Online production detection method and device of connector

Abstract

The invention discloses an online production detection method and device for a connector, and relates to the technical field of production detection, and the method comprises the steps: receiving an online production detection task; activating the electrical performance factor of the connector to obtain an electrical expected deviation detection coefficient; activating a connector function factor to obtain a function expectation deviation detection coefficient; activating the mechanical property factor of the connector, obtaining a mechanical expected deviation detection coefficient, and drawing a connector detection cloud picture; and judging whether the connector detection cloud picture meets a connector expected deviation constraint or not, and generating a connector detection early warning signal. The technical problems that in the prior art, connector production detection accuracy is low, and product quality is affected are solved, and the technical effects that connector production detection accuracy and reliability are improved, and product quality is guaranteed are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of production detection, and in particular to an online production detection method and device for a connector. Background Art

[0002] In the field of connector production, with the increasing sophistication and diversification of electronic equipment, the quality requirements for connectors are also getting higher and higher. As a key connection component in electronic equipment, the accuracy and reliability of the performance of the connector are directly related to the stable operation of the entire electronic system. Traditional connector production and testing technologies often have many limitations. In terms of accuracy, some detection methods only focus on the testing of a single performance, such as only focusing on electrical performance or mechanical performance, while ignoring the impact of other performance on the overall quality. At the same time, the limited accuracy of the detection equipment, the interference of environmental factors, and the unscientific data processing can easily lead to large deviations in the test results, making it difficult to accurately reflect the true performance of the connector.

[0003] The existing technology has the technical problem of low accuracy in connector production detection, which affects product quality. Summary of the invention

[0004] The present application provides an online production detection method and device for connectors, which are used to solve the technical problem in the prior art that connector production detection has low accuracy and affects product quality.

[0005] In view of the above problems, the present application provides an online production detection method and device for connectors.

[0006] In a first aspect of the present application, a method for online production detection of a connector is provided, the method comprising: Receive an online production inspection task, wherein the online production inspection task includes a target connector and a connector production plan corresponding to the target connector; activate the connector electrical performance factor, and perform an electrical performance expectation deviation detection on the target connector in combination with the connector production plan to obtain an electrical expectation deviation detection coefficient; activate the connector function factor, and perform a functional expectation deviation detection on the target connector in combination with the connector production plan to obtain a functional expectation deviation detection coefficient; activate the connector mechanical performance factor, and perform a mechanical performance expectation deviation detection on the target connector in combination with the connector production plan to obtain a mechanical expectation deviation detection coefficient; sort the electrical expectation deviation detection coefficient, the functional expectation deviation detection coefficient, and the mechanical expectation deviation detection coefficient to draw a connector inspection cloud map; determine whether the connector inspection cloud map satisfies the connector expectation deviation constraint; if the connector inspection cloud map does not satisfy the connector expectation deviation constraint, generate a connector inspection warning signal.

[0007] A second aspect of the present application provides an online production detection device for a connector, the device comprising: A detection task receiving module, the detection task receiving module is used to receive an online production detection task, wherein the online production detection task includes a target connector and a connector production plan corresponding to the target connector; an electrical expected deviation detection coefficient acquisition module, the electrical expected deviation detection coefficient acquisition module is used to activate the connector electrical performance factor, and in combination with the connector production plan, perform an electrical performance expected deviation detection on the target connector to obtain an electrical expected deviation detection coefficient; a functional expected deviation detection coefficient acquisition module, the functional expected deviation detection coefficient acquisition module is used to activate the connector functional factor, and in combination with the connector production plan, perform a functional expected deviation detection on the target connector to obtain a functional expected deviation detection coefficient; a mechanical expected deviation detection coefficient acquisition module, the mechanical expected deviation detection coefficient acquisition module The mechanical expected deviation detection coefficient acquisition module is used to activate the mechanical performance factor of the connector, and in combination with the connector production plan, performs mechanical performance expected deviation detection on the target connector to obtain the mechanical expected deviation detection coefficient; the connector detection cloud map drawing module, the connector detection cloud map drawing module is used to organize the electrical expected deviation detection coefficient, the functional expected deviation detection coefficient and the mechanical expected deviation detection coefficient, and draw the connector detection cloud map; the expected deviation constraint judgment module, the expected deviation constraint judgment module is used to judge whether the connector detection cloud map meets the connector expected deviation constraint; the connector detection warning signal generation module, the connector detection warning signal generation module is used to generate a connector detection warning signal if the connector detection cloud map does not meet the connector expected deviation constraint.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Receive online production inspection tasks; activate the electrical performance factor of the connector to obtain the electrical expected deviation detection coefficient; activate the functional factor of the connector to obtain the functional expected deviation detection coefficient; activate the mechanical performance factor of the connector to obtain the mechanical expected deviation detection coefficient; sort out the electrical expected deviation detection coefficient, the functional expected deviation detection coefficient and the mechanical expected deviation detection coefficient, and draw a connector inspection cloud map; determine whether the connector inspection cloud map meets the connector expected deviation constraint; if the connector inspection cloud map does not meet the connector expected deviation constraint, generate a connector inspection warning signal. The technical effect of improving the accuracy and reliability of connector production inspection and ensuring product quality is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a flow chart of an online production detection method for a connector provided in an embodiment of the present application; Figure 2 A schematic structural diagram of an online production detection device for a connector provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: detection task receiving module 10, electrical expected deviation detection coefficient acquisition module 20, functional expected deviation detection coefficient acquisition module 30, mechanical expected deviation detection coefficient acquisition module 40, connector detection cloud map drawing module 50, expected deviation constraint judgment module 60, connector detection warning signal generation module 70. DETAILED DESCRIPTION

[0012] The present application provides an online production detection method and device for connectors, which is used to solve the technical problem in the prior art that connector production detection has low accuracy and affects product quality.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides an online production detection method for a connector, the method comprising: Step S100: receiving an online production inspection task, wherein the online production inspection task includes a target connector and a connector production plan corresponding to the target connector.

[0015] Specifically, the online production inspection process begins and the online production inspection task is received. This task clearly specifies the specific object to be inspected, that is, the target connector. The target connector can be connectors of various types and specifications, in different production stages or production lines. At the same time, the task also includes the connector production plan corresponding to the target connector. The connector production plan is very critical information, which usually includes detailed content of many aspects such as the connector's design parameters, production process, quality standards, material requirements, etc. This information is of great guiding significance for subsequent inspection work, because the inspection process needs to judge whether the target connector meets the quality and performance expectations based on the standards and requirements in the production plan.

[0016] Step S200: activating the connector electrical performance factor, and performing electrical performance expectation deviation detection on the target connector in combination with the connector production plan to obtain an electrical expectation deviation detection coefficient.

