WO2024066784A1

WO2024066784A1 - Method and apparatus for monitoring stability of test device, and electronic device and storage medium

Info

Publication number: WO2024066784A1
Application number: PCT/CN2023/113394
Authority: WO
Inventors: 夏雪; 韩冰; 张加民; 崔巍; 卜有照; 黄灏
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-09-27
Filing date: 2023-08-16
Publication date: 2024-04-04
Also published as: CN117827568A

Abstract

A method and apparatus for monitoring the stability of a test device, and an electronic device and a storage medium, which are applied to the technical field of production quality control. The method comprises: acquiring target test data, which is respectively sent by at least two test devices (201); determining a feature value of each test device according to the target test data, wherein the feature value is used for indicating the dispersion of the target test data (202); determining an outlier factor of each feature value, wherein the outlier factor is used for indicating a density relationship between the feature value and other feature values (203); and determining that a test device corresponding to a target outlier factor is an abnormal test device, wherein the target outlier factor is an outlier factor that does not meet a preset condition (204).

Description

Monitoring method, device, electronic device and storage medium for testing device stability

CROSS-REFERENCE TO RELATED APPLICATIONS

The present disclosure is based on Chinese patent application 202211181015.3, filed on September 27, 2022, entitled “Monitoring method, device, electronic device and storage medium for testing equipment stability”, and claims the priority of the patent application, and all the contents disclosed therein are incorporated into the present disclosure by reference.

Technical Field

The embodiments of the present disclosure relate to the technical field of production quality control, and in particular to a monitoring method, device, electronic device and storage medium for testing the stability of equipment.

Background technique

In order to improve the qualified rate of products leaving the factory, there is usually a testing link in the production and processing process of products. With the development of intelligence and the introduction of a large number of production automation equipment, the focus of quality has shifted from personnel execution to equipment stability, which means that quality requirements have been upgraded. Whether the stability of test equipment can be identified and evaluated in time is crucial.

Summary of the invention

The embodiments of the present disclosure provide a monitoring method, apparatus, electronic device and storage medium for testing equipment stability, so as to solve the problem that in general technology, the stability of testing equipment is determined by using MSA, and experimental determination can only be performed on a single testing equipment one by one, resulting in a complex experimental scheme and a long cycle.

In a first aspect, an embodiment of the present disclosure provides a method for monitoring stability of a test device, comprising:

Obtain target test data respectively sent by at least two test devices;

Determine a characteristic value of each of the test devices according to the target test data, wherein the characteristic value is used to indicate the discreteness of the target test data;

Determine an outlier factor for each eigenvalue, where the outlier factor is used to indicate a close or sparse relationship between the eigenvalue and other eigenvalues;

The test device corresponding to the target outlier factor is determined to be an abnormal test device, and the target outlier factor is the outlier factor that does not meet a preset condition.

In a second aspect, an embodiment of the present disclosure provides a monitoring device for testing the stability of a device, comprising:

An acquisition module, configured to acquire target test data respectively sent by at least two test devices;

A first determination module, configured to determine a characteristic value of each of the test devices according to the target test data, wherein the characteristic value is used to indicate a discreteness of the target test data;

A second determination module is configured to determine an outlier factor of each of the eigenvalues, wherein the outlier factor is used to indicate a sparse or dense relationship between the eigenvalue and other eigenvalues;

The third determination module is used to determine that the test device corresponding to the outlier factor that does not meet the preset condition is an abnormal test device.

