Mould state data acquisition method, system, equipment and medium

Abstract

The invention provides a mold state data acquisition method and system, equipment and a medium, and relates to the technical field of equipment state monitoring, and the method comprises the steps: obtaining first state data of a target mold, and generating a first abnormal coefficient of the target mold according to the first state data; obtaining a correlation coefficient of the target mold and a correlation mold, wherein the correlation mold is a mold having an upstream and downstream relationship with the target mold in the technological process; acquiring second state data of the associated mold, and generating a second abnormal coefficient of the associated mold according to the second state data; the first abnormal index is adjusted in combination with the correlation coefficient and the second abnormal coefficient, and a target abnormal coefficient of the target mold is generated; when the target abnormal coefficient is larger than a preset threshold value, abnormal information of the target mold is generated, and a maintenance suggestion of the target mold is generated according to the abnormal information. The technical effect of the invention is that the accuracy of anomaly detection is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of equipment state monitoring, in particular to a mold state data acquisition method, system, device and medium. BACKGROUND

[0002] In modern manufacturing, as the core process of metal forming, the stability and reliability of the stamping production line directly affect the product quality, production efficiency and equipment safety. In the long-term high-load operation process, stamping dies are affected by material fatigue, wear and tear, stress concentration and other factors, and are prone to abnormal states such as size deviation, surface damage and structural deformation. If these abnormalities cannot be identified and processed in a timely and accurate manner, it will lead to an increase in product scrap rate, frequent equipment failures, and even safety accidents. Therefore, establishing an effective mold state monitoring and abnormal detection system has become a key technical requirement for the intelligent management of stamping production lines.

[0003] In the prior art, mold state monitoring mainly uses a method based on independent analysis of a single mold. By installing displacement sensors, pressure sensors and other monitoring equipment on the mold, the physical state parameters of the mold are collected in real time. Then, based on the preset threshold range or statistical analysis method, the state data of a single mold is detected and evaluated for abnormalities. This method can identify the direct abnormal state of the mold to some extent and provide basic data support for equipment maintenance. However, in actual stamping production lines, each mold does not work independently, but forms a close upstream and downstream relationship through the process. The abnormal state of one mold often affects the working state of other molds through the process. The above-mentioned single mold independent analysis method cannot effectively identify and quantify the associated influence between molds, resulting in insufficient accuracy of abnormal detection. SUMMARY

[0004] The present application provides a mold state data acquisition method, system, device and medium for improving the accuracy of abnormal detection.

[0005] In a first aspect, the application provides a mold state data acquisition method, which comprises: acquiring first state data of a target mold sent by a height sensor installed on a stamping device, generating a first abnormality coefficient of the target mold according to the first state data; acquiring a correlation coefficient of the target mold and a correlation mold, the correlation mold being a mold having an upstream-downstream relationship with the target mold in a process flow; acquiring second state data of the correlation mold, generating a second abnormality coefficient of the correlation mold according to the second state data; adjusting the first abnormality index in combination with the correlation coefficient and the second abnormality coefficient, generating a target abnormality coefficient of the target mold; when the target abnormality coefficient is greater than a preset threshold, generating abnormal information of the target mold, and generating a maintenance suggestion of the target mold according to the abnormal information.

[0006] By adopting the above technical solution, the accuracy of mold abnormality identification and the scientificity of maintenance decision are significantly improved by establishing a multi-mold coordinated state monitoring and abnormality detection mechanism. The system can accurately reflect the basic abnormal state of the target mold itself by generating a first abnormality coefficient from the first state data of the target mold. The influence strength between upstream and downstream molds in the process flow is quantified scientifically by acquiring the correlation coefficient of the target mold and the correlation mold. The first abnormality coefficient is adjusted in combination with the correlation coefficient and the second abnormality coefficient of the correlation mold to generate a target abnormality coefficient, so that the system can comprehensively consider the state of the target mold itself and the influence effect of the correlation mold, accurately evaluate the real abnormality degree of the target mold in a complex production environment, and effectively avoid the abnormality evaluation deviation caused by ignoring the upstream and downstream influences in the traditional single-mold independent analysis method. When the target abnormality coefficient is greater than the preset threshold, the abnormal information and the maintenance suggestion are automatically generated, realizing a complete closed-loop management from abnormality detection to maintenance decision, and improving the accuracy of abnormality detection.

[0007] In a second aspect, the application provides a large-scale three-dimensional scene reconstruction system, which comprises: a first acquisition module, a second acquisition module, a third acquisition module, a combination module and a generation module, wherein, The first acquisition module is configured to acquire first state data of a target die sent by a height sensor installed on a stamping device, and generate a first abnormality coefficient of the target die according to the first state data; the second acquisition module is configured to acquire a correlation coefficient of the target die and a correlation die, the correlation die being a die having an upstream-downstream relationship with the target die in a process flow; the third acquisition module is configured to acquire second state data of the correlation die, and generate a second abnormality coefficient of the correlation die according to the second state data; the combination module is configured to combine the correlation coefficient and the second abnormality coefficient to adjust the first abnormality index, and generate a target abnormality coefficient of the target die; and the generation module is configured to generate abnormality information of the target die when the target abnormality coefficient is greater than a preset threshold, and generate a maintenance suggestion of the target die according to the abnormality information.

[0008] In a third aspect, the present application provides an electronic device, which adopts the technical scheme as follows: comprising a processor, a memory, a user interface and a network interface, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to execute the computer program of any of the die state data acquisition methods.

[0009] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the technical scheme as follows: storing a computer program capable of being loaded by a processor and executing any of the die state data acquisition methods.

[0010] In summary, the present application includes at least one of the following beneficial technical effects: By establishing a multi-die coordinated state monitoring and abnormality detection mechanism, the accuracy of die abnormality identification and the scientificity of maintenance decision are significantly improved. The system can accurately reflect the basic abnormal state of the target die itself by acquiring the first state data of the target die to generate the first abnormality coefficient, scientifically quantify the influence strength between the upstream and downstream dies in the process flow by acquiring the correlation coefficient of the target die and the correlation die, and adjust the first abnormality coefficient by combining the correlation coefficient and the second abnormality coefficient of the correlation die to generate the target abnormality coefficient, so that the system can comprehensively consider the state of the target die itself and the influence effect of the correlation die, accurately evaluate the real abnormality degree of the target die in the complex production environment, and effectively avoid the abnormality evaluation deviation caused by ignoring the upstream and downstream influences in the traditional single-die independent analysis method. When the target abnormality coefficient is greater than the preset threshold, the abnormality information and the maintenance suggestion are automatically generated to realize the complete closed-loop management from abnormality detection to maintenance decision, and the accuracy of abnormality detection is improved. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1is a flowchart of a mold state data acquisition method provided by an embodiment of the present application. Figure 2 is a schematic diagram of a mold state data acquisition and abnormality analysis system provided by an embodiment of the present application. Figure 3 is a structural schematic diagram of a mold state data acquisition system provided by an embodiment of the present application. Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0012] Legend: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0013] In order to enable persons skilled in the art to better understand the technical solutions in the present specification, the technical solutions in the present specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the present specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0014] In the description of the embodiments of the present application, the words "exemplary", "for example", or "for instance" are used to mean serving as an example, instance, or illustration. Any embodiment or design solution described as "exemplary", "for example", or "for instance" in the embodiments of the present application should not be interpreted as being more preferred or having more advantages than other embodiments or design solutions. Rather, the words "exemplary", "for example", or "for instance" are used to present the relevant concept in a specific manner.

[0015] Figure 1 is a flowchart of a mold state data acquisition method provided by an embodiment of the present application. As shown in Figure 1 , the method comprises S101-S105: S101, acquiring first state data of a target mold sent by a height sensor installed on a stamping device, and generating a first abnormality coefficient of the target mold according to the first state data.