[0017] Specifically, first activate multiple factors closely related to the electrical performance of the target connector, such as contact resistance, insulation resistance, withstand voltage, withstand current, etc. These factors are key indicators for evaluating the electrical performance of the connector, combined with the connector production plan corresponding to the target connector, which contains the design standards and expected requirements for the electrical performance of this connector. Then, based on these factors and the production plan, the target connector is tested for expected deviations in electrical performance. During the test, the actual measured electrical performance data is compared and analyzed with the expected electrical performance standards in the production plan, and finally an electrical expected deviation detection coefficient that can quantify the degree of electrical performance deviation is obtained. This coefficient intuitively reflects the difference between the actual electrical performance of the target connector and the expected electrical performance, and provides an important basis for subsequent judgment of whether the electrical performance of the connector is qualified and whether it needs to be adjusted or improved.

[0018] Step S300: activating the connector function factor, and performing function expectation deviation detection on the target connector in combination with the connector production plan to obtain a function expectation deviation detection coefficient.

[0019] Specifically, the connector functional factors are activated. These functional factors cover multiple aspects that play a key role in the function of the connector. For example, insertion loss reflects the degree of signal loss when passing through the connector. If the insertion loss is too large, the signal will be weakened, affecting the quality and reliability of signal transmission. Return loss is also an important functional factor. It indicates the reflection of the signal at the connector. Inappropriate return loss will cause signal reflection to interfere with the transmission of normal signals. Transmission efficiency reflects the efficiency of the connector in transmitting signals or energy, while transmission quality comprehensively considers the impact of various factors on signal transmission, including signal distortion, noise, etc. Then, the functional expectation deviation detection is carried out in combination with the connector production plan. The production plan stipulates the expected performance and standards of the connector in terms of function. By comparing and analyzing the actual functional performance of the target connector with the expected function in the production plan, the functional expectation deviation detection coefficient is finally obtained. This coefficient quantifies the degree of deviation between the function of the target connector and the expected function, which can help determine whether the function of the connector meets the production requirements and whether there are functional defects or deviations, and provides clear data support for subsequent quality control and improvement measures.

[0020] Step S400: activating the connector mechanical performance factor, and performing mechanical performance expected deviation detection on the target connector in combination with the connector production plan to obtain a mechanical expected deviation detection coefficient.

[0021] Specifically, the evaluation of various factors related to the mechanical performance of the connector is initiated, and mechanical performance factors such as connector structure size, connector surface quality, plug-in force and mechanical strength are activated. Among them, the connector structure size determines its adaptability and installation stability with other components. If there is a deviation in the size, it will cause connection problems; the surface quality of the connector affects the contact performance and corrosion resistance, and the rough surface leads to poor contact and susceptibility to corrosion; the plug-in force is related to the user's operating experience and connection stability. Too large or too small plug-in force will bring adverse consequences; mechanical strength ensures that the connector can still maintain a reliable connection in the face of various external forces such as tension, compression, bending, and vibration shock. Combined with the production plan of the target connector, the mechanical performance expectation deviation detection is carried out. The production plan has clear design requirements and expected standards for mechanical performance. By comparing and analyzing the actual mechanical performance of the target connector with the expected performance in the production plan, the mechanical expectation deviation detection coefficient is finally obtained. This coefficient can quantify the degree of deviation of the target connector from the expected mechanical performance, and provide accurate data support for the subsequent judgment of whether the mechanical performance of the connector is qualified and whether it needs to be adjusted and improved, which helps to ensure that the connector meets the production and use requirements in terms of mechanical performance.

[0022] Step S500: Arrange the electrical expected deviation detection coefficient, the functional expected deviation detection coefficient and the mechanical expected deviation detection coefficient, and draw a connector detection cloud diagram.

[0023] Specifically, the electrical expected deviation detection coefficient, functional expected deviation detection coefficient and mechanical expected deviation detection coefficient obtained in the previous steps are sorted out. These coefficients reflect the deviation between the actual performance and the expected performance of the target connector from different performance dimensions. Then, based on these sorted coefficients, a connector detection cloud map is drawn. The cloud map is an intuitive data visualization method that can present complex data information in a graphical form. In this connector detection cloud map, the deviation detection coefficients of electrical, functional and mechanical properties are given different colors, shapes or sizes according to different coefficient ranges and importance. Such a cloud map makes it possible to understand the overall performance of the target connector at a glance and quickly discover possible performance problems or areas where deviations are concentrated. At the same time, the cloud map also helps to compare and analyze the performance between connectors of different batches or models, providing strong support for the optimization and quality control of the production process.

[0024] Step S600: Determine whether the connector detection cloud graph satisfies the connector expected deviation constraint.

[0025] Specifically, the drawn connector inspection cloud map is analyzed. By evaluating the deviation of various electrical, functional, mechanical and other performances presented in the cloud map, it is determined whether they are within the allowable range, that is, whether they meet the expected deviation constraints set previously. For example, if in terms of electrical performance, according to the design requirements and quality standards, the deviation of the contact resistance cannot exceed a certain numerical range, then when judging, it will be checked whether the contact resistance deviation coefficient reflected in the cloud map is within this limited range. Similarly, similar judgments will be made for functional performance (such as insertion loss, return loss, etc.) and mechanical performance (such as plug-in force, mechanical strength, etc.). If the performance deviation coefficients in the cloud map are all within the range specified by the expected deviation constraint, then it can be considered that the overall performance of the connector meets the requirements; conversely, if the deviation coefficients of any one or more performances exceed the corresponding constraint range, it indicates that the connector has performance problems or quality risks, which require further analysis and processing.

[0026] Step S700: If the connector detection cloud map does not satisfy the connector expected deviation constraint, a connector detection warning signal is generated.

[0027] Specifically, when it is found that the connector detection cloud map does not meet the connector's expected deviation constraint, it means that the connector has deviations or problems beyond the specified range in terms of electrical performance, functional performance or mechanical performance. At this time, a connector detection warning signal is generated. This warning signal can be in various forms, such as popping up a striking prompt box on the interface of the detection system, issuing a specific sound and light alarm, or sending a message notification to the equipment of relevant personnel (such as computers, mobile phones, etc.). Its purpose is to promptly attract the attention of relevant personnel (such as production management personnel, quality control personnel, technical engineers, etc.) so that they can quickly know that there are performance problems or quality risks in the connector. In this way, relevant personnel can take corresponding measures in time, such as suspending production for further testing and troubleshooting, adjusting production processes or equipment, repairing or replacing problematic connectors, etc., to prevent defective connectors from flowing into subsequent production links or markets, thereby ensuring the quality and reliability of connector products and reducing losses and adverse effects caused by quality problems.

[0028] In a possible implementation, step S200 further includes: S210: The electrical performance factors of the connector include contact resistance, insulation resistance, withstand voltage and withstand current.

[0029] S220: Based on the connector electrical performance factor and the connector production plan, perform an expected electrical performance confidence prediction on the target connector to obtain an expected electrical performance result.

[0030] S230: Based on the connector electrical performance factor, perform an electrical performance confidence test on the target connector to obtain an electrical performance test result.

[0031] S240: Perform deviation identification based on the electrical performance expected result and the electrical performance detection result to obtain an electrical expected deviation identification result.

[0032] S250: Based on the electrical expectation deviation identification result, the electrical expectation deviation detection coefficient is generated according to the three channels of electrical expectation deviation detection.

