Dynamic critical area process inspection method and system based on real-time data drive

Abstract

The present application provides a dynamic critical area process inspection method and system driven by real-time data, which relates to the field of process inspection management of equipment production. The method includes: dividing the parts to be inspected into different quality batches according to the parameter value range of the process behavior data; in the same quality batch, constructing a mapping relationship between the process behavior data and the processing area of ​​the target part according to the part processing positions corresponding to multiple acquisition timestamps of the process behavior data of the target part produced in the same time period; constructing a target geometric area set based on the mapping relationship and the fluctuation characteristics of the process behavior data; determining the defect risk score corresponding to each target geometric area in the target geometric area set according to the risk prediction model, and then determining the target critical area of ​​the process inspection. Implementing this method can ensure that inspection resources are more accurately invested in high-risk areas, thereby improving the efficiency of resource utilization in process inspection.

Description

Technical Field

[0001] The present application relates to the field of process inspection management of equipment production, and in particular to a dynamic key area process inspection method and system based on real-time data drive. Background Art

[0002] As the manufacturing industry continues to transform towards intelligent manufacturing, quality inspections during the production process are gradually shifting from traditional static manual inspections to intelligent, automated, dynamic inspections. In modern manufacturing, product quality inspections have a significant impact on a company's production efficiency and product qualification rates. This is particularly true in the field of high-precision parts manufacturing, where timely detection and prevention of defects have become critical to ensuring product quality.

[0003] In related technologies, a common practice in industrial production is to determine critical and non-critical inspection areas during the part design phase based on the product's structural characteristics and functional requirements. Designers divide the product into different inspection areas and develop corresponding inspection procedures based on static factors such as the part's geometric characteristics and stress distribution. During actual inspection, inspectors adhere to the established area division scheme from the design phase, dedicating more inspection resources to critical areas and employing less frequent spot checks for non-critical areas.

[0004] However, this approach of fixing inspection areas during the design phase has practical limitations. Because the requirements in the inspection procedures are pre-defined, the allocation of inspection resources is often relatively fixed. In actual production, parts produced in different batches and time periods may exhibit varying quality conditions. A unified inspection procedure makes it difficult to flexibly adjust inspection resources based on actual conditions, which can lead to inefficient use of inspection resources. Summary of the Invention

[0005] The present application provides a dynamic key area process inspection method and system based on real-time data drive, which is used to address the problem of how to improve the efficiency of inspection resource utilization in process inspection.

[0006] In a first aspect, the present application provides a dynamic critical area process inspection method based on real-time data drive, which is applied to an equipment inspection control system, and the method includes:

[0007] Divide the parts to be inspected into different quality batches based on the parameter value range of the process behavior data corresponding to the parts to be inspected. The process behavior data is collected during the production process of the parts to be inspected by multiple types of sensors deployed on production equipment. Different quality batches correspond to different processing area division rules;

[0008] In the same quality batch, a mapping relationship between the process behavior data and the processing area of ​​the target part is established based on the process behavior data of the target part produced in the same time period and the part processing positions corresponding to multiple acquisition time stamps of the process behavior data, where the processing area includes multiple processing positions;

[0009] Based on the mapping relationship, a target processing area corresponding to the target part and a target geometric area set are selected from the multiple processing areas corresponding to the target part, wherein the fluctuation characteristics of the process behavior data corresponding to the acquisition time stamp exceed a preset threshold, and the fluctuation characteristics include fluctuation frequency, fluctuation amplitude and fluctuation trend;

[0010] Inputting the process behavior data corresponding to each target geometric area in the target geometric area set into a preset risk prediction model, and outputting a defect risk score corresponding to each target geometric area, wherein the risk prediction model is trained based on historical process behavior data and corresponding historical defect risk scores;

[0011] The target geometric area whose defect risk score exceeds a preset risk threshold is determined as a target critical area for process inspection for resource allocation.

