Working data acquisition method and system of connector production machine

Abstract

The invention relates to the technical field of data processing, in particular to a working data acquisition method and system of a connector production machine. The method comprises the following steps: acquiring pre-insertion pressure and riveting pressure of a produced connector, and determining a volatility value of a target connector; determining an inconsistency value corresponding to the target connector, and determining a target pruning threshold by using the volatility value and the inconsistency value of the target connector; performing pruning processing on data points in a pre-constructed data point set by using the target pruning threshold; and obtaining prompt data by using the pruned data points and the data points corresponding to the target connector. According to the technical scheme, the obtained prompt data can conveniently and accurately monitor the production process of the connector.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly relates to a method and system for collecting working data of a connector production machine. Background Art

[0002] A connector is an electronic component that can achieve electrical connection between electronic devices, so as to realize signal transmission between electronic devices. Connectors can be applied to electronic devices such as mobile phones, computers, TVs, and network devices; connectors can also play a role in mechanically fixing the connection parts of electronic devices to prevent loosening or detachment between two electronic devices.

[0003] Pre-insertion and riveting are two important steps in the production process of connectors; pre-insertion refers to inserting the pins into the pre-set holes of the housing or substrate according to the design requirements during the production process of connectors. After pre-insertion, the positions of the pins are relatively stable, which helps the matching of the embossed teeth and the housing hole wall during the riveting process, thus avoiding riveting failure caused by position deviation.

[0004] Riveting is a process of applying pressure through mechanical equipment to cause plastic deformation of the embossed teeth of the pins and the housing hole wall, so as to achieve mechanical locking and electrical connection between the pins and the housing. During the pre-insertion and riveting processes of connectors, due to possible abnormalities in the riveting process, the connectors may not achieve the expected electrical connection performance or mechanical connection performance.

[0005] Or, due to improper pre-insertion, the electrical connection performance or mechanical connection performance of the connector after riveting may be poor. Therefore, it is necessary to collect the working data of the connector production machine to monitor the production process of the connector. Summary of the Invention

[0006] In order to collect the working data of the connector production machine to monitor the production process of the connector, this application provides a method and system for collecting working data of a connector production machine.

[0007] According to the first aspect of the embodiments of the present application, a method for collecting working data of a connector production machine is provided, including: obtaining the pre-insertion pressure and riveting pressure of the produced connectors, and determining the volatility value of the target connector; the volatility value is used to characterize the difference degree between the target connector and other connectors produced within the neighborhood time period in terms of pre-insertion pressure and riveting pressure; determining the inconsistency value between the difference of the target connector from other connectors in the neighborhood time period in terms of pre-insertion pressure and the difference of the target connector from other connectors in the neighborhood time period in terms of riveting pressure, and adjusting a preset pruning threshold by using the volatility value and the inconsistency value of the target connector to obtain a target pruning threshold; pruning the data points in a pre-constructed data point set by using the target pruning threshold; the data point set is constructed by using the pre-insertion pressure and riveting pressure within the neighborhood time period; obtaining prompt data by using the pruned data points and the data points corresponding to the target connector; the prompt data is used to prompt whether there is an abnormality when the connector production machine produces the target connector.

[0008] In this way, the obtained prompt data can better reflect whether there is an abnormality in the internal components of the connector production machine, avoid false prompts caused by changes in the external power input of the connector production machine, so as to more accurately achieve the pair.

[0009] Optionally, the volatility value of the target connector is determined by the following method: , where Q is the volatility value of the target connector, and n is the number of other connectors produced within the neighborhood time period; is the difference degree value between the target connector and the j-th other connector produced within the neighborhood time period in terms of pre-insertion pressure and riveting pressure; the difference degree value is determined according to the sum of the squares of the difference value in terms of pre-insertion pressure and the difference value in terms of riveting pressure.

[0010] In this way, the volatility value of the target connector can consider the fluctuation of the target connector relative to other connectors in terms of pre-insertion pressure, and can also consider the fluctuation of the target connector relative to other connectors in terms of riveting pressure.

[0011] Optionally, the inconsistency value is determined by the following method: , where P is the inconsistency value, norm is the normalization processing function, n is the number of other connectors produced within the neighborhood time period, is the pre-insertion pressure of the target connector, is the pre-insertion pressure of the j-th other connector produced within the neighborhood time period, is the riveting pressure of the target connector, is the riveting pressure of the j-th other connector produced within the neighborhood time period, and a is a preset positive number.

[0012] In this way, by corresponding to the differences between the two change directions of the pre-insertion pressure and the riveting pressure respectively, it is possible to avoid the influence of the change in the external power input of the connector production machine on the determination process of whether there are abnormalities in the internal components of the connector production machine.

[0013] Optionally, the target pruning threshold is determined in the following manner: , where T is the target pruning threshold corresponding to the target connector, M is the preset pruning threshold, exp is the exponential function with the natural constant as the base, Q is the volatility value of the target connector, is the volatility value of the previous connector of the target connector produced by the connector production machine, and P is the inconsistency value.

