A measurement signal data analysis and evaluation method for precision wire testing

Abstract

The present invention relates to the field of precision wire test signal data analysis, and in particular to a measurement signal data analysis and evaluation method for precision wire testing, comprising: establishing a change time domain of real-time measurement signal data according to real-time measurement signal data of the precision wire test; performing linear analysis and screening processing according to the change time domain of the real-time measurement signal data to obtain a linear analysis and screening processing result of the real-time measurement signal data; using the linear analysis and screening processing result of the real-time measurement signal data to obtain a measurement signal data analysis and evaluation result, thereby realizing an overall combined cross-analysis of a test system and actual wire parameters, iteratively verifying the data output by the test signal itself, extracting relevant features for subsequent verification implementation, and ensuring a system stable self-check of the output test signal.

Description

Technical Field

[0001] The present invention relates to the field of precision wire test signal data analysis, and in particular to a measurement signal data analysis and evaluation method for precision wire test. Background Art

[0002] In precision cable testing, signal data often exhibit independence and have few connections with each other, making it difficult to fully analyze external test reasons or internal cable problems, resulting in the output results being unable to fully cover the entire measurement process. At the same time, multiple types of parameters are output simultaneously, making it difficult to reflect the specific circumstances of the cable problem and lacking accurate and stable result output guarantees. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a measurement signal data analysis and evaluation method for precision wire testing, which quickly obtains accurate output of the final test signal data by analyzing and screening various types of test data on the test system side and the wire parameter side.

[0004] To achieve the above object, the present invention provides a measurement signal data analysis and evaluation method for precision wire testing, comprising:

[0005] S1. Establishing a time domain of real-time measurement signal data change according to real-time measurement signal data of precision wire material testing;

[0006] S2, performing linear analysis and screening processing according to the change time domain of the real-time measurement signal data to obtain a linear analysis and screening processing result of the real-time measurement signal data;

[0007] S3. Obtaining a measurement signal data analysis and evaluation result by using the linear analysis and screening processing result of the real-time measurement signal data.

[0008] Preferably, the step of establishing a change time domain of real-time measurement signal data according to the real-time measurement signal data of the precision wire material test comprises:

[0009] S1-1, respectively obtain the real-time test voltage value, real-time test current value, real-time withstand voltage value and real-time electrical performance data of the precision wire;

[0010] S1-2, using the real-time test voltage value, real-time test current value, real-time withstand voltage value and real-time electrical performance data of the precision wire as real-time measurement signal data for precision wire testing;

[0011] S1-3, using the real-time measurement signal data of the precision wire test to obtain the periodic characteristics of the measurement signal data and establish the change time domain of the real-time measurement signal data;

[0012] Among them, the electrical performance data includes the resistance value, capacitance value, and capacitance polarity of the precision wire.

[0013] Furthermore, using the real-time measurement signal data of the precision wire test to obtain the periodic characteristics of the measurement signal data and establish the change time domain of the real-time measurement signal data includes:

[0014] S1-3-1, obtaining the current time as the periodic starting time t;

[0015] S1-3-2, obtaining a real-time test voltage value at the periodic starting time t according to the periodic starting time t;

[0016] S1-3-3, determine whether the real-time test voltage value at the periodic starting time t is the same as the real-time test voltage value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-2, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the test voltage value;

[0017] S1-3-4, obtaining a real-time test current value at the periodic starting time t according to the periodic starting time t;

[0018] S1-3-5, determine whether the real-time test current value at the periodic starting time t is the same as the real-time test current value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-4, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the test current value;

[0019] S1-3-6. Obtaining a real-time withstand voltage value at the periodic starting time t according to the periodic starting time t;

[0020] S1-3-7, determine whether the real-time withstand voltage value at the periodic starting time t is the same as the real-time withstand voltage value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-6, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the withstand voltage value;

[0021] S1-3-8, acquiring real-time electrical performance data at the periodic starting time t according to the periodic starting time t;

[0022] S1-3-9, determine whether the real-time electrical performance data at the periodic starting time t is the same as the real-time electrical performance data at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-8, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the electrical performance data;

[0023] S1-3-10. Utilize the change cycle of the test voltage value, the change cycle of the test current value, the change cycle of the withstand voltage value and the change cycle of the electrical performance data as the change time domain of the real-time measurement signal data.