[0012] Through the above-described embodiment, the system dynamically divides quality batches and key inspection areas using real-time collected process behavior data, breaking through the limitations of fixed inspection areas in traditional inspection methods. Based on actual data fluctuations during the production process, the system can intelligently identify areas that truly require focused inspection and dynamically allocate inspection resources accordingly. This data-driven dynamic inspection approach ensures that inspection resources are more accurately allocated to high-risk areas, to a certain extent avoiding over-inspection of low-risk areas, thereby improving the efficiency of inspection resource utilization.

[0013] In some embodiments, before the step of dividing the parts to be inspected into different quality batches according to the parameter value range of the process behavior data corresponding to the parts to be inspected, the step further includes:

[0014] Calculating the parameter fluctuation value corresponding to the process behavior data according to the difference between the process behavior data corresponding to all parts to be inspected and the preset ideal process behavior data;

[0015] The parameter fluctuation value is divided into a plurality of parameter fluctuation ranges based on a preset ratio to obtain a plurality of corresponding parameter value ranges. The processing area division granularities corresponding to different parameter value ranges are not all the same.

[0016] Through the above-described embodiment, the system calculates the degree of deviation between process behavior data and ideal data, establishing a mechanism for aligning different parameter value ranges with different processing area granularity. This multi-level zoning approach, based on actual processing parameter fluctuations, allows for more targeted inspection area division, allowing the appropriate inspection granularity to be selected based on the actual processing status of different product batches, avoiding the waste of resources caused by overly coarse or overly detailed zoning.

[0017] In some embodiments, after the step of dividing the parameter fluctuation value into a plurality of parameter fluctuation ranges based on a preset ratio to obtain a plurality of corresponding parameter value ranges, the method further includes:

[0018] Based on the machining feature size and machining accuracy requirements of the parts, a multi-level fine-grained division level of the machining area is constructed, each of the fine-grained division levels corresponds to a different area division size;

[0019] Setting a preset parameter range corresponding to each of the fine-grained division levels based on parameter fluctuation value distribution characteristics in historical processing data;

[0020] Calculate the overlap ratio of the parameter fluctuation values ​​within each parameter value range within the preset parameter range;

[0021] The fine-grained division level corresponding to the preset parameter range with the largest overlap ratio is determined as the fine-grained division level corresponding to the parameter value range.

[0022] Through the above-mentioned implementation, the system establishes a multi-level, fine-grained classification hierarchy based on the part's machining feature dimensions and precision requirements, and determines the optimal classification hierarchy through historical data analysis. This adaptive regional division method considers both the product's technical requirements and the distribution characteristics of actual production data, making regional division more scientific and reasonable and better guiding the allocation of inspection resources.

[0023] In some embodiments, before the step of establishing a mapping relationship between the process behavior data and the processing area of ​​the target part based on the process behavior data of the target part produced in the same time period and the part processing positions corresponding to multiple acquisition timestamps of the process behavior data in the same quality batch, the method further includes:

[0024] Acquiring production trajectory data of the target part, the production trajectory data including a motion trajectory and a processing speed of a processing tool of a production equipment relative to the target part;

[0025] The part processing positions of the target part corresponding to different acquisition time stamps are calibrated based on the production trajectory data to obtain the calibrated part processing positions.

[0026] Through the above-mentioned implementation, the system achieves precise calibration and alignment of part processing positions by collecting and analyzing the motion trajectory data of production equipment. This dynamic position tracking mechanism ensures a precise correspondence between process behavior data and the actual processing area, providing a reliable data foundation for subsequent area division and risk assessment.

[0027] In some embodiments, the step of constructing a target geometric region set by selecting, from the multiple processing regions corresponding to the target part, target processing regions whose fluctuation characteristics of process behavior data corresponding to the acquisition timestamp exceeds a preset threshold based on the mapping relationship specifically includes:

[0028] Based on the mapping relationship, constructing a process behavior data sequence corresponding to each continuous acquisition time stamp according to one or more continuous acquisition time stamps corresponding to each processing area;

[0029] When it is detected that the fluctuation characteristics of any process behavior data sequence corresponding to the processing area exceed a preset threshold, the processing area is marked as a target processing area;

[0030] A target geometric area set is constructed based on all the target processing areas.

