Connector residual life prediction model training method and residual life prediction method

Abstract

The application discloses a connector residual life prediction model training method and a residual life prediction method. The model training method comprises the following steps: acquiring various sample connectors for model training, and determining historical test data of each connector in a connector test process; for any sample connector, determining sample training data of the current sample connector based on the historical test data; and training the connector residual life prediction model based on the sample training data of each sample connector to obtain a trained connector residual life prediction model. Through the technical scheme disclosed by the application, the time consumption and cost waste of the connector in the replacement process are solved, the residual life of the connector is accurately predicted, and the time consumption and cost of the connector in the replacement process are reduced.

Description

Technical Field

[0001] This invention relates to the field of industrial testing technology, and in particular to a method for training a connector remaining life prediction model and a method for predicting remaining life. Background Technology

[0002] When using connectors to test the object under test, if the lifespan of the connectors is not estimated and they are only replaced when they fail, the entire testing equipment needs to be troubleshooted before replacement. This process involves analyzing the faulty components to pinpoint the connector problem and then replacing it. This replacement process is very time-consuming and reduces testing efficiency. Another scenario involves setting a fixed number of uses for the connectors and replacing them after that number. However, often this number is only a manufacturer-provided reference number of plug-in / plug-out cycles. Such replacements result in many connectors being rendered unusable before they are actually damaged, leading to wasted testing costs.

[0003] At present, accurately determining the remaining lifespan of connectors can help solve the problems encountered in the aforementioned connector replacement process. Summary of the Invention

[0004] This invention provides a method for training a connector remaining life prediction model and a method for predicting remaining life, in order to solve the problems of time consumption and cost waste in the replacement process of connectors in the prior art, and to achieve accurate prediction of the remaining life of connectors, thereby reducing the time consumption and cost in the replacement process of connectors.

[0005] In a first aspect, embodiments of the present invention provide a method for training a connector remaining life prediction model, the method comprising:

[0006] Obtain each sample connector used for model training, and determine the historical test data of each connector during the connection test process;

[0007] For any sample connector, the sample training data for the current sample connector is determined based on the historical test data;

[0008] The remaining life prediction model of the connector is trained based on the sample training data of each of the sample connectors to obtain the trained remaining life prediction model of the connector.

[0009] Optionally, the historical test data includes the number of tests, test results, test video data, and contact direction and contact force between the connector and the object under test during the test.

[0010] Accordingly, determining the historical test data of each connector during the connection test process includes:

[0011] The number of tests and test results of the sample connector during the testing process are obtained based on the preset test data collection.

[0012] Test video data of the sample connector during the testing process is acquired using a preset camera device;

[0013] The contact direction and contact force between the connector and the object under test are collected based on preset sensors during the testing process.

[0014] Optionally, the preset sensor includes a pressure sensor and an attitude sensor; the pressure sensor and the attitude sensor are respectively placed inside the sample connector;

[0015] Accordingly, the contact direction and contact force between the connector and the object under test during the test based on the preset sensor data acquisition process include:

[0016] Based on the contact direction between the connector and the object under test during the test process acquired by the attitude sensor;

[0017] The pressure sensor collects the contact force between the connector and the object under test during the testing process.

[0018] Optionally, determining the sample training data for the current sample connector based on the historical test data includes:

[0019] This refers to obtaining the test time for each test performed on the current sample connector during the testing process;

[0020] The sample training data for the current sample connector is generated based on the test time and the corresponding historical test data.

[0021] Optionally, training the connector remaining life prediction model based on the sample training data of each of the sample connectors to obtain the trained connector remaining life prediction model includes:

[0022] The sample training data is input into the connector remaining lifetime prediction model to be trained to obtain the remaining lifetime prediction value output by the model.

[0023] The model loss function of the connector remaining lifetime prediction model in the current iteration is generated based on the number of tests conducted on the sample connector during the testing process and the remaining lifetime prediction value.

[0024] The model parameters of the connector remaining lifetime prediction model are adjusted in the current iteration based on the loss function.

[0025] The remaining life prediction model of the connector is iteratively trained until the iteration stopping condition is met, and the trained remaining life prediction model of the connector is obtained.

[0026] Secondly, embodiments of the present invention also provide a method for predicting the remaining lifespan of a connector, the method comprising:

[0027] Obtain the target connector to be tested and determine the historical usage data of the target connector during the historical plugging test process;

[0028] The historical usage data is input into a pre-trained connector remaining life prediction model to obtain the remaining life of the target connector.

