Vehicle-mounted cable terminal evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of trains, and discloses a vehicle-mounted cable terminal evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: exporting normal spectral data and defect spectral data from a terahertz time-domain spectroscopy system; obtaining current spectral data, and inputting the current spectral data into the trained YOLOv8 target detection model; processing the current spectral data through the trained YOLOv8 target detection model to obtain a defect detection result of the current vehicle-mounted cable terminal; when the defect detection result is a normal label, acquiring a radar spectrogram corresponding to the current vehicle-mounted cable terminal, acquiring a polygon area in the radar spectrogram, when the polygon area in the radar spectrogram is not greater than a preset area, evaluating that the current vehicle-mounted cable terminal is not in an aging state, and when the polygon area in the radar spectrogram is greater than the preset area, evaluating that the current vehicle-mounted cable terminal is not in an aging state. And evaluating that the current vehicle-mounted cable terminal is in an aging state. According to the invention, defects and aging of the current vehicle-mounted cable terminal can be evaluated.

Description

Technical Field

[0001] The present application relates to the field of train technology, and in particular to a vehicle-mounted cable terminal evaluation method, device, electronic device, and storage medium. Background Art

[0002] Exposed onboard cable terminals are highly susceptible to harsh environments. Under these conditions, they are subject to prolonged thermal, electrical, and vibration stresses, making them susceptible to aging and degradation of insulation. Therefore, assessing whether onboard cable terminals are aging is a pressing technical challenge.

[0003] Furthermore, due to the on-site construction environment and the technical level of the construction workers, the assembly process of the on-board cable terminal is prone to problems such as scratches on the internal insulation surface, residual conductive metal particles, insufficient pressure at the interface connection, and unreasonable electric field margin design. These problems can easily induce internal defects in the on-board cable terminal. Therefore, how to obtain the defect identification results of the current on-board cable terminal is also a technical problem that needs to be solved urgently.

[0004] In summary, how to obtain the defect identification results of the current on-board cable terminals and how to evaluate whether the current on-board cable terminals are in an aging state are both technical problems that need to be solved urgently. Summary of the Invention

[0005] The embodiments of the present application provide a vehicle-mounted cable terminal evaluation method, device, electronic device and storage medium to solve the technical problem of how to obtain the defect identification result of the current vehicle-mounted cable terminal and how to evaluate whether the current vehicle-mounted cable terminal is in an aging state.

[0006] In a first aspect, an embodiment of the present application provides a vehicle-mounted cable terminal evaluation method, which is applied to an electronic device. The vehicle-mounted cable terminal evaluation method includes:

[0007] Exporting normal spectrum data and defect spectrum data from a terahertz time-domain spectroscopy system;

[0008] Normal spectral data and normal labels are combined into normal samples, and defect spectral data and defect labels are combined into defect samples;

[0009] Different normal samples and different defect samples are combined into a training set, and the training set is used to train the YOLOv8 target detection model;

[0010] Get the loss value of the YOLOv8 target detection model in the training set. When the loss value is less than the preset value, save the trained YOLOv8 target detection model.

[0011] Obtain current spectral data and input the current spectral data into the trained YOLOv8 target detection model. The current spectral data is the terahertz time domain spectral data and terahertz frequency domain spectral data obtained by the terahertz time domain data system testing the current on-board cable terminal.

[0012] The trained YOLOv8 target detection model is used to process the current spectral data and obtain the defect detection results of the current on-board cable terminal.

[0013] When the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the polygon area in the radar spectrum, and when the polygon area in the radar spectrum is not larger than the preset area, evaluate that the current on-board cable terminal is not in an aging state; when the polygon area in the radar spectrum is larger than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0014] In a possible implementation of the first aspect, deriving normal spectrum data and defect spectrum data from the terahertz time-domain spectroscopy system includes:

[0015] exporting a first data file and a second data file from a terahertz time-domain spectroscopy system;

[0016] Normal spectrum data in the first data file is obtained, and normal spectrum data in the second data file is obtained.

[0017] In a possible implementation of the first aspect, forming a training set from different normal samples and different defective samples, and using the training set to train a YOLOv8 object detection model includes:

[0018] Different normal samples and different defect samples are combined into a training set;

[0019] Obtain the model file, load the YOLOv8 target detection model through the model file, and use the training set to train the YOLOv8 target detection model.

[0020] In a possible implementation of the first aspect, obtaining a loss value of the YOLOv8 object detection model in a training set, and saving the trained YOLOv8 object detection model when the loss value is less than a preset value, includes:

[0021] Obtain the loss value of the YOLOv8 target detection model in the training set through the cross entropy loss function;

[0022] When the loss value is less than the preset value, stop training the YOLOv8 target detection model and save the trained YOLOv8 target detection model.

