S301: Acquire performance information of each sample cable under different collected environmental factor information, types, service life and service time, and determine an aging assessment value of each sample cable based on the performance information.

[0062] Step S302: determine sample input data according to the environmental factor information, type, service life and usage duration of each sample cable, determine the aging assessment value of each sample cable as the sample output data associated with the sample input data, and determine the sample input data and the sample output data as a training data set.

[0063] After the aging assessment value of each sample cable is determined based on the performance information, the sample input data is determined according to the environmental factor information, type, service life and service time of each sample cable, and the aging assessment value of each sample cable is correspondingly determined as the sample output data associated with the sample input data, and the sample input data and the sample output data are determined as the training data set. Optionally, the environmental factor information includes multiple environmental factors and corresponding environmental factor values. A method for determining the training data set may be: determining the preset interval associated with the corresponding environmental factor into which each environmental factor value of the sample cable falls, superimposing the factor assessment values ​​corresponding to the preset interval into which each environmental factor value falls to obtain the environmental comprehensive assessment value of the corresponding sample cable, and determining the environmental comprehensive assessment value, type, service life and service time of each sample cable as the sample input data. An exemplary example may be that the type of sample cable a is model A, the service life is 30 years, the service time is 5 years, the aging assessment value is 30%, and the environmental factor information of sample cable a includes temperature, humidity, and wind force. The corresponding temperature value, humidity value, and wind force value are 30°C, 40%, and level 2, respectively. The preset intervals associated with temperature are (0°C, 10°C], (10°C, 20°C], (20°C, 30°C], and (30°C, 40°C]; the preset intervals associated with humidity are (0%, 30%], (30%, 60%], and (60%, 100%]; the preset intervals associated with wind force are (0, level 2], (2 level, level 4], and (4 level, level 6]; the temperature value of sample cable a falls into the interval (20°C, 30°C], corresponding to The temperature evaluation value is 0.75, the humidity value of sample cable a falls into the interval of (30%, 60%], and the corresponding humidity evaluation value is 0.5. The humidity value of sample cable a falls into the interval of (0, 2 levels], and the corresponding humidity evaluation value is 0.2. The comprehensive environmental evaluation value of sample cable a is 1.45. 1.45, model A, 30 years, and 5 years are determined as the sample input data of sample cable a, and 30% is determined as the corresponding sample output data. In another embodiment, the environmental factor information of each sample cable includes only one environmental factor and the corresponding environmental factor value. The environmental factor of the sample cable and the environmental factor value, type, service life, and service time are determined as the sample input data, and the corresponding aging evaluation value is determined as the sample output data.

[0064] Step S303: performing model training based on the training data set and the preset pre-training model to obtain a trained cable aging assessment model.

[0065] Step S304: Obtain environmental factor information, type, service life and usage duration of the cable to be evaluated, determine input data based on the environmental factor information, type, service life and usage duration of the cable to be evaluated, and input the input data into the cable aging assessment model to perform aging assessment to obtain an aging assessment result of the cable to be evaluated.

[0066] From the above, it can be seen that after the aging assessment value of each sample cable is determined based on the performance information, the sample input data is determined according to the environmental factor information, type, service life and service time of each sample cable, and the aging assessment value of each sample cable is correspondingly determined as the sample output data associated with the sample input data, and the sample input data and the sample output data are determined as the training data set. This solution obtains a training data set by arranging the sample data of each sample cable, which enables the model to learn the laws and characteristics of cable aging.

[0067] Figure 4 A flowchart of another cable aging evaluation determination method based on sample data provided by an embodiment of the present invention provides a specific method for optional model training, such as Figure 4 As shown, specifically including:

[0068] Step S401: Acquire performance information of each sample cable under different collected environmental factor information, types, service life and service time, and determine an aging assessment value of each sample cable based on the performance information.

[0069] Step S402: determining a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and usage duration.

[0070] Step S403: input the sample input data in the training data set into the preset pre-trained model for prediction to obtain a corresponding predicted aging assessment value, compare the predicted aging assessment value with the sample output data in the training data set to obtain a corresponding difference value, and adjust the preset pre-trained model based on the difference value to obtain a trained cable aging assessment model.