[0024] Furthermore, the linear analysis and screening processing is performed according to the time domain of the change of the real-time measurement signal data to obtain the linear analysis and screening processing result of the real-time measurement signal data, including:

[0025] S2-1, establishing a linear classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data;

[0026] S2-2. Perform screening processing according to the linear classification model of the real-time measurement signal data to obtain a linear analysis screening processing result of the real-time measurement signal data.

[0027] Furthermore, establishing a linear classification model of the real-time measurement signal data according to the change time domain of the real-time measurement signal data includes:

[0028] S2-1-1, establishing a time domain period classification model for the real-time measurement signal data according to the time domain of the change of the real-time measurement signal data;

[0029] S2-1-2, establishing a data change classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data;

[0030] S2-1-3. Use the time domain period classification model and the data change classification model of the real-time measurement signal data as a linear classification model for the real-time measurement signal data.

[0031] Furthermore, establishing a time domain period classification model of the real-time measurement signal data according to the change time domain of the real-time measurement signal data includes:

[0032] S2-1-1-1, using the change time domain of the real-time measurement signal data to correspond to the change period of the test voltage value and the change period of the test current value to establish a voltage-current change period mapping;

[0033] S2-1-1-2, using the change period of the withstand voltage value corresponding to the change period of the real-time measurement signal data and the change period of the electrical performance data to establish a material performance change period mapping;

[0034] S2-1-1-3, using the voltage-current change period mapping to obtain the corresponding historical voltage-current change period mapping to establish an input training set;

[0035] S2-1-1-4, using the material performance change cycle mapping to obtain the corresponding historical material performance change cycle mapping to establish an output training set;

[0036] S2-1-1-5, using the input training set as input, the output training set corresponding to the input training set as output, the normal threshold and abnormal threshold of the precision wire to establish a hidden layer, and training based on a neural network to obtain a time domain period classification model for real-time measurement signal data;

[0037] Among them, the abnormal threshold is the abnormal working parameter of the precision wire.

[0038] Furthermore, establishing a data change classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data includes:

[0039] According to the change period of the test voltage value corresponding to the change time domain of the real-time measurement signal data, the voltage value before and after the change of the historical test voltage value are obtained to establish a first training set;

[0040] According to the change period of the test current value corresponding to the change time domain of the real-time measurement signal data, the current value before and after the change of the historical test current value are obtained to establish a second training set;

[0041] According to the change period of the withstand voltage value corresponding to the change time domain of the real-time measurement signal data, the withstand voltage value before and after the change of the historical withstand voltage value are obtained to establish a third training set;

[0042] According to the change period of the electrical performance data corresponding to the change time domain of the real-time measurement signal data, the electrical performance data before and after the change of the historical electrical performance data are acquired to establish a fourth training set;

[0043] Using the first training set as input, the first training set and the corresponding second training set as output, and training based on a neural network to obtain a voltage-current numerical mapping model;

[0044] Using the second training set as input, the second training set and the corresponding third training set as output, and training based on a neural network to obtain a current-withstand voltage numerical mapping model;

[0045] Using the third training set as input, the third training set and the corresponding fourth training set as output, training based on a neural network to obtain a pressure resistance-material value change model;

[0046] The voltage-current numerical mapping model, the current-withstand voltage numerical mapping model and the withstand voltage-material numerical variation model are used to sequentially establish a data variation classification model for real-time measurement signal data.

[0047] Furthermore, the linear analysis and screening processing results of the real-time measurement signal data obtained by screening according to the linear classification model of the real-time measurement signal data include:

[0048] S2-2-1. Using the real-time measurement signal data of the precision wire test to input the linear classification model of the real-time measurement signal data, the corresponding data change classification model obtains the voltage-current numerical mapping result, the current-withstand voltage numerical mapping result and the withstand voltage-material numerical change result of the real-time measurement signal data;

[0049] S2-2-2, using the real-time measurement signal data of the precision wire test to obtain a voltage-current change cycle mapping of the real-time measurement signal data;

[0050] S2-2-3, mapping the voltage-current change period of the real-time measurement signal data into a linear classification model corresponding to a time domain period classification model to obtain a time domain period classification result of the real-time measurement signal data;

[0051] S2-2-4, determine whether the voltage-current numerical mapping result of the real-time measurement signal data corresponds to the time domain period classification result, if so, execute S2-2-5, otherwise, update the input training set using the voltage-current numerical mapping result corresponding to the voltage-current change period mapping, and return to S2-1-1-5;

[0052] S2-2-5. Determine whether the voltage-resistance-material numerical change result of the real-time measurement signal data corresponds to the time domain period classification result. If so, use the voltage-current numerical mapping result, current-voltage-resistance numerical mapping result, voltage-resistance-material numerical change result and time domain period classification result of the real-time measurement signal data as the linear analysis screening processing result of the real-time measurement signal data. Otherwise, use the voltage-resistance-material numerical change result to correspond to the material performance change period mapping to update the output training set, and return to S2-1-1-5.