[0033] Specifically, the specific contents of the connector electrical performance factors are clarified. Contact resistance is an indicator to measure the conductive performance of the contact part of the connector. Excessive contact resistance will cause heat and energy loss; insulation resistance reflects the insulation performance of the insulating part of the connector. Too low insulation resistance will cause safety problems such as leakage; voltage resistance indicates the highest voltage that the connector can withstand without being broken down, which is crucial for connectors working in different voltage environments; current resistance reflects the maximum current allowed to pass through the connector. Exceeding the current resistance will cause overheating or even burning.

[0034] To obtain the expected results of electrical performance using the Bayesian network model, first, collect a large amount of historical data related to the electrical performance of the connector. These data include the electrical performance factors of different connectors (contact resistance, insulation resistance, withstand voltage, withstand current, etc.), the corresponding production plans (materials, processes, design parameters, etc.) and the actual electrical performance results. Construct the Bayesian network structure and determine the nodes: take the electrical performance factors such as contact resistance, insulation resistance, withstand voltage, withstand current as nodes, and the key factors in the production plan, such as material type, process parameters, etc., as nodes, and set up a node representing the expected results of electrical performance. Establish connections and determine the connections between nodes based on expert knowledge and dependencies in the data. Use historical data to learn the parameters of the Bayesian network, that is, determine the conditional probability distribution between each node. For each node, according to its connection relationship with other nodes and historical data, calculate the probability of the node being in different states under the state of a given parent node (if any). For example, for the contact resistance node, if the material type is one of its parent nodes, then according to the distribution of contact resistance under different material types in the historical data, calculate the probability that the contact resistance is in different value ranges under different material types. Conduct confidence prediction of expected electrical performance. When predicting a new target connector, input the production plan information of the target connector, set the state of its corresponding node, and use the Bayesian network reasoning algorithm to calculate the probability distribution of the electrical performance expected result node based on the established network structure and parameters. In this way, the Bayesian network model can comprehensively consider the complex relationship between the connector electrical performance factors and the production plan, and make a more accurate prediction of the expected electrical performance results of the target connector.

[0035] The testing work is based on the electrical performance factors of the connector. Professional testing equipment and specific methods are used to conduct comprehensive electrical performance confidence testing on the target connector. In terms of contact resistance, by applying current to the connector under a specific environment and measuring the voltage at both ends, the contact resistance value is calculated according to Ohm's law, and precision instruments such as micro-ohmmeters are used to ensure accuracy. For insulation resistance, a DC voltage is applied between different parts of the connector, and the current passing through is measured to calculate the resistance. Insulation resistance testers are commonly used tools. During voltage resistance testing, a voltage higher than normal operation is applied to the connector for a period of time to observe whether there is a breakdown or flashover phenomenon. A voltage resistance tester can assist in completing this operation. Current resistance testing allows the connector to pass a gradually increasing current to observe its temperature, resistance changes, and whether it is overheated or damaged under different currents. Current sources and temperature sensors are also used. After these rigorous testing operations, the electrical performance test results presented in the form of specific data are finally obtained, covering the precise value of contact resistance, the size of insulation resistance, the withstand voltage, and the performance under different currents. These results objectively reflect the true electrical performance of the target connector and provide a key basis for subsequent analysis and evaluation.

[0036] Based on the expected electrical performance results and the electrical performance test results obtained previously, deviation identification is performed, the two are compared, and the difference between the actual performance and the expected performance is calculated. If the difference exceeds a certain allowable range, it can be determined that there is a deviation. In this way, it can be determined whether the electrical performance of the target connector meets expectations, as well as the specific degree and direction of the deviation, and the electrical expectation deviation identification result can be obtained.

[0037] The work is carried out based on the obtained electrical expectation deviation identification results. This identification result has clearly identified the difference between the target connector and the expected electrical performance. Then, the electrical expectation deviation detection coefficient is generated based on the three channels of electrical expectation deviation detection. Among them, the electrical expectation deviation depth detection channel focuses on analyzing the severity of the deviation. It will quantify the deviation of each electrical performance factor. For example, when the actual value of the contact resistance is far beyond the expected range, it will accurately calculate the depth value of this deviation; the electrical expectation deviation breadth detection channel pays more attention to the range of deviation. It will integrate the deviation of multiple electrical performance factors and evaluate the breadth of the overall deviation. When the deviation of multiple performance factors occurs at the same time, it will measure this wide deviation; and the coupling weighted channel will comprehensively consider the two aspects of depth and breadth. Through the weighted algorithm, the influence of the two is integrated. Finally, an electrical expectation deviation detection coefficient that can comprehensively and accurately reflect the electrical performance deviation is obtained from the comprehensive calculation of these three channels. This coefficient can provide key and quantitative data support for subsequent quality assessment, problem analysis and formulation of improvement measures.

[0038] In a possible implementation, step S220 further includes: S221: Using the connector production plan as a connector retrieval constraint, and using the detection parameters of the connector electrical performance factor as a connector retrieval target.

[0039] S222: Retrieve connector electrical performance test records according to the connector retrieval constraint and the connector retrieval target to obtain an electrical performance test sample set.

[0040] S223: Classifying the electrical performance test sample set according to the connector electrical performance factor to obtain a plurality of electrical performance test sample clusters.

[0041] S224: traverse the plurality of electrical performance detection sample clusters, and extract a first electrical performance detection sample cluster.

[0042] S225: Perform confidence optimization according to the first electrical performance detection sample cluster to construct a first electrical performance detection confidence cluster that meets the confidence evaluation constraint.

[0043] S226: Performing concentrated value calculation according to the first electrical performance detection confidence cluster to obtain a first electrical performance expected confidence value, and adding the first electrical performance expected confidence value to the electrical performance expected result.

[0044] Specifically, the connector production plan contains key information such as production process, materials, and design specifications, which are used as search constraints to filter out only connector records that meet the specific production plan. For example, if the production plan stipulates the use of specific materials and processes, then only connectors produced under these conditions are considered during the search. The test parameters of the connector electrical performance factors (such as contact resistance, insulation resistance, withstand voltage, withstand current, etc.) are used as search targets, making it clear that the test records related to these electrical performance parameters are to be retrieved.

[0045] Using the set search constraints and targets, a comprehensive search is performed in the database or storage system. For example, in a database containing a large number of connector test records, screening is performed based on the specific conditions of the production plan (such as specific materials, specific process time period, etc.) and the test parameter range of the electrical performance factor (such as contact resistance within a certain range, insulation resistance greater than a certain value, etc.). The final electrical performance test sample set is a collection of all connector test records that meet these conditions. It contains a large number of sample data with similar production plans and electrical performance characteristics to the target connector.

[0046] The sample set is classified according to different electrical performance factors. For example, the sample set can be divided into different groups according to different ranges of contact resistance, different levels of insulation resistance, different ranges of withstand voltage and withstand current, etc. Each group is an electrical performance test sample cluster, so multiple sample clusters are obtained, and the samples in each sample cluster have similarities in specific electrical performance factors.