[0016] In the stamping production process, the height change of the die is an important indicator reflecting its working state and wear degree. The traditional manual detection method has problems such as low efficiency, poor precision, and inability to monitor in real time, and therefore an automatic state data acquisition and abnormal detection mechanism needs to be established. The present application installs a height sensor at a key position of the stamping equipment to monitor the height change of the target die in the working process in real time. The target die refers to a specific die that is currently being monitored, and is distinguished from other dies on the production line. The height sensor uses a laser displacement sensor or a contact displacement sensor to continuously collect the distance data from the die surface to the sensor reference surface at a frequency of milliseconds, forming first state data containing time stamp, position coordinate and height value.

[0017] After the first state data is preprocessed, the system first extracts the reference state data of the target die from the database. The reference state data refers to the standard height value of the die in the new or standard working state, which is usually obtained by a precision measuring device when the die is first put into use and stored in the system. The system calculates the deviation value between the first state data and the reference state data, which reflects the deviation of the current state of the die from the ideal state. When the deviation value is positive, it indicates that the height of the die increases, which may be caused by material accumulation or deformation. When the deviation value is negative, it indicates that the height of the die decreases, which is usually caused by wear or mechanical deformation.

[0018] Based on the size and distribution characteristics of the deviation value, the system uses a multi-level evaluation mechanism to determine the deviation level. The deviation level is divided into four levels: slight deviation, moderate deviation, severe deviation and extremely severe deviation. Slight deviation corresponds to a deviation value within ±2% of the reference value, moderate deviation corresponds to ±2% to ±5%, severe deviation corresponds to ±5% to ±10%, and extremely severe deviation corresponds to more than ±10%. The system also considers the change trend of the deviation value by calculating the change rate of the deviation value in the continuous time window to identify different patterns of sharp change and slow change. Sharp change often indicates a sudden failure, while slow change reflects gradual wear.

[0019] According to the deviation level and the preset abnormality coefficient calculation rule, the system generates a first abnormality coefficient of the target mold, the first abnormality coefficient being a value between 0 and 1, used to quantify the abnormality degree of the current state of the mold, and the value closer to 1 indicates a higher abnormality degree. The abnormality coefficient calculation rule adopts a segmented linear function combined with a weight coefficient, for a slight deviation, the abnormality coefficient is set to between 0.1 and 0.3, for a moderate deviation, the abnormality coefficient is set to between 0.3 and 0.6, for a serious deviation, the abnormality coefficient is set to between 0.6 and 0.9, and for an extremely serious deviation, the abnormality coefficient is set to between 0.9 and 1.0. At the same time, the system introduces a time weight factor, giving a higher weight to the recent abnormal state, and the weight of the historical abnormal state decays over time, ensuring that the abnormality coefficient can timely reflect the latest state change of the mold.

[0020] On the basis of the above embodiment, as an optional implementation manner, in S101, generating a first abnormality coefficient of the target mold according to the first state data specifically comprises S11-S13: S11, obtaining reference state data of the target mold, the reference state data being a standard height value of the target mold in a normal working state.

[0021] The system first obtains reference state data of the target mold from the database, the reference state data being a standard height value of the target mold in a normal working state, which is usually obtained by a precision measuring device during initial installation and debugging of the mold, or calculated by analyzing stable state data during normal working of the mold. The reference state data not only contains a single value, but also contains an allowed normal fluctuation range, because even in a normal working state, the height of the mold will produce a slight fluctuation due to factors such as temperature change and mechanical vibration. The system stores the reference state data as a data structure containing a standard value, an upper limit value and a lower limit value, providing a complete reference standard for subsequent deviation calculation.

[0022] S12, calculating a deviation value between the first state data and the reference state data, and determining a deviation level according to the deviation value.

[0023] Based on the obtained reference state data, the system calculates a deviation value between the first state data and the reference state data, the deviation value being a core index reflecting the degree of deviation of the current state of the mold from the normal standard. The system adopts a relative deviation calculation method, i.e. the deviation value equals the measured value minus the reference value and then divided by the reference value. This processing method eliminates the influence of size difference of different molds, making the abnormality judgment have better universality. The system also calculates statistical characteristics of the deviation value, including average deviation, standard deviation and deviation change rate, which can more comprehensively reflect the change characteristics of the mold state.

[0024] According to the calculated deviation value, the system determines the corresponding deviation level, which is a qualitative classification of the mold abnormality degree. The system divides the deviation level into four levels: when the deviation value is within ±2%, it is determined as a first-level deviation, indicating a slight deviation from the normal state; when the deviation value is within ±2% to ±5%, it is determined as a second-level deviation, indicating a moderate deviation; when the deviation value is within ±5% to ±10%, it is determined as a third-level deviation, indicating a more serious deviation; and when the deviation value exceeds ±10%, it is determined as a fourth-level deviation, indicating a serious abnormal state. The division standard of the deviation level is determined based on a large amount of production practice data and equipment maintenance experience, which can effectively distinguish different degrees of abnormal state.

[0025] S13, according to the deviation level and the preset abnormality coefficient calculation rule, a first abnormality coefficient of the target mold is generated.

[0026] Based on the determined deviation level and the preset abnormality coefficient calculation rule, the system generates the first abnormality coefficient of the target mold. The abnormality coefficient calculation rule uses a piecewise linear mapping method to convert the deviation level into a value between 0 and 1. For a first-level deviation, the abnormality coefficient is set within 0.1 to 0.3, for a second-level deviation, within 0.3 to 0.6, for a third-level deviation, within 0.6 to 0.9, and for a fourth-level deviation, within 0.9 to 1.0. The system also considers the specific position of the deviation value within each level and determines the exact abnormality coefficient value through linear interpolation, ensuring that the abnormality coefficient can continuously reflect the subtle changes in the abnormality degree.

[0027] S102, obtaining the correlation coefficient of the target mold and the associated mold, the associated mold being a mold having an upstream and downstream relationship with the target mold in the process flow.

[0028] In the stamping production line, each mold does not work independently, but forms a close upstream and downstream relationship through the process flow. The working state change of the upstream mold directly affects the working load and wear degree of the downstream mold, and similarly, the abnormality of the downstream mold may also affect the state of the upstream mold in the opposite direction. Therefore, simply monitoring the state data of the target mold cannot fully reflect its real working condition and potential risks. In order to achieve more accurate abnormality detection and predictive maintenance, the system needs to establish an influence relationship quantification mechanism between the target mold and its associated molds, and describe the strength of the mutual influence through the correlation coefficient.

[0029] The associated mold refers to the mold having an upstream and downstream relationship with the target mold in the process flow, including the directly adjacent preceding mold and subsequent mold, and the mold indirectly connected through multiple process steps. The system first configures the process flow information of the stamping production line, which contains detailed data such as mold number, processing sequence, material transfer path of each station, etc. By analyzing these configuration information, the system can automatically identify all associated molds adjacent or indirectly connected to the target mold in the process flow. In the identification process, the system constructs a process flow map, taking each mold as a node and the material transfer relationship as a directed edge to form a complete process network topology.

[0030] Based on the process network topology, the system determines the process transfer path between each associated mold and the target mold. The process transfer path refers to the sequence of process steps and the material flow path between the associated mold and the target mold. The system uses the shortest path algorithm in graph theory to calculate the process distance parameter between the target mold and each associated mold. The process distance parameter represents the degree of separation between molds in the process flow. The smaller the value, the stronger the correlation between the two molds in the process flow. For directly adjacent molds, the process distance parameter is set to 1, and the distance parameter for molds passing through an intermediate station is 2, and so on. Meanwhile, considering the complexity of material transfer, for cases involving branching, merging, and other complex transfer paths, a path complexity correction factor is introduced.