[0014] In this way, it is possible to adaptively determine a matching target pruning threshold for the target connector, taking into account reducing the redundancy of data points in the data point set and ensuring the reference value of the data points after pruning.

[0015] Optionally, the data point set is constructed in the following manner: taking the pre-insertion pressure of the connectors produced within the neighborhood time period as the abscissa and the riveting pressure of the connectors as the ordinate, obtaining the data points corresponding to the connectors in the plane rectangular coordinate system, so as to obtain a plurality of data points corresponding to the plurality of connectors produced within the neighborhood time period; and forming the obtained plurality of data points into a data point set.

[0016] Optionally, pruning the data points in the pre-constructed data point set by using the target pruning threshold includes: dividing the data space where the data point set is located into grids, obtaining a plurality of grids of the same size after division, and determining the distance information entropy of the candidate data points in the data space; the distance information entropy is used to characterize the complexity of the distances from the candidate data points to other data points in the grid to which they belong; and pruning the candidate data points in the data space whose distance information entropy is less than or equal to the target pruning threshold.

[0017] Optionally, the method further includes: when the distance information entropy of the candidate data points is less than or equal to the target pruning threshold, discarding the distances from the candidate data points to other data points in the grid to which they belong from the storage space of the data storage device; the data storage device is used to store the data generated during the pruning process.

[0018] In this way, it is possible to release the data storage occupancy space of the data storage device and reduce the pressure on the data storage device for data storage.

[0019] Optionally, the prompt data is determined as follows: taking the data point corresponding to the target connector as the target data point, and using the local outlier factor algorithm to determine the local reachability density of the target data point; the local reachability density is equal to the reciprocal of the average distance from the target data point to the nearest multiple data points among the pruned data points; determining the local outlier factor according to the local reachability density of the target data point; the local outlier factor is used to characterize the degree of difference in local reachability density from the nearest multiple pruned data points; determining the corresponding prompt data from multiple preset prompt messages according to the local outlier factor.

[0020] Optionally, determining the corresponding prompt data from multiple preset prompt messages according to the local outlier factor includes: when the local outlier factor is greater than or equal to a preset outlier threshold, taking the first preset prompt message as the prompt data; the first preset prompt message is used to prompt that there is an abnormality when the connector production machine produces the target connector; when the local outlier factor is less than the preset outlier threshold, taking the second preset prompt message as the prompt data; the second preset prompt message is used to prompt that there is no abnormality when the connector production machine produces the target connector.

[0021] According to a second aspect of the embodiments of the present application, there is provided a working data acquisition system for a connector production machine, including: a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the steps of the working data acquisition method for the connector production machine provided in the first aspect of the present application are implemented.

[0022] The technical solutions provided by the embodiments of the present application may include the following beneficial effects: during the production process of the connector, adjusting the preset pruning threshold by using the volatility value and the inconsistency value of the target connector to obtain the target pruning threshold can adaptively perform pruning processing on the data points in the pre-constructed data point set, and avoid redundancy of the data points included in the data point set while ensuring the accuracy of the pruned data points; obtaining prompt data by using the pruned data points and the data points corresponding to the target connector, and the prompt data can facilitate the monitoring of the production process of the connector.

[0023] At the same time, since the inconsistency value of the difference in pre-insertion pressure of the target connector relative to other connectors in the neighboring time period and the difference in riveting pressure of the target connector relative to other connectors in the neighboring time period is considered, the obtained prompt data can prompt abnormalities in the internal components of the connector production machine and avoid false prompts that may be caused by changes in the external power input of the connector production machine.

[0024] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit the present application. Description of the Drawings

[0025] Figure 1 is a flowchart of a method for collecting working data of a connector production machine shown according to an exemplary embodiment; Figure 2 is a schematic structural diagram of a system for collecting working data of a connector production machine shown according to an exemplary embodiment. Detailed implementation manners

[0026] First, a simple introduction to the application scenario of the embodiments of the present application is given. In the application scenario of the present application, during the production process of connectors, pre-insertion and riveting are two related and relatively critical links. It may be due to improper pre-insertion that the electrical connection performance or mechanical connection performance of the connector after riveting is not good. Therefore, it is necessary to collect the working data of the connector production machine to monitor the production process of the connector production machine.

[0027] To solve the above technical problems, the embodiments of the present application provide a method and system for collecting working data of a connector production machine, which can be applied to a connector production machine or other devices for monitoring the working state of a connector production machine. Figure 1 is a flowchart of a method for collecting working data of a connector production machine shown according to an exemplary embodiment, as Figure 1 shown, the method includes the following steps.

[0028] In step S101, obtain the pre-insertion pressure and riveting pressure of the produced connector, and determine the volatility value of the target connector.

[0029] The connector production machine may be provided with a pre-insertion mechanism and a riveting mechanism. The pre-insertion mechanism can perform pre-insertion processing on the pins of the connector to be produced, and the riveting mechanism can perform riveting processing on the connector after pre-insertion processing.

[0030] The pre-insertion pressure of the connector in the pre-insertion processing stage may refer to the pressure applied to the produced connector during the pre-insertion process; the riveting pressure of the connector in the riveting processing stage may refer to the pressure applied to the produced connector during the riveting process.