In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

The memory is configured to store a computer program;

The processor is configured to execute the program stored in the memory to implement the method for monitoring the stability of the testing equipment described in the first aspect.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for monitoring the stability of the test equipment described in the first aspect is implemented.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the general technology, The drawings required for use in the embodiments or general technical descriptions will be briefly introduced. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

FIG1 is an application scenario diagram of a method for monitoring stability of a test device provided by an embodiment of the present disclosure;

FIG2 is a flow chart of a method for monitoring the stability of a test device provided in an embodiment of the present disclosure;

FIG3 is a two-dimensional scatter plot of characteristic values in a method for monitoring stability of a test device provided in an embodiment of the present disclosure;

FIG4 is a schematic diagram showing a test device display of a method for monitoring the stability of a test device provided by an embodiment of the present disclosure;

FIG5 is a structural diagram of a monitoring device for testing equipment stability provided by an embodiment of the present disclosure;

FIG. 6 is a structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed ways

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

The inventors of the present disclosure have found that the test equipment for different models of products are different but have the same characteristics: they are all machined assemblies. During use, the various parts have different degrees of wear and tear over time, which manifests as the instability of the test equipment. The TS16949 quality management system standard uses the classic quality tool - measurement system analysis (MSA) to determine the stability of test equipment. It uses statistical analysis to conduct statistical variation analysis and research on the various influencing factors that constitute the measurement system to obtain a conclusion on whether the measurement system is accurate and reliable. This is a quality tool. MSA is an important task in quality improvement. Before determining the stability of equipment, a series of preparations need to be made, including preparing experimental samples, formulating experimental plans, and implementing experimental plans. After obtaining experimental data, input them into Minitab software to obtain the stability determination results. MSA can be used to determine the stability of test equipment. Through experimental verification and the performance of product quality-related data, the results show that the poor quality of test equipment (a certain degree of loss) will cause misjudgment of product testing, resulting in unnecessary waste of manpower and production capacity.

However, MSA usually involves testing individual test equipment one by one, with complex experimental schemes and long cycles. It is usually conducted every six months or a year, and cannot provide continuous and effective monitoring of the test equipment. There are hundreds of test equipment involved in the actual industrial production process, and it is time-consuming and labor-intensive to use MSA to determine each one, and the application value is relatively small.

Based on the above technical problems, the present disclosure provides a monitoring method, device, electronic device and storage medium for testing equipment stability, so as to solve the problem that in general technology, the stability of testing equipment is determined by MSA, and experimental determination can only be performed on a single testing equipment one by one, resulting in complex experimental schemes and long cycles.

According to an embodiment of the present disclosure, a monitoring method for the stability of a test device is provided. In an embodiment of the present disclosure, the monitoring method for the stability of the test device can be applied to a hardware environment composed of a terminal 101 and a server 102 as shown in Figure 1. As shown in Figure 1, the server 102 is connected to the terminal 101 via a network, and can be configured to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server, and is configured to provide data storage services for the server 102. The above network includes but is not limited to: a wide area network, a metropolitan area network or a local area network, and the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, etc.

The monitoring method for the stability of the test equipment of the embodiment of the present disclosure may be executed by the server 102, or by the terminal 101, or by both the server 102 and the terminal 101. The terminal 101 may execute the monitoring method for the stability of the test equipment of the embodiment of the present disclosure, or the client installed thereon.

Taking the terminal executing the monitoring method of the stability of the test device according to the embodiment of the present disclosure as an example, FIG. 2 is a flow chart of an optional monitoring method of the stability of the test device according to the embodiment of the present disclosure. As shown in FIG2 , the process of the method may include the following steps:

Step 201: Obtain target test data respectively sent by at least two test devices.

In some embodiments, each test device may test more than one abnormal item, and may obtain more than one test result for each abnormal item. The test device is usually configured to determine that the tested product is qualified after meeting the preset test conditions. The abnormal item may be generated during the production or testing process of the product.

Based on this, after each test, the test equipment first selects the test data with qualified test results from the obtained test data, and selects the target test data from the qualified test data, which can reduce the computational complexity of the test equipment monitoring process and improve the monitoring efficiency of the test equipment.

The target test data may be the test data corresponding to the test item that is most associated with the abnormality of the test device. Therefore, the target test data may be obtained by screening the test data.

In one embodiment, the acquiring target test data respectively sent by at least two test devices includes:

Acquire initial test data of at least one test item sent by each of the test devices; and filter out a target test item corresponding to the target test data from the initial test data, wherein the target test item is a test item that is most highly correlated with an abnormality of the test device among at least one of the test items.