[0023] In a possible implementation of the first aspect, obtaining the current spectral data and inputting the current spectral data into a trained YOLOv8 object detection model includes:

[0024] exporting a third data file from the terahertz time-domain spectroscopy system;

[0025] Obtaining current spectral data from a third data file and inputting the current spectral data into a trained YOLOv8 target detection model. In one possible implementation of the first aspect, when the defect detection result is a normal label, obtaining a radar spectrum corresponding to the current on-board cable terminal, obtaining a polygonal area in the radar spectrum, and when the polygonal area in the radar spectrum is not greater than a preset area, evaluating that the current on-board cable terminal is not in an aging state; and when the polygonal area in the radar spectrum is greater than a preset area, evaluating that the current on-board cable terminal is in an aging state, includes:

[0026] When the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the current value of each evaluation indicator in the current on-board cable terminal, and perform dimensionless processing on the current value of each evaluation indicator in the current on-board cable terminal through a standard normalization method to obtain the standard value of each evaluation indicator in the current on-board cable terminal;

[0027] Obtain the weight value corresponding to each evaluation indicator, generate the fan angle of each evaluation indicator according to the weight value corresponding to each evaluation indicator and the first generation model, generate the polygon area in the radar spectrum according to the standard value of each evaluation indicator in the current on-board cable terminal, the fan angle corresponding to each evaluation indicator and the preset second generation model, when the polygon area in the radar spectrum is not larger than the preset area, evaluate that the current on-board cable terminal is not in an aging state, and when the polygon area in the radar spectrum is larger than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0028] In a possible implementation of the first aspect,

[0029] After evaluating that the current on-board cable terminal is in an aging state when the polygon area in the radar spectrum is greater than a preset area, the on-board cable terminal evaluation method includes:

[0030] Displays a reminder message that the current vehicle cable terminal is in an aging state.

[0031] In a second aspect, an embodiment of the present application provides a vehicle-mounted cable terminal evaluation device, which is applied to an electronic device, including:

[0032] An export module, used to export normal spectrum data and defect spectrum data from the terahertz time-domain spectroscopy system;

[0033] A composition module, configured to combine normal spectral data and normal labels into normal samples, and combine defect spectral data and defect labels into defect samples;

[0034] A module is used to combine different normal samples and different defect samples into a training set, and the training set is used to train the YOLOv8 target detection model;

[0035] The saving module is used to obtain the loss value of the YOLOv8 target detection model in the training set. When the loss value is less than the preset value, the trained YOLOv8 target detection model is saved;

[0036] An acquisition module is used to obtain current spectral data and input the current spectral data into the trained YOLOv8 target detection model. The current spectral data is the terahertz time domain spectral data and terahertz frequency domain spectral data obtained by the terahertz time domain data system testing the current on-board cable terminal;

[0037] The detection module is used to process the current spectral data using the trained YOLOv8 target detection model to obtain the defect detection results of the current on-board cable terminal;

[0038] The evaluation module is used to obtain the radar spectrum corresponding to the current on-board cable terminal when the defect detection result is a normal label, obtain the polygon area in the radar spectrum, and when the polygon area in the radar spectrum is not greater than the preset area, evaluate that the current on-board cable terminal is not in an aging state; when the polygon area in the radar spectrum is greater than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the vehicle cable terminal evaluation method of the first aspect when executing the computer program.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the vehicle-mounted cable terminal evaluation method of the first aspect.

[0041] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the vehicle cable terminal evaluation method of the first aspect.

[0042] The beneficial effects of the embodiments of the present application lie in two aspects. On the one hand, the current spectral data is processed by the trained YOLOv8 target detection model to obtain the defect detection result of the current on-board cable terminal, thereby solving the technical problem of how to obtain the defect identification result of the current on-board cable terminal; on the other hand, when the defect detection result is a normal label, the radar spectrum corresponding to the current on-board cable terminal is obtained, and the polygon area in the radar spectrum is obtained. When the polygon area in the radar spectrum is not greater than the preset area, it is evaluated that the current on-board cable terminal is not in an aging state. When the polygon area in the radar spectrum is greater than the preset area, it is evaluated that the current on-board cable terminal is in an aging state. Therefore, the technical problem of how to evaluate whether the current on-board cable terminal is in an aging state is solved. Since the current on-board cable terminal is automatically evaluated as to whether it is in an aging state, the aging evaluation time of the current on-board cable terminal is reduced, which is conducive to improving the aging evaluation efficiency of the current on-board cable terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 This is a diagram showing an application scenario of the vehicle-mounted cable terminal evaluation method provided in an embodiment of the present application;

[0045] Figure 2 1 is a flow chart of a vehicle-mounted cable terminal evaluation method provided in an embodiment of the present application;

[0046] Figure 3 A flowchart for evaluating aging status provided in an embodiment of the present application;

[0047] Figure 4 A schematic block diagram of a vehicle-mounted cable terminal evaluation device provided in an embodiment of the present application;

[0048] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0049] Figure 6 This is a first example diagram provided in the embodiment of the present application;

[0050] Figure 7 A second example diagram provided for an embodiment of the present application;

[0051] Figure 8 This is the third sample diagram provided for the embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0053] The vehicle-mounted cable terminal evaluation method provided in the embodiments of the present application can be applied to electronic devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). The embodiments of the present application do not impose any restrictions on the specific types of electronic devices.

[0054] See also Figure 1 , Figure 1 The application scenario diagram of the vehicle-mounted cable terminal evaluation method provided in the embodiment of the present application is detailed as follows:

[0055] The electronic device derives normal spectrum data and defect spectrum data from the terahertz time-domain spectroscopy system.