[0031] By setting a mechanical sensor on the pre-insertion mechanism, the pre-insertion pressure of the produced connector can be obtained periodically; by setting a mechanical sensor on the riveting mechanism, the riveting pressure of the produced connector can be obtained periodically.

[0032] The target connector and other connectors produced within a neighboring time period are connectors of the same model and specification produced by the same connector production machine at different times; during the pre-insertion process and riveting process of the connector production machine, in order to ensure the consistency of the produced connectors, the produced connectors can be pre-inserted with a relatively stable pre-insertion pressure and riveted with a relatively stable riveting pressure.

[0033] When the production process of the connector production machine is normal, the pre-insertion process and riveting process of the connectors produced by the connector production machine are relatively stable. Therefore, the pre-insertion pressure and riveting pressure of the connectors produced by the same connector production machine at different times have high consistency.

[0034] During the pre-insertion process and riveting process of the connector production machine, it may be affected by external disturbances or have its own wear, resulting in abnormalities at one or more moments of the connector production machine, such that the pre-insertion pressure or riveting pressure applied by the connector production machine to a certain connector is abnormal, causing one or more connectors produced by the connector production machine to be abnormal, affecting the quality of the obtained connectors.

[0035] When the connector production machine is abnormal at a certain moment, since at least one of the pre-insertion pressure and riveting pressure applied by the connector production machine at the abnormal moment is abnormal, the consistency of the pre-insertion pressure or riveting pressure applied by the same connector production machine to connectors of the same model is reduced.

[0036] The target connector can be a connector produced by the connector production machine within the historical time period of the current moment to achieve a review of the connectors produced within the historical time period; or, the target connector can be a connector produced by the connector production machine at the current moment to achieve real-time monitoring of the connector production machine.

[0037] The volatility value is used to characterize the degree of difference in pre-insertion pressure and riveting pressure between the target connector and other connectors produced within the neighboring time period; the larger the volatility value of the target connector, the greater the degree of difference in pre-insertion pressure and riveting pressure between the target connector and other connectors produced by the connector production machine within the neighboring time period.

[0038] Since the connector production machine can complete the pre-insertion operation and riveting operation of multiple connectors within the same second, the neighboring time period can, for example, refer to the time period with the moment when the target connector undergoes the pre-insertion operation as the end moment and a duration equal to the preset time period.

[0039] The preset duration can be set according to actual requirements. For example, the preset duration can refer to the duration required for a same connector production machine to produce a preset number of connectors. The preset number can be between 30 and 40, which is convenient for comparing the pre-insertion pressure and riveting pressure of multiple connectors successively produced by the same connector production machine, so as to monitor the production status of the connector production machine.

[0040] In one embodiment, the volatility value of the target connector is determined in the following manner: , where Q is the volatility value of the target connector, and n is the number of other connectors produced within the neighborhood time period; is the difference degree value between the target connector and the jth other connector produced within the neighborhood time period in terms of pre-insertion pressure and riveting pressure. The difference degree value is determined based on the sum of the squares of the difference value in pre-insertion pressure and the difference value in riveting pressure.

[0041] The difference value between the target connector and the jth other connector produced within the neighborhood time period in terms of pre-insertion pressure can be equal to the absolute value of the difference between the pre-insertion pressure of the target connector and the pre-insertion pressure of the jth other connector produced within the neighborhood time period.

[0042] The difference value between the target connector and the jth other connector produced within the neighborhood time period in terms of riveting pressure can be equal to the absolute value of the difference between the riveting pressure of the target connector and the riveting pressure of the jth other connector produced within the neighborhood time period.

[0043] In this way, through the volatility degree value of the target connector, the differences between the target connector produced by the connector production machine and other connectors within the neighborhood time period in terms of pre-insertion pressure and riveting pressure can be comprehensively considered, thereby reflecting to a certain extent the possible abnormalities of the connector production machine.

[0044] In step S102, determine the inconsistency value between the difference in pre-insertion pressure of the target connector relative to other connectors within the neighborhood time period and the difference in riveting pressure of the target connector relative to other connectors within the neighborhood time period, and adjust the preset pruning threshold by using the volatility value and the inconsistency value of the target connector to obtain the target pruning threshold.

[0045] When there is a certain difference between the pre-insertion pressure of the target connector produced by the connector production machine and the pre-insertion pressures of other connectors produced by the connector production machine during the adjacent time period; or, when there is a certain difference between the riveting pressure of the target connector produced by the connector production machine and the riveting pressures of other connectors produced by the connector production machine during the adjacent time period; this difference between the target connector and other connectors produced during the adjacent time period may be caused by the aging or wear of the connector production machine, or may be caused by the fluctuations in the external power input of the connector production machine.

[0046] When there are fluctuations in the external power input of the connector production machine, for example, an accidental increase in the overall input current of the connector production machine causes the output power during pre-insertion and the output power during riveting of the connector production machine to increase simultaneously. Therefore, when the pre-insertion pressure and the riveting pressure of the target connector increase simultaneously compared to other connectors during the adjacent time period, the difference between the connector production machine when producing the target connector and other connectors is more likely to be caused by an abnormal increase in the external power input of the connector production machine, and the probability of abnormal internal components of the connector production machine is lower.