[0029] Thirdly, embodiments of the present invention also provide a connector remaining life prediction model training device, the device comprising:

[0030] The historical test data acquisition module is used to acquire each sample connector used for model training and determine the historical test data of each connector during the connection test process.

[0031] The sample training data determination module is used to determine the sample training data of the current sample connector based on the historical test data for any sample connector.

[0032] The model training module is used to train the remaining life prediction model of the connector based on the sample training data of each of the sample connectors, so as to obtain the trained remaining life prediction model of the connector.

[0033] Fourthly, embodiments of the present invention also provide a connector remaining life prediction device, the device comprising:

[0034] The historical usage data acquisition module is used to acquire the target connector to be tested and determine the historical usage data of the target connector during the historical plugging test process.

[0035] The remaining lifetime prediction module is used to input the historical usage data into a pre-trained connector remaining lifetime prediction model to obtain the remaining lifetime of the target connector.

[0036] Fifthly, embodiments of the present invention also provide an electronic device, comprising:

[0037] At least one processor; and

[0038] A memory communicatively connected to the at least one processor; wherein,

[0039] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the connector remaining life prediction model training method and / or connector remaining life prediction method according to any embodiment of the present invention.

[0040] Sixthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement the connector remaining lifetime prediction model training method and / or connector remaining lifetime prediction method according to any embodiment of the present invention.

[0041] The technical solution of this invention specifically includes acquiring sample connectors for model training and determining historical test data for each connector during the connection testing process; for any sample connector, determining sample training data for the current sample connector based on the historical test data; and training the connector remaining life prediction model based on the sample training data of each sample connector to obtain a trained connector remaining life prediction model. This technical solution generates sample training data by acquiring historical test data of the connector during the historical testing process, and trains the model based on this data to obtain a trained connector remaining life prediction model. This solves the problem of time-consuming and costly connector replacement processes in the prior art, achieving accurate prediction of connector remaining life and reducing time and cost during connector replacement.

[0042] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart of a connector remaining life prediction model training method provided in Embodiment 1 of the present invention;

[0045] Figure 2 This is a schematic diagram of the historical test data acquisition principle applicable to Embodiment 1 of the present invention.

[0046] Figure 3 This is a flowchart of a connector remaining life prediction method provided in Embodiment 2 of the present invention;

[0047] Figure 4 This is a schematic diagram of the structure of a connector remaining life prediction model training device according to Embodiment 3 of the present invention;

[0048] Figure 5 This is a schematic diagram of the structure of a connector remaining life prediction device provided in Embodiment 4 of the present invention;

[0049] Figure 6 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. Detailed Implementation

[0050] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0052] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0053] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0054] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0055] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0056] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0057] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0058] Example 1

[0059] Figure 1 This invention provides a flowchart of a connector remaining life prediction model training method according to Embodiment 1. This embodiment is applicable to situations where connectors are tested during the testing process to facilitate replacement. The method can be executed by a connector remaining life prediction model training device, which can be implemented in hardware and / or software. This device can be configured in a mobile terminal, PC, or server. Figure 1 As shown, the method includes:

[0060] S110. Obtain each sample connector used for model training and determine the historical test data of each connector during the connection test process.

[0061] In this embodiment of the invention, the connector can be understood as a basic electrical component used for the transmission and control of electrical signals, as well as for electrical connections between various electrical devices. Specifically, the connector can be connected to the interface of the object under test, thereby enabling testing of the object under test. For example, when the object under test is a battery, the connector is connected to the battery's interface to enable battery testing.

[0062] Specifically, by using connectors that have reached the end of their service life during historical testing as training samples, and by determining the corresponding training data from historical test data, a connector remaining life prediction model is trained based on this training data. This results in a well-trained connector remaining life prediction model that can accurately predict the remaining lifespan of connectors, allowing for timely replacement without waste and improving testing efficiency. The reason for choosing connectors that have reached the end of their service life as training samples is that the number of tests conducted on these connectors can be directly obtained, representing their total service life, and used as one of the training sample data points to train the model, resulting in a well-trained connector remaining life prediction model.

[0063] It should be noted that during the testing of the object under test based on the connector, each connection generates test data for that connection test. Specifically, the current test data includes the test result, which can be either normal or abnormal. Optionally, during subsequent tests, if the current test result is normal, the next connection test is performed; conversely, if the test result is abnormal, it indicates that the current connector is unusable and cannot be tested again, requiring replacement. Optionally, test data from multiple tests can be used as the historical test data for the current connector.