[0031] In order to quantify the actual influence of the associated mold on the target mold, the system obtains the historical state data change records of the target mold and each associated mold within a preset time period. The preset time period usually selects data within the last 30 days or the last 100 production cycles to ensure sufficient sample size and reflect the current production status. The system uses time series analysis method to calculate the influence correlation coefficient of the state change of each associated mold on the state change of the target mold. This coefficient is obtained through Pearson correlation analysis or Granger causality test, with a value range of -1 to 1. A positive value indicates a positive influence, a negative value indicates a negative influence, and the absolute value size reflects the influence strength.

[0032] The system inputs the process distance parameter and the influence correlation coefficient into the association coefficient calculation function. The association coefficient calculation function uses a weighted average method, with the reciprocal of the process distance parameter as the position weight and the absolute value of the influence correlation coefficient as the influence strength weight. Through normalization processing, the final association coefficient is generated. The association coefficient is used to quantify the comprehensive influence of the associated mold on the target mold. The larger the value, the more significant the influence of the associated mold on the target mold. For molds with close process distance and strong historical influence correlation, their association coefficients will be relatively high, while for molds with distant process distance or weak influence correlation, their association coefficients will be relatively low.

[0033] On the basis of the above embodiments, as an optional implementation, in S102, the correlation coefficient of the target mold and the associated mold specifically includes S21-S24: S21, according to the process flow configuration information of the stamping production line, the associated molds which are adjacent or indirectly connected to the target mold in the process flow are identified, and the process transmission path between each associated mold and the target mold is determined.

[0034] The system first reads the process flow configuration information of the stamping production line, which describes the mold layout, process sequence and connection relationship of the whole production line in detail. Based on these configuration information, the system uses graph theory algorithm to identify the associated molds which are adjacent or indirectly connected to the target mold in the process flow. Adjacent position refers to the upstream or downstream mold directly connected to the target mold in the process flow, and indirect connection position refers to the mold which forms process transmission relationship with the target mold through one or more intermediate molds. The system constructs a directed graph model of the process flow, in which the nodes represent each mold and the edges represent the process transmission direction. Through graph traversal algorithm, the process transmission path between each associated mold and the target mold is determined, which describes the specific path and intermediate link through which the influence is transmitted from the associated mold to the target mold.

[0035] S22, according to the process transmission path, the process distance parameter between the target mold and each associated mold is calculated, which represents the position interval degree between molds in the process flow.

[0036] After determining the process transmission path, the system calculates the process distance parameter between the target mold and each associated mold, which is an important index to quantify the position interval degree between molds in the process flow. The system sets the process distance between directly adjacent molds as 1, and increases 1 for each intermediate mold, for example, the process distance between the target mold and the second upstream mold is 2, and the process distance between the target mold and the third upstream mold is 3. Considering the attenuation characteristics of influence intensity in the process transmission process, the system also introduces attenuation coefficient, for the molds with long distance, the influence intensity is adjusted according to the exponential attenuation law. The process distance parameter not only reflects the spatial position relationship, but also embodies the physical mechanism of process transmission, which provides a theoretical basis for the quantification of correlation strength.

[0037] S23, the historical state data change records of the target mold and each associated mold in a preset time period are obtained, and the influence correlation coefficient of the state change of each associated mold on the state change of the target mold is calculated.

[0038] In order to accurately evaluate the actual influence effect of each associated mold on the target mold, the system acquires the historical state data change records of the target mold and each associated mold in a preset time period, usually 1-2 months of data, to ensure the reliability of the data quantity supporting statistical analysis. The system uses a sliding window method to segment the historical data, calculates the influence correlation coefficient of the state change of each associated mold on the state change of the target mold, and the influence correlation coefficient reflects the actual correlation degree between the state change of the associated mold and the state change of the target mold. The system uses multiple statistical methods such as Pearson correlation coefficient and Granger causality test for comprehensive analysis, and considering the possible time delay effect, the system also calculates the correlation coefficient under different time lags, and selects the strongest correlation time lag as the final influence correlation coefficient.

[0039] S24, input the process distance parameter and the influence correlation coefficient into the association coefficient calculation function, generate the association coefficient of the target mold and each associated mold, and the association coefficient is used to quantify the influence degree of the associated mold on the target mold.

[0040] Based on the calculated process distance parameter and influence correlation coefficient, the system inputs the two key parameters into the preset association coefficient calculation function to generate the association coefficient of the target mold and each associated mold. The association coefficient calculation function uses a weighted fusion method to reasonably combine the process distance parameter and the influence correlation coefficient. The specific calculation formula is: association coefficient Cij=ρij×e^(-λ×dij)×αij, where ρij represents the influence correlation coefficient of associated mold i on target mold j, dij represents the process distance parameter between associated mold i and target mold j, λ is the distance attenuation factor, usually taking the value of 0.5-0.8, and αij is the process direction adjustment coefficient, which takes the value of 1.2 when the associated mold is located upstream of the target mold to reflect the importance of upstream influence, and takes the value of 0.8 when the associated mold is located downstream of the target mold to reflect the relatively weak characteristics of downstream reverse influence. This design not only considers the actual influence strength, but also reflects the attenuation effect of the process distance and the influence difference of the process flow. The system also normalizes the calculation results by dividing by the maximum value of all association coefficients to ensure that all association coefficients are between 0 and 1, facilitating subsequent numerical calculation and result interpretation.

[0041] S103, acquire the second state data of the associated mold, and generate the second abnormality coefficient of the associated mold according to the second state data.

[0042] Because the abnormal state of the associated die will have a chain effect on the target die through the process transmission path, if only the correlation strength is known without understanding the actual state of the associated die, the degree of influence that the target die may be subjected to cannot be accurately predicted and evaluated. For example, although a certain upstream die has a high correlation coefficient with the target die, if the upstream die is in a normal working state, its influence on the target die is relatively small, and vice versa, if the upstream die has a serious abnormality, even if the correlation coefficient is moderate, it may have a significant impact on the target die.

[0043] The system obtains the second state data of each associated die through the same data acquisition mechanism as the target die, and the second state data refers to the height change data of the associated die in the same time period. The acquisition method is completely consistent with the first state data of the target die, ensuring the synchronization and comparability of the data. Since the stamping production line usually adopts a synchronous operation mode, each die completes its own processing action in a similar time, therefore the system needs to ensure that the acquisition time window of the second state data is consistent with the first state data, avoiding data correlation deviation caused by time difference. For the process flow with time delay, the system will make corresponding compensation adjustment to the data acquisition time according to the material transmission time in the process transmission path.

[0044] After obtaining the second state data, the system generates a corresponding second abnormality coefficient for each associated die using the same calculation method and evaluation standard as the first abnormality coefficient of the target die. The system first extracts the reference state data of each associated die from the database, and each associated die has its own unique reference state data, because the design specifications, processing precision requirements and working load of different dies are different. By calculating the deviation value between the second state data and the corresponding reference state data, the system determines the deviation level of each associated die, and the deviation level classification standard is consistent with the target die, ensuring the uniformity and comparability of the abnormality evaluation.

[0045] In the process of generating the second abnormality coefficient, the system specially considers the differences in working characteristics of different types of associated dies. For example, the wear pattern of a drawing die is significantly different from that of a blanking die because it bears a larger forming force, so a die type correction factor is introduced in the abnormality coefficient calculation rule. For high-stress forming dies, the system will lower the abnormality determination threshold and increase the sensitivity to small changes, while for blanking dies that mainly bear shear force, more attention is paid to the height change pattern caused by blade wear. This differentiated evaluation mechanism ensures that the second abnormality coefficient can accurately reflect the actual abnormality degree of different types of associated dies.