[0056] The electronic device exports the first data file and the second data file from the terahertz time-domain spectroscopy system, obtains normal spectrum data in the first data file, and obtains normal spectrum data in the second data file.

[0057] In the embodiment of the present application, the electronic device can access the first data file and the second data file simultaneously, obtain the normal spectrum data in the first data file, and obtain the normal spectrum data in the second data file.

[0058] See also Figure 2 , Figure 2 This is a flow chart of a vehicle-mounted cable terminal evaluation method provided in an embodiment of the present application, which can be applied to electronic equipment.

[0059] like Figure 2 As shown, the vehicle-mounted cable terminal evaluation method provided in the embodiment of the present application includes the following steps, which are detailed as follows:

[0060] S201, exporting normal spectrum data and defect spectrum data from a terahertz time-domain spectroscopy system;

[0061] Among them, the normal spectrum data and defect spectrum data are derived from the terahertz time-domain spectroscopy system, including:

[0062] exporting a first data file and a second data file from a terahertz time-domain spectroscopy system;

[0063] Normal spectrum data in the first data file is obtained, and normal spectrum data in the second data file is obtained.

[0064] Among them, the normal spectrum data is the terahertz time domain spectrum data and terahertz frequency domain spectrum data obtained by the terahertz time domain data system testing a normal preset on-board cable terminal;

[0065] Among them, the defect spectrum data are terahertz time domain spectrum data and terahertz frequency domain spectrum data obtained by the terahertz time domain data system testing a preset vehicle cable terminal with defects.

[0066] Among them, terahertz time-domain spectroscopy data is the data of terahertz waves in the time domain.

[0067] Among them, terahertz frequency domain spectral data is the data of terahertz waves in the frequency domain.

[0068] Among them, the preset vehicle-mounted cable terminal is a preset vehicle-mounted cable terminal.

[0069] S202, normal spectrum data and normal labels are combined into normal samples, and defect spectrum data and defect labels are combined into defect samples;

[0070] S203, different normal samples and different defect samples are combined into a training set, and the training set is used to train a YOLOv8 object detection model;

[0071] The method of forming a training set with different normal samples and different defect samples and using the training set to train the YOLOv8 target detection model includes:

[0072] Different normal samples and different defect samples are combined into a training set;

[0073] Obtain the model file, load the YOLOv8 target detection model through the model file, and use the training set to train the YOLOv8 target detection model.

[0074] Among them, the YOLOv8 target detection model is the eighth-generation target detection model in the YOLO series.

[0075] Among them, YOLO’s Chinese name is: Single Detection, and YOLO’s full English name is: You Only Look Once.

[0076] S204, obtaining the loss value of the YOLOv8 target detection model in the training set, and when the loss value is less than a preset value, saving the trained YOLOv8 target detection model;

[0077] The step of obtaining the loss value of the YOLOv8 target detection model in the training set and saving the trained YOLOv8 target detection model when the loss value is less than a preset value includes:

[0078] Obtain the loss value of the YOLOv8 target detection model in the training set through the cross entropy loss function;

[0079] When the loss value is less than the preset value, stop training the YOLOv8 target detection model and save the trained YOLOv8 target detection model.

[0080] S205, obtaining current spectral data, and inputting the current spectral data into the trained YOLOv8 target detection model, where the current spectral data is terahertz time domain spectral data and terahertz frequency domain spectral data obtained by the terahertz time domain data system testing the current on-board cable terminal;

[0081] Among them, the current on-board cable terminal is the current on-board cable terminal.

[0082] The onboard cable terminal is indeed a key component in the train. It transmits electrical energy to the traction system, which drives the train.

[0083] The step of obtaining the current spectral data and inputting the current spectral data into the trained YOLOv8 target detection model includes:

[0084] exporting a third data file from the terahertz time-domain spectroscopy system;

[0085] The current spectral data in the third data file is obtained, and the current spectral data is input into the trained YOLOv8 target detection model.

[0086] S206, processing the current spectral data using the trained YOLOv8 target detection model to obtain a defect detection result of the current on-board cable terminal;

[0087] Since the defect recognition result of the current on-board cable terminal is automatically obtained, the defect recognition time of the current on-board cable terminal is reduced, which is beneficial to improving the defect recognition efficiency of the current on-board cable terminal.

[0088] S207, when the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the polygon area in the radar spectrum, when the polygon area in the radar spectrum is not greater than the preset area, evaluate that the current on-board cable terminal is not in an aging state, when the polygon area in the radar spectrum is greater than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0089] Wherein, when the defect detection result is a normal label, obtaining a radar spectrum corresponding to the current on-board cable terminal, obtaining a polygonal area in the radar spectrum, when the polygonal area in the radar spectrum is not greater than a preset area, evaluating that the current on-board cable terminal is not in an aging state; when the polygonal area in the radar spectrum is greater than a preset area, evaluating that the current on-board cable terminal is in an aging state, includes:

[0090] When the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the current value of each evaluation indicator in the current on-board cable terminal, and perform dimensionless processing on the current value of each evaluation indicator in the current on-board cable terminal through a standard normalization method to obtain the standard value of each evaluation indicator in the current on-board cable terminal;

[0091] Obtain the weight value corresponding to each evaluation indicator, generate the fan angle of each evaluation indicator according to the weight value corresponding to each evaluation indicator and the first generation model, generate the polygon area in the radar spectrum according to the standard value of each evaluation indicator in the current on-board cable terminal, the fan angle corresponding to each evaluation indicator and the preset second generation model, when the polygon area in the radar spectrum is not larger than the preset area, evaluate that the current on-board cable terminal is not in an aging state, and when the polygon area in the radar spectrum is larger than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0092] Wherein, when the polygon area in the radar spectrum is greater than the preset area, after evaluating that the current on-board cable terminal is in an aging state, the on-board cable terminal evaluation method includes:

[0093] Displays a reminder message that the current vehicle cable terminal is in an aging state.