[0064] In this embodiment, the historical test data includes the number of times the sample connector was tested, the test results, the test video data, and the contact direction and contact force between the connector and the object under test during the testing process. It should be explained that the historical test data includes the test results, test video data, and the contact direction and contact force between the connector and the object under test for each test.

[0065] Optionally, methods for obtaining historical test data may include: acquiring the number of tests and test results of the sample connector during the test process based on preset test data collection; acquiring test video data of the sample connector during the test process based on preset camera devices; and acquiring the contact direction and contact force between the connector and the test object during the test process based on preset sensors.

[0066] See details Figure 2 , Figure 2 This is a schematic diagram for collecting test data from connectors during the testing process. Specifically, Figure 2 The computer testing software communicates with the sample connector to collect the number of tests and test results of the sample connector during the testing process. Optionally, the computer testing software includes a test count plugin and a test result acquisition plugin. The test count plugin is used to count the total number of tests for the current sample connector and the test rank of a specific test; the test result acquisition plugin is used to obtain the test results of any number of connector tests.

[0067] Specifically, Figure 2 It also includes a camera to capture the plug-in operations of testers, forming test video data, and sending the collected test video data to computer testing software so that sample training data can be generated later based on the test time when the current plug-in is used as a training sample.

[0068] Specifically, Figure 2The system also includes preset sensors for collecting the contact direction and contact force between the connector and the test object during the test. Optionally, the sensors include a pressure sensor and an attitude sensor; the pressure sensor and attitude sensor are respectively placed inside the sample connector; correspondingly, the method for collecting the contact direction and contact force between the connector and the test object during the test based on the preset sensors may include: collecting the contact direction between the connector and the test object during the test based on the attitude sensor; and collecting the contact force between the connector and the test object during the test based on the pressure sensor.

[0069] Specifically, the sensor information parsing plugin performs signal analysis on the data collected by the pressure sensor and attitude sensor to obtain the contact force and contact direction between the connector and the object under test, and sends it to the computer testing software so that sample training data can be generated based on the test time when the current connector is used as a training sample.

[0070] S120. For any sample connector, determine the sample training data for the current sample connector based on historical test data.

[0071] In this embodiment of the invention, based on the historical test data of the current sample connector, the test time corresponding to each test data in the historical test data is obtained, and the test data in the historical test data is associated with the test time to generate sample training data for the sample connector.

[0072] Optionally, the method for determining the sample training data of the current sample connector based on historical test data may include: obtaining the test time of each test performed by the current sample connector during the test process; and generating the sample training data of the current sample connector based on each test time and the corresponding historical test data.

[0073] Specifically, for any sample connector, historical test data generated during the historical testing process is obtained, and the test time corresponding to each test in the historical test data is determined. The test data corresponding to each test is then associated with the test time. Optionally, the test times are formed into a time series, and the test data are concatenated according to the test time series to obtain concatenated test data. Then, sample training data corresponding to the current sample connector is generated based on the time series and the corresponding concatenated test data. The effect of generating sample test data based on test time in this embodiment is that connectors with different usage durations have different remaining lifespans. Using test time as one of the factors affecting the prediction of the remaining lifespan of the connector can make the prediction model trained based on this as sample training data more reliable in obtaining prediction results.

[0074] S130. Based on the sample training data of each sample connector, train the connector remaining life prediction model to obtain the trained connector remaining life prediction model.

[0075] In this embodiment of the invention, based on the sample data of individual connectors generated according to the above implementation method, the remaining lifetime prediction model of the connector is trained based on the training data of each sample. Optionally, the training process includes: inputting the sample training data into the remaining lifetime prediction model of the connector to be trained, and obtaining the remaining lifetime prediction value output by the model; generating a model loss function for the remaining lifetime prediction model of the connector in the current iteration based on the number of tests and the remaining lifetime prediction value of the sample connector in the testing process; adjusting the model parameters of the remaining lifetime prediction model of the connector in the current iteration based on the loss function; and iteratively training the remaining lifetime prediction model of the connector until the iteration stopping condition is met, thereby obtaining the trained remaining lifetime prediction model of the connector.