[0071] Among them, the predicted aging assessment value is used to characterize the cable aging assessment value predicted by the preset pre-trained model by learning the rules and characteristics of the training data set. The sample input data in the training data set is input into the preset pre-trained model for prediction to obtain the corresponding predicted aging assessment value, the predicted aging assessment value is compared with the sample output data in the training data set to obtain the corresponding difference value, and the preset pre-trained model is adjusted based on the difference value to obtain a trained cable aging assessment model. Optionally, the parameters of the preset pre-trained model are adjusted according to the difference value, and the sample input data in the training data set is input into the adjusted preset pre-trained model for prediction again, until the difference value is less than the preset standard value to determine that the preset pre-trained model training is completed and determined as the cable aging assessment model, wherein the parameters of the preset pre-trained model mainly include variables that the preset pre-trained model needs to learn during the training process, such as weights and biases. An illustrative example may be that the currently input sample input data is an environmental factor comprehensive evaluation value of 1.5, cable type model A, service life of 30 years, and service time of 10 years. The corresponding sample output data is an aging evaluation value of 35%, and the predicted aging evaluation value predicted by the preset pre-trained model is 40%. The calculated difference between the predicted aging evaluation value and the sample output data is 5%, and the preset standard value is 1%. The difference value is greater than the preset standard value. The variable parameters such as weights and bias of the preset training model are adjusted according to the difference value of 5%. After the adjustment is completed, the environmental factor comprehensive evaluation value of 1.5, cable type model A, service life of 30 years, and service time of 10 years are input into the adjusted preset pre-trained model again to obtain a predicted aging evaluation value of 35.1%. The calculated difference between the predicted aging evaluation value and the sample output data is 0.1%, which is less than the preset standard value. The adjusted preset pre-trained model is determined as the cable aging evaluation model. In another embodiment, the parameters of the preset pre-trained model are adjusted according to the difference value, and the sample input data in the training data set is input into the adjusted preset pre-trained model for prediction again, until the number of adjustments reaches the preset number of times, it is determined that the training of the preset pre-trained model is completed and determined as the cable aging assessment model.

[0072] Step S404: Obtain environmental factor information, type, service life and usage duration of the cable to be evaluated, determine input data based on the environmental factor information, type, service life and usage duration of the cable to be evaluated, and input the input data into the cable aging assessment model to perform aging assessment to obtain an aging assessment result of the cable to be evaluated.

[0073] From the above, it can be seen that the sample input data in the training data set is input into the preset pre-trained model for prediction to obtain the corresponding predicted aging assessment value, the predicted aging assessment value is compared with the sample output data in the training data set to obtain the corresponding difference value, and the preset pre-trained model is adjusted based on the difference value to obtain the trained cable aging assessment model. This solution obtains a trained cable aging assessment model by training the training data set and the preset pre-trained model, which can simplify the subsequent actual cable aging assessment and ensure the accuracy of the cable aging assessment results.

[0074] Figure 5 This is a module structure block diagram of a cable aging evaluation determination system based on sample data provided by an embodiment of the present invention. The system is used to execute the cable aging evaluation determination method based on sample data provided by the above embodiment, and has the corresponding functional modules and beneficial effects of the execution method. Figure 5 As shown, the system specifically includes:

[0075] The acquisition module 101 is used to acquire the performance information of each sample cable under different environmental factor information, types, service life and service time;

[0076] An aging assessment value determination module 102, configured to determine an aging assessment value of each sample cable based on the performance information;

[0077] A training data determination module 103 is used to determine a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and service time;

[0078] A model training module 104 is used to perform model training based on the training data set and a preset pre-training model to obtain a trained cable aging assessment model;

[0079] The acquisition module 101 is also used to obtain the environmental factor information, type, service life and service time of the cable to be evaluated;

[0080] An input data determination module 105 is used to determine input data according to the environmental factor information, type, service life and service time of the cable to be evaluated;

[0081] The aging assessment module 106 is used to input the input data into the cable aging assessment model to perform aging assessment to obtain an aging assessment result of the cable to be assessed.

[0082] It can be seen from the above scheme that the performance information of each sample cable under different environmental factor information, types, service life and service time is obtained, the aging assessment value of each sample cable is determined based on the performance information, the training data set is determined according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and service time, the model training is performed based on the training data set and the preset pre-training model to obtain a trained cable aging assessment model, the environmental factor information, type, service life and service time of the cable to be evaluated is obtained, the input data is determined according to the environmental factor information, type, service life and service time of the cable to be evaluated, and the input data is input into the cable aging assessment model for aging assessment to obtain the aging assessment result of the cable to be evaluated. This scheme uses sample data to evaluate the aging of the cable, which solves the problems of low evaluation accuracy and efficiency in the existing cable aging assessment technology, and poor applicability to field conditions that are difficult to observe. It can efficiently and accurately realize cable aging assessment, is simple and easy, and has low labor costs.