[0094] The content of the reminder message indicating that the vehicle-mounted cable terminal is in an aging state is set by the user or by the system by default.

[0095] For ease of explanation, the following examples are given:

[0096] For example, the content of the reminder message that the current vehicle cable terminal is in an aging state is: The current vehicle cable terminal is in an aging state, please check it immediately.

[0097] For example, the content of the reminder message that the current vehicle cable terminal is in an aging state is: The current vehicle cable terminal is in an aging state, please replace it in time.

[0098] Optionally, after S206, the vehicle-mounted cable terminal evaluation method further includes:

[0099] Step A: When the defect detection result is a defect label, a reminder message indicating that the current vehicle-mounted cable terminal has a defect is displayed.

[0100] After S206, S207 or step A is executed.

[0101] The content of the reminder message indicating that the vehicle-mounted cable terminal has defects is set by the user or by system default.

[0102] For ease of explanation, the following examples are given:

[0103] For example, the content of the reminder message that the current vehicle cable terminal has a defect is: The current vehicle cable terminal has a defect, please check it immediately.

[0104] For example, the content of the reminder message that the current vehicle cable terminal is defective is: The current vehicle cable terminal is defective, please replace it in time.

[0105] The beneficial effects of the embodiments of the present application lie in two aspects. On the one hand, the current spectral data is processed by the trained YOLOv8 target detection model to obtain the defect detection result of the current on-board cable terminal, thereby solving the technical problem of how to obtain the defect identification result of the current on-board cable terminal; on the other hand, when the defect detection result is a normal label, the radar spectrum corresponding to the current on-board cable terminal is obtained, and the polygon area in the radar spectrum is obtained. When the polygon area in the radar spectrum is not greater than the preset area, it is evaluated that the current on-board cable terminal is not in an aging state. When the polygon area in the radar spectrum is greater than the preset area, it is evaluated that the current on-board cable terminal is in an aging state. Therefore, the technical problem of how to evaluate whether the current on-board cable terminal is in an aging state is solved. Since the current on-board cable terminal is automatically evaluated as to whether it is in an aging state, the aging evaluation time of the current on-board cable terminal is reduced, which is conducive to improving the aging evaluation efficiency of the current on-board cable terminal.

[0106] See also Figure 3 , Figure 3 The flowchart for evaluating the aging status provided in the embodiment of the present application is detailed as follows:

[0107] S301, when the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the current value of each evaluation indicator in the current on-board cable terminal, and perform dimensionless processing on the current value of each evaluation indicator in the current on-board cable terminal using a standard normalization method to obtain the standard value of each evaluation indicator in the current on-board cable terminal;

[0108] Among them, S301 includes:

[0109] When the defect detection result is a normal label, starting from the positive direction of the x-axis, in a counterclockwise direction, the sector area corresponding to each evaluation indicator is drawn, and the sector area corresponding to each evaluation indicator is combined to form the radar spectrum of the current vehicle cable;

[0110] The current value of each evaluation indicator in the current on-board cable terminal is obtained, and the current value of each evaluation indicator in the current on-board cable terminal is dimensionlessly processed by a standard normalization method to obtain the standard value of each evaluation indicator in the current on-board cable terminal.

[0111] S302, obtain the weight value corresponding to each evaluation indicator, generate the fan angle of each evaluation indicator according to the weight value corresponding to each evaluation indicator and the first generation model, generate the polygon area in the radar spectrum according to the standard value of each evaluation indicator in the current on-board cable terminal, the fan angle corresponding to each evaluation indicator and the preset second generation model, when the polygon area in the radar spectrum is not larger than the preset area, evaluate that the current on-board cable terminal is not in an aging state, when the polygon area in the radar spectrum is larger than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0112] Exemplarily, the first generative model is:

[0113] θ j =2×L j ×π;

[0114] Among them, L j is the weight value of the jth evaluation index; θ j is the sector angle of the jth evaluation indicator, and π represents pi, which is used to convert the weight value of the jth evaluation indicator into an angle in radians.

[0115] For ease of explanation, the following examples are given:

[0116] For example, L j =0.25:θ j It is 0.5π, which is the radian corresponding to half a circle.

[0117] For example, L j =0.125:θ jIt is 0.25π, which is the arc corresponding to one quarter of a circle.

[0118] Exemplarily, the second generative model is:

[0119]

[0120] Where S is the polygon area in the radar spectrum, x j represents the standard value of the jth evaluation index of the current vehicle cable terminal, θ j represents the fan angle of the jth evaluation index, θ j-1 It represents the fan angle of the previous evaluation indicator of the j-th evaluation indicator, where j is the serial number of the evaluation indicator.