[0046] The system also establishes a correlation mold abnormality propagation model. By analyzing the correlation between the abnormal state of the correlation mold and the subsequent state change of the target mold in the historical data, the time delay and intensity decay law of abnormality propagation are identified. The abnormal influence of some correlation molds may not appear on the target mold until several production cycles later, while the abnormal influence of some correlation molds may be partially absorbed or amplified by intermediate process steps. Based on these propagation laws, the system performs time-weighted processing on the second abnormality coefficient, giving higher weight to recent abnormal states, while considering the propagation delay time of abnormal influence.

[0047] In S104, the first abnormality index is adjusted in combination with the correlation coefficient and the second abnormality coefficient to generate the target abnormality coefficient of the target mold.

[0048] After obtaining the first abnormality coefficient of the target mold and the second abnormality coefficient of each correlation mold, the system needs to comprehensively analyze these dispersed abnormal information, because the actual abnormality degree of the target mold depends not only on its own state change, but also on the superimposed influence of the abnormal state of the correlation mold. Traditional single mold monitoring methods often ignore this correlation influence, leading to deviation in abnormality detection results, which may result in the situation that the target mold itself appears normal but is actually affected by upstream abnormality, or the target mold shows slight abnormality but the actual risk is amplified due to the chain reaction of downstream molds. Therefore, the system needs to establish a comprehensive adjustment mechanism to use the correlation coefficient and the second abnormality coefficient as correction factors to scientifically adjust the first abnormality coefficient of the target mold.

[0049] The system first calculates the actual influence intensity of each correlation mold on the target mold. By performing arithmetic multiplication operation on the correlation coefficient of each correlation mold and its corresponding second abnormality coefficient, the influence coefficient of each correlation mold is generated. The influence coefficient is a comprehensive index that considers not only the objective correlation strength between the correlation mold and the target mold, but also the actual abnormality degree of the correlation mold, and the larger the value, the more significant the current influence of the correlation mold on the target mold. For example, the correlation coefficient of an upstream mold is 0.8, and the second abnormality coefficient is 0.6, then the influence coefficient is 0.48, which means that the abnormal state of the upstream mold will have a moderate negative influence on the target mold.

[0050] Based on the influence coefficient of each associated die, the system determines the influence weight value of each associated die by using the normalization processing method. The influence coefficient and the influence weight value are in direct proportion. The associated die with a larger influence coefficient occupies a larger weight in the subsequent adjustment process. The normalization processing ensures that the sum of the influence weight values of all associated dies is equal to 1, avoiding the problem of unbalanced weight distribution. The system also introduces an influence attenuation factor. Considering the natural attenuation effect in the process transmission path, the influence weight value of the associated die farther from the target die will be correspondingly reduced. This processing method is more in line with the physical law of influence transmission in actual production.

[0051] The system performs weighted summation operation on the influence weight values of all associated dies to generate an associated influence adjustment factor. The associated influence adjustment factor is a value between 0 and 1, which is used to quantify the comprehensive influence degree of the abnormal state of all associated dies on the target die. When all associated dies are in a normal state, the associated influence adjustment factor is close to 0, indicating that the associated influence is small. When multiple associated dies simultaneously appear abnormal, the associated influence adjustment factor will significantly increase, reflecting the composite risk faced by the target die. The system also considers the directionality of the influence. For the favorable influence that can reduce the working load of the target die, a negative adjustment factor is used, while for the unfavorable influence that increases the working load or accelerates the wear of the target die, a positive adjustment factor is used.

[0052] After generating the associated influence adjustment factor, the system uses a hierarchical adjustment strategy to combine the first abnormality coefficient and the associated influence adjustment factor. The system first judges whether the associated influence adjustment factor is greater than the preset adjustment threshold. The adjustment threshold is usually set to 0.3, which is an empirical value determined based on a large amount of historical data statistical analysis, and can effectively distinguish between significant influence and weak influence. When the associated influence adjustment factor is greater than the adjustment threshold, it indicates that the abnormal state of the associated die has a non-negligible influence on the target die. The system multiplies the associated influence adjustment factor by a preset influence amplification coefficient to obtain an adjustment increment value. The influence amplification coefficient is customized according to different production line characteristics and die types, and is usually between 1.2 and 2.0.

[0053] The system performs addition operation on the first abnormality coefficient of the target die and the adjustment increment value to generate the target abnormality coefficient of the target die. The target abnormality coefficient reflects the true abnormality degree of the target die after considering the associated influence. When the associated influence adjustment factor is less than or equal to the adjustment threshold, it indicates that the influence degree of the associated die is low and is not sufficient to significantly change the abnormality evaluation result of the target die. In this case, the system directly uses the first abnormality coefficient as the target abnormality coefficient, avoiding excessive adjustment due to small influence. To ensure the reasonableness of the target abnormality coefficient, the system also sets an upper limit constraint mechanism. When the calculation result exceeds 1.0, it is automatically adjusted to 1.0, maintaining the standardized range of the abnormality coefficient.

[0054] On the basis of the above-mentioned embodiments, as an optional implementation, in S104, the first abnormality index is adjusted in combination with the correlation coefficient and the second abnormality coefficient to generate the target abnormality coefficient of the target mold, which specifically includes S41-S43: S41, the correlation coefficient and the second abnormality coefficient of each associated mold are arithmetically multiplied to generate an influence coefficient of each associated mold, and the influence weight value of each associated mold is determined according to the influence coefficient, and the influence coefficient is proportional to the influence weight value.

[0055] In order to accurately reflect the real abnormality state of the target mold in the multi-mold cooperative working environment, the system needs to integrate the influence effect of the associated mold into the abnormality evaluation process of the target mold, because the first abnormality coefficient calculated based on the state data of the target mold itself cannot completely reflect the actual abnormality degree in the complex production environment. In actual production, the abnormality state of a mold may be significantly affected by the upstream and downstream associated molds, for example, slight wear of an upstream mold may cause the downstream mold to bear additional stress and exhibit abnormal characteristics. If the correlation influence is ignored, it may lead to misjudgment of the abnormality degree of the target mold, affecting the accuracy of the maintenance decision.

[0056] The system first quantitatively calculates the actual influence intensity of each associated mold, arithmetically multiplies the correlation coefficient and the corresponding second abnormality coefficient of each associated mold to generate an influence coefficient of each associated mold. The influence coefficient reflects the actual influence intensity of the associated mold on the target mold in the current abnormality state, and its calculation logic is that the correlation coefficient represents the potential ability of influence transmission, and the second abnormality coefficient represents the current abnormality degree of the associated mold, and the influence coefficient obtained by multiplying the two represents the actual influence of the associated mold on the target mold in the current state. For example, even if a certain associated mold has a high correlation coefficient, but if its second abnormality coefficient is low, it means that the mold is currently in a normal state, and the actual influence on the target mold is relatively small.

[0057] S42, the influence weight values of all associated molds are weighted and summed to generate a correlation influence adjustment factor.

[0058] Based on the calculated correlation mold influence coefficient, the system determines the influence weight value of each correlation mold, which is used to reflect the importance difference of different correlation molds in subsequent weighted calculation. The system adopts a normalization processing method, divides the influence coefficient of a certain correlation mold by the sum of the influence coefficients of all correlation molds, to obtain the influence weight value of the correlation mold, ensuring that the sum of all influence weight values is equal to 1. This processing method makes the influence coefficient and the influence weight value in direct proportion, and the correlation mold with a larger influence coefficient obtains a higher influence weight value and plays a more important role in the final abnormality coefficient adjustment process. At the same time, the normalization processing eliminates the influence of the number of correlation molds on the calculation result, ensuring the stability and consistency of the abnormality coefficient adjustment.