[0047] The multiple electrical performance test sample clusters that have been classified previously are checked one by one. These sample clusters are generated by carefully dividing the electrical performance test sample set according to the connector electrical performance factors. Each sample cluster has unique electrical performance characteristics and corresponding ranges. The "first electrical performance test sample cluster" is extracted from these sample clusters. The "first" here does not simply refer to the first in order, but is selected according to specific rules or actual needs. For example, the number of samples can be considered. If you want to choose a more representative sample cluster with sufficient data, you may choose the one with the largest number of samples. The purpose is to determine a suitable sample set from many sample clusters for subsequent in-depth analysis, confidence optimization and related calculations, and ultimately provide strong support for accurate confidence prediction of electrical performance expectations.

[0048] Confidence optimization is a process of screening and adjusting sample data to improve its credibility and reliability. Deleting samples that do not meet the confidence evaluation constraints is one of the specific operations of confidence optimization. Confidence evaluation constraints are usually some standards and conditions set based on statistical principles and actual needs. For example, set an error range for sample data. If the deviation between the measured value of a sample and the mean or median of the sample cluster exceeds this error range, the sample is considered to not meet the confidence evaluation constraint and is deleted from the sample cluster. Or according to the distribution characteristics of the sample data, such as for the data of normal distribution, those outlier samples at the tail of the distribution are deleted, because these outliers will cause great interference to the subsequent analysis and calculation. After such screening and processing, the first electrical performance detection confidence cluster that meets the confidence evaluation constraints is constructed. This confidence cluster is a more reliable and accurate sample set obtained after optimization. It meets the confidence evaluation constraints set in advance and can better reflect the real characteristics and laws of the target connector in terms of specific electrical performance.

[0049] First, the operation is performed on the first electrical performance detection confidence cluster. This confidence cluster is a reliable sample set obtained after the previous screening and optimization. It excludes outliers and samples that do not meet the confidence evaluation constraints, and can more accurately represent the characteristics of the target connector in terms of specific electrical performance. Calculating the central value is a key step. The central value is a statistic used to describe the trend in the data set. Calculate the arithmetic mean, that is, add the corresponding electrical performance values ​​of all samples in the confidence cluster and divide it by the number of samples; the first electrical performance expected confidence value is obtained through the central value calculation. This value reflects the typical performance or central trend of the electrical performance in the sample set that has been screened and optimized. It is a reasonable estimate and prediction of the electrical performance of the target connector. Finally, the first electrical performance expected confidence value is added to the electrical performance expected result. The electrical performance expected result is a comprehensive expectation and prediction of the electrical performance of the target connector. Adding the newly calculated first electrical performance expected confidence value can enrich and improve this expected result, making the electrical performance expected result more comprehensive and accurate. In a possible implementation, step S250 further includes: S251: The three electrical expected deviation detection channels include an electrical expected deviation depth detection channel, an electrical expected deviation breadth detection channel and an electrical deviation detection coupling weighted channel.

[0050] S252: Input the electrical expected deviation recognition result into the electrical expected deviation depth detection channel to obtain an electrical expected deviation depth detection coefficient.

[0051] S253: Based on the electrical expected deviation identification result, and according to the electrical expected deviation width detection channel, an electrical expected deviation width detection coefficient is obtained.

[0052] S254: Input the electrical expected deviation depth detection coefficient and the electrical expected deviation width detection coefficient into the electrical deviation detection coupling weighted channel to obtain the electrical expected deviation detection coefficient.

[0053] Specifically, the three channels of electrical expected deviation detection include the electrical expected deviation depth detection channel, the electrical expected deviation breadth detection channel and the electrical deviation detection coupling weighted channel, which clarifies that the analysis is carried out from three different angles and dimensions when performing electrical expected deviation detection.

[0054] The electrical expectation deviation identification results obtained above are passed as input information to the electrical expectation deviation depth detection channel, which will play its specific function to process these data. Taking contact resistance and insulation resistance as examples, first, the deviation amount of each electrical performance indicator is assigned a corresponding weight, and different indicators have different degrees of influence on the overall electrical performance. The deviation amount of each indicator is preliminarily quantified. For contact resistance, its deviation ratio is calculated, and the absolute value of the difference between the actual contact resistance value and the expected contact resistance value is divided by the expected contact resistance value. Then, the electrical expectation deviation depth detection coefficient is determined by weighted summation. The deviation ratio of each indicator is multiplied by the corresponding weight and then added. Through such a series of operations and calculations, the electrical expectation deviation depth detection coefficient finally obtained can clearly reflect the severity of the deviation of electrical performance from expectations in specific aspects.

[0055] Based on the electrical expected deviation identification results, the electrical expected deviation breadth detection channel is used for analysis. Analyze the deviation of a single electrical performance factor For each electrical performance factor, such as contact resistance, first determine its actual measured value and expected standard value. Calculate the deviation of the factor and subtract the expected value from the actual value to get the difference.

[0056] The deviations of multiple electrical performance factors are integrated to summarize the deviations of all electrical performance factors. Considering the weights between different factors, some factors have a greater impact on the overall electrical performance, and their weights are correspondingly higher; while some factors have relatively small impacts and have lower weights. These weights can be determined based on experience or actual needs. Finally, the deviation quantization value of each factor is multiplied by its corresponding weight, and all weighted deviation quantization values ​​are added together. Based on the result of the addition and a suitable normalization factor (such as the sum of all factor weights), a value within a certain range is calculated, which is the electrical expected deviation breadth detection coefficient.

[0057] The two key coefficients, the electrical expected deviation depth detection coefficient and the electrical expected deviation breadth detection coefficient, are used as input data and input into the electrical deviation detection coupling weighted channel. The function of this channel is to comprehensively process and couple the information of depth and breadth. In this channel, the weighted method will be used to integrate the two coefficients. The purpose of weighting is to give different weights to the depth detection coefficient and the breadth detection coefficient according to different actual needs and the difference in the degree of emphasis on the depth and breadth factors. After weighted calculation and coupling processing, the electrical expected deviation detection coefficient is finally obtained.

[0058] In a possible implementation, step S300 further includes: S310: The connector functional factors include insertion loss, return loss, transmission efficiency and transmission quality.

[0059] S320: Based on the connector functional factor and the connector production plan, perform function expectation confidence prediction on the target connector to obtain a function expectation result.

[0060] S330: Based on the connector function factor, perform a function confidence test on the target connector to obtain a function test result.

[0061] S340: Perform deviation identification based on the function expectation result and the function detection result to obtain a function expectation deviation identification result.

[0062] S350: Based on the functional expectation deviation identification result, the functional expectation deviation detection coefficient is generated according to the three channels of functional expectation deviation detection, wherein the three channels of functional expectation deviation detection include a functional expectation deviation depth detection channel, a functional expectation deviation breadth detection channel and a functional deviation detection coupling weighted channel.