[0121] Among them, the second generation model is expanded and detailed as follows:

[0122]

[0123] Where S is the polygon area in the radar spectrum, x1 represents the standard value of the first evaluation index of the current vehicle cable terminal, x2 represents the standard value of the second evaluation index of the current vehicle cable terminal, x3 represents the standard value of the third evaluation index of the current vehicle cable terminal, θ1 represents the sector angle of the jth evaluation index, θ2 represents the sector angle of the second evaluation index, θ3 represents the sector angle of the third evaluation index, and θ j represents the fan angle of the jth evaluation index, θ j-1 It represents the fan angle of the previous evaluation indicator of the j-th evaluation indicator, where j is the serial number of the evaluation indicator.

[0124] Furthermore, for the sake of convenience, the second generation model is given as an example with the value of j being 4, and is described in detail as follows:

[0125]

[0126] Where S is the polygon area in the radar spectrum, x1 represents the standard value of the first evaluation index of the current on-board cable terminal, x2 represents the standard value of the second evaluation index of the current on-board cable terminal, x3 represents the standard value of the third evaluation index of the current on-board cable terminal, x4 represents the standard value of the fourth evaluation index of the current on-board cable terminal, θ1 represents the sector angle of the j-th evaluation index, θ1 represents the sector angle of the first evaluation index, θ2 represents the sector angle of the second evaluation index, θ3 represents the sector angle of the third evaluation index, and θ4 represents the sector angle of the fourth evaluation index.

[0127] Among them, the first evaluation index of the current on-board cable terminal is transmittance;

[0128] Among them, the second evaluation index of the current on-board cable terminal is the extinction coefficient;

[0129] Among them, the third evaluation indicator of the current on-board cable terminal is dielectric loss;

[0130] Among them, the fourth evaluation indicator of the current on-board cable terminal is the refractive index.

[0131] Among them, the aging state includes thermal aging state, electrothermal aging state, and vibration electrothermal aging state.

[0132] Among them, the thermal aging state is the performance degradation state caused by thermal effects;

[0133] Among them, the electrothermal aging state is the performance degradation state caused by both electrothermal effect and thermal effect;

[0134] Among them, the vibration electrothermal aging state is a performance degradation state caused by vibration effect, electrothermal effect and thermal effect.

[0135] refer to Figure 6 , Figure 6 This is the first example diagram provided for the embodiment of the present application.

[0136] For ease of explanation, the radar spectrum is used as the first example, as follows:

[0137] The first sample diagram includes fan-shaped areas corresponding to the transmittance, extinction coefficient, dielectric loss, and refractive index. The area composed of the non-aged area in the first sample diagram is selected as the first area. When the polygon area in the first sample diagram is not larger than the first area, it is evaluated that the current on-board cable terminal is not in an aging state. When the polygon area in the first sample diagram is larger than the first area, the larger the polygon area in the first sample diagram, the more days the current on-board cable terminal is in a thermal aging state.

[0138] Among them, heat aging 4d means that the number of days in the heat aging state is 4 days.

[0139] Among them, heat aging 6d means that the number of days in the heat aging state is 6 days.

[0140] Among them, heat aging 12d means that the number of days in the heat aging state is 12 days.

[0141] Among them, heat aging 16d means that the number of days in the heat aging state is 16 days.

[0142] The heat aging state 20d indicates that the number of days in the heat aging state is 20 days.

[0143] refer to Figure 7 , Figure 7 This is the second example diagram provided for the embodiment of the present application.

[0144] For ease of explanation, the radar spectrum is used as the second sample diagram as an example as follows:

[0145] The second sample graph includes fan-shaped areas corresponding to the transmittance, extinction coefficient, dielectric loss, and refractive index. The area composed of the non-aged areas in the second sample graph is selected as the second area. When the polygon area in the second sample graph is not larger than the second area, it is evaluated that the current vehicle cable terminal is not in an aging state. When the polygon area in the second sample graph is larger than the second area, the larger the polygon area in the second sample graph, the more days the current vehicle cable terminal is in an electrothermal aging state.

[0146] Among them, electrothermal aging 4d means that the number of days in the electrothermal aging state is 4 days.

[0147] Among them, electrothermal aging 6d means that the number of days in the electrothermal aging state is 6 days.

[0148] Among them, electrothermal aging 12d means that the number of days in the electrothermal aging state is 12 days.

[0149] Among them, electrothermal aging 16d means that the number of days in the electrothermal aging state is 16 days.

[0150] The electrothermal aging state 20d indicates that the number of days in the electrothermal aging state is 20 days.

[0151] refer to Figure 8 , Figure 8 This is the third sample diagram provided for the embodiment of the present application.

[0152] For ease of explanation, the radar spectrum is used as the third sample diagram as an example, as follows:

[0153] The third sample diagram includes fan-shaped areas corresponding to the transmittance, extinction coefficient, dielectric loss, and refractive index. The area composed of the non-aged areas in the third sample diagram is selected as the third area. When the polygon area in the third sample diagram is not larger than the third area, it is evaluated that the current vehicle cable terminal is not in a vibration aging and electrothermal aging state. When the polygon area in the third sample diagram is larger than the third area, the larger the polygon area in the third sample diagram, the more days the current vehicle cable terminal is in a vibration and electrothermal aging state.