[0059] The system performs weighted summation on the influence weight values of all correlation molds to generate a correlation influence adjustment factor, which is a core index quantifying the comprehensive influence effect of all correlation molds on the target mold. The specific calculation process of weighted summation is to multiply the influence weight value of each correlation mold by its corresponding second abnormality coefficient, and then add all the product results to obtain the value of the correlation influence adjustment factor. The value of the correlation influence adjustment factor ranges from 0 to 1, and the larger the value, the more serious the negative influence of the correlation mold on the target mold, and the greater the upward adjustment of the abnormality degree of the target mold is needed. The smaller the value, the relatively lighter the influence of the correlation mold, and the smaller the adjustment amplitude of the abnormality degree of the target mold.

[0060] S43, the first abnormality coefficient and the correlation influence adjustment factor are combined to generate the target abnormality coefficient of the target mold.

[0061] After obtaining the correlation influence adjustment factor, the system combines the first abnormality coefficient and the correlation influence adjustment factor to generate the target abnormality coefficient of the target mold. The combination operation adopts a weighted average method, and the specific calculation formula is: target abnormality coefficient = a x first abnormality coefficient + β x correlation influence adjustment factor, where a and β are weight coefficients, usually a = 0.7 and β = 0.3. This weight distribution not only ensures the dominant role of the target mold itself, but also reasonably considers the influence effect of the correlation mold. The system also sets upper and lower limit constraints for the abnormality coefficient, ensuring that the target abnormality coefficient is always within a reasonable range of 0 to 1. When the calculation result exceeds the upper limit, it is automatically set to 1, and when the calculation result is lower than the lower limit, it is automatically set to 0, avoiding the interference of abnormal values on subsequent analysis.

[0062] On the basis of the above embodiment, as an optional implementation, in S43, the first abnormality coefficient and the correlation influence adjustment factor are combined to generate the target abnormality coefficient of the target mold, which specifically includes S431-S432: S431, determine whether the correlation influence adjustment factor is greater than a preset adjustment threshold value, when the correlation influence adjustment factor is greater than the adjustment threshold value, multiply the correlation influence adjustment factor by a preset influence amplification coefficient to obtain an adjustment increment value; perform an addition operation on the first abnormality coefficient and the adjustment increment value to generate a target abnormality coefficient of the target mold.

[0063] S432, when the correlation influence adjustment factor is less than or equal to the adjustment threshold value, the first abnormality coefficient is taken as the target abnormality coefficient of the target mold.

[0064] In order to ensure the scientificity and effectiveness of the correlation influence adjustment, the system needs to establish an intelligent adjustment judgment mechanism, because not all correlation mold influences need to adjust the abnormality coefficient of the target mold, only when the correlation influence reaches a certain degree will it have a significant actual influence on the target mold. If the slight correlation influence is also adjusted, unnecessary noise interference may be introduced, reducing the accuracy of abnormality assessment, and if the significant correlation influence is ignored, the abnormality assessment will be incomplete. Therefore, the system adopts the threshold judgment and hierarchical processing strategy to ensure that only when the correlation influence is significant enough will the corresponding abnormality coefficient adjustment be performed.

[0065] The system first judges the size of the correlation influence adjustment factor, compares it with the preset adjustment threshold value, and the adjustment threshold value is a critical value determined based on a large amount of historical data statistical analysis, usually set to 0.3, this threshold value represents the demarcation point from slight to significant correlation mold influence. The determination of the adjustment threshold value takes into account the statistical distribution characteristics of the correlation mold influence, the sensitivity requirements of abnormality detection and the fault tolerance requirements in actual production process, which ensures that the truly meaningful correlation influence can be identified, and avoids overreaction to normal slight fluctuations.

[0066] When the correlation influence adjustment factor is greater than the adjustment threshold value, it means that the correlation mold has a significant negative influence on the target mold, and the abnormality degree of the target mold needs to be adjusted upwards. The system multiplies the correlation influence adjustment factor by a preset influence amplification coefficient to obtain an adjustment increment value, the influence amplification coefficient is an important parameter for controlling the adjustment range of the correlation influence, usually set to 1.5 to 2.0, the setting of this coefficient is based on the transmission attenuation characteristics of the correlation influence and the statistical law of the actual influence effect. The introduction of the influence amplification coefficient is because the correlation influence adjustment factor has been normalized, its value is relatively small, and it needs to be amplified appropriately to reflect its actual influence strength on the abnormality degree of the target mold.

[0067] The system performs an addition operation on the first abnormality coefficient and the calculated adjustment increment value to generate the target abnormality coefficient of the target mold, and the specific calculation formula is: target abnormality coefficient = first abnormality coefficient + adjustment increment value, wherein the adjustment increment value = correlation influence adjustment factor × influence amplification coefficient. This addition operation ensures that the abnormal state of the target mold itself is always the basis, and the correlation influence is only an incremental adjustment based on this basis, reflecting the dominant position of the target mold state and the auxiliary role of the correlation influence. In order to prevent the target abnormality coefficient after adjustment from exceeding the reasonable range, the system sets an upper limit constraint mechanism, and when the calculation result exceeds 1, the target abnormality coefficient is automatically set to 1, ensuring the effectiveness and interpretability of the value.

[0068] When the correlation influence adjustment factor is less than or equal to the adjustment threshold, it means that the influence of the correlation mold on the target mold is relatively light and is not sufficient to significantly affect the abnormality assessment of the target mold. At this time, the system directly uses the first abnormality coefficient as the target abnormality coefficient of the target mold. This processing method avoids excessive sensitivity to small correlation influences, maintains the stability and reliability of the abnormality assessment, and also simplifies the calculation process and improves the running efficiency of the system. Through this hierarchical processing strategy, the system can ensure the integrity of the correlation influence while avoiding unnecessary noise interference and calculation complexity.

[0069] S105, when the target abnormality coefficient is greater than the preset threshold, generating abnormal information of the target mold, and generating maintenance suggestions for the target mold according to the abnormal information.

[0070] After confirming that the target abnormality coefficient exceeds the preset threshold, the system begins to generate the abnormal information of the target mold. The abnormal information is a comprehensive description and analysis of the current abnormal state of the target mold, including key elements such as abnormal occurrence time, abnormality degree level, abnormal feature description, and possible influencing factors. The system determines the abnormality degree level according to the specific value of the target abnormality coefficient, and divides 0.7 to 0.8 as mild abnormality, 0.8 to 0.9 as moderate abnormality, and 0.9 to 1.0 as severe abnormality. Different levels correspond to different emergency levels and processing priorities. The abnormal feature description identifies specific abnormal forms by analyzing the change pattern of the first state data, such as high and sustained decline indicating accelerated wear, high and increased volatility indicating decreased accuracy, and high and sudden jumps indicating possible mechanical failure.

[0071] The system also determines the possible influencing factors of the anomaly through backtracking analysis, combines the second anomaly coefficient of the associated mold and the correlation coefficient, and identifies whether there are upstream and downstream transmission influencing factors. If the second anomaly coefficient of a certain associated mold is high and the correlation coefficient with the target mold is large, the system will identify it as the main influencing factor and explicitly indicate the specific source and transmission path of the associated influence in the anomaly information. At the same time, the system also analyzes the historical state change trend of the target mold itself, judges whether there are different abnormal modes such as gradual wear, sudden failure or periodic anomaly, and provides an important basis for subsequent maintenance strategy making.

[0072] Based on the generated anomaly information, the system further generates maintenance suggestions for the target mold. The maintenance suggestion is a specific maintenance guidance scheme provided by the system for the target mold according to the anomaly type, severity, historical maintenance record and best practice experience. The generation of the maintenance suggestion adopts a method combining expert system and machine learning. The system has a rich fault diagnosis knowledge base and maintenance experience database built-in, and recommends the most suitable maintenance strategy for the current abnormal condition through pattern matching and similar case retrieval. For mild anomalies, the system may suggest preventive maintenance, such as cleaning and lubrication, tightening inspection and other routine maintenance operations. For moderate anomalies, the system may suggest local repair, such as edge grinding, surface treatment and other special maintenance. For severe anomalies, the system may suggest immediate shutdown for repair or replacement of key components.