In some embodiments, by testing the test equipment with determined target test data, it is not necessary to calculate the test data corresponding to each test item, which can reduce the amount of calculation in the monitoring process of the test equipment and improve the monitoring efficiency of the test equipment.

In an optional embodiment, there are multiple ways to determine the target test items, for example, the following ways can be used:

Acquire experimental data, wherein the experimental data is obtained after conducting an experiment on the test equipment having at least one abnormal item, and the experimental data includes the at least one test item; calculate the correlation between the abnormal item and the at least one test item based on the experimental data; and determine that the test item with the largest correlation is the target test item.

In view of the structural design of the test equipment, the components that are prone to loss or abnormality in the structure are sorted out to form points to be identified (i.e. abnormal items). At the same time, the test data is collected, the test items are sorted out and sorted according to the proportion. Whether there is some connection between the points to be identified and the test items needs to be identified by establishing the correlation between the two. The identification method adopts the correlation analysis method of the spearman test.

For example, taking a key 5G product as an example, the abnormal points of its test equipment (i.e. abnormal items) are sorted out, and a total of five types of abnormal points to be identified are sorted out, including poor contact of the RF ejector pin, dirty connector RF head, loose connector, cover plate not pressed in place, and large line loss. There are many test items for the product, among which the difference between the rated power and the transmission power, the ACPR value, and the channel attenuation value are prone to failure in daily work, but whether there is a strong correlation with the abnormality of the test equipment and the degree of correlation need to be identified. The Spearman test can be effectively identified, and the specific operations are as follows:

Step 1: Collect data and obtain the test value of each test item based on the abnormal point of the test equipment. 1 represents the occurrence of this abnormality, and 0 represents the absence of this abnormality. Record the test result values corresponding to the three test items under each abnormal combination, as shown in Table 1 below.

Table 1:

Step 2: Write the code for the core calculation formula of the spearman test. x is the independent variable, representing the abnormal points of the test equipment, and y is the dependent variable, representing the three affected test items. x and y are used as the input of the model for calculation to obtain the correlation coefficient and probability value between the two.

The calculation formula is:

Correlation coefficient

Among them, i represents the i-th test data in each set of test data, x represents the abnormal point data, and y represents the test item data.

Based on the above method, the correlation result table between the test equipment abnormality and the three test items is calculated. Table 2 is the spearman correlation coefficient table. The larger the value, the higher the correlation between the abnormal point and the test item. It can be seen from the table that the test item of rated power and transmission power difference is correlated with each abnormal point and the correlation is high.

Table 2:

Furthermore, the probability value of the correlation between the outlier and the test item can be calculated based on the chi-square distribution.

Table 3 is the probability value result table, also known as the P value. P<0.05 indicates a strong correlation between the two. The larger the P value, the lower the correlation between the outlier and the test item, which corresponds to the spearman correlation coefficient.

table 3:

Therefore, through the above two result tables 2 and 3, it can be concluded that the difference between the rated power and the transmitted power is most susceptible to the workstation environment, and its test value can be used for subsequent analysis. The above method can be used to select appropriate data to be analyzed for each type/model of product.

Step 202: Determine a characteristic value of each of the test devices according to the target test data, wherein the characteristic value is used to indicate a discreteness of the target test data.

In some embodiments, each of the target test data includes at least two test data, and determining the characteristic value of each of the test devices according to the target test data includes:

A test mean and a test standard deviation are calculated based on the at least two test data; and the test mean and the test standard deviation are determined as the characteristic values.

In order to make the data features more significant during subsequent anomaly detection, in this embodiment, a feature engineering construction method is used to obtain better data features from the target test data to improve the detection effect. Since the test equipment determines whether the product is qualified through the test data, the identification of abnormal test equipment can also be converted into abnormal fluctuations in the test data of the test item, and the manifestation of abnormal fluctuations is represented by the feature vector of the target test data.