[0047] Or, an accidental decrease in the overall input voltage of the connector production machine causes the output power during pre-insertion and the output power during riveting of the connector production machine to decrease simultaneously; therefore, when the pre-insertion pressure and the riveting pressure of the target connector decrease simultaneously compared to other connectors during the adjacent time period, the difference between the connector production machine when producing the target connector and other connectors is more likely to be caused by an abnormal decrease in the external power input of the connector production machine, and the probability of abnormal internal components of the connector production machine is lower.

[0048] For another example, since the direction of the influence of the change in the external power input of the connector production machine on the pre-insertion pressure and the riveting pressure is the same, when the pre-insertion pressure of the target connector decreases compared to other connectors during the adjacent time period, while the riveting pressure of the target connector increases compared to other connectors during the adjacent time period, it indicates that the difference between the target connector and other connectors is more likely to be caused by abnormalities in the internal components of the connector production machine.

[0049] Since the direction of the influence of the change in the external power input of the connector production machine on the pre-insertion pressure and the riveting pressure is the same, the inconsistency value determined by the embodiments of the present application can at least characterize the degree of inconsistency between the change direction of the pre-insertion pressure when the connector production machine produces the target connector and the change direction of the riveting pressure when the connector production machine produces the target connector, thereby characterizing the probability of abnormalities in the internal components of the connector production machine through the inconsistency value.

[0050] In one embodiment, the inconsistency value is determined as follows: , where P is the inconsistency value, norm is the normalization function, n is the number of other connectors produced within the neighborhood time period, is the pre-insertion pressure of the target connector, is the pre-insertion pressure of the j-th other connector produced within the neighborhood time period, is the riveting pressure of the target connector, is the riveting pressure of the j-th other connector produced within the neighborhood time period, and a is a preset positive number.

[0051] In the calculation formula of the inconsistency value, can reflect the change direction of the pre-insertion pressure of the target connector relative to the j-th other connector within the neighborhood time period; since the units of the numerator and the denominator are the same, it can eliminate the influence of the dimension of the pre-insertion pressure on the subsequent comparison result.

[0052] In the calculation formula of the inconsistency value, can reflect the change direction of the riveting pressure of the target connector relative to the j-th other connector within the neighborhood time period; since the units of the numerator and the denominator are the same, it can eliminate the influence of the dimension of the riveting pressure on the subsequent comparison result.

[0053] Since can reflect the change direction of the pre-insertion pressure of the target connector relative to the j-th other connector within the neighborhood time period, can reflect the change direction of the riveting pressure of the target connector relative to the j-th other connector within the neighborhood time period, by using and the absolute value of the difference between them, it can reflect the change direction of the pre-insertion pressure of the target connector relative to the j-th other connector within the neighborhood time period, and the degree of inconsistency between the two change directions of the riveting pressure of the target connector relative to the j-th other connector within the neighborhood time period.

[0054] The existence of the preset positive number can ensure that the summation result is at least greater than 0, and the preset positive number can be set according to actual needs; for example, the preset positive number can be relatively small values such as 0.01 and 0.02 relative to 1.

[0055] In the case where there is a change in the external power input of the connector production machine, the influence degrees of the change in the external power input on the pre-insertion process and the riveting process of the connector production machine may be the same; for example, when the voltage of the external power input of the connector production machine rises and the power of the connector production machine during operation rises by 5%, the pre-insertion pressure and the riveting pressure during the production of the connector by the connector production machine may both rise by 5%.

[0056] Using and the absolute value of the difference, in addition to reflecting the inconsistency between the change direction of the pre-insertion pressure of the target connector relative to other connectors within the neighboring time period and the change direction of the riveting pressure of the target connector relative to other connectors within the neighboring time period, can also reflect the inconsistency between the change amplitude of the pre-insertion pressure of the target connector relative to other connectors within the neighboring time period and the change amplitude of the riveting pressure of the target connector relative to other connectors within the neighboring time period, so as to more accurately determine whether the abnormality existing in the connector production machine is caused by the abnormality of the internal components of the connector production machine, and avoid misjudgment caused by the change of the external power input of the connector production machine.

[0057] In this way, by determining the change direction of the pre-insertion pressure between the target connector and other connectors within the neighboring time period, and determining the change direction of the riveting pressure between the target connector and other connectors within the neighboring time period, through the difference between the two change directions corresponding to the pre-insertion pressure and the riveting pressure respectively, the probability of the existence of abnormalities in the internal components of the connector production machine when producing the target connector can be reflected.

[0058] In one embodiment, the target pruning threshold is determined in the following manner: , where T is the target pruning threshold corresponding to the target connector, M is the preset pruning threshold, exp is the exponential function with the natural constant as the base, Q is the volatility value of the target connector, is the volatility value of the connector preceding the target connector produced by the connector production machine, and P is the inconsistency value.