[0063] Specifically, connector functional factors include insertion loss, return loss, transmission efficiency and transmission quality. Insertion loss refers to the signal power loss caused by the insertion of connectors and other devices in the transmission system. It affects the signal strength and transmission distance, and is an important indicator to measure the degree of signal attenuation of the connector. Return loss reflects the degree to which the signal is reflected back due to impedance mismatch and other reasons during the transmission process. The greater the return loss, the less the reflected signal is, and the better the transmission quality. Transmission efficiency refers to the ratio of the energy actually transmitted by the signal when passing through the connector to the input energy, which reflects the efficiency of the connector's signal transmission capability. Transmission quality is a comprehensive concept that comprehensively considers the overall impact of multiple factors such as insertion loss, return loss, and noise interference on signal transmission, and is usually measured by indicators such as bit error rate and signal-to-noise ratio.

[0064] Use Bayesian network to predict the confidence of functional expectation. First, construct the Bayesian network structure to determine the nodes including connector functional factors such as insertion loss, return loss, transmission efficiency, transmission quality, and key factors of connector production plan such as material selection, process parameters, and design features. Connect these nodes according to the actual causal relationship and dependency relationship, such as materials and processes will affect functional factors. Then determine the probability distribution of the node. On the one hand, give the prior probability based on historical data or expert experience, such as the probability of a certain material in a certain insertion loss range; on the other hand, determine the conditional probability, such as the probability of insertion loss in different numerical ranges under a certain material and process. Then perform the confidence prediction of functional expectation, input the specific production plan information into the network as evidence to update the network, use the probabilistic reasoning algorithm such as Bayesian reasoning, update the node probability distribution according to the input evidence and the established probability relationship, and obtain the posterior probability distribution for the functional factor node. Finally, based on this distribution, comprehensively consider the value range and probability of each functional factor to determine the functional expectation result.

[0065] Perform functional confidence testing on the target connector based on the functional factors of the connector. For insertion loss, use professional signal testing equipment to input the signal into the transmission line containing the target connector, and calculate the insertion loss value by measuring the power change before and after the signal passes. In terms of return loss detection, use a network analyzer to transmit a signal of a specific frequency, measure the signal strength reflected back from the system, and calculate the return loss value based on the relationship between return loss and reflection coefficient. For transmission efficiency, it is determined by comparing the total energy input to the connector with the effective energy at the receiving end. For example, a certain energy signal is sent at the transmitting end, and the receiving end measures the received energy and then calculates it. The transmission quality can be judged by comprehensively considering factors such as bit error rate and signal stability, using corresponding test instruments and evaluation methods, such as counting the number of bit errors over a period of time. Through these detection means and methods for different functional factors, we can finally obtain functional test results that can accurately reflect the actual functional status of the target connector. The functional expectation result (predicted functional level) is compared with the functional test result (actual measured functional level). If there is a difference, it can be determined that there is a deviation from the functional expectation. The functional expectation deviation depth detection channel focuses on the severity of the deviation, that is, how big the difference is between the actual value of the functional indicator and the expected value. For example, if the actual value of the insertion loss is much larger than the expected value, then the larger deviation depth will be reflected in the depth detection channel. The functional expectation deviation breadth detection channel focuses on the scope of the deviation, considering the deviation of multiple functional factors or the overall function. For example, if multiple functional factors have a certain degree of deviation, or the deviation involves multiple key functional aspects of the connector, then the breadth detection channel will reflect the breadth of the deviation. The functional deviation detection coupled weighted channel integrates the information of both depth and breadth and combines them in a weighted manner. Because in actual applications, both depth and breadth are important for a comprehensive assessment of functional expectation deviation, but their importance may vary depending on the specific situation, so weighting is used to balance the impact of the two. The final generated functional expectation deviation detection coefficient is a quantitative indicator that comprehensively reflects the functional expectation deviation, which can provide a basis for subsequent analysis, evaluation and improvement.

[0066] In a possible implementation, step S400 further includes: S410: The connector mechanical performance factors include connector structure size, connector surface quality, plug-in force and mechanical strength.

[0067] S420: Based on the connector mechanical performance factor and the connector production plan, perform expected confidence prediction of mechanical performance of the target connector to obtain expected mechanical performance results.

[0068] S430: Based on the connector mechanical property factor, perform a mechanical property confidence test on the target connector to obtain a mechanical property test result.

[0069] S440: Perform deviation identification based on the expected mechanical performance result and the mechanical performance detection result to obtain a mechanical expected deviation identification result.

[0070] S450: Based on the mechanical expected deviation identification result, the mechanical expected deviation detection coefficient is generated according to the three channels of mechanical expected deviation detection.

[0071] Specifically, the mechanical performance factors of the connector include the connector structure size, connector surface quality, plug-in force and mechanical strength: Connector structure size. Accurate structure size is crucial to the compatibility of the connector with other components. Dimensional deviation will lead to loose connection or failure to connect normally. Connector surface quality. Good surface quality can ensure reliable electrical contact, reduce contact resistance and signal interference. Surface defects or roughness affect the stability of the connection. Plug-in force. Appropriate plug-in force can ensure reliable connection and facilitate operation. Too large or too small plug-in force will cause problems in use. Mechanical strength. Sufficient mechanical strength can make the connector stable in various environments and stress conditions, not easy to damage, and ensure long-term and reliable connection.

[0072] Using the Bayesian network model, determine the nodes, set the connector mechanical performance factors (connector structure size, connector surface quality, plug-in force, mechanical strength) and the key factors in the connector production plan (such as material properties, processing technology, design parameters, etc.) as network nodes. Determine the conditional probability relationship between each node based on historical data, expert experience or experimental results. Collect a large amount of historical data related to the mechanical properties and production plan of the connector, including the performance of the connector under different production conditions, the effects of different material and process combinations, etc. Use the collected data to train the Bayesian network and adjust the conditional probability distribution between nodes so that it can more accurately reflect the actual situation. Through continuous iteration and optimization, improve the prediction accuracy of the model. Input the specific connector production plan information (including selected materials, process parameters, design features, etc.) and the current preliminary estimate or known information of the mechanical performance factors into the Bayesian network model. Based on the probability distribution, the possible states of each mechanical performance factor are comprehensively considered to obtain the expected results of mechanical performance.

[0073] The target connector is tested for mechanical performance confidence based on the connector mechanical performance factor. For the connector structure size, precision measuring tools are used, such as calipers and micrometers for measuring simple linear dimensions, and three-dimensional coordinate measuring machines are used for accurate measurement of complex three-dimensional structure dimensions to obtain accurate dimensional data. In terms of connector surface quality inspection, first visual inspection is performed under appropriate lighting to check for obvious defects, and then small defects are magnified and observed using an optical or electron microscope. A surface roughness measuring instrument is also used to measure the degree of surface micro-contour fluctuation by moving the probe to obtain the roughness value. For the detection of plug-in and pull-out force, the plug and socket are fixed on the fixture with the help of plug-in and pull-out force test equipment. When the equipment simulates the plug-in and pull-out action, the force sensor is used to measure the force value during the plug-in and pull-out process in real time. Through these professional detection methods for different mechanical performance factors, the test results that can truly reflect the mechanical performance status of the target connector are finally obtained.