In order to better describe the characteristic distribution of a set of data, the origin moment and central moment indicators commonly used in statistics can be used to characterize it, which are also called mean and standard deviation in mathematics. Therefore, the origin moment and central moment of a set of test data of the test equipment can be used to characterize the level of the test equipment. This set of characteristic values is used as the input of outlier detection, thereby converting the identification of test equipment anomalies into anomaly identification of multiple sets of characteristic values.

Step 203: determine an outlier factor for each eigenvalue, where the outlier factor is used to indicate a close or sparse relationship between the eigenvalue and other eigenvalues.

Among them, for each product and each test process, the corresponding test items are selected according to the above method, and the test values corresponding to the test items fluctuate within the range of passing the test. From the above analysis, it can be seen that a set of production test data tested by the test equipment can represent the test to a certain extent. Equipment level, and the quality level of a set of data can be reflected by the mean and standard deviation from a statistical perspective. Therefore, based on the test equipment dimension, the mean and standard deviation of a set of data tested by each test equipment are calculated. For the same type of products that pass the test, the data fluctuation is within the set range and conforms to the same normal distribution.

Based on the above embodiment, if one or a few groups of data (i.e., target test data of at least two test devices) fluctuating within a set range have a large degree of deviation, which is manifested as a deviation of the mean and the standard deviation, it can be considered that the fluctuation of the test data is caused by the abnormality of the test device. The test data of all test devices are calculated and analyzed simultaneously, and one or several deviations are manifested as abnormal points in the group, so an abnormal point detection algorithm can be used for identification.

In this embodiment, a local outlier factor (LOF) detection algorithm is used to detect abnormal test equipment. According to the above-mentioned related embodiments, the target test data is screened, and the mean and standard deviation are calculated according to the test equipment to form a two-dimensional scatter plot, see Figure 3. In Figure 3, a point represents the mean and standard deviation obtained by a test equipment testing a group of target test data.

Assume that p is the point to be determined, define d(p,o) as the distance between p and o, and set C as all points to be determined (i.e., the points where the eigenvalues of all target test data are located). Define k-distance as the kth distance, d _k (p) = d(p,o), and satisfy:

There are at least k points o' in the set C that do not include p, satisfying d(p,o ^, )≤d(p,o);

In the set C, there are at most k-1 points o', not including p, satisfying d(p,o ^, )＜d(p,o);

Then the kth distance of p is the distance of the point that is kth farthest from p. Set all points within (including) the kth distance of p as the kth distance domain N _k (p) of point p. The kth reachable distance from point o to point p is defined as:
reach-distance _k (p,o)＝max{k-distance(o),d(p,o)}

The kth reachable distance from point o to point p is at least the kth distance of o or the true distance between o and p. The reachable distances from o to the k points closest to o are considered equal and are all equal to d _k (o). The calculation formula for the sum of the distances from the points in the kth region of point p to p is:

The local reachability density of a point p is expressed as the inverse of the average reachability distance of point p:

Similarly, the local reachability density of point o in the domain of point p is lrd _k (o), and the sum of the ratios of the local reachability density of all points in the domain to the local reachability density of point p is:

The local outlier factor of point p is expressed as the average of the ratio of the local reachability density in the area of point p to the local reachability density of point p:

According to the above formula, the outlier factor value of each point is calculated. The outlier feature of p can be determined by the relationship between the outlier factor value and the value 1. If the ratio is closer to 1, it means that the density of p and its domain points is similar, and p may belong to the same cluster as the domain; if the ratio is less than 1, it means that the density of p is higher than the density of its domain points, and p is a dense point; if the ratio is greater than 1, it means that the density of p is less than the density of its domain points, and p is more likely to be an outlier.

Step 204: Determine that the test device corresponding to the target outlier factor is an abnormal test device, and the target outlier factor is the outlier factor that does not meet a preset condition.

In some embodiments, after the outlier factor is calculated, the target outlier factor that does not meet the preset condition can be determined, so that the test device corresponding to the target outlier factor is determined to be an abnormal test device, thereby achieving monitoring of the test device.