[0154] Among them, vibration electrothermal aging 4d means that the number of days in the vibration electrothermal aging state is 4 days.

[0155] Among them, vibration electrothermal aging 6d means that the number of days in the vibration electrothermal aging state is 6 days.

[0156] Among them, vibration electrothermal aging 12d means that the number of days in the vibration electrothermal aging state is 12 days.

[0157] Among them, 16d of vibration electrothermal aging indicates that the number of days in the vibration electrothermal aging state is 16 days.

[0158] Among them, 20d of vibration electrothermal aging indicates that the number of days in the vibration electrothermal aging state is 20 days.

[0159] Among them, the first area, the second area, and the third area are different areas.

[0160] Among them, d in 4d, 6d, 12d, 16d, 20d is the abbreviation of day, and the Chinese of day is day.

[0161] In the embodiments of the present application, since the current on-vehicle cable terminal is automatically evaluated for its aging state, the aging evaluation time of the current on-vehicle cable terminal is reduced, which is beneficial to improving the aging evaluation efficiency of the current on-vehicle cable terminal.

[0162] Corresponding to the on-vehicle cable terminal evaluation method described in the above embodiments, please refer to Figure 4 , Figure 4 which is a schematic block diagram of the on-vehicle cable terminal evaluation device provided by the embodiments of the present application. Figure 4 The shown on-vehicle cable terminal evaluation device 400 can be applied to an electronic device in the application scenario diagram shown in Figure 1 The following takes the electronic device as an example to elaborate on the Figure 4 shown on-vehicle cable terminal evaluation device 400 in detail. The on-vehicle cable terminal evaluation device 400 may include an export module 401, a composition module 402, an adoption module 403, a storage module 404, an acquisition module 405, a detection module 406, and an evaluation module 407.

[0163] The export module 401 is used to export normal spectral data and defect spectral data from the terahertz time-domain spectroscopy system;

[0164] The composition module 402 is used to form normal samples by combining normal spectral data and normal labels, and form defect samples by combining defect spectral data and defect labels;

[0165] The adoption module 403 is used to form a training set by combining different normal samples and different defect samples, and train the YOLOv8 object detection model using the training set;

[0166] The storage module 404 is used to obtain the loss value of the YOLOv8 object detection model in the training set, and when the loss value is less than the preset value, save the trained YOLOv8 object detection model;

[0167] An acquisition module 405 is configured to acquire current spectral data and input the current spectral data into a trained YOLOv8 target detection model. The current spectral data is terahertz time domain spectral data and terahertz frequency domain spectral data obtained by the terahertz time domain data system testing the current on-board cable terminal.

[0168] The detection module 406 is used to process the current spectral data using the trained YOLOv8 target detection model to obtain a defect detection result of the current on-board cable terminal;

[0169] Evaluation module 407 is used to obtain the radar spectrum corresponding to the current on-board cable terminal when the defect detection result is a normal label, obtain the polygon area in the radar spectrum, and when the polygon area in the radar spectrum is not greater than the preset area, evaluate that the current on-board cable terminal is not in an aging state; when the polygon area in the radar spectrum is greater than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0170] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced to each other.

[0171] The beneficial effects of the embodiments of the present application lie in two aspects. On the one hand, the current spectral data is processed by the trained YOLOv8 target detection model to obtain the defect detection result of the current on-board cable terminal, thereby solving the technical problem of how to obtain the defect identification result of the current on-board cable terminal; on the other hand, when the defect detection result is a normal label, the radar spectrum corresponding to the current on-board cable terminal is obtained, and the polygon area in the radar spectrum is obtained. When the polygon area in the radar spectrum is not greater than the preset area, it is evaluated that the current on-board cable terminal is not in an aging state. When the polygon area in the radar spectrum is greater than the preset area, it is evaluated that the current on-board cable terminal is in an aging state. Therefore, the technical problem of how to evaluate whether the current on-board cable terminal is in an aging state is solved. Since the current on-board cable terminal is automatically evaluated as to whether it is in an aging state, the aging evaluation time of the current on-board cable terminal is reduced, which is conducive to improving the aging evaluation efficiency of the current on-board cable terminal.

[0172] See also Figure 5 , Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0173] like Figure 5 As shown, Figure 5The electronic device 2 includes: at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 implements the steps of any of the above-mentioned method embodiments when executing the computer program 22.

[0174] The electronic device 2 may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will appreciate that Figure 5 This is merely an example of the electronic device 2 and does not constitute a limitation on the electronic device 2 . The electronic device 2 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 2 may also include input and output devices, network access devices, etc.

[0175] The processor 20 is configured to run a computer program 22 stored in the memory 21 and implement the following steps when executing the computer program 22:

[0176] Exporting normal spectrum data and defect spectrum data from a terahertz time-domain spectroscopy system;

[0177] Normal spectral data and normal labels are combined into normal samples, and defect spectral data and defect labels are combined into defect samples;

[0178] Different normal samples and different defect samples are combined into a training set, and the training set is used to train the YOLOv8 target detection model;

[0179] Get the loss value of the YOLOv8 target detection model in the training set. When the loss value is less than the preset value, save the trained YOLOv8 target detection model.