[0053] Furthermore, the measurement signal data analysis and evaluation results obtained by using the linear analysis and screening processing results of the real-time measurement signal data include:

[0054] S3-1, determine whether the number of executions of S2-2-3 at the current moment is greater than 3, if so, update the current moment to the periodic start moment t, and return to S1-3-1, otherwise, execute S3-2;

[0055] S3-2, obtaining a first cycle start value and a first cycle end value of a corresponding voltage-current change cycle according to the voltage-current numerical mapping result;

[0056] S3-3, obtaining a second cycle start value and a second cycle end value of a corresponding pressure-resistance-material change cycle according to the pressure-resistance-material value change result;

[0057] S3-4, using the first cycle start value, the first cycle end value, the second cycle start value and the second cycle end value to perform a bilateral cross-validation process according to the current-withstand voltage numerical mapping result to obtain a measurement signal data analysis and evaluation result;

[0058] Among them, the first cycle starting value includes the starting value of the changing cycle of the voltage value and the starting value of the changing cycle of the current value, the first cycle ending value includes the ending value of the changing cycle of the voltage value and the ending value of the changing cycle of the current value, the second cycle starting value includes the starting value of the changing cycle of the withstand voltage value and the starting value of the changing cycle of the electrical performance data, and the second cycle ending value includes the ending value of the changing cycle of the withstand voltage value and the ending value of the changing cycle of the electrical performance data.

[0059] Further, the measurement signal data analysis and evaluation results obtained by performing a bilateral cross-validation process based on the current-withstand voltage numerical mapping result using the first cycle start value, the first cycle end value, the second cycle start value and the second cycle end value include:

[0060] S3-4-1. Use the current-withstand voltage value mapping result to correspond to the current value change cycle and the withstand voltage value change cycle as the system side change cycle auxiliary label and the wire side change cycle auxiliary label respectively;

[0061] S3-4-2, using the current value change threshold and the voltage value change threshold corresponding to the current-voltage value mapping result as the system side value range auxiliary label and the wire side value range auxiliary label respectively;

[0062] S3-4-3, determine whether the first cycle start value and the first cycle end value are the same, if so, the system side data analysis and evaluation result is normal, and execute S3-4-4, otherwise, directly execute S3-4-5;

[0063] S3-4-4, determine whether the second cycle start value and the second cycle end value are the same, if so, the wire side data analysis and evaluation result is normal, the output measurement signal data analysis and evaluation result is normal, otherwise, directly execute S3-4-6;

[0064] S3-4-5, determine whether the system-side change period auxiliary label corresponds to the system-side value range auxiliary label. If so, the system-side data analysis and evaluation result is normal, and return to S3-4-4. Otherwise, the wire-side data analysis and evaluation result is abnormal;

[0065] S3-4-6, judging whether the wire side change cycle auxiliary label corresponds to the wire side value range auxiliary label, if so, the wire side data analysis and evaluation result is normal, otherwise, the wire side data analysis and evaluation result is abnormal;

[0066] S3-4-7, using the system side data analysis and evaluation results and the wire side data analysis and evaluation results as measurement signal data analysis and evaluation results;

[0067] The current value change threshold is a numerical range corresponding to a change period of the current value, and the withstand voltage value change threshold is a numerical range corresponding to a change period of the withstand voltage value.