[0083] In a possible embodiment, the aging assessment value determination module 102 is specifically configured to:

[0084] Aging assessment standard information corresponding to each different type of performance change data is determined respectively, and an aging assessment value of each sample cable is determined based on the performance change data and the aging assessment standard information.

[0085] In a possible embodiment, the aging assessment value determination module 102 is further configured to:

[0086] The performance degradation percentage is divided by the unit degradation percentage and multiplied by the corresponding standard aging assessment value to obtain the aging assessment value to be integrated, the preset weights of each different type of performance change data are determined, the aging assessment value to be integrated is multiplied by the corresponding preset weights and superimposed to obtain the aging assessment value of the sample cable.

[0087] In a possible embodiment, the training data determination module 103 is specifically configured to:

[0088] The sample input data is determined according to the environmental factor information, type, service life and usage time of each sample cable, the aging assessment value of each sample cable is correspondingly determined as the sample output data associated with the sample input data, and the sample input data and the sample output data are determined as a training data set.

[0089] In a possible embodiment, the training data determination module 103 is further used to:

[0090] Determine the preset interval associated with the corresponding environmental factor into which each environmental factor value of the sample cable falls, and superimpose the factor evaluation values ​​corresponding to the preset interval into which each environmental factor value falls to obtain the environmental comprehensive evaluation value of the corresponding sample cable;

[0091] The comprehensive environmental assessment value, type, service life and usage duration of each sample cable are determined as sample input data.

[0092] In a possible embodiment, the model training module 104 is specifically used to:

[0093] Inputting the sample input data in the training data set into the preset pre-training model for prediction to obtain a corresponding predicted aging assessment value, and comparing the predicted aging assessment value with the sample output data in the training data set to obtain a corresponding difference value;

[0094] The preset pre-trained model is adjusted based on the difference value to obtain a trained cable aging assessment model.

[0095] In a possible embodiment, the model training module 104 is further used to:

[0096] The parameters of the preset pre-trained model are adjusted according to the difference value, and the sample input data in the training data set is input into the adjusted preset pre-trained model for prediction again, until the difference value is less than the preset standard value, it is determined that the training of the preset pre-trained model is completed and determined as the cable aging assessment model.

[0097] Figure 6 A schematic diagram of a cable aging assessment and determination device based on sample data provided by an embodiment of the present invention is shown in FIG. Figure 6 As shown, the device includes a processor 201, a memory 202, an input device 203 and an output device 204; the number of processors 201 in the device can be one or more. Figure 6 A processor 201 is taken as an example; the processor 201, memory 202, input device 203 and output device 204 in the device can be connected by a bus or other means. Figure 6The example of connecting through a bus is taken. The memory 202, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions or modules corresponding to the cable aging assessment determination method based on sample data in the embodiment of the present invention. The processor 201 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 202, that is, implements the above-mentioned cable aging assessment determination method based on sample data. The input device 203 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the device. The output device 204 may include a display device such as a display screen.

[0098] An embodiment of the present invention further provides a storage medium containing computer executable instructions, wherein when the computer executable instructions are executed by a computer processor, the computer executable instructions are used to perform a cable aging evaluation determination method based on sample data, the method comprising:

[0099] Acquire the performance information of each sample cable under different environmental factor information, types, service life and service time, and determine the aging assessment value of each sample cable based on the performance information;

[0100] Determine a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and usage duration, and perform model training based on the training data set and a preset pre-trained model to obtain a trained cable aging assessment model;

[0101] The environmental factor information, type, service life and usage duration of the cable to be evaluated are obtained, input data is determined according to the environmental factor information, type, service life and usage duration of the cable to be evaluated, and the input data is input into the cable aging assessment model for aging assessment to obtain an aging assessment result of the cable to be evaluated.

[0102] It is worth noting that in the embodiment of the cable aging assessment determination method system based on sample data, the various units and modules included are only divided according to functional logic, but are not limited to the above 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 protection scope of the embodiments of the present invention.

[0103] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the embodiments of the present invention are not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the embodiments of the present invention. Therefore, although the embodiments of the present invention are described in more detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the embodiments of the present invention, and the scope of the embodiments of the present invention is determined by the scope of the appended claims.