[0076] Specifically, before inputting the sample training data into the connector remaining life prediction model to be trained, principal component analysis is performed on each test data in the sample training data to determine the influence weight corresponding to each test data. Optionally, each test data in the sample training data and its corresponding influence weight are input into the connector remaining life prediction model to be trained to obtain the model's output remaining life prediction value. Optionally, the remaining life prediction can be understood as the remaining number of times the connector will be used. Then, based on this remaining life value and the number of tests in the test data, an absolute value error loss function of the model is generated, and the parameters of the model under training are modified based on this absolute value error loss function. Subsequent iterative training is performed based on the modified parameters until the iteration stopping condition is met, resulting in the trained connector remaining life prediction model. Optionally, this connector remaining life prediction model is used to predict the remaining life of connectors in use.

[0077] The technical solution of this invention specifically includes acquiring sample connectors for model training and determining historical test data for each connector during the connection testing process; for any sample connector, determining sample training data for the current sample connector based on the historical test data; and training the connector remaining life prediction model based on the sample training data of each sample connector to obtain a trained connector remaining life prediction model. This technical solution generates sample training data by acquiring historical test data of the connector during the historical testing process, and trains the model based on this data to obtain a trained connector remaining life prediction model. This solves the problem of time-consuming and costly connector replacement processes in the prior art, achieving accurate prediction of connector remaining life and reducing time and cost during connector replacement.

[0078] Based on the above embodiments, this invention also provides a preferred embodiment for specifically introducing a training method for a connector remaining life prediction model. The specific steps of this embodiment include:

[0079] A pre-set data acquisition device is used to collect relevant data from the manual splicing process, including the direction, force, number of contacts, operation images, and test results. The design is as follows:

[0080] The orientation of the connector is mainly a process quantity, which is recorded from the moment the button on the connector is manually pressed. An orientation sensor (similar to an attitude sensor) is added inside the connector to monitor the orientation of the connector in real time.

[0081] The force applied to a connector is also a process quantity. The force is detected from the moment the connector is manually brought into contact with the plugged end, and the force is collected on the core inside the connector (similar to a pressure sensor).

[0082] The computer testing software is used to count the number of times connectors are plugged in and unplugged, and to obtain the test results of the plugging and unplugging tests.

[0083] Based on video data of connector operation during plug-in / plug-out testing captured by camera.

[0084] Its main function is to fuse directional data, pressure data, usage statistics, normal or abnormal test results, and video data of manual operations together in a time series, record them to form a database, and continue collecting data until the device is scrapped (using full-cycle data). Optionally, the above data can be used as training data for model training.

[0085] Optionally, before training the model based on the above data, the following preprocessing steps are included: preprocessing the collected data on the direction, force, number of times the plug-in was contacted, the test results, and the video data of manual operation. This mainly includes methods such as noise removal and missing value imputation of the collected data. Principal component analysis is then used to confirm the weight of each influencing factor, and the processed data is normalized to obtain the corresponding eigenvalues ​​and contribution rates.

[0086] Optionally, the model training process includes: processing the training and test datasets to ensure each sample contains time-series information; then dividing the training and test sets in an 8:2 ratio. Simultaneously, the training data serves as the model's input variable, and the remaining lifetime value is used as the expected output variable. A connector remaining lifetime prediction model based on a deep convolutional neural network (AlexNet) is established, using the absolute value error loss function as the model's loss function. During training, to improve the model's generalization performance and prevent overfitting in the AlexNet deep convolutional neural network model, L-type loss functions are used in the fully connected layers. 2Parameter regularization. The model is trained using the training set and validated using the test set. Mean squared error (MSE) is used to evaluate the model's accuracy. If the evaluation passes, the trained connector remaining life prediction model is obtained.

[0087] Example 2

[0088] Figure 3 This is a flowchart of a connector remaining life prediction method provided in Embodiment 2 of the present invention. This embodiment is applicable to situations where connectors are tested during the testing process to facilitate replacement. This method can be executed by a connector remaining life prediction device, which can be implemented in hardware and / or software. This connector remaining life prediction device can be configured in a mobile terminal, PC, or server. Figure 3 As shown, the method includes:

[0089] S210. Obtain the target connector to be tested and determine the historical usage data of the target connector during the historical plug-in test process.

[0090] In this embodiment of the invention, the target connector can be understood as a connector currently in use. Specifically, usage data of the connector during its use, as well as the corresponding time data, can be collected to generate historical usage data of the target connector.

[0091] S220. Input historical usage data into a pre-trained connector remaining life prediction model to obtain the remaining life of the target connector.