[0068] Compared with the closest prior art, the present invention has the following beneficial effects:

[0069] The overall cross-analysis of the test system and the actual parameters of the wire is realized, the data of the test signal output is iteratively verified, and relevant features are extracted for subsequent verification and implementation, which ensures the system stability self-inspection of the output test signal. Combined with the existing reliable neural network technology, single-layer and multi-layer perceptrons are used to establish a rapid screening and analysis model, and the linear relationship of the normal output signal is used as the basis. Ultimately, the stable output of the bilateral verification is guaranteed, and the analysis and judgment efficiency of the precision wire is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a flow chart of a measurement signal data analysis and evaluation method for precision wire material testing provided by the present invention. DETAILED DESCRIPTION

[0071] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0072] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] Embodiment 1:

[0074] The present invention provides a measurement signal data analysis and evaluation method for precision wire testing, such as Figure 1 As shown, including:

[0075] S1. Establishing a time domain of real-time measurement signal data change according to real-time measurement signal data of precision wire material testing;

[0076] S2, performing linear analysis and screening processing according to the change time domain of the real-time measurement signal data to obtain a linear analysis and screening processing result of the real-time measurement signal data;

[0077] S3. Obtaining a measurement signal data analysis and evaluation result by using the linear analysis and screening processing result of the real-time measurement signal data.

[0078] S1 specifically includes:

[0079] S1-1, respectively obtain the real-time test voltage value, real-time test current value, real-time withstand voltage value and real-time electrical performance data of the precision wire;

[0080] S1-2, using the real-time test voltage value, real-time test current value, real-time withstand voltage value and real-time electrical performance data of the precision wire as real-time measurement signal data for precision wire testing;

[0081] S1-3, using the real-time measurement signal data of the precision wire material test to obtain the periodic characteristics of the measurement signal data and establish the change time domain of the real-time measurement signal data;

[0082] Among them, the electrical performance data includes the resistance value, capacitance value, and capacitance polarity of the precision wire.

[0083] S1-3 specifically includes:

[0084] S1-3-1, obtaining the current time as the periodic starting time t;

[0085] S1-3-2, obtaining a real-time test voltage value at the periodic starting time t according to the periodic starting time t;

[0086] S1-3-3, determine whether the real-time test voltage value at the periodic starting time t is the same as the real-time test voltage value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-2, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the test voltage value;

[0087] S1-3-4, obtaining a real-time test current value at the periodic starting time t according to the periodic starting time t;

[0088] S1-3-5, determine whether the real-time test current value at the periodic starting time t is the same as the real-time test current value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-4, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the test current value;

[0089] S1-3-6. Obtaining a real-time withstand voltage value at the periodic starting time t according to the periodic starting time t;

[0090] S1-3-7, determine whether the real-time withstand voltage value at the periodic starting time t is the same as the real-time withstand voltage value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-6, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the withstand voltage value;

[0091] S1-3-8, acquiring real-time electrical performance data at the periodic starting time t according to the periodic starting time t;

[0092] S1-3-9, determine whether the real-time electrical performance data at the periodic starting time t is the same as the real-time electrical performance data at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-8, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the electrical performance data;

[0093] S1-3-10. Utilize the change cycle of the test voltage value, the change cycle of the test current value, the change cycle of the withstand voltage value and the change cycle of the electrical performance data as the change time domain of the real-time measurement signal data.

[0094] S2 specifically includes:

[0095] S2-1, establishing a linear classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data;

[0096] S2-2. Perform screening processing according to the linear classification model of the real-time measurement signal data to obtain a linear analysis screening processing result of the real-time measurement signal data.

[0097] S2-1 specifically includes:

[0098] S2-1-1, establishing a time domain period classification model for the real-time measurement signal data according to the time domain of the change of the real-time measurement signal data;

[0099] S2-1-2, establishing a data change classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data;

[0100] S2-1-3. Use the time domain period classification model and the data change classification model of the real-time measurement signal data as a linear classification model for the real-time measurement signal data.

[0101] S2-1-1 specifically includes:

[0102] S2-1-1-1, using the change time domain of the real-time measurement signal data to correspond to the change period of the test voltage value and the change period of the test current value to establish a voltage-current change period mapping;

[0103] S2-1-1-2, using the change period of the withstand voltage value corresponding to the change period of the real-time measurement signal data and the change period of the electrical performance data to establish a material performance change period mapping;

[0104] S2-1-1-3, using the voltage-current change period mapping to obtain the corresponding historical voltage-current change period mapping to establish an input training set;

[0105] S2-1-1-4, using the material performance change cycle mapping to obtain the corresponding historical material performance change cycle mapping to establish an output training set;

[0106] S2-1-1-5, using the input training set as input, the output training set corresponding to the input training set as output, the normal threshold and abnormal threshold of the precision wire to establish a hidden layer, and training based on a neural network to obtain a time domain period classification model for real-time measurement signal data;

[0107] Among them, the abnormal threshold is the abnormal working parameter of the precision wire.