[0180] Obtain current spectral data, and input the current spectral data into the trained YOLOv8 target detection model. The current spectral data is terahertz time domain spectral data and terahertz frequency domain spectral data obtained by the terahertz time domain data system to test the current on-board cable terminal; the current spectral data is processed by the trained YOLOv8 target detection model to obtain the defect detection result of the current on-board cable terminal; when the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, and obtain the polygon area in the radar spectrum. When the polygon area in the radar spectrum is not greater than the preset area, it is evaluated that the current on-board cable terminal is not in an aging state. When the polygon area in the radar spectrum is greater than the preset area, it is evaluated that the current on-board cable terminal is in an aging state.

[0181] In some embodiments, the processor 20 is configured to implement:

[0182] exporting a first data file and a second data file from a terahertz time-domain spectroscopy system;

[0183] Normal spectrum data in the first data file is obtained, and normal spectrum data in the second data file is obtained.

[0184] In some embodiments, the processor 20 is configured to implement:

[0185] Different normal samples and different defect samples are combined into a training set;

[0186] Obtain the model file, load the YOLOv8 target detection model through the model file, and use the training set to train the YOLOv8 target detection model.

[0187] In some embodiments, the processor 20 is configured to implement:

[0188] Obtain the loss value of the YOLOv8 target detection model in the training set through the cross entropy loss function;

[0189] When the loss value is less than the preset value, stop training the YOLOv8 target detection model and save the trained YOLOv8 target detection model.

[0190] In some embodiments, the processor 20 is configured to implement:

[0191] exporting a third data file from the terahertz time-domain spectroscopy system;

[0192] The current spectral data in the third data file is obtained, and the current spectral data is input into the trained YOLOv8 target detection model.

[0193] In some embodiments, the processor 20 is configured to implement:

[0194] When the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the current value of each evaluation indicator in the current on-board cable terminal, and perform dimensionless processing on the current value of each evaluation indicator in the current on-board cable terminal through a standard normalization method to obtain the standard value of each evaluation indicator in the current on-board cable terminal;

[0195] Obtain the weight value corresponding to each evaluation indicator, generate the fan angle of each evaluation indicator according to the weight value corresponding to each evaluation indicator and the first generation model, generate the polygon area in the radar spectrum according to the standard value of each evaluation indicator in the current on-board cable terminal, the fan angle corresponding to each evaluation indicator and the preset second generation model, when the polygon area in the radar spectrum is not larger than the preset area, evaluate that the current on-board cable terminal is not in an aging state, and when the polygon area in the radar spectrum is larger than the preset area, evaluate that the current on-board cable terminal is in an aging state.

[0196] In some embodiments, the processor 20 is configured to implement:

[0197] Displays a reminder message that the current vehicle cable terminal is in an aging state.

[0198] The processor 20 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors, application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0199] In some embodiments, the memory 21 may be an internal storage unit of the electronic device 2, such as a hard disk or memory of the electronic device 2. In other embodiments, the memory 21 may also be an external storage device of the electronic device 2. Furthermore, the memory 21 may include both an internal storage unit of the electronic device 2 and an external storage device. The memory 21 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 21 may also be used to temporarily store data that has been output or is about to be output.

[0200] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0201] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the steps in the above-mentioned various method embodiments.

[0202] The computer-readable storage medium stores program codes, which can be called by a processor to execute the vehicle-mounted cable terminal evaluation method described in the above method embodiment.

[0203] The computer-readable storage medium has a storage space for program codes.

[0204] The program code includes the code of any step in the vehicle cable terminal evaluation method described in the above method embodiment.

[0205] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0206] Since the computer program stored in the computer-readable storage medium can execute any of the vehicle-mounted cable terminal evaluation methods provided in the embodiments of the present application, the computer-readable storage medium can achieve the beneficial effects that can be achieved by any of the vehicle-mounted cable terminal evaluation methods provided in the embodiments of the present application. Please refer to the previous embodiments for details and will not be repeated here.

[0207] An embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the above-mentioned vehicle cable terminal evaluation method.

[0208] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0209] Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable medium includes at least: an entity or device that carries the computer program code to an electronic device, a computer memory, a read-only memory (ROM), and a random access memory (RAM).

[0210] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle-mounted cable terminal evaluation method, characterized in that: Applied to electronic equipment, the vehicle-mounted cable terminal evaluation method includes: Exporting normal spectrum data and defect spectrum data from a terahertz time-domain spectroscopy system; Normal spectral data and normal labels are combined into normal samples, and defect spectral data and defect labels are combined into defect samples; Different normal samples and different defect samples are combined into a training set, and the training set is used to train the YOLOv8 target detection model; Get the loss value of the YOLOv8 target detection model in the training set. When the loss value is less than the preset value, save the trained YOLOv8 target detection model. Obtain current spectral data and input the current spectral data into the trained YOLOv8 target detection model. The current spectral data is the terahertz time domain spectral data and terahertz frequency domain spectral data obtained by the terahertz time domain data system testing the current on-board cable terminal. The trained YOLOv8 target detection model is used to process the current spectral data and obtain the defect detection results of the current on-board cable terminal. When the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the polygon area in the radar spectrum, and when the polygon area in the radar spectrum is not larger than the preset area, evaluate that the current on-board cable terminal is not in an aging state; when the polygon area in the radar spectrum is larger than the preset area, evaluate that the current on-board cable terminal is in an aging state.