[0092] Specifically, based on the historical usage data of the target connector, this historical usage data is input into a pre-trained connector remaining lifespan prediction model to obtain the remaining lifespan of the target connector. Optionally, the remaining lifespan can be understood as the remaining number of times the target connector will be used in subsequent use.

[0093] The technical solution of this invention generates sample training data by acquiring historical test data of the connector during the historical testing process, and trains a model based on this data to obtain a trained connector remaining life prediction model. Based on the trained connector remaining life prediction model, the remaining life of the target connector is predicted. This solves the problem of time-consuming and cost-wasting connector replacement process in the prior art, and achieves accurate prediction of connector remaining life, reducing the time-consuming and cost-consuming process of connector replacement.

[0094] Example 3

[0095] Figure 4This is a schematic diagram of a connector remaining life prediction model training device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a historical test data acquisition module 310, a sample training data determination module 320, and a model training module 330; wherein,

[0096] The historical test data acquisition module 310 is used to acquire each sample connector used for model training and determine the historical test data of each connector during the connection test process.

[0097] The sample training data determination module 320 is used to determine the sample training data of the current sample connector based on the historical test data for any sample connector.

[0098] The model training module 330 is used to train the remaining life prediction model of the connector based on the sample training data of each of the sample connectors, so as to obtain the trained remaining life prediction model of the connector.

[0099] Optionally, based on the above implementation method, the historical test data includes the number of tests, test results, test video data, and contact direction and contact force between the connector and the object under test during the test process.

[0100] Correspondingly, the historical test data acquisition module 310 includes:

[0101] The test count and test result acquisition unit is used to acquire the test count and test results of the sample connector during the test process based on preset test data collection.

[0102] The test video data acquisition unit is used to acquire test video data of the sample connector during the test process based on a preset camera device;

[0103] The contact direction and contact force acquisition unit is used to acquire the contact direction and contact force between the connector and the object under test during the test based on a preset sensor.

[0104] Optionally, based on the above embodiments, the preset sensor includes a pressure sensor and an attitude sensor; the pressure sensor and the attitude sensor are respectively placed inside the sample connector;

[0105] Correspondingly, the contact direction and contact force acquisition unit includes:

[0106] The contact direction acquisition subunit is used to acquire the contact direction between the connector and the object under test during the test based on the attitude sensor.

[0107] The contact force acquisition subunit is used to acquire the contact force between the connector and the object under test during the test based on the pressure sensor.

[0108] Optionally, based on the above implementation method, the sample training data determination module 320 includes:

[0109] The test time acquisition unit is used to acquire the test time of each test performed on the current sample connector during the test process;

[0110] The sample training number determination unit is used to generate sample training data for the current sample connector based on each test time and the corresponding historical test data.

[0111] Optionally, based on the above implementation method, the model training module 330 includes:

[0112] The remaining lifetime prediction value acquisition unit is used to input the sample training data into the connector remaining lifetime prediction model to be trained, and obtain the remaining lifetime prediction value output by the model.

[0113] The model loss function determination unit is used to generate the model loss function of the connector remaining lifetime prediction model in the current iteration based on the number of tests of the sample connector in the testing process and the remaining lifetime prediction value.

[0114] The model parameter adjustment unit is used to adjust the model parameters of the connector remaining lifetime prediction model in the current iteration process based on the loss function.

[0115] The connector remaining life prediction model acquisition unit is used to iteratively train the connector remaining life prediction model until the iteration stopping condition is met, so as to obtain the trained connector remaining life prediction model.

[0116] The connector remaining life prediction model training device provided in the embodiments of the present invention can execute the connector remaining life prediction model training method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0117] Example 4

[0118] Figure 5 This is a schematic diagram of a connector remaining life prediction model training device provided in Embodiment 4 of the present invention. Figure 5 As shown, the device includes: a historical usage data acquisition module 410 and a remaining lifespan prediction module 420; wherein,

[0119] The historical usage data acquisition module 410 is used to acquire the target connector to be tested and determine the historical usage data of the target connector during the historical plugging test process.

[0120] The remaining lifetime prediction module 420 is used to input the historical usage data into a pre-trained connector remaining lifetime prediction model to obtain the remaining lifetime of the target connector.

[0121] The connector remaining life prediction device provided in the embodiments of the present invention can execute the connector remaining life prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0122] Example 5

[0123] Figure 6 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0124] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0126] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as connector remaining lifetime prediction model training methods, and / or connector remaining lifetime prediction methods.