[0031] Through the above examples, the system establishes a time-series-based method for analyzing process data fluctuation characteristics. By monitoring data fluctuations in different areas, it accurately identifies potential high-risk areas. This continuous data monitoring mechanism can promptly capture abnormal fluctuations in the processing process and effectively prevent quality issues from occurring.

[0032] In some embodiments, after the step of determining the target geometric area having the defect risk score exceeding a preset risk threshold as a target critical area for process inspection and allocating resources, the method further includes:

[0033] Obtaining the candidate critical areas and non-critical areas determined during the design phase of the part to be inspected;

[0034] A first spatial overlap portion between the target key area and the non-key area is adjusted to be the to-be-selected key area.

[0035] Through the above-described embodiment, the system integrates and optimizes dynamically identified target key areas with areas determined during the design phase, establishing a mechanism for determining inspection areas that balances design requirements with actual production conditions. This approach ensures that necessary design requirements are met while allowing for flexible adjustment of inspection strategies based on actual production conditions.

[0036] In some embodiments, after the step of adjusting the first spatial overlap portion between the target key area and the non-key area as the to-be-selected key area, the method further includes:

[0037] Dividing the regional priorities corresponding to different target geometric areas in the selected key area according to the risk assessment result of the part to be inspected in the design phase, wherein the area corresponding to the first spatial overlapping portion has the lowest priority;

[0038] The region priority is adjusted according to a second spatial overlap portion between the target key region and the selected key region, so that the region priority corresponding to the second spatial overlap portion is the highest.

[0039] Through the above-mentioned implementation, the system introduces a dynamic adjustment mechanism for regional priorities. By analyzing the spatial overlap of different types of key areas, it achieves intelligent allocation of inspection priorities. This multi-dimensional prioritization method ensures that inspection resources can maximize coverage of high-risk areas, further improving inspection efficiency.

[0040] In a second aspect, the present application provides an equipment inspection control system, the equipment inspection control system comprising: one or more processors and a memory;

[0041] The memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions so that the equipment inspection control system can implement a dynamic critical area process inspection method based on real-time data driving provided in the above embodiment, which will not be repeated here.

[0042] On the third aspect, the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on an equipment inspection control system, the equipment inspection control system can implement a dynamic critical area process inspection method based on real-time data driving provided in the above embodiment, which will not be repeated here.

[0043] Fourthly, the present application provides a computer program product. When the computer program product runs on an equipment inspection and control system, the equipment inspection and control system can implement a dynamic critical area process inspection method based on real-time data driving provided in the above embodiment, which will not be repeated here.

[0044] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0045] 1. By collecting real-time process behavior data, a dynamic quality batch division and critical area identification mechanism has been established. Based on actual data fluctuations during the production process, the system intelligently identifies areas requiring focused inspection and dynamically allocates inspection resources in real time. This ensures that inspection resources are precisely allocated to high-risk areas, avoids over-inspection of low-risk areas, and ensures that emerging potential risk areas are not missed, fundamentally improving the efficiency of inspection resource utilization.

[0046] 2. By establishing a correspondence between process parameter fluctuations and the granularity of processing area divisions, and combining part machining feature dimensions, precision requirements, and historical data distribution characteristics, a multi-level, fine-grained, adaptive area division system was constructed. This mechanism achieves precise position calibration using production trajectory data and continuously monitors data fluctuations based on time series analysis. This ensures that the division of inspection areas meets technical requirements while allowing for flexible adjustments based on actual production status, providing a reliable spatial positioning foundation for precise inspection.

[0047] 3. Intelligently integrate dynamically identified target key areas with pre-set areas during the design phase. By analyzing the spatial overlap of different key areas, a dynamic adjustment mechanism for inspection priorities based on multi-dimensional analysis has been established. This integrated optimization strategy not only ensures that design requirements are met, but also allows for flexible adjustment of inspection strategies based on actual production conditions, maximizing the accuracy of inspection coverage and the efficiency of resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flow chart of a dynamic key area process inspection method based on real-time data drive in an embodiment of the present application;

[0049] Figure 2 This is another flow chart of a dynamic key area process inspection method based on real-time data driving in an embodiment of the present application;

[0050] Figure 3 It is a schematic diagram of the structure of a physical device of the equipment inspection control system in the embodiment of the present application. DETAILED DESCRIPTION

[0051] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0052] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0053] For ease of understanding, the following describes the process of the method provided by this implementation. Figure 1 , which is a flow chart of a dynamic key area process inspection method based on real-time data driving in an embodiment of the present application.