[0059] The target pruning threshold in the embodiments of the present application is used to perform pruning processing on the data points in the pre-constructed data point set; the data point set is constructed using the pre-insertion pressure and the riveting pressure within the neighboring time period; the smaller the target pruning threshold, the pruning processing of a smaller number of redundant data points in the data point set can be achieved; on the contrary, the larger the target pruning threshold, the pruning processing of a larger number of redundant data points in the data point set can be achieved.

[0060] In the calculation formula of the target pruning threshold, is the adjustment term for the preset pruning threshold; after being processed by the exponential function with the natural constant as the base, the value of the reciprocal of the exponential function is between 0 and 1, so that the value of the adjustment term for the preset pruning threshold is between 0.5 and 1.5, which can make the obtained target pruning threshold within the range of 0.5 times the preset pruning threshold to 1.5 times the preset pruning threshold, and the obtained pruning threshold is more flexible.

[0061] The larger the inconsistency value corresponding to the target connector, the greater the probability that the abnormality existing in the connector production machine belongs to the abnormality of the internal components of the connector production machine in the case of an abnormality in the connector production machine; on the contrary, the smaller the inconsistency value corresponding to the target connector, the smaller the probability that there is an abnormality in the internal components of the connector production machine.

[0062] In the determination formula of the target pruning threshold, the inconsistency value is normalized, and the value of the inconsistency value P ranges from 0 to 1. Therefore, the larger the value of the inconsistency value P, the closer the value of P is to 1; on the contrary, the smaller the value of the inconsistency value P, the closer the value of P is to 0.

[0063] In the case where the volatility value of the target connector is greater than or equal to the volatility value of the previous connector produced by the connector production machine, it indicates that the volatility of the target connector in the pre-insertion pressure and the riveting pressure has increased. has a value greater than or equal to 1.

[0064] On the contrary, in the case where the volatility value of the target connector is less than the volatility value of the previous connector produced by the connector production machine, it indicates that the volatility of the target connector in the pre-insertion pressure and the riveting pressure has decreased. has a value less than 1.

[0065] When the volatility of the target connector increases or remains unchanged, is greater than or equal to 1. Since the inconsistency value is a positive number less than or equal to 1, it makes have a value greater than or equal to 1; on the contrary, when the volatility of the target connector decreases, is less than 1. Since the inconsistency value is a positive number less than or equal to 1, it makes have a value less than 1.

[0066] For example, when is 1.2 and P is 0.8, is equal to 1.157; when is 0.8 and P is 0.1, is equal to 0.9779.

[0067] It can be seen that when the base term for the exponential operation is a positive number less than 1 and the exponential term is a positive number less than 1; although the smaller the value of P, the larger the exponential operation result, the obtained exponential operation result is always less than 1. Therefore, the obtained when the volatility of the target connector increases or remains unchanged is always greater than the obtained when the volatility of the target connector decreases, making the target pruning threshold obtained when the volatility of the target connector increases or remains unchanged always less than the target pruning threshold obtained when the volatility of the target connector decreases.

[0068] In an embodiment of the present application, when the volatility of the target connector increases or remains unchanged, and the greater the inconsistency value, it indicates that there is a higher probability of an abnormality in the connector production machine when producing the target connector, and this abnormality is more likely to be caused by an abnormality in the internal components of the connector, so as to obtain a smaller target pruning threshold in order to retain a larger number of data points and better determine.

[0069] When the volatility of the target connector decreases, it can at least be determined that there is a lower probability of an abnormality in the connector production machine when producing the target connector, so as to obtain a larger target pruning threshold, so as to reduce the redundancy of the data points in the data point set while ensuring the reference value of the data point set after pruning.

[0070] In this way, according to the change direction of the target connector and the previous connector in the fluctuation value, and the inconsistency value corresponding to the target connector, a matching target pruning threshold can be adaptively determined for the target connector, so as to adaptively prune the redundant data points in the data point set.

[0071] In step S103, the data points in the pre-constructed data point set are pruned using the target pruning threshold.

[0072] The data point set is constructed using the pre-insertion pressure and riveting pressure within the neighborhood time period; different data points in the data point set respectively correspond to different connectors produced by the connector production machine within the neighborhood time period, and the same data point includes the pre-insertion pressure and riveting pressure received by the corresponding connector during production.

[0073] The performance of the connector production machine within the neighborhood time period can provide a relatively valuable reference for the performance of the connector production machine when producing the target connector. However, there may be some redundant data points in the data point set, which makes the data calculation volume large when comparing the data points corresponding to the target connector with the data points in the data point set later. Therefore, the data points in the pre-constructed data point set can be pruned using the target pruning threshold, thereby reducing data redundancy.

[0074] In one embodiment, the data point set is constructed in the following manner: taking the pre-insertion pressure of the connectors produced within the neighborhood time period as the abscissa and the riveting pressure of the connectors as the abscissa, obtaining the data points corresponding to the connectors in the plane rectangular coordinate system to obtain multiple data points corresponding to the multiple connectors produced within the neighborhood time period; and forming the obtained multiple data points into a data point set.