[0108] S2-1-2 specifically includes:

[0109] S2-1-2-1, according to the change period of the test voltage value corresponding to the change time domain of the real-time measurement signal data, obtain the voltage value before and after the change of the historical test voltage value to establish a first training set;

[0110] S2-1-2-2, according to the change period of the test current value corresponding to the change time domain of the real-time measurement signal data, obtain the current value before and after the change of the historical test current value to establish a second training set;

[0111] S2-1-2-3, according to the change period of the withstand voltage value corresponding to the change time domain of the real-time measurement signal data, obtain the withstand voltage value before the change and the withstand voltage value after the change of the historical withstand voltage value to establish a third training set;

[0112] S2-1-2-4, obtaining the electrical performance data before and after the change of the historical electrical performance data according to the change period of the electrical performance data corresponding to the change time domain of the real-time measurement signal data to establish a fourth training set;

[0113] S2-1-2-5. Using the first training set as input, the first training set and the corresponding second training set as output, and obtaining a voltage-current numerical mapping model through training based on a neural network;

[0114] S2-1-2-6, using the second training set as input, the second training set and the corresponding third training set as output, and obtaining a current-withstand voltage numerical mapping model through training based on a neural network;

[0115] S2-1-2-7, using the third training set as input, the third training set and the corresponding fourth training set as output, and training based on a neural network to obtain a pressure resistance-material numerical change model;

[0116] S2-1-2-8. Use the voltage-current numerical mapping model, current-withstand voltage numerical mapping model and withstand voltage-material numerical change model to sequentially establish a data change classification model for real-time measurement signal data.

[0117] S2-2 specifically includes:

[0118] S2-2-1. Using the real-time measurement signal data of the precision wire test to input the linear classification model of the real-time measurement signal data, the corresponding data change classification model obtains the voltage-current numerical mapping result, the current-withstand voltage numerical mapping result and the withstand voltage-material numerical change result of the real-time measurement signal data;

[0119] S2-2-2, using the real-time measurement signal data of the precision wire test to obtain a voltage-current change cycle mapping of the real-time measurement signal data;

[0120] S2-2-3, mapping the voltage-current change period of the real-time measurement signal data into a linear classification model corresponding to a time domain period classification model to obtain a time domain period classification result of the real-time measurement signal data;

[0121] S2-2-4, determine whether the voltage-current numerical mapping result of the real-time measurement signal data corresponds to the time domain period classification result, if so, execute S2-2-5, otherwise, update the input training set using the voltage-current numerical mapping result corresponding to the voltage-current change period mapping, and return to S2-1-1-5;

[0122] S2-2-5. Determine whether the voltage-resistance-material numerical change result of the real-time measurement signal data corresponds to the time domain period classification result. If so, use the voltage-current numerical mapping result, current-voltage-resistance numerical mapping result, voltage-resistance-material numerical change result and time domain period classification result of the real-time measurement signal data as the linear analysis screening processing result of the real-time measurement signal data. Otherwise, use the voltage-resistance-material numerical change result to correspond to the material performance change period mapping to update the output training set, and return to S2-1-1-5.

[0123] S3 specifically includes:

[0124] S3-1, determine whether the number of executions of S2-2-3 at the current moment is greater than 3, if so, update the current moment to the periodic start moment t, and return to S1-3-1, otherwise, execute S3-2;

[0125] S3-2, obtaining a first cycle start value and a first cycle end value of a corresponding voltage-current change cycle according to the voltage-current numerical mapping result;

[0126] S3-3, obtaining a second cycle start value and a second cycle end value of a corresponding pressure-resistance-material change cycle according to the pressure-resistance-material value change result;

[0127] S3-4, using the first cycle start value, the first cycle end value, the second cycle start value and the second cycle end value to perform a bilateral cross-validation process according to the current-withstand voltage numerical mapping result to obtain a measurement signal data analysis and evaluation result;

[0128] Among them, the first cycle starting value includes the starting value of the changing cycle of the voltage value and the starting value of the changing cycle of the current value, the first cycle ending value includes the ending value of the changing cycle of the voltage value and the ending value of the changing cycle of the current value, the second cycle starting value includes the starting value of the changing cycle of the withstand voltage value and the starting value of the changing cycle of the electrical performance data, and the second cycle ending value includes the ending value of the changing cycle of the withstand voltage value and the ending value of the changing cycle of the electrical performance data.