[0054] S101. Divide the parts to be inspected into different quality batches according to the parameter value ranges to which the process behavior data corresponding to the parts to be inspected belong.

[0055] Among them, process behavior data refers to the physical parameters collected by multiple types of sensors deployed on production equipment during the production process of the parts to be inspected. These data reflect the process status of the parts during production, including but not limited to temperature, vibration, pressure, etc.

[0056] This step is executed before the system performs process inspection on parts. It is applied to the quality inspection scenario of batch-produced parts on the production line. By dividing the quality batches, more targeted inspection plans can be formulated according to the characteristics of different batches.

[0057] Specifically, the equipment inspection control system first receives process behavior data of the parts to be inspected, collected by multiple types of sensors deployed on the production equipment. It then analyzes this data to determine the parameter value range to which each data point belongs. Based on the different parameter value ranges, the parts to be inspected are divided into different quality batches. For example, if the temperature parameter value range during production of a certain type of part is A, the parts produced are classified as quality batch 1; if the temperature parameter value range is B, the parts produced are classified as quality batch 2. Different quality batches correspond to different processing area division rules.

[0058] In some embodiments, quality batches can be divided based on process behavior data in a variety of ways: Optionally, the system pre-sets multiple parameter value ranges and compares the collected process behavior data against these ranges. If the data falls within a certain range, the corresponding part is assigned to the quality batch corresponding to that range. For example, if the temperature range is set to [80 - 90]°C for quality batch A and [91 - 100]°C for quality batch B, and the temperature data for a part is detected to be 85°C during production, the part is assigned to quality batch A.

[0059] Optionally, clustering algorithms can be used to analyze process behavior data. First, the process behavior data for all parts to be inspected is imported into a clustering algorithm model. The algorithm automatically groups the data into clusters based on similarities, with each cluster corresponding to a quality batch. For example, using the K-means clustering algorithm, based on the combined similarities of multiple process behavior data such as temperature and pressure, parts can be divided into three quality batches, each corresponding to different process characteristics.

[0060] S102 . In the same quality batch, a mapping relationship between the process behavior data and the processing area of ​​the target part is established based on the process behavior data of the target part produced in the same time period and the part processing positions corresponding to multiple acquisition timestamps of the process behavior data.

[0061] Among them, the collection timestamp is used to mark the specific time point of process behavior data collection. The timestamp can be used to determine the processing progress of the part when the data is collected; the part processing position represents the specific processing position of the target part on the production equipment at different collection time points, which is used to determine the spatial location where the process behavior occurs; the processing area is a collection of multiple part processing positions, representing different processing locations in the part production process.

[0062] Specifically, the equipment inspection and control system collects the process behavior data of the target parts in the same quality batch within the same time period, as well as the collection timestamps and part processing position information corresponding to these data. Then, the process behavior data under each timestamp is associated with the corresponding part processing position, and the data with the same or similar processing positions are classified into a processing area, thereby establishing a mapping relationship between the process behavior data and the target part processing area. For example, in a certain quality batch, the temperature data collected at 10:00 for the target part is 85°C, and the part processing position is point A. The temperature data collected at 10:05 is 86°C, and the processing position is point B. If points A and B are close, the two data can be associated with the corresponding positions to construct a mapping relationship to the same processing area.

[0063] In some embodiments, the mapping relationship can be constructed in a variety of ways: Optionally, first create an empty mapping table with columns for process behavior data, acquisition timestamp, and part processing location. Then, all process behavior data records for the target parts in the same quality batch are traversed, and the data in each record is filled into the mapping table according to the column definitions. Finally, the data in the mapping table is grouped according to the similarity of the part processing locations, with each group corresponding to a processing area, thereby completing the construction of the mapping relationship. For example, adjacent locations are considered close if the distance is less than 1 cm, and the mapping table data is grouped according to this rule.