Claims

1. A cable aging assessment determination method based on sample data, characterized in that: include: Acquire the performance information of each sample cable under different environmental factor information, types, service life and service time, and determine the aging assessment value of each sample cable based on the performance information; Determine a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and usage duration, and perform model training based on the training data set and a preset pre-trained model to obtain a trained cable aging assessment model; The environmental factor information, type, service life and usage duration of the cable to be evaluated are obtained, input data is determined according to the environmental factor information, type, service life and usage duration of the cable to be evaluated, and the input data is input into the cable aging assessment model for aging assessment to obtain an aging assessment result of the cable to be evaluated.

2. The cable aging evaluation determination method based on sample data according to claim 1, characterized in that: The performance information includes a plurality of different types of performance change data, and determining the aging evaluation value of each sample cable based on the performance information includes: Aging assessment standard information corresponding to each different type of performance change data is determined respectively, and an aging assessment value of each sample cable is determined based on the performance change data and the aging assessment standard information.

3. The cable aging evaluation determination method based on sample data according to claim 2 is characterized in that: The performance change data includes a performance degradation percentage, the aging assessment standard information includes a standard aging assessment value corresponding to a unit degradation percentage, and determining the aging assessment value of each sample cable based on the performance change data and the aging assessment standard information includes: The performance degradation percentage is divided by the unit degradation percentage and multiplied by the corresponding standard aging assessment value to obtain the aging assessment value to be integrated, the preset weights of each different type of performance change data are determined, the aging assessment value to be integrated is multiplied by the corresponding preset weights and superimposed to obtain the aging assessment value of the sample cable.

4. The cable aging assessment determination method based on sample data according to any one of claims 1 to 3, characterized in that: The determining of the training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and service time includes: The sample input data is determined according to the environmental factor information, type, service life and usage time of each sample cable, the aging assessment value of each sample cable is correspondingly determined as the sample output data associated with the sample input data, and the sample input data and the sample output data are determined as a training data set.

5. The cable aging evaluation determination method based on sample data according to claim 4 is characterized in that: The environmental factor information includes multiple environmental factors and corresponding environmental factor values. The sample input data is determined according to the environmental factor information, type, service life and service time of each sample cable, including: Determine the preset interval associated with the corresponding environmental factor into which each environmental factor value of the sample cable falls, and superimpose the factor evaluation values ​​corresponding to the preset interval into which each environmental factor value falls to obtain the environmental comprehensive evaluation value of the corresponding sample cable; The comprehensive environmental assessment value, type, service life and usage duration of each sample cable are determined as sample input data.

6. The cable aging assessment determination method based on sample data according to any one of claims 1 to 3, characterized in that: The method of performing model training based on the training data set and the preset pre-training model to obtain a trained cable aging assessment model includes: Inputting the sample input data in the training data set into the preset pre-training model for prediction to obtain a corresponding predicted aging assessment value, and comparing the predicted aging assessment value with the sample output data in the training data set to obtain a corresponding difference value; The preset pre-trained model is adjusted based on the difference value to obtain a trained cable aging assessment model.

7. The cable aging evaluation determination method based on sample data according to claim 6 is characterized in that: The method of adjusting the preset pre-trained model based on the difference value to obtain a trained cable aging assessment model includes: The parameters of the preset pre-trained model are adjusted according to the difference value, and the sample input data in the training data set is input into the adjusted preset pre-trained model for prediction again, until the difference value is less than the preset standard value, it is determined that the training of the preset pre-trained model is completed and determined as the cable aging assessment model.

8. A cable aging assessment and determination system based on sample data, characterized in that: include: An acquisition module is used to acquire performance information of each sample cable under different environmental factor information, types, service life and service time; An aging assessment value determination module, configured to determine an aging assessment value of each sample cable based on the performance information; A training data determination module, used to determine a training data set according to the aging assessment value of each sample cable and the corresponding environmental factor information, type, service life and service time; A model training module, used for performing model training based on the training data set and a preset pre-training model to obtain a trained cable aging assessment model; The acquisition module is also used to obtain environmental factor information, type, service life and service time of the cable to be evaluated; An input data determination module, used to determine input data according to the environmental factor information, type, service life and service time of the cable to be evaluated; The aging assessment module is used to input the input data into the cable aging assessment model to perform aging assessment to obtain an aging assessment result of the cable to be assessed.

9. A cable aging assessment and determination device based on sample data, the device comprising: one or more processors; A storage device 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 cable aging assessment determination method based on sample data as described in any one of claims 1-7.

10. A storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the cable aging evaluation determination method based on sample data according to any one of claims 1 to 7 when executed by a computer processor.

Images