In an optional embodiment, determining the target outlier factor includes:

Screening a first outlier factor that is greater than a preset threshold value among the outlier factors;

Determine the first outlier factor as the target outlier factor; or determine the first outlier factor whose confidence level is higher than a second preset threshold as the target outlier factor.

In some embodiments, after the outlier factor is calculated, a preset threshold may be set so that an outlier factor greater than a first preset threshold is regarded as an abnormal outlier factor.

In order to improve the accuracy and precision of determining the target outlier factor, the confidence level is increased based on optimizing the parameter adjustment of the outlier threshold.

LOF is used to detect outliers. The distribution of most data is regarded as the current capability. Data that is different from the current capability is more likely to be caused by abnormal conditions, and the cause needs further analysis. When the data is outliers, the confidence level reaches 99.73% before it is judged as outliers, further optimizing the outlier judgment results.

Preferably, the 3sigma principle can be used to deal with outlier factors. 3sigma is also called the standard deviation method. In statistics, the standard deviation itself can reflect the degree of dispersion of the factor, which is based on the mean value Xmean of the factor. The 3sigma principle means that there is a 99.73% probability that the value falls in the group. Any error exceeding this interval is not a random error but a gross error, and therefore is an outlier.

Exemplarily, the confidence level is set to 99.73%, and the results of tracking the abnormality are used to investigate and analyze the test equipment corresponding to the abnormal point. It is found that the RF cable of the corresponding channel of the test equipment is loose, which causes poor contact of the cable. The transmission power value read by the instrument is small, and the index value is smaller than normal. In addition to causing the test data to shift, the loose phenomenon will increase the retest rate of the test equipment if it is not discovered in time, resulting in an increase in test hours and labor costs. After the test equipment was rectified, the test data of the test equipment was observed, and the overall data returned to normal.

In an optional embodiment, after determining that the test device corresponding to the outlier factor that does not meet the preset condition is an abnormal test device, the method further includes:

Acquire device information of the abnormal test device; and display the distribution of the characteristic value and the device information.

In some embodiments, after abnormal test equipment is detected, in order to facilitate relevant personnel to be informed in time, the equipment information of the abnormal test equipment is displayed, so that relevant personnel can understand the equipment information of the abnormal test equipment more intuitively and then take corresponding measures to perform maintenance.

The backend can obtain production test data through the API interface, filter the product bill code, channel and frequency one by one according to the product characteristics, obtain the required data, and input abnormal Calculations are performed in the point detection model, and the Python interface is implemented according to the data content that needs to be displayed on the front-end interface.

The front-end interface is implemented with IOT drag-and-drop components, which has the characteristics of simple operation, fast development, and clear interface display. First, the multi-product selection function must be implemented to complete the configuration of the interface input parameters. After selecting the corresponding product and test item parameter configuration, the results calculated by the algorithm are displayed in the form of a scatter plot. The horizontal and vertical axes are the mean and standard deviation of a set of test data calculated by the test equipment after screening and filtering. The calculation results of the abnormal points are reflected by the third feature, as shown in Figure 4. The black solid points in the figure are normal data points determined by the algorithm, and the black hollow points are abnormal test equipment obtained by the judgment. In addition to the scatter plot that intuitively displays the degree of outlier of the abnormal point, the abnormal station information contained in the abnormal point must also be displayed for subsequent investigation and analysis.

Each test device will perform multiple tests on each product, and each item has a test value and a set range. After the test is completed, a judgment will be made on whether the product has passed the test. If the product is judged to have passed the test, its test value is within the set range. For products that fail the test, their test values will exceed the range and have a large deviation. There are many reasons for the failure, including abnormal performance of the product itself, unstable test environment, etc., which will be analyzed and determined by the maintenance personnel. The test values of products that pass the test are within the set range. Therefore, for products of the same type/model, even if they are tested on different devices, according to statistical principles, their test values conform to the same normal distribution for a sufficient sample size.