[0073] The maintenance suggestion also contains detailed operation guidance and resource requirement information, such as required maintenance tools, spare parts list, estimated maintenance time, skill requirements, etc., to help maintenance personnel make full preparation. The system will provide personalized maintenance guidance according to the model specifications and historical maintenance records of the target mold, including key inspection points, common failure modes, maintenance precautions and other professional information. At the same time, the system also evaluates the urgency and impact of the maintenance to provide decision support for production scheduling, such as suggesting maintenance after the current production task is completed to minimize the impact on production, or suggesting immediate shutdown for maintenance to avoid more serious equipment damage.

[0074] On the basis of the above embodiments, the method further comprises S106-S109: S106, when the target anomaly coefficient is not greater than the preset threshold, obtaining the first historical state data of the target mold and the second historical state data of the associated mold.

[0075] When the target abnormality coefficient is not greater than the preset threshold, it indicates that the target mold is currently in a relatively normal working state, but this does not mean that monitoring and management of it can be ignored, because the abnormality of the mold is often a gradual development process, from the initial small change to the obvious abnormal state, if only relying on the static judgment of the current state, the best preventive maintenance opportunity may be missed. The traditional passive maintenance mode often waits until the equipment fails before repairing, which not only causes unplanned production interruption, but also may cause more serious equipment damage and higher maintenance cost. Therefore, the system needs to realize real predictive maintenance by analyzing the trend of historical data when the target mold has not reached the abnormal threshold, to identify the potential abnormal development trend in advance.

[0076] The system starts the historical data backtracking analysis process to obtain the first historical state data of the target mold and the second historical state data of each associated mold. The time span of the historical data is usually set to the last 3 months or the last 500 production cycles, ensuring that the data volume is sufficient to support the statistical requirements of trend analysis, and at the same time ensuring that the timeliness of the data can reflect the current production conditions and equipment state. The first historical state data contains all the high change records of the target mold in the historical time period, and the data is arranged in chronological order, each data point contains an accurate timestamp and a corresponding measurement value, providing a basis for subsequent time series analysis. The second historical state data contains the state change records of each associated mold in the same time period, and the system ensures the time synchronization of all historical data to avoid time deviation interference with the correlation analysis.

[0077] In S107, the first historical abnormality coefficient change sequence of the target mold is calculated according to the first historical state data, and the second historical abnormality coefficient change sequence of the associated mold is calculated according to the second historical state data.

[0078] Based on the obtained first historical state data, the system calculates the first historical abnormality coefficient change sequence of the target mold using the sliding time window method. The sliding time window refers to the system moving the calculation window on the historical data with a fixed time interval as the step, and calculating the corresponding abnormality coefficient for the data in each time window. The size of the time window is usually set to the data volume of one production shift or one day, and the step is set to one quarter of the window size, ensuring enough overlap between adjacent time windows to capture continuous changes. The system calculates the abnormality coefficient for each time window using the same calculation method as the current target abnormality coefficient, ensuring that the historical abnormality coefficient is comparable to the current abnormality coefficient, forming a first historical abnormality coefficient change sequence arranged in chronological order.

[0079] The same processing method is applied to the second historical state data of each associated mold, and the system calculates the second historical abnormal coefficient change sequence of each associated mold, which reflects the abnormal state evolution process of the associated mold in the historical time period. Since different associated molds may have different working tempos and maintenance periods, the system considers these differences in the calculation process and adjusts the size of the time window and the calculation frequency accordingly to ensure that the state change characteristics of each associated mold can be accurately captured. The system also smooths the historical abnormal coefficient change sequence to eliminate data fluctuations caused by measurement noise or accidental factors and highlights the true change trend.

[0080] In S108, based on the association coefficient, the first historical abnormal coefficient change sequence and the second historical abnormal coefficient change sequence are associated analyzed to determine the change rule of the target abnormal coefficient.

[0081] Based on the determined association coefficient, the system performs association analysis on the first historical abnormal coefficient change sequence and the second historical abnormal coefficient change sequence of each associated mold. The association analysis uses multivariate time series analysis methods, including Granger causality test, vector autoregressive model, and dynamic time warping. The system first identifies the time lag relationship between the sequences, because the state change of the associated mold may have a certain time delay on the target mold. The system determines the optimal lag time through cross-correlation analysis, which is usually between several hours and several production shifts. After determining the time lag relationship, the system calculates the influence weight of the historical abnormal coefficient change of each associated mold on the historical abnormal coefficient change of the target mold. The influence weight combines the association coefficient and the actual historical correlation, and more accurately reflects the actual influence degree of each associated mold on the target mold.

[0082] By comprehensively analyzing the first historical abnormal coefficient change sequence and the weighted second historical abnormal coefficient change sequence, the system identifies the change rule of the target abnormal coefficient, including periodic change pattern, trend change pattern, and sudden change pattern. The periodic change pattern reflects the regular fluctuations related to production tempo, maintenance period, or seasonal factors. The trend change pattern reflects the progressive change process of mold wear and aging. The sudden change pattern reflects sudden impact factors such as equipment failure and process adjustment. The system uses frequency domain analysis method to identify periodic components, trend decomposition method to identify long-term trends, and anomaly detection algorithm to identify mutation points, forming a comprehensive understanding of the change rule of the target abnormal coefficient.

[0083] Based on the above embodiments, as an optional implementation, in S108, based on the association coefficient, the first historical abnormal coefficient change sequence and the second historical abnormal coefficient change sequence are associated analyzed to determine the change rule of the target abnormal coefficient, which specifically includes S81-S84: S81, calculate the change slope and change period of the first historical abnormal coefficient change sequence.

[0084] The system first conducts in-depth mathematical analysis on the first historical abnormal coefficient change sequence, calculates the change slope and change period of the sequence, and the change slope reflects the rate and direction of the change of the target mold abnormal coefficient with time, which is a key indicator for judging the evolution trend of the mold state. The system uses the least square method to linearly fit the historical abnormal coefficient change sequence, calculates the slope of the fitting straight line as the overall change slope, a positive value indicates that the abnormality degree gradually increases, a negative value indicates that the abnormality degree gradually decreases, and the numerical value reflects the speed of change. In order to capture the detailed features in the change process, the system also uses the moving average method to calculate the local change slope, and by comparing the local slopes of different time periods, the acceleration, deceleration or turning point in the change process is identified.

[0085] In calculating the change period, the system uses the frequency domain analysis method to conduct Fourier transform on the first historical abnormal coefficient change sequence, identifies the periodic components in the sequence, and the change period reflects the regularity of the change of the target mold abnormal coefficient, which is usually related to factors such as production rhythm, maintenance period, raw material batch change, etc. The system determines the dominant period frequency through power spectral density analysis, and at the same time identifies multiple secondary period components, because the mold state change is often affected by the composite influence of multiple periodic factors. For each identified period component, the system calculates its corresponding amplitude and phase, quantifies the contribution degree of the period component to the overall change mode, and provides important periodic parameters for the subsequent prediction model.

[0086] S82, the second historical abnormal coefficient change sequence and the correlation coefficient are weighted to obtain the correlation influence sequence.