[0074] The deviation between the mechanical performance test results and the corresponding mechanical performance expected results is identified, and the two are compared to calculate the difference between the actual performance and the expected performance. If the difference exceeds a certain allowable range, it can be determined that there is a deviation. In this way, it is possible to determine whether the mechanical performance of the target connector meets expectations, as well as the specific degree and direction of the deviation, and obtain the mechanical performance deviation identification result.

[0075] First of all, we should carry out work based on the results of mechanical expectation deviation identification. The three channels of mechanical expectation deviation detection include depth detection channel, breadth detection channel and coupling weighted channel. The depth detection channel mainly evaluates the severity of deviation of a single mechanical performance factor. For example, for the deviation of plugging and unplugging force, if the difference between the actual and expected plugging and unplugging force is large, this channel will focus on the size of the difference. The breadth detection channel focuses on the overall deviation of multiple mechanical performance factors. For example, when there are deviations in multiple factors such as the structural size, surface quality, plugging and unplugging force and mechanical strength of the connector, it will comprehensively consider the overall range and distribution of these deviations. The coupling weighted channel combines the information of depth and breadth, and considers the differences in the importance of depth and breadth under different application scenarios or product requirements by setting reasonable weights. When generating the mechanical expectation deviation detection coefficient, first sort out the deviation data of each factor in the mechanical expectation deviation identification result, and then analyze it through three channels. The depth detection channel calculates the relative or absolute deviation of a single factor, the breadth detection channel evaluates the comprehensive deviation of multiple factors, and the coupled weighted channel fuses the results of the first two and the preset weights. Finally, this information is integrated to generate a mechanical expected deviation detection coefficient that can comprehensively reflect the overall situation of mechanical performance deviation, providing a quantitative basis for subsequent evaluation and improvement measures.

[0076] In a possible implementation, step S450 further includes: S451: The three channels of mechanical expected deviation detection include a mechanical expected deviation depth detection channel, a mechanical expected deviation breadth detection channel and a mechanical deviation detection coupling weighted channel.

[0077] S452: Input the mechanical expected deviation recognition result into the mechanical expected deviation depth detection channel to obtain a mechanical expected deviation depth detection coefficient.

[0078] S453: Based on the mechanical expectation deviation identification result, according to the mechanical expectation deviation breadth detection channel, a mechanical expectation deviation breadth detection coefficient is obtained.

[0079] S454: Input the mechanical expected deviation depth detection coefficient and the mechanical expected deviation width detection coefficient into the mechanical deviation detection coupling weighted channel to obtain the mechanical expected deviation detection coefficient.

[0080] Specifically, the depth detection channel of mechanical expectation deviation focuses on the severity of deviation of a single mechanical performance factor from expectations, that is, an in-depth analysis of the degree of deviation of a specific factor. The breadth detection channel of mechanical expectation deviation pays more attention to the deviation of multiple mechanical performance factors combined, and evaluates the degree of deviation from the perspective of overall scope and distribution. The mechanical deviation detection coupling weighted channel plays a role of comprehensive coordination, integrating the results of depth detection and breadth detection according to a certain weight relationship to more comprehensively and accurately reflect the overall situation of mechanical expectation deviation.

[0081] It is clear that there are deviation values ​​of multiple mechanical performance factors in the expected deviation identification results of the machinery. For each factor's deviation value, first calculate its absolute deviation value, that is, no matter whether the deviation is positive or negative, only take its numerical value. Determine the expected range corresponding to each factor, which usually has a minimum value and a maximum value. Then, by calculating the relative deviation degree, that is, the proportion of the absolute deviation value in the expected range, such as the ratio of the deviation value of a factor to the difference between the maximum and minimum values ​​of the expected range of the factor. After that, assign an importance weight to each factor to reflect the difference in importance of different factors in depth detection. Finally, multiply the relative deviation degree of each factor by its corresponding weight and sum them up. The sum obtained is the mechanical expected deviation depth detection coefficient. This coefficient comprehensively reflects the depth of deviation of each mechanical performance factor from the expectation. The larger the coefficient, the more significant the deviation in depth.

[0082] According to the deviation values ​​of multiple mechanical performance factors in the expected deviation identification results of the machinery, a deviation threshold is first set. This threshold is a standard for judging whether the deviation is significant. Then the number of factors with deviation values ​​exceeding this threshold is counted, and then the standard deviation of all factor deviation values ​​is calculated. The standard deviation can reflect the degree of dispersion of the deviation value. At the same time, the average value of all factor deviation values ​​needs to be calculated. After that, two parts of the breadth detection coefficient are defined. One is the proportion of the number of factors with deviation values ​​exceeding the threshold to the total number of factors, which reflects how many factors have a large deviation; the other is the coefficient of dispersion of the deviation value, which is reflected by the relationship between the standard deviation and the average value. Then, weights are assigned to these two parts respectively. The determination of the weights is based on actual needs and the judgment of the importance of these two parts. Finally, the two parts are multiplied by their respective weights and summed up. The result is the expected deviation breadth detection coefficient of the machinery, which comprehensively reflects the overall breadth of the deviation of the mechanical performance factors. The larger the coefficient, the more extensive or comprehensive the deviation is in breadth.

[0083] The two key coefficients, the mechanical expected deviation depth detection coefficient and the mechanical expected deviation breadth detection coefficient, are used as input data and input into the mechanical deviation detection coupling weighted channel. The function of this channel is to comprehensively process and couple the information of depth and breadth. In this channel, the weighted method will be used to integrate the two coefficients. The purpose of weighting is to give different weights to the depth detection coefficient and the breadth detection coefficient according to different actual needs and the difference in the degree of emphasis on the depth and breadth factors. After weighted calculation and coupling processing, the mechanical expected deviation detection coefficient is finally obtained.

[0084] Embodiment 2 is based on the same inventive concept as the in-line production detection method of a connector in the above embodiment. Figure 2 As shown, the present application provides an online production detection device for connectors, and the device and method embodiments in the present application are based on the same inventive concept. The device includes: The detection task receiving module 10 is used to receive an online production detection task, wherein the online production detection task includes a target connector and a connector production plan corresponding to the target connector.

[0085] The electrical expected deviation detection coefficient acquisition module 20 is used to activate the connector electrical performance factor, perform electrical performance expected deviation detection on the target connector in combination with the connector production plan, and obtain the electrical expected deviation detection coefficient.

[0086] The function expectation deviation detection coefficient acquisition module 30 is used to activate the connector function factor, perform function expectation deviation detection on the target connector in combination with the connector production plan, and obtain the function expectation deviation detection coefficient.

[0087] The mechanical expected deviation detection coefficient acquisition module 40 is used to activate the connector mechanical performance factor, perform mechanical performance expected deviation detection on the target connector in combination with the connector production plan, and obtain the mechanical expected deviation detection coefficient.

[0088] The connector detection cloud map drawing module 50 is used to sort out the electrical expected deviation detection coefficient, the functional expected deviation detection coefficient and the mechanical expected deviation detection coefficient to draw a connector detection cloud map.