[0075] Taking the pre-insertion pressure of the connectors produced within the neighborhood time period as the abscissa and the riveting pressure of the connectors as the abscissa, it is possible to achieve a visual display of the pre-insertion pressure and the riveting pressure of the connector production machine within the neighborhood time period, thereby facilitating the comparison of the pre-insertion pressure and the riveting pressure of the connector production machine at different times.

[0076] Forming a data point set from the obtained multiple data points can facilitate determining whether there are abnormalities when the connector production machine produces the target connector.

[0077] In one embodiment, pruning the data points in the pre-constructed data point set by using a target pruning threshold includes: dividing the data space where the data point set is located into grids, obtaining multiple grids of the same size after division, and determining the distance information entropy of the candidate data points in the data space; the distance information entropy is used to characterize the complexity of the distances from the candidate data points to other data points in the grid to which they belong; pruning the candidate data points in the data space whose distance information entropy is less than or equal to the target pruning threshold.

[0078] For example, for the plane rectangular coordinate system where the data points in the data point set are located, it is possible to determine the upper bound of the abscissa, the lower bound of the abscissa, the upper bound of the ordinate, and the lower bound of the ordinate where the data points are distributed in the plane rectangular coordinate system, and determine the target area enclosed by the upper bound of the abscissa, the lower bound of the abscissa, the upper bound of the ordinate, and the lower bound of the ordinate.

[0079] For the target area determined in the plane rectangular coordinate system, the target area can be divided into grids to obtain multiple grids of the same size, and the multiple grids obtained together form the target area; dividing the target area into grids can narrow the range of data processing, so as to improve the efficiency of pruning the data points in the data point set.

[0080] For example, dividing the data space into multiple grids can facilitate determining the redundant data points existing in the same grid, so as to remove the redundant data points existing in the same grid and retain the non-redundant data points in the same grid.

[0081] The candidate data point can be any data point distributed in the data space, and the data space in the embodiments of the present application can refer to the smallest rectangular area including all data points in the plane rectangular coordinate system.

[0082] Determining the distance information entropy of the candidate data points in the data space, the distance information entropy is used to characterize the complexity of the distances from the candidate data points to other data points in the grid to which they belong; the greater the distance information entropy of the candidate data point, the lower the redundancy degree of the candidate data point in the data space; on the contrary, the smaller the distance information entropy of the candidate data point, the higher the redundancy degree of the candidate data point in the data space.

[0083] The determination process of the distance information entropy of candidate data points in the data space can be implemented by referring to the determination process of the information entropy of data. The information entropy is used to measure the uncertainty or amount of information of a random variable, and the information entropy can be determined according to the proportion of the frequency of occurrence of the variable in the set.

[0084] The determination process of the information entropy belongs to the common knowledge of those skilled in the art, and the embodiments of the present application will not elaborate on the determination process of the information entropy here.

[0085] When the distance information entropy of the candidate data point is less than or equal to the target pruning threshold, it indicates that there are at least multiple other data points with similar or identical features to the candidate data point distributed in the same grid. After removing the candidate data point, multiple other data points with similar features to the candidate data point can still be retained in the same grid, and the data points retained in the same grid are already able to determine whether the data points corresponding to the target connector are abnormal.

[0086] When the distance information entropy of the candidate data point is less than or equal to the target pruning threshold, since there are still other data points with similar or identical features to the candidate pixel point in the candidate data point, therefore, pruning the candidate data point can reduce the redundancy of the data points while ensuring the reference value of the pruned data set, thereby reducing the computational amount required for the subsequent determination process of abnormal data points, improving the computational efficiency, and reducing the consumption of the running memory.

[0087] Since the target pruning threshold is determined at least according to the inconsistency value of the corresponding target connector, therefore, using the target pruning threshold to prune the data points in the pre-constructed data point set can make the pruning process of the data point set adapt to the performance of the connector production machine.

[0088] In this way, pruning the candidate data points in the data space whose distance information entropy is less than or equal to the target pruning threshold can take into account both improving the accuracy and reducing the data redundancy.

[0089] In one embodiment, it is also possible to discard the distances from the candidate data point to other data points in the grid to which it belongs when the distance information entropy of the candidate data point is less than or equal to the target pruning threshold; the data storage device is used to store the data generated during the pruning process.

[0090] The data storage device may refer to the memory of the connector production machine, or may also refer to the memory of other devices used to monitor the working state of the connector production machine; the data storage device can realize the storage of the data generated during the pruning process.

[0091] When the distance information entropy of a candidate data point is less than or equal to the target pruning threshold, it indicates that the candidate data point will be pruned from the data point set. Since the data point set after pruning will no longer include candidate data points with a distance information entropy less than or equal to the target pruning threshold, the distances from the candidate data point to other data points in its belonging grid will not be called again in the subsequent calculation process. Therefore, the distances stored for the candidate data point to other data points in its belonging grid can be discarded, reducing the occupancy of the data storage space of the data storage device.

[0092] In step S104, hint data is obtained by using the pruned data points and the data points corresponding to the target connector.

[0093] After pruning the data points in the data point set, the obtained pruned data points at least retain the reference value of the original data point set and contain fewer redundant data points; by comparing the pruned data points with the data points corresponding to the target connector, hint data for prompting whether there is an abnormality in the connector production machine can be determined.