Based on the above conditions, the present disclosure analyzes the relationship between the loss of the test equipment and the fluctuation of the test value of the tested products, and based on the requirement of sufficient sample size (optional, the number is greater than 30), selects a group of test data of products that have passed the test of each test equipment, and calculates the mean and standard deviation of each group of data, respectively, to characterize the level of the test equipment. The statistical calculation value (mean and standard deviation) of each group of data forms a two-dimensional data point, and multiple groups of data form multiple data points. The degree of outlier of each data point is calculated based on the local outlier factor detection (LOF) algorithm, and the outlier is determined according to the set threshold, that is, the test equipment that causes fluctuations in the group or groups of test data is found, and the algorithm is improved in combination with actual applications to achieve simultaneous monitoring of multiple test equipment, which is used to identify equipment loss in advance, make corrections in time, and avoid equipment loss. The continuous deterioration of power consumption causes the failure of product batch testing, thereby reducing the impact of online production quality and testing capacity.

The disclosed monitoring method for the stability of test equipment analyzes the correlation between production test data and test equipment, and uses a local outlier factor detection algorithm in combination with the characteristics of production test data to identify abnormalities in test equipment, thereby continuously and effectively monitoring all test equipment, thus solving the current shortcomings of only using the measurement system to analyze and determine test equipment. At the same time, in order to address the accuracy issues in the algorithm application process, threshold adjustment and limiting conditions based on the 3sigma abnormality judgment principle are adopted to make its application more accurate and complete. This method provides a series of principle methods from test equipment analysis, test data calculation and processing to optimization, making test equipment monitoring a new management model, promoting the maintenance and upgrade of test equipment, and further optimizing the guarantee mechanism.

Based on the same concept, a monitoring device for testing the stability of equipment is provided in an embodiment of the present disclosure. The implementation of the device can refer to the description of the method embodiment part, and the repeated parts will not be repeated. As shown in FIG5, the device mainly includes:

An acquisition module 501 is configured to acquire target test data respectively sent by at least two test devices;

A first determination module 502 is configured to determine a characteristic value of each of the test devices according to the target test data, wherein the characteristic value is used to indicate a discreteness of the target test data;

A second determination module 503 is configured to determine an outlier factor for each of the eigenvalues, where the outlier factor is used to indicate a sparse or dense relationship between the eigenvalue and other eigenvalues;

The third determination module 504 is configured to determine that the test device corresponding to the outlier factor that does not meet the preset condition is an abnormal test device.

Based on the same concept, an electronic device is also provided in an embodiment of the present disclosure, as shown in FIG6 , the electronic device mainly includes: a processor 601, a memory 602 and a communication bus 603, wherein the processor 601 and the memory 602 communicate with each other through the communication bus 603. The memory 602 stores a program executable by the processor 601, and the processor 601 executes the program stored in the memory 602 to implement the following steps:

Obtain target test data respectively sent by at least two test devices;

Determine the characteristic value of each of the test devices according to the target test data, the characteristic The value is used to indicate the discreteness of the target test data;

The communication bus 603 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 603 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in FIG6 , but it does not mean that there is only one bus or one type of bus.

The memory 602 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk storage. The memory may also be at least one storage device located away from the processor 601.

The above-mentioned processor 601 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., and can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

Compared with the general technology, the above technical solution provided by the embodiment of the present disclosure has the following advantages: the method provided by the embodiment of the present disclosure obtains target test data respectively sent by at least two test devices; determines the characteristic value of each test device according to the target test data, and the characteristic value is used to indicate the discreteness of the target test data; determines the outlier factor of each characteristic value, and the outlier factor is used to indicate the sparseness relationship between the characteristic value and other characteristic values; determines the test device corresponding to the target outlier factor as an abnormal test device; The target outlier factor is the outlier factor that does not meet the preset conditions. In this way, when it is necessary to determine the stability of the test equipment, it can be determined based on the test data of multiple test equipment, which improves the accuracy of the stability determination of the test equipment. The outlier factor calculated by the characteristic value of the acquired target test data determines the density relationship between the test data of each test equipment and other test data, thereby determining the abnormal test equipment, realizing real-time monitoring of the test equipment, improving the monitoring efficiency of the test equipment, and thus reducing the defective rate of the equipment shipped out of the factory.