[0127] In some embodiments, the connector remaining lifetime prediction model training method, and / or the connector remaining lifetime prediction method, may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the connector remaining lifetime prediction model training method, and / or the connector remaining lifetime prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the connector remaining lifetime prediction model training method, and / or the connector remaining lifetime prediction method, by any other suitable means (e.g., by means of firmware).

[0128] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0132] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0133] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0134] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0135] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for training a connector remaining life prediction model, characterized in that, include: Obtain each sample connector used for model training, and determine the historical test data of each connector during the connection test process; For any sample connector, the sample training data for the current sample connector is determined based on the historical test data; The remaining life prediction model of the connector is trained based on the sample training data of each of the sample connectors to obtain the trained remaining life prediction model of the connector. The historical test data includes the number of tests, test results, test video data, and contact direction and contact force between the connector and the tested object during the test process. Accordingly, determining the historical test data of each connector during the connection test process includes: The number of tests and test results of the sample connector during the testing process are obtained based on the preset test data collection. Test video data of the sample connector during the testing process is acquired using a preset camera device; The contact direction and contact force between the connector and the object under test are collected based on preset sensors during the testing process.

2. The method according to claim 1, characterized in that, The preset sensor includes a pressure sensor and an attitude sensor; the pressure sensor and the attitude sensor are respectively placed inside the sample connector; Accordingly, the contact direction and contact force between the connector and the object under test during the test based on the preset sensor data acquisition process include: Based on the contact direction between the connector and the object under test during the test process acquired by the attitude sensor; The pressure sensor collects the contact force between the connector and the object under test during the testing process.

3. The method according to claim 1, characterized in that, The step of determining the sample training data for the current sample connector based on the historical test data includes: This refers to obtaining the test time for each test performed on the current sample connector during the testing process; The sample training data for the current sample connector is generated based on the test time and the corresponding historical test data.

4. The method according to claim 1, characterized in that, The process of training the remaining lifetime prediction model of the connector based on the sample training data of each of the sample connectors to obtain the trained remaining lifetime prediction model of the connector includes: The sample training data is input into the connector remaining lifetime prediction model to be trained to obtain the remaining lifetime prediction value output by the model. The model loss function of the connector remaining lifetime prediction model in the current iteration is generated based on the number of tests conducted on the sample connector during the testing process and the remaining lifetime prediction value. The model parameters of the connector remaining lifetime prediction model are adjusted in the current iteration based on the loss function. The remaining life prediction model of the connector is iteratively trained until the iteration stopping condition is met, and the trained remaining life prediction model of the connector is obtained.

5. A method for predicting the remaining lifespan of a connector, characterized in that, The connector remaining life prediction model is obtained using the connector remaining life prediction model training method described in any one of claims 1-4, including: Obtain the target connector to be tested and determine the historical usage data of the target connector during the historical plugging test process; The historical usage data is input into a pre-trained connector remaining life prediction model to obtain the remaining life of the target connector.

6. A connector remaining life prediction model training device, characterized in that, include: The historical test data acquisition module is used to acquire each sample connector used for model training and determine the historical test data of each connector during the connection test process. The sample training data determination module is used to determine the sample training data of the current sample connector based on the historical test data for any sample connector. The model training module is used to train the remaining life prediction model of the connector based on the sample training data of each of the sample connectors, so as to obtain the trained remaining life prediction model of the connector. The historical test data includes the number of tests, test results, test video data, and contact direction and contact force between the connector and the tested object during the test process. The historical test data acquisition module includes: The test count and test result acquisition unit is used to acquire the test count and test results of the sample connector during the test process based on preset test data collection. The test video data acquisition unit is used to acquire test video data of the sample connector during the test process based on a preset camera device; The contact direction and contact force acquisition unit is used to acquire the contact direction and contact force between the connector and the object under test during the test based on a preset sensor.

7. A connector remaining life prediction device, characterized in that, The connector remaining life prediction model is obtained using the connector remaining life prediction model training method described in any one of claims 1-4, including: The historical usage data acquisition module is used to acquire the target connector to be tested and determine the historical usage data of the target connector during the historical plugging test process. The remaining lifetime prediction module is used to input the historical usage data into a pre-trained connector remaining lifetime prediction model to obtain the remaining lifetime of the target connector.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform connector remaining life prediction model training according to any one of claims 1-4, and / or connector remaining life prediction method according to claim 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute and implement the connector remaining life prediction model training according to any one of claims 1-4, and / or the connector remaining life prediction method according to claim 5.

Images