[0094] The hint data is used to prompt whether there is an abnormality in the connector production machine when producing the target connector. The hint data can be one or more of various types of hint data. For example, the hint data can be used to make the connector production machine output at least one of audio hint information, vibration hint information, and light hint information.

[0095] In one embodiment, the hint data is determined in the following manner: taking the data points corresponding to the target connector as target data points, and using the local outlier factor algorithm to determine the local reachability density of the target data points; the local reachability density is equal to the reciprocal of the average distance from the target data point to the nearest multiple data points among the pruned data points; determining the local outlier factor according to the local reachability density of the target data points; the local outlier factor is used to characterize the degree of difference in local reachability density from the nearest multiple pruned data points; determining the corresponding hint data from multiple preset hint information according to the local outlier factor.

[0096] In the local outlier factor algorithm, the degree of outlier of a data point is measured by comparing the local density of a data point with that of its neighbor data points. For example, if the local density of a data point is significantly lower than the density of its neighbor data points, the data point can be regarded as an outlier with an abnormality.

[0097] In the process of determining the local reachability density or local outlier factor of the target data points, the number of neighbor data points used can be set according to actual needs. For example, the 6 to 8 data points among the pruned data points that are closest to the target data point are used as the neighbor data points of the target data point to obtain the local reachability density or local outlier factor of the target data point.

[0098] The local reachability density corresponding to the target data point determined according to the target data point and the data points obtained after pruning can be determined with reference to the determination process of the local reachability density of data points in the LOF (Local Outlier Factor) algorithm in the prior art, and the embodiments of the present application will not elaborate herein.

[0099] The local outlier factor corresponding to the target data point determined according to the target data point and the data points obtained after pruning can be determined with reference to the determination process of the local outlier factor of data points in the LOF algorithm in the prior art, and the embodiments of the present application will not elaborate herein.

[0100] After pruning the data points in the data point set corresponding to the neighborhood time period, the number of data points obtained after pruning is smaller, which can reduce the number of local reachability densities or local outlier factors that need to be determined; and since the data points with higher reference value are retained after the pruning process, therefore, it can ensure or improve the monitoring accuracy of the production process of the connector production machine.

[0101] Since the local outlier factor is used to characterize the degree of difference in local reachability density between the target data point and the nearest multiple data points obtained after pruning, the degree of difference in local reachability density of the target data point can more accurately reflect the probability of abnormality when the connector production machine produces the target connector.

[0102] In this way, determining the corresponding prompt data from multiple preset prompt messages according to the local outlier factor can make the obtained prompt data more accurate, so as to achieve more accurate monitoring of the connector production machine.

[0103] The obtained prompt data can be used to enable the monitoring device to monitor the production process of the connector production machine; the monitoring device can be integrated into the connector production machine or can be other devices provided outside the connector production machine.

[0104] For example, the connector production machine can send the prompt data to the monitoring device so that the user of the monitoring device can monitor the working process of the connector production machine.

[0105] In one embodiment, determining the corresponding prompt data from multiple preset prompt messages according to the local outlier factor includes: when the local outlier factor is greater than or equal to the preset outlier threshold, using the first preset prompt message as the prompt data; the first preset prompt message is used to prompt that there is an abnormality when the connector production machine produces the target connector; when the local outlier factor is less than the preset outlier threshold, using the second preset prompt message as the prompt data; the second preset prompt message is used to prompt that there is no abnormality when the connector production machine produces the target connector.

[0106] The preset outlier threshold can be set according to actual requirements; for example, in the local outlier factor algorithm, the preset outlier threshold can usually be equal to 1, or it can be determined according to the value range of the local outlier factor.

[0107] Since the local outlier factor can better characterize the probability of anomalies in the internal components of the connector production machine and avoid the influence of possible anomalies in the external power input of the connector production machine on the local outlier factor, when the local outlier factor is greater than or equal to the preset outlier threshold, it indicates that there is a high probability that the internal components of the connector production machine actually have anomalies when the connector production machine produces the target connector. The first preset prompt message can be used as prompt data so that the user can perform operations such as maintenance or replacement on the connector production machine to ensure the reliability of the connector production machine.

[0108] When the local outlier factor is less than the preset outlier threshold, it can at least indicate that there is a high probability that the internal components of the connector production machine do not have anomalies when the connector production machine produces the target connector. The second preset prompt message can be used as prompt data.

[0109] In this way, the corresponding prompt data can be determined according to the magnitude relationship between the obtained local outlier factor and the preset outlier threshold.

[0110] Figure 2 It is a schematic structural diagram of a working data acquisition system 1000 of a connector production machine shown according to an exemplary embodiment. Refer to Figure 2 , the working data acquisition system 1000 of the connector production machine includes: a processor 1100 and a memory 1200. The memory 1200 stores computer program instructions, and when the computer program instructions are executed by the processor 1100, all or part of the steps of the working data acquisition method of the connector production machine in this application are implemented.