In another embodiment of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program runs on a computer, the computer executes the method for monitoring the stability of the test equipment described in the above embodiment.

In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instruction is loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instruction is transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape, etc.), an optical medium (e.g., a DVD) or a semiconductor medium (e.g., a solid-state hard disk), etc.

It should be noted that in this article, relational terms such as "first" and "second" It is used only to distinguish one entity or operation from another entity or operation, and does not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

A monitoring method for testing the stability of equipment, comprising:

Obtain target test data respectively sent by at least two test devices;

Determine a characteristic value of each of the test devices according to the target test data, wherein the characteristic value is used to indicate the discreteness of the target test data;

Determine an outlier factor for each eigenvalue, where the outlier factor is used to indicate a close or sparse relationship between the eigenvalue and other eigenvalues;

The test device corresponding to the target outlier factor is determined to be an abnormal test device, and the target outlier factor is the outlier factor that does not meet a preset condition.
The method according to claim 1, wherein the obtaining target test data respectively sent by at least two test devices comprises:

Acquire initial test data of at least one test item sent by each of the test devices;

A target test item corresponding to the target test data is screened out from the initial test data, and the target test item is a test item that is most highly correlated with the abnormality of the test device among at least one of the test items.
The method according to claim 2, wherein the process of determining the test item most associated with the abnormality of the test device comprises:

Acquiring experimental data, wherein the experimental data is obtained after conducting an experiment based on the test device having at least one abnormal item, and the experimental data includes the at least one test item;

Calculating the correlation between the abnormal item and the at least one test item based on the experimental data;

The test item with the greatest correlation is determined as the target test item.
The method according to claim 1, wherein each of the target test data includes at least two test data, and determining the characteristic value of each of the test devices according to the target test data comprises:

Calculate a test mean and a test standard deviation based on the at least two test data;

The test mean and the test standard deviation are determined as the characteristic values.
The method according to claim 1, wherein determining the outlier factor of each of the eigenvalues comprises:

Calculate the reachable distance between each of the eigenvalues and a neighborhood eigenvalue, wherein the neighborhood eigenvalue is a eigenvalue within a preset neighborhood of the eigenvalue;

Calculate a first local reachable density of the eigenvalue based on the reachable distance;

Calculate the second local reachable density of each of the neighborhood eigenvalues;

The outlier factor is calculated based on the first local reachable density and the second local reachable density.
The method according to claim 1, wherein determining the target outlier factor comprises:

Screening a first outlier factor that is greater than a preset threshold value among the outlier factors;

Determine the first outlier factor as the target outlier factor; or determine the first outlier factor whose confidence level is higher than a second preset threshold as the target outlier factor.
The method according to claim 1, wherein after determining that the test device corresponding to the outlier factor that does not meet the preset condition is an abnormal test device, it also includes:

Acquire device information of the abnormal test device;

The distribution of the characteristic values and the device information are displayed.
A monitoring device for testing the stability of equipment, comprising:

An acquisition module, configured to acquire target test data respectively sent by at least two test devices;

A first determination module, configured to determine a characteristic value of each of the test devices according to the target test data, wherein the characteristic value is used to indicate a discreteness of the target test data;

A second determination module is configured to determine an outlier factor of each of the eigenvalues, wherein the outlier factor is used to indicate a sparse or dense relationship between the eigenvalue and other eigenvalues;

The third determination module is configured to determine that the test device corresponding to the outlier factor that does not meet the preset condition is an abnormal test device.
An electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

The memory is configured to store a computer program;

The processor is configured to execute the program stored in the memory to implement the method for monitoring the stability of the testing equipment according to any one of claims 1 to 7.
A computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for monitoring the stability of a test device according to any one of claims 1 to 7 is implemented.