2. The vehicle-mounted cable terminal evaluation method according to claim 1, characterized in that: The method of deriving normal spectrum data and defect spectrum data from the terahertz time-domain spectroscopy system includes: exporting a first data file and a second data file from a terahertz time-domain spectroscopy system; Normal spectrum data in the first data file is obtained, and normal spectrum data in the second data file is obtained.

3. The vehicle-mounted cable terminal evaluation method according to claim 1, characterized in that: The method comprises forming a training set with different normal samples and different defect samples, and using the training set to train the YOLOv8 target detection model, including: Different normal samples and different defect samples are combined into a training set; Obtain the model file, load the YOLOv8 target detection model through the model file, and use the training set to train the YOLOv8 target detection model.

4. The vehicle-mounted cable terminal evaluation method according to claim 1, characterized in that: The method of obtaining the loss value of the YOLOv8 target detection model in the training set and saving the trained YOLOv8 target detection model when the loss value is less than a preset value includes: Obtain the loss value of the YOLOv8 target detection model in the training set through the cross entropy loss function; When the loss value is less than the preset value, stop training the YOLOv8 target detection model and save the trained YOLOv8 target detection model.

5. The vehicle-mounted cable terminal evaluation method according to claim 1, characterized in that: The obtaining of the current spectral data and inputting the current spectral data into the trained YOLOv8 target detection model includes: exporting a third data file from the terahertz time-domain spectroscopy system; The current spectral data in the third data file is obtained, and the current spectral data is input into the trained YOLOv8 target detection model.

6. The vehicle-mounted cable terminal evaluation method according to claim 1, characterized in that: When the defect detection result is a normal label, obtaining a radar spectrum corresponding to the current on-board cable terminal, obtaining a polygonal area in the radar spectrum, and when the polygonal area in the radar spectrum is not greater than a preset area, evaluating that the current on-board cable terminal is not in an aging state; when the polygonal area in the radar spectrum is greater than a preset area, evaluating that the current on-board cable terminal is in an aging state, including: When the defect detection result is a normal label, obtain the radar spectrum corresponding to the current on-board cable terminal, obtain the current value of each evaluation indicator in the current on-board cable terminal, and perform dimensionless processing on the current value of each evaluation indicator in the current on-board cable terminal through a standard normalization method to obtain the standard value of each evaluation indicator in the current on-board cable terminal; Obtain the weight value corresponding to each evaluation indicator, generate the fan angle of each evaluation indicator according to the weight value corresponding to each evaluation indicator and the first generation model, generate the polygon area in the radar spectrum according to the standard value of each evaluation indicator in the current on-board cable terminal, the fan angle corresponding to each evaluation indicator and the preset second generation model, when the polygon area in the radar spectrum is not larger than the preset area, evaluate that the current on-board cable terminal is not in an aging state, and when the polygon area in the radar spectrum is larger than the preset area, evaluate that the current on-board cable terminal is in an aging state.

7. The vehicle-mounted cable terminal evaluation method according to claim 1, characterized in that: After evaluating that the current on-board cable terminal is in an aging state when the polygon area in the radar spectrum is greater than a preset area, the on-board cable terminal evaluation method includes: Displays a reminder message that the current vehicle cable terminal is in an aging state.

8. A vehicle-mounted cable terminal evaluation device, characterized in that: Used in electronic equipment, including: An export module, used to export normal spectrum data and defect spectrum data from the terahertz time-domain spectroscopy system; A composition module, configured to combine normal spectral data and normal labels into normal samples, and combine defect spectral data and defect labels into defect samples; A module is used to combine different normal samples and different defect samples into a training set, and the training set is used to train the YOLOv8 target detection model; The saving module is used to obtain the loss value of the YOLOv8 target detection model in the training set. When the loss value is less than the preset value, the trained YOLOv8 target detection model is saved; An acquisition module is used to obtain current spectral data and input the current spectral data into the trained YOLOv8 target detection model. The current spectral data is the terahertz time domain spectral data and terahertz frequency domain spectral data obtained by the terahertz time domain data system testing the current on-board cable terminal; The detection module is used to process the current spectral data using the trained YOLOv8 target detection model to obtain the defect detection results of the current on-board cable terminal; The evaluation module is used to obtain the radar spectrum corresponding to the current on-board cable terminal when the defect detection result is a normal label, obtain the polygon area in the radar spectrum, and when the polygon area in the radar spectrum is not greater than the preset area, evaluate that the current on-board cable terminal is not in an aging state; when the polygon area in the radar spectrum is greater than the preset area, evaluate that the current on-board cable terminal is in an aging state.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the vehicle-mounted cable terminal evaluation method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the vehicle-mounted cable terminal evaluation method according to any one of claims 1 to 7 is implemented.

Images