[0111] Those skilled in the art will readily think of other implementation schemes of this application after considering the specification and practicing the invention disclosed herein. This application aims to cover any variations, uses, or adaptive changes of this application, and these variations, uses, or adaptive changes follow the general principles of this application and include common general knowledge or conventional technical means in the technical field not disclosed in this application. The specification and embodiments are only regarded as exemplary.

[0112] It should be understood that this application is not limited to the exact structure already described and shown in the drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for collecting working data of a connector production machine, characterized in that, include: Obtaining the pre-insertion pressure and the riveting pressure of the produced connector, and determining the volatility value of the target connector; The volatility value is used to characterize the degree of difference in pre-insertion pressure and riveting pressure between the target connector and other connectors produced in the adjacent time period; Determine the difference in pre-insertion pressure of the target connector relative to other connectors in the neighborhood time period, and the inconsistency value of the difference in riveting pressure of the target connector relative to other connectors in the neighborhood time period, and use the volatility value and inconsistency value of the target connector to adjust the preset pruning threshold to obtain the target pruning threshold; Pruning the data points in the pre-constructed data point set using the target pruning threshold; The data point set is constructed using the pre-insertion pressure and the riveting pressure in the neighborhood time period; Prompt data is obtained using the pruned data points and the data points corresponding to the target connector; the prompt data is used to prompt the connector production machine whether there is an abnormality when producing the target connector.

2. The method for collecting working data of a connector production machine according to claim 1, characterized in that, The volatility value of the target connector is determined as follows: , where Q is the volatility value of the target connector, and n is the number of other connectors produced within the neighborhood time period; is the difference degree value between the target connector and the j-th other connector produced within the neighborhood time period in terms of pre-insertion pressure and riveting pressure; the difference degree value is determined based on the sum of the squares of the difference value in pre-insertion pressure and the difference value in riveting pressure.

3. The method for collecting working data of a connector production machine according to claim 1, characterized in that, The inconsistency value is determined in the following manner: , where P is the inconsistency value, norm is the normalization function, n is the number of other connectors produced within the neighborhood time period, is the pre-insertion pressure of the target connector, is the pre-insertion pressure of the j-th other connector produced within the neighborhood time period, is the riveting pressure of the target connector, is the riveting pressure of the j-th other connector produced within the neighborhood time period, and a is a preset positive number.

4. The method for collecting working data of a connector production machine according to claim 1, characterized in that, The target pruning threshold is determined in the following way: , where T is the target pruning threshold corresponding to the target connector, M is the preset pruning threshold, exp is the exponential function with the natural constant as the base, Q is the volatility value of the target connector, is the volatility value of the previous connector of the target connector produced by the connector production machine, and P is the inconsistency value.

5. The method for collecting working data of a connector production machine according to claim 1, characterized in that, The data point set is constructed in the following way: Taking the pre-insertion pressure of the connector produced in the neighboring time period as the horizontal coordinate and the riveting pressure of the connector as the horizontal coordinate, the data points corresponding to the connector in the plane rectangular coordinate system are obtained to obtain multiple data points corresponding to multiple connectors produced in the neighboring time period; The obtained multiple data points are combined into a data point set.

6. The method for collecting working data of a connector production machine according to claim 1, characterized in that, The target pruning threshold is used to prune the data points in the pre-constructed data point set, including: Gridding the data space where the data point set is located to obtain multiple grids of the same size after division, and determining the distance information entropy of the candidate data points in the data space; the distance information entropy is used to characterize the complexity of the distance from the candidate data point to other data points in the grid to which it belongs; Prune candidate data points whose distance information entropy in the data space is less than or equal to the target pruning threshold.

7. The method for collecting working data of a connector production machine according to claim 6, characterized in that, The method further comprises: When the distance information entropy of the candidate data point is less than or equal to the target pruning threshold, the distance from the candidate data point to other data points in the grid to which it belongs is discarded from the storage space of the data storage device; the data storage device is used to store the data generated during the pruning process.

8. The method for collecting working data of a connector production machine according to claim 1, characterized in that, The prompt data is determined in the following manner: The data point corresponding to the target connector is taken as the target data point, and the local reachability density of the target data point is determined by using the local outlier factor algorithm; the local reachability density is equal to the inverse of the average distance from the target data point to the nearest multiple data points among the pruned data points; The local outlier factor is determined according to the local reachable density of the target data point; the local outlier factor is used to characterize the degree of difference in local reachable density from the nearest multiple pruned data points; Corresponding prompt data is determined from a variety of preset prompt information according to the local outlier factor.

9. The method for collecting working data of a connector production machine according to claim 8, characterized in that, According to the local outlier factor, corresponding prompt data is determined from a variety of preset prompt information, including: When the local outlier factor is greater than or equal to a preset outlier threshold, the first preset prompt message is used as the prompt data; the first preset prompt message is used to prompt that there is an abnormality when the connector production machine produces the target connector. When the local outlier factor is less than the preset outlier threshold, the second preset prompt message is used as the prompt data; the second preset prompt message is used to prompt that there is no abnormality when the connector production machine produces the target connector.

10. A working data acquisition system for a connector production machine, characterized in that, Comprising: A processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the working data acquisition method of the connector production machine according to any one of claims 1-9 is implemented.

Images