[0087] Based on the second historical abnormal coefficient change sequence of each correlation mold and the corresponding correlation coefficient, the system performs weighted processing to generate the correlation influence sequence, and the purpose of weighted processing is to reasonably combine the influences of different correlation molds according to their actual importance. The system performs point-by-point multiplication operation on the second historical abnormal coefficient change sequence of each correlation mold and its corresponding correlation coefficient to obtain the weighted influence sequence of the correlation mold, and the influence of the mold with larger correlation coefficient is amplified accordingly, and the influence of the mold with smaller correlation coefficient is reduced accordingly. Subsequently, the system performs arithmetic summation on the weighted influence sequences of all correlation molds to generate a comprehensive correlation influence sequence, which reflects the change of the overall influence effect of all correlation molds on the target mold with time.

[0088] S83, analyze the time delay correlation between the correlation influence sequence and the first historical abnormal coefficient change sequence, and determine the delay time of the correlation influence.

[0089] To accurately describe the transmission characteristics of the correlation influence, the system analyzes the time delay correlation between the correlation influence sequence and the first historical abnormal coefficient change sequence, determines the delay time of the correlation influence, which refers to the time interval required for the correlation mold state change to have an impact on the target mold. The system uses cross-correlation function analysis method to calculate the correlation coefficient between the two sequences under different time delays, and determines the optimal delay time by finding the peak position of the correlation coefficient. Considering that there may be multiple transmission paths and different transmission mechanisms in actual production, the system also identifies multiple local peaks corresponding to different delay times, reflecting the complex multi-path transmission effect.

[0090] Based on the determination of the delay time, the system performs time offset processing on the correlation influence sequence to achieve the best alignment in time with the first historical abnormal coefficient change sequence. This processing eliminates the deviation caused by time delay in correlation analysis and improves the accuracy of influence relationship identification. The system calculates the dynamic correlation between the two sequences after time alignment and identifies the change law of correlation with time, because the strength of the correlation influence may be dynamically adjusted with changes in production conditions, equipment state and other factors. By analyzing the change pattern of dynamic correlation, the system can identify the stability and predictability of influence transmission.

[0091] S84, in combination with the change slope, the change period and the delay time, the change law of the target abnormal coefficient is determined.

[0092] In combination with the key parameters such as the calculated change slope, change period and delay time, the system constructs a comprehensive mathematical model of the change law of the target abnormal coefficient, which includes three main components: trend item, periodic item and correlation influence item. The trend item describes the long-term development trend of the target abnormal coefficient based on the change slope, the periodic item describes the regular fluctuation pattern based on the identified change period, and the correlation influence item describes the transmission effect of external influence based on the delay time and the correlation influence sequence. The system uses polynomial regression or machine learning algorithm to optimize the combination of the three components, determines the weight coefficients and interaction relationships of each part, and forms a complete mathematical expression that can accurately describe the historical change pattern of the target abnormal coefficient.

[0093] S109, according to the change law, the change trend of the target abnormal coefficient in the future preset time period is predicted; according to the change trend, the maintenance suggestion of the target mold is generated.

[0094] Based on the identified change law, the system establishes a prediction model of the target abnormality coefficient. The prediction model uses machine learning algorithms such as long short-term memory network, support vector regression or time series prediction algorithm, combines the change law in the historical data and the current state information, and predicts the change trend of the target abnormality coefficient in the future preset time period. The future preset time period is usually set to 1-4 weeks in the future, which can provide enough preparation time for maintenance plan and ensure the reliability of the prediction result. The prediction result includes the expected value of the target abnormality coefficient, the change rate, the possible time to reach the abnormal threshold and other key information. The system also provides a prediction confidence interval to quantify the uncertainty of the prediction result.

[0095] According to the predicted change trend, the system generates maintenance suggestions for the target mold. The maintenance suggestions are different in nature from the repair suggestions in S105. The former focuses on preventive maintenance, and the latter focuses on fault repair. When the prediction shows that the target abnormality coefficient may exceed the preset threshold at a certain time point in the future, the system suggests scheduling preventive maintenance before that time point, such as early cleaning and maintenance, precision adjustment or partial component replacement, to avoid further development of abnormal state. The maintenance suggestion also includes maintenance time window recommendation. The system will recommend the most suitable maintenance time based on the production plan and equipment load, to ensure the maintenance effect and minimize the impact on production. For the case where the prediction shows that the abnormality coefficient develops slowly, the system may suggest extending the monitoring frequency or adjusting the maintenance cycle to optimize the allocation of maintenance resources.

[0096] The application also integrates a complete data acquisition and communication guarantee function module, which establishes real-time data connection with the height sensor on the stamping equipment through serial communication technology, obtains the original measurement data of the mold height, and provides a reliable data source basis for the entire abnormality detection system.

[0097] The system has an intelligent data quality control mechanism, which automatically checks the format and validity of the received raw data, can accurately identify and extract valid data containing device number and height value, and automatically filter out invalid data with format errors, abnormal values or transmission damage, to ensure the data quality for subsequent analysis and processing.

[0098] In order to ensure the security and reliability of the data, the system adopts a double storage strategy, which writes the valid data that passes the verification into both local CSV file and remote database, ensuring real-time availability of the data, providing data backup protection, and effectively preventing data loss risk caused by single storage failure.

[0099] The system also has a perfect communication stability guarantee mechanism. A timer is used to monitor the state of the receiving buffer of the serial port communication in real time. When the data accumulation in the buffer exceeds a preset threshold, an automatic emptying operation is performed to prevent buffer overflow and affect data reception. At the same time, the receiving time interval of valid data is monitored. When a communication interruption or data reception anomaly is detected, a restart process is automatically performed to restore normal data collection functions.

[0100] In addition, the system is equipped with an automatic reconnection mechanism. When the serial port communication is unexpectedly disconnected, the system can automatically start a reconnection process and continuously attempt to reestablish a connection at a preset time interval to ensure that the communication can be immediately resumed for normal data acquisition and storage operations, thereby maximizing the continuity of data collection and the stability of system operation.

[0101] As shown in Figure 2 , Figure 2 is a schematic diagram of a mold state data collection and abnormality analysis system provided by an embodiment of the present application. The schematic diagram systematically demonstrates a complete logical closed loop of a mold state data collection and abnormality analysis method. The overall architecture is divided into a physical device layer, a data transmission layer, and a data processing layer from bottom to top. In the physical device layer at the bottom, the "target mold" on the left is equipped with a height sensor to collect first state data in real time. The "associated mold" on the right is a device that has an upstream and downstream relationship in the process flow and synchronously collects its operating parameters, i.e., second state data. The dashed line between the two indicates the clear process correlation and correlation coefficient. The two sets of collected data are aggregated to the "data processing center" at the top via the intermediate data transmission channel. The server first calculates the basic "first abnormality coefficient" of the target mold based on the first state data, and then introduces the key correction logic, i.e., uses the "second abnormality coefficient" of the associated mold and the "correlation coefficient" to weight or adjust the preliminary result, thereby generating a "target abnormality coefficient" that better reflects the real working conditions. Finally, the system compares the coefficient with a preset threshold. Once the threshold is exceeded, the abnormal information is output and the corresponding maintenance suggestion is automatically generated, as shown on the right side of the alarm module, thereby completing the entire process from sensor raw data collection to intelligent maintenance decision-making.

[0102] Based on the above method, the present application also discloses a mold state data collection system, as shown in Figure 3 , Figure 3 is a structural schematic diagram of a mold state data collection system provided by an embodiment of the present application. The system includes a first acquisition module, a second acquisition module, a third acquisition module, a combination module, and a generation module. Wherein, The first obtaining module is configured to obtain first state data of a target die sent by a height sensor installed on a stamping device, and generate a first abnormality coefficient of the target die according to the first state data; the second obtaining module is configured to obtain a correlation coefficient of the target die and a correlation die, the correlation die being a die having an upstream or downstream relationship with the target die in a process flow; the third obtaining module is configured to obtain second state data of the correlation die, and generate a second abnormality coefficient of the correlation die according to the second state data; the combining module is configured to combine the correlation coefficient and the second abnormality coefficient to adjust the first abnormality index, and generate a target abnormality coefficient of the target die; and the generating module is configured to generate abnormality information of the target die when the target abnormality coefficient is greater than a preset threshold, and generate a repair suggestion of the target die according to the abnormality information.