[0089] The expected deviation constraint judgment module 60 is used to judge whether the connector detection cloud graph satisfies the connector expected deviation constraint.

[0090] The connector detection warning signal generating module 70 is used to generate a connector detection warning signal if the connector detection cloud map does not satisfy the connector expected deviation constraint.

[0091] Furthermore, the electrical expected deviation detection coefficient acquisition module 20 also includes: The electrical performance factors of the connector include contact resistance, insulation resistance, withstand voltage and withstand current.

[0092] An electrical performance expected result acquisition unit is configured to perform an electrical performance expected confidence prediction on the target connector based on the connector electrical performance factor and the connector production plan to obtain an electrical performance expected result.

[0093] An electrical performance test result acquisition unit is configured to perform an electrical performance confidence test on the target connector based on the connector electrical performance factor to obtain an electrical performance test result.

[0094] The electrical expectation deviation identification result acquisition unit performs deviation identification based on the electrical performance expectation result and the electrical performance detection result to obtain the electrical expectation deviation identification result.

[0095] An electrical expectation deviation detection coefficient generation unit is configured to generate the electrical expectation deviation detection coefficient based on the electrical expectation deviation recognition result and according to three electrical expectation deviation detection channels.

[0096] Furthermore, the electrical performance expected result acquisition unit further includes: A connector retrieval constraint determination unit is used to use the connector production plan as a connector retrieval constraint and the detection parameters of the connector electrical performance factor as a connector retrieval target.

[0097] An electrical performance test sample set acquisition unit is used to retrieve connector electrical performance test records according to the connector retrieval constraint and the connector retrieval target to obtain an electrical performance test sample set.

[0098] An electrical performance test sample cluster acquisition unit is used to classify the electrical performance test sample set according to the connector electrical performance factor to obtain a plurality of electrical performance test sample clusters.

[0099] An electrical performance detection sample cluster extraction unit is used to traverse the multiple electrical performance detection sample clusters and extract a first electrical performance detection sample cluster.

[0100] An electrical performance detection confidence cluster construction unit, wherein the electrical performance detection confidence cluster construction unit is used to perform confidence optimization according to the first electrical performance detection sample cluster to construct a first electrical performance detection confidence cluster that meets the confidence evaluation constraint.

[0101] An electrical performance expected confidence value adding unit is used to perform centralized value calculation according to the first electrical performance detection confidence cluster to obtain a first electrical performance expected confidence value, and add the first electrical performance expected confidence value to the electrical performance expected result.

[0102] Furthermore, the electrical expected deviation detection coefficient generation unit further includes: The three electrical expected deviation detection channels include an electrical expected deviation depth detection channel, an electrical expected deviation breadth detection channel and an electrical deviation detection coupling weighted channel.

[0103] An electrical expected deviation depth detection coefficient acquisition unit is used to input the electrical expected deviation recognition result into the electrical expected deviation depth detection channel to obtain an electrical expected deviation depth detection coefficient.

[0104] An electrical expectation deviation width detection coefficient acquisition unit is configured to obtain an electrical expectation deviation width detection coefficient based on the electrical expectation deviation recognition result and the electrical expectation deviation width detection channel.

[0105] A detection coefficient input unit, wherein the detection coefficient input unit is used to input the electrical expected deviation depth detection coefficient and the electrical expected deviation width detection coefficient into the electrical deviation detection coupling weighted channel to obtain the electrical expected deviation detection coefficient.

[0106] Furthermore, the function expectation deviation detection coefficient acquisition module 30 further includes: The connector functional factors include insertion loss, return loss, transmission efficiency and transmission quality.

[0107] A functional expectation result acquisition unit is configured to perform functional expectation confidence prediction on the target connector based on the connector functional factor and the connector production plan to obtain a functional expectation result.

[0108] A function test result acquisition unit is configured to perform a function confidence test on the target connector based on the connector function factor to obtain a function test result.

[0109] A function expectation deviation identification result acquisition unit is configured to perform deviation identification based on the function expectation result and the function detection result to obtain a function expectation deviation identification result.

[0110] A function expectation deviation detection coefficient generating unit, wherein the function expectation deviation detection coefficient generating unit generates the function expectation deviation detection coefficient based on the function expectation deviation identification result and according to three channels of function expectation deviation detection, wherein the three channels of function expectation deviation detection include a function expectation deviation depth detection channel, a function expectation deviation breadth detection channel and a function deviation detection coupling weighted channel.

[0111] Furthermore, the mechanical expected deviation detection coefficient acquisition module 40 also includes: The connector mechanical performance factors include connector structure size, connector surface quality, plug-in force and mechanical strength.

[0112] A mechanical performance expected result acquisition unit is configured to perform mechanical performance expected confidence prediction on the target connector based on the connector mechanical performance factor and the connector production plan to obtain the mechanical performance expected result.

[0113] A mechanical property test result acquisition unit is configured to perform a mechanical property confidence test on the target connector based on the connector mechanical property factor to obtain a mechanical property test result.

[0114] A mechanical expected deviation identification result acquisition unit is configured to perform deviation identification based on the mechanical performance expected result and the mechanical performance detection result to obtain a mechanical expected deviation identification result.

[0115] A mechanical expected deviation detection coefficient generation unit is used to generate the mechanical expected deviation detection coefficient based on the mechanical expected deviation recognition result and according to three mechanical expected deviation detection channels.

[0116] Furthermore, the mechanical expected deviation detection coefficient generation unit further includes: The three channels for detecting the mechanical expected deviation include a mechanical expected deviation depth detection channel, a mechanical expected deviation breadth detection channel and a mechanical deviation detection coupling weighted channel.

[0117] A mechanical expected deviation depth detection coefficient acquisition unit is used to input the mechanical expected deviation recognition result into the mechanical expected deviation depth detection channel to obtain a mechanical expected deviation depth detection coefficient.

[0118] A mechanical expectation deviation width detection coefficient acquisition unit is configured to obtain a mechanical expectation deviation width detection coefficient based on the mechanical expectation deviation recognition result and the mechanical expectation deviation width detection channel.

[0119] A mechanical expected deviation detection coefficient acquisition unit is used to input the mechanical expected deviation depth detection coefficient and the mechanical expected deviation breadth detection coefficient into the mechanical deviation detection coupling weighted channel to obtain the mechanical expected deviation detection coefficient.

[0120] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0121] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0122] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for online production detection of connectors, characterized in that: The method comprises: Receiving an online production inspection task, wherein the online production inspection task includes a target connector and a connector production plan corresponding to the target connector; Activate the connector electrical performance factor, and perform electrical performance expectation deviation detection on the target connector in combination with the connector production plan to obtain an electrical expectation deviation detection coefficient; Activate the connector function factor, combine the connector production plan, perform function expectation deviation detection on the target connector, and obtain the function expectation deviation detection coefficient; Activate the connector mechanical performance factor, and perform mechanical performance expected deviation detection on the target connector in combination with the connector production plan to obtain a mechanical expected deviation detection coefficient; Arrange the electrical expected deviation detection coefficient, the functional expected deviation detection coefficient and the mechanical expected deviation detection coefficient, and draw a connector detection cloud diagram; Determining whether the connector detection cloud graph satisfies the connector expected deviation constraint; If the connector detection cloud map does not satisfy the connector expected deviation constraint, a connector detection warning signal is generated.