[0129] In the present embodiment, a measurement signal data analysis and evaluation method for precision wire material testing is provided, wherein the basis for setting the number of executions in S3-1 is to combine the existence of loop iterations in each step in S2-2, so as to ensure to the greatest extent that the energy content of each loop can be executed after the same standard time.

[0130] S3-4 specifically includes:

[0131] S3-4-1. Use the current-withstand voltage value mapping result to correspond to the current value change cycle and the withstand voltage value change cycle as the system side change cycle auxiliary label and the wire side change cycle auxiliary label respectively;

[0132] S3-4-2, using the current value change threshold and the voltage value change threshold corresponding to the current-voltage value mapping result as the system side value range auxiliary label and the wire side value range auxiliary label respectively;

[0133] S3-4-3, determine whether the first cycle start value and the first cycle end value are the same, if so, the system side data analysis and evaluation result is normal, and execute S3-4-4, otherwise, directly execute S3-4-5;

[0134] S3-4-4, determine whether the second cycle start value and the second cycle end value are the same, if so, the wire side data analysis and evaluation result is normal, the output measurement signal data analysis and evaluation result is normal, otherwise, directly execute S3-4-6;

[0135] S3-4-5, determine whether the system-side change period auxiliary label corresponds to the system-side value range auxiliary label. If so, the system-side data analysis and evaluation result is normal, and return to S3-4-4. Otherwise, the wire-side data analysis and evaluation result is abnormal;

[0136] S3-4-6, judging whether the wire side change cycle auxiliary label corresponds to the wire side value range auxiliary label, if so, the wire side data analysis and evaluation result is normal, otherwise, the wire side data analysis and evaluation result is abnormal;

[0137] S3-4-7, using the system side data analysis and evaluation results and the wire side data analysis and evaluation results as measurement signal data analysis and evaluation results;

[0138] The current value change threshold is a numerical range corresponding to a change period of the current value, and the withstand voltage value change threshold is a numerical range corresponding to a change period of the withstand voltage value.

[0139] In this embodiment, a measurement signal data analysis and evaluation method for precision wire testing relies on accurate data provided by an external test system when testing voltage and current. In order to ensure the accuracy and reliability of the test results, the entire test process is subdivided into two main parts: system-side testing and wire self-testing. The system-side test focuses on evaluating the performance and stability of the external test equipment to ensure that the required voltage and current can be applied accurately. The wire self-test focuses on the performance of the wire in actual applications, including its ability to withstand voltage and current and any performance degradation that may occur. When analyzing these data features, not only the values ​​themselves are focused on, but also the meaning behind them is explored in depth. For example, how the stability of the voltage affects the fluctuation of the current, and how the magnitude of the current determines the degree of the wire's own performance. By combining the data on the system side and the wire itself, a comprehensive perspective can be obtained to more accurately evaluate the performance of the wire under different conditions. This comprehensive analysis method helps to identify potential problems and provides strong data support for improving wire design and testing processes.