[0064] S103 , based on the mapping relationship, select target processing regions whose fluctuation characteristics of process behavior data corresponding to the acquisition timestamp exceeds a preset threshold from multiple processing regions corresponding to the target part to construct a target geometric region set.

[0065] After successfully building the mapping relationship between process behavior data and processing areas (i.e., step S102 is completed), this step is performed when it is necessary to identify processing areas that may have quality risks.

[0066] Specifically, the equipment inspection and control system obtains the corresponding process behavior data and its acquisition timestamp for each processing area of ​​the target part based on the mapping relationship established in S102. It then analyzes the fluctuation characteristics of this data (including fluctuation frequency, fluctuation amplitude, and fluctuation trend), and then compares the fluctuation frequency, fluctuation amplitude, and fluctuation trend with the corresponding preset thresholds. When any of the fluctuation characteristics of the process behavior data corresponding to a certain processing area exceeds the preset threshold, the processing area is marked as a target processing area. Finally, all marked target processing areas are integrated to form a target geometric area set. For example, if the preset fluctuation amplitude threshold is 5°C, if the temperature data fluctuation amplitude in a certain processing area reaches 6°C, then the processing area is determined to be a target processing area, and all similar areas constitute the target geometric area set.

[0067] It should be noted that the process behavior data includes multiple physical parameters. When the fluctuation characteristics corresponding to any physical parameter exceeds the corresponding preset threshold, the processing area corresponding to the physical parameter is determined to be the target processing area.

[0068] S104: Input the process behavior data corresponding to each target geometric area in the target geometric area set into a preset risk prediction model, and output a defect risk score corresponding to each target geometric area.

[0069] Specifically, the equipment inspection and control system obtains the target geometric area set obtained in S103, and extracts the corresponding process behavior data for each target geometric area in the set. Then, these process behavior data are sequentially input into the preset risk prediction model. The risk prediction model analyzes and processes the input data based on the relationship between process behavior data and defect risk learned in advance, and finally outputs the defect risk score corresponding to each target geometric area. For example, if the process behavior data corresponding to target geometric area A shows large temperature fluctuations and unstable pressure, the risk prediction model combines the correlation between similar process behaviors and defect occurrences in historical data and gives the area a defect risk score of 80 points (out of 100 points), indicating that the area has a high defect risk.

[0070] It should be noted that when building the risk prediction model, the system collects a large amount of historical process behavior data collected by multiple types of sensors during the production process, including parameters such as temperature and pressure, and records the corresponding historical defect risk scores. The data is then preprocessed to address missing values ​​and standardize or normalize the data to eliminate scale differences. An appropriate model is selected based on the data characteristics, such as a multilayer perceptron neural network that can handle complex nonlinear relationships. After dividing the data into training and test sets, training begins. Predictions are calculated through forward propagation, and errors are calculated using a loss function. Backpropagation and gradient descent are then used to update the weights to fit the model to the data. The model is then evaluated using the test set, and performance is measured by metrics such as accuracy and mean squared error. Optimization is then performed based on the evaluation results, with methods such as increasing the amount of data in case of overfitting and increasing model complexity in case of underfitting, until the model performance reaches the expected level.

[0071] In some embodiments, the output of a defect risk score using a risk prediction model can be achieved in a variety of ways: Optionally, a neural network model can be used as a risk prediction model. First, the process behavior data of the target geometric area is preprocessed, and the data is standardized or normalized to meet the input requirements of the neural network. Then, the processed data is input into the trained neural network model, and the neurons in the model calculate and transmit the data layer by layer according to the pre-trained weights and thresholds. Finally, the corresponding defect risk score is obtained through the output layer of the model. For example, a multi-layer perceptron (MLP) neural network is used, where the input layer receives the process behavior data, the hidden layer performs feature extraction and complex nonlinear transformation, and the output layer gives the