[0103] It should be noted that the system provided in the above embodiments is only used as an example to divide the above functional modules when realizing the functions, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is described in the method embodiments, which will not be described here.

[0104] Please refer to Figure 4 The embodiment of the present application provides a structural schematic diagram of an electronic device. As shown in the figure, Figure 4 The electronic device 1000 can include at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0105] The communication bus 1002 is used to realize the connection and communication between the components.

[0106] The user interface 1003 can include a display screen (Display) and a camera (Camera), and the optional user interface 1003 can also include a standard wired interface and a wireless interface.

[0107] The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0108] The processor 1001 can include one or more processing cores. The processor 1001 connects various parts within the server through various interfaces and lines, and performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Alternatively, the processor 1001 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 1001 can integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interfaces, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 1001, but can be realized by a separate chip.

[0109] The memory 1005 can include a random access memory (RAM) and a read-only memory (ROM). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 1005 can also be at least one storage device located away from the aforementioned processor 1001. As shown, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of a mold state data acquisition method. Figure 4

[0110] In Figure 4 ​In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 1001 can be used to call an application program stored in the memory 1005 and storing a mold state data acquisition method, which, when executed by one or more processors, causes the electronic device to perform the method described in one or more of the above embodiments.

[0111] An electronic device readable storage medium stores instructions. When executed by one or more processors, the electronic device performs the method described in one or more of the above embodiments.

[0112] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0113] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0114] In several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some services interfaces, devices or units, and can be electrical or other forms.

[0115] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0116] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0117] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned memory includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0118] The above is only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the disclosure herein. The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional techniques in the art that are not described in the present disclosure. The specification and examples are only considered as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for acquiring mold status data, characterized in that, The method includes: Acquire the first state data of the target mold sent by the height sensor installed on the stamping equipment, and generate the first anomaly coefficient of the target mold based on the first state data; Obtain the correlation coefficient between the target mold and the associated mold, wherein the associated mold is a mold that has an upstream or downstream relationship with the target mold in the process flow; Obtain the second state data of the associated mold, and generate the second anomaly coefficient of the associated mold based on the second state data; By combining the correlation coefficient and the second anomaly coefficient, the first anomaly index is adjusted to generate the target anomaly coefficient of the target mold; When the target anomaly coefficient is greater than a preset threshold, anomaly information of the target mold is generated, and maintenance suggestions for the target mold are generated based on the anomaly information.

2. The mold status data acquisition method according to claim 1, characterized in that, The method further includes: When the target anomaly coefficient is not greater than a preset threshold, the first historical state data of the target mold and the second historical state data of the associated mold are obtained. Based on the first historical state data, calculate the first historical anomaly coefficient change sequence of the target mold; based on the second historical state data, calculate the second historical anomaly coefficient change sequence of the associated mold. Based on the correlation coefficient, the first historical anomaly coefficient change sequence and the second historical anomaly coefficient change sequence are correlated to determine the change pattern of the target anomaly coefficient; Based on the aforementioned pattern of change, predict the trend of the target anomaly coefficient over a future preset time period; Based on the changing trend, maintenance recommendations for the target mold are generated.

3. The mold status data acquisition method according to claim 2, characterized in that, The step of performing correlation analysis on the first historical anomaly coefficient change sequence and the second historical anomaly coefficient change sequence based on the correlation coefficient to determine the change pattern of the target anomaly coefficient includes: Calculate the slope and period of the first historical anomaly coefficient change sequence; The second historical anomaly coefficient change sequence is weighted with the correlation coefficient to obtain the correlation influence sequence; Analyze the time delay correlation between the associated impact sequence and the first historical anomaly coefficient change sequence to determine the delay time of the associated impact; By combining the change slope, the change period, and the delay time, the change pattern of the target anomaly coefficient is determined.

4. The mold status data acquisition method according to claim 1, characterized in that, The step of generating the first anomaly coefficient of the target mold based on the first state data includes: Obtain the reference state data of the target mold, wherein the reference state data is the standard height value of the target mold under normal working conditions; Calculate the deviation between the first state data and the reference state data, and determine the deviation level based on the deviation value; Based on the deviation level and the preset anomaly coefficient calculation rules, the first anomaly coefficient of the target mold is generated.

5. The mold status data acquisition method according to claim 1, characterized in that, The step of obtaining the correlation coefficient between the target mold and the associated mold includes: Based on the process flow configuration information of the stamping production line, identify the associated molds that are adjacent or indirectly connected to the target mold in the process flow, and determine the process transfer path between each associated mold and the target mold. Based on the process transfer path, calculate the process distance parameters between the target mold and each of the associated molds. The process distance parameters characterize the degree of positional interval between the molds in the process flow. Acquire historical state data change records of the target mold and each of the associated molds within a preset time period, and calculate the correlation coefficient of the influence of the state changes of each of the associated molds on the state changes of the target mold. The process distance parameter and the influence correlation coefficient are input into the correlation coefficient calculation function to generate the correlation coefficient between the target mold and each of the associated molds. The correlation coefficient is used to quantify the degree of influence of the associated molds on the target mold.

6. The mold status data acquisition method according to claim 1, characterized in that, The step of adjusting the first anomaly index by combining the correlation coefficient and the second anomaly coefficient to generate the target anomaly coefficient for the target mold includes: The correlation coefficient and the second anomaly coefficient of each of the associated molds are arithmetically multiplied to generate the influence coefficient of each of the associated molds. The influence weight value of each of the associated molds is determined based on the influence coefficient. The influence coefficient is directly proportional to the influence weight value. The influence weights of all the aforementioned associated molds are weighted and summed to generate an association influence adjustment factor. The first anomaly coefficient is combined with the correlation influence adjustment factor to generate the target anomaly coefficient of the target mold.

7. The mold status data acquisition method according to claim 6, characterized in that, The step of combining the first anomaly coefficient with the correlation influence adjustment factor to generate the target anomaly coefficient of the target mold includes: Determine whether the correlation influence adjustment factor is greater than a preset adjustment threshold; When the correlation influence adjustment factor is greater than the adjustment threshold, the correlation influence adjustment factor is multiplied by the preset influence amplification coefficient to obtain the adjustment increment value; the first anomaly coefficient is added to the adjustment increment value to generate the target anomaly coefficient of the target mold. When the correlation influence adjustment factor is less than or equal to the adjustment threshold, the first anomaly coefficient is used as the target anomaly coefficient of the target mold.

8. A mold status data acquisition system, characterized in that, The system includes: a first acquisition module, a second acquisition module, a third acquisition module, a combination module, and a generation module; wherein, The first acquisition module is used to acquire the first state data of the target mold sent by the height sensor installed on the stamping equipment, and generate the first anomaly coefficient of the target mold based on the first state data. The second acquisition module is used to acquire the correlation coefficient between the target mold and the associated mold, wherein the associated mold is a mold that has an upstream or downstream relationship with the target mold in the process flow; The third acquisition module is used to acquire the second state data of the associated mold and generate the second anomaly coefficient of the associated mold based on the second state data. The combining module is used to combine the correlation coefficient and the second anomaly coefficient to adjust the first anomaly index and generate the target anomaly coefficient of the target mold. The generation module is used to generate abnormal information of the target mold when the target abnormality coefficient is greater than a preset threshold, and to generate maintenance suggestions for the target mold based on the abnormal information.

9. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1-7.

Images