[0140] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0141] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0142] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A measurement signal data analysis and evaluation method for precision wire testing, characterized in that: include: S1. Establishing a time domain of real-time measurement signal data change according to real-time measurement signal data of precision wire material testing; S1-1, respectively obtain the real-time test voltage value, real-time test current value, real-time withstand voltage value and real-time electrical performance data of the precision wire; S1-2, using the real-time test voltage value, real-time test current value, real-time withstand voltage value and real-time electrical performance data of the precision wire as real-time measurement signal data for precision wire testing; S1-3, using the real-time measurement signal data of the precision wire material test to obtain the periodic characteristics of the measurement signal data and establish the change time domain of the real-time measurement signal data; S1-3-1, obtaining the current time as the periodic starting time t; S1-3-2, obtaining a real-time test voltage value at the periodic starting time t according to the periodic starting time t; S1-3-3, determine whether the real-time test voltage value at the periodic starting time t is the same as the real-time test voltage value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-2, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the test voltage value; S1-3-4, obtaining a real-time test current value at the periodic starting time t according to the periodic starting time t; S1-3-5, determine whether the real-time test current value at the periodic starting time t is the same as the real-time test current value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-4, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the test current value; S1-3-6. Obtaining a real-time withstand voltage value at the periodic starting time t according to the periodic starting time t; S1-3-7, determine whether the real-time withstand voltage value at the periodic starting time t is the same as the real-time withstand voltage value at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-6, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the withstand voltage value; S1-3-8, acquiring real-time electrical performance data at the periodic starting time t according to the periodic starting time t; S1-3-9, determine whether the real-time electrical performance data at the periodic starting time t is the same as the real-time electrical performance data at time t+1, if so, use time t+1 as the updated periodic starting time t, and return to execute S1-3-8, otherwise, use the interval time between the periodic starting time t and time t+1 as the change period of the electrical performance data; S1-3-10, using the change cycle of the test voltage value, the change cycle of the test current value, the change cycle of the withstand voltage value and the change cycle of the electrical performance data as the change time domain of the real-time measurement signal data; Wherein, the electrical performance data includes the resistance value, capacitance value, and capacitance polarity of the precision wire; S2, performing linear analysis and screening processing according to the change time domain of the real-time measurement signal data to obtain a linear analysis and screening processing result of the real-time measurement signal data; S2-1, establishing a linear classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data; S2-1-1, establishing a time domain period classification model for the real-time measurement signal data according to the time domain of the change of the real-time measurement signal data; S2-1-1-1, using the change time domain of the real-time measurement signal data to correspond to the change period of the test voltage value and the change period of the test current value to establish a voltage-current change period mapping; S2-1-1-2, using the change period of the withstand voltage value corresponding to the change period of the real-time measurement signal data and the change period of the electrical performance data to establish a material performance change period mapping; S2-1-1-3, using the voltage-current change period mapping to obtain the corresponding historical voltage-current change period mapping to establish an input training set; S2-1-1-4, using the material performance change cycle mapping to obtain the corresponding historical material performance change cycle mapping to establish an output training set; S2-1-1-5, using the input training set as input, the output training set corresponding to the input training set as output, the normal threshold and abnormal threshold of the precision wire to establish a hidden layer, and training based on a neural network to obtain a time domain period classification model for real-time measurement signal data; Wherein, the abnormal threshold is the abnormal working parameter of the precision wire; S2-1-2, establishing a data change classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data; S2-1-3, using the time domain period classification model and the data change classification model of the real-time measurement signal data as a linear classification model for the real-time measurement signal data; S2-2, performing screening processing according to the linear classification model of the real-time measurement signal data to obtain a linear analysis screening processing result of the real-time measurement signal data; S3. Obtaining a measurement signal data analysis and evaluation result by using the linear analysis and screening processing result of the real-time measurement signal data.

2. A measurement signal data analysis and evaluation method for precision wire material testing according to claim 1, characterized in that: Establishing a data change classification model for the real-time measurement signal data according to the change time domain of the real-time measurement signal data includes: According to the change period of the test voltage value corresponding to the change time domain of the real-time measurement signal data, the voltage value before and after the change of the historical test voltage value are obtained to establish a first training set; According to the change period of the test current value corresponding to the change time domain of the real-time measurement signal data, the current value before and after the change of the historical test current value are obtained to establish a second training set; According to the change period of the withstand voltage value corresponding to the change time domain of the real-time measurement signal data, the withstand voltage value before and after the change of the historical withstand voltage value are obtained to establish a third training set; According to the change period of the electrical performance data corresponding to the change time domain of the real-time measurement signal data, the electrical performance data before and after the change of the historical electrical performance data are acquired to establish a fourth training set; Using the first training set as input, the first training set and the corresponding second training set as output, and training based on a neural network to obtain a voltage-current numerical mapping model; Using the second training set as input, the second training set and the corresponding third training set as output, and training based on a neural network to obtain a current-withstand voltage numerical mapping model; Using the third training set as input, the third training set and the corresponding fourth training set as output, training based on a neural network to obtain a pressure resistance-material value change model; The voltage-current numerical mapping model, the current-withstand voltage numerical mapping model and the withstand voltage-material numerical variation model are used to sequentially establish a data variation classification model for real-time measurement signal data.