2. The method according to claim 1, characterized in that Activate the connector electrical performance factor, combine the connector production plan, perform electrical performance expectation deviation detection on the target connector, and obtain the electrical expectation deviation detection coefficient, including: The electrical performance factors of the connector include contact resistance, insulation resistance, withstand voltage and withstand current; Based on the connector electrical performance factor and the connector production plan, predict the expected electrical performance of the target connector with confidence to obtain the expected electrical performance result; Based on the connector electrical performance factor, performing electrical performance confidence testing on the target connector to obtain an electrical performance test result; Perform deviation identification based on the electrical performance expected result and the electrical performance detection result to obtain an electrical expected deviation identification result; Based on the electrical expectation deviation identification result, the electrical expectation deviation detection coefficient is generated according to three channels of electrical expectation deviation detection.

3. The method according to claim 2, characterized in that Based on the connector electrical performance factor and the connector production plan, an expected electrical performance confidence prediction is performed on the target connector to obtain an expected electrical performance result, including: The connector production scheme is used as a connector retrieval constraint, and the detection parameter of the connector electrical performance factor is used as a connector retrieval target; Retrieve the connector electrical performance test record according to the connector retrieval constraint and the connector retrieval target to obtain an electrical performance test sample set; Classifying the electrical performance test sample set according to the connector electrical performance factor to obtain a plurality of electrical performance test sample clusters; Traversing the plurality of electrical performance detection sample clusters, and extracting a first electrical performance detection sample cluster; Performing confidence optimization according to the first electrical performance detection sample cluster to construct a first electrical performance detection confidence cluster that satisfies the confidence evaluation constraint; A concentrated value calculation is performed according to the first electrical performance detection confidence cluster to obtain a first electrical performance expected confidence value, and the first electrical performance expected confidence value is added to the electrical performance expected result.

4. The method according to claim 2, characterized in that Based on the electrical expectation deviation identification result, the electrical expectation deviation detection coefficient is generated according to the electrical expectation deviation detection three channels, including: The three electrical expected deviation detection channels include an electrical expected deviation depth detection channel, an electrical expected deviation breadth detection channel and an electrical deviation detection coupling weighted channel; Inputting the electrical expected deviation recognition result into the electrical expected deviation depth detection channel to obtain an electrical expected deviation depth detection coefficient; Based on the electrical expectation deviation identification result, and according to the electrical expectation deviation breadth detection channel, obtaining an electrical expectation deviation breadth detection coefficient; The electrical expected deviation depth detection coefficient and the electrical expected deviation width detection coefficient are input into the electrical deviation detection coupling weighted channel to obtain the electrical expected deviation detection coefficient.

5. The method according to claim 1, characterized in that Activate the connector function factor, combine the connector production plan, perform function expectation deviation detection on the target connector, and obtain the function expectation deviation detection coefficient, including: The connector functional factors include insertion loss, return loss, transmission efficiency and transmission quality; Based on the connector functional factor and the connector production plan, a functional expectation confidence prediction is performed on the target connector to obtain a functional expectation result; Based on the connector function factor, performing a function confidence test on the target connector to obtain a function test result; Perform deviation identification based on the functional expectation result and the functional detection result to obtain a functional expectation deviation identification result; Based on the functional expectation deviation identification result, the functional expectation deviation detection coefficient is generated according to the three channels of functional expectation deviation detection, wherein the three channels of functional expectation deviation detection include a functional expectation deviation depth detection channel, a functional expectation deviation breadth detection channel and a functional deviation detection coupling weighted channel.

6. The method according to claim 1, characterized in that Activate the connector mechanical performance factor, combine the connector production plan, perform mechanical performance expected deviation detection on the target connector, and obtain the mechanical expected deviation detection coefficient, including: The connector mechanical performance factors include connector structure size, connector surface quality, plug-in force and mechanical strength; Based on the connector mechanical performance factor and the connector production plan, predict the expected mechanical performance confidence of the target connector to obtain the expected mechanical performance result; Based on the connector mechanical property factor, performing a mechanical property confidence test on the target connector to obtain a mechanical property test result; Perform deviation identification based on the expected mechanical performance result and the mechanical performance test result to obtain a mechanical expected deviation identification result; Based on the mechanical expected deviation identification result, the mechanical expected deviation detection coefficient is generated according to the three channels of mechanical expected deviation detection.

7. The method according to claim 6, characterized in that Based on the mechanical expected deviation identification result, the mechanical expected deviation detection coefficient is generated according to the three channels of mechanical expected deviation detection, including: The three channels for mechanical expected deviation detection include a mechanical expected deviation depth detection channel, a mechanical expected deviation breadth detection channel and a mechanical deviation detection coupling weighted channel; Inputting the mechanical expected deviation recognition result into the mechanical expected deviation depth detection channel to obtain a mechanical expected deviation depth detection coefficient; Based on the mechanical expectation deviation identification result, and according to the mechanical expectation deviation breadth detection channel, a mechanical expectation deviation breadth detection coefficient is obtained; The mechanical expected deviation depth detection coefficient and the mechanical expected deviation breadth detection coefficient are input into the mechanical deviation detection coupling weighted channel to obtain the mechanical expected deviation detection coefficient.

8. An online production detection device for connectors, characterized in that: The device comprises: A detection task receiving module, the detection task receiving module is used to receive an online production detection task, wherein the online production detection task includes a target connector and a connector production plan corresponding to the target connector; An electrical expected deviation detection coefficient acquisition module, the electrical expected deviation detection coefficient acquisition module is used to activate the connector electrical performance factor, and in combination with the connector production plan, perform electrical performance expected deviation detection on the target connector to obtain the electrical expected deviation detection coefficient; A function expectation deviation detection coefficient acquisition module, wherein the function expectation deviation detection coefficient acquisition module is used to activate the connector function factor, perform function expectation deviation detection on the target connector in combination with the connector production plan, and obtain the function expectation deviation detection coefficient; A mechanical expected deviation detection coefficient acquisition module, wherein the mechanical expected deviation detection coefficient acquisition module is used to activate the connector mechanical performance factor, perform mechanical performance expected deviation detection on the target connector in combination with the connector production plan, and obtain the mechanical expected deviation detection coefficient; A connector detection cloud map drawing module, the connector detection cloud map drawing module is used to sort out the electrical expected deviation detection coefficient, the functional expected deviation detection coefficient and the mechanical expected deviation detection coefficient, and draw a connector detection cloud map; An expected deviation constraint judgment module, the expected deviation constraint judgment module is used to judge whether the connector detection cloud graph satisfies the connector expected deviation constraint; A connector detection warning signal generation module is used to generate a connector detection warning signal if the connector detection cloud map does not meet the connector expected deviation constraint.

Images