3. A measurement signal data analysis and evaluation method for precision wire material testing as claimed in claim 2, characterized in that: The linear analysis and screening results of the real-time measurement signal data obtained by screening and processing according to the linear classification model of the real-time measurement signal data include: S2-2-1. Using the real-time measurement signal data of the precision wire test to input the linear classification model of the real-time measurement signal data, the corresponding data change classification model obtains the voltage-current numerical mapping result, the current-withstand voltage numerical mapping result and the withstand voltage-material numerical change result of the real-time measurement signal data; S2-2-2, using the real-time measurement signal data of the precision wire test to obtain a voltage-current change cycle mapping of the real-time measurement signal data; S2-2-3, mapping the voltage-current change period of the real-time measurement signal data into a linear classification model corresponding to a time domain period classification model to obtain a time domain period classification result of the real-time measurement signal data; S2-2-4, determine whether the voltage-current numerical mapping result of the real-time measurement signal data corresponds to the time domain period classification result, if so, execute S2-2-5, otherwise, update the input training set using the voltage-current numerical mapping result corresponding to the voltage-current change period mapping, and return to S2-1-1-5; S2-2-5. Determine whether the voltage-resistance-material numerical change result of the real-time measurement signal data corresponds to the time domain period classification result. If so, use the voltage-current numerical mapping result, current-voltage-resistance numerical mapping result, voltage-resistance-material numerical change result and time domain period classification result of the real-time measurement signal data as the linear analysis screening processing result of the real-time measurement signal data. Otherwise, use the voltage-resistance-material numerical change result to correspond to the material performance change period mapping to update the output training set, and return to S2-1-1-5.

4. A measurement signal data analysis and evaluation method for precision wire material testing as claimed in claim 3, characterized in that: The measurement signal data analysis and evaluation results obtained by using the linear analysis and screening processing results of the real-time measurement signal data include: S3-1, determine whether the number of executions of S2-2-3 at the current moment is greater than 3, if so, update the current moment to the periodic start moment t, and return to S1-3-1, otherwise, execute S3-2; S3-2, obtaining a first cycle start value and a first cycle end value of a corresponding voltage-current change cycle according to the voltage-current numerical mapping result; S3-3, obtaining a second cycle start value and a second cycle end value of a corresponding pressure-resistance-material change cycle according to the pressure-resistance-material value change result; S3-4, using the first cycle start value, the first cycle end value, the second cycle start value and the second cycle end value to perform a bilateral cross-validation process according to the current-withstand voltage numerical mapping result to obtain a measurement signal data analysis and evaluation result; Among them, the first cycle starting value includes the starting value of the changing cycle of the voltage value and the starting value of the changing cycle of the current value, the first cycle ending value includes the ending value of the changing cycle of the voltage value and the ending value of the changing cycle of the current value, the second cycle starting value includes the starting value of the changing cycle of the withstand voltage value and the starting value of the changing cycle of the electrical performance data, and the second cycle ending value includes the ending value of the changing cycle of the withstand voltage value and the ending value of the changing cycle of the electrical performance data.

5. A measurement signal data analysis and evaluation method for precision wire material testing as claimed in claim 4, characterized in that: The measurement signal data analysis and evaluation results obtained by performing a bilateral cross-validation process based on the current-withstand voltage numerical mapping result using the first cycle start value, the first cycle end value, the second cycle start value and the second cycle end value include: S3-4-1. Use the current-withstand voltage value mapping result to correspond to the current value change cycle and the withstand voltage value change cycle as the system side change cycle auxiliary label and the wire side change cycle auxiliary label respectively; S3-4-2, using the current value change threshold and the voltage value change threshold corresponding to the current-voltage value mapping result as the system side value range auxiliary label and the wire side value range auxiliary label respectively; S3-4-3, determine whether the first cycle start value and the first cycle end value are the same, if so, the system side data analysis and evaluation result is normal, and execute S3-4-4, otherwise, directly execute S3-4-5; S3-4-4, determine whether the second cycle start value and the second cycle end value are the same, if so, the wire side data analysis and evaluation result is normal, the output measurement signal data analysis and evaluation result is normal, otherwise, directly execute S3-4-6; S3-4-5, determine whether the system-side change period auxiliary label corresponds to the system-side value range auxiliary label. If so, the system-side data analysis and evaluation result is normal, and return to S3-4-4. Otherwise, the wire-side data analysis and evaluation result is abnormal; S3-4-6, judging whether the wire side change cycle auxiliary label corresponds to the wire side value range auxiliary label, if so, the wire side data analysis and evaluation result is normal, otherwise, the wire side data analysis and evaluation result is abnormal; S3-4-7, using the system side data analysis and evaluation results and the wire side data analysis and evaluation results as measurement signal data analysis and evaluation results; The current value change threshold is a numerical range corresponding to a change period of the current value, and the withstand voltage value change threshold is a numerical range corresponding to a change period of the withstand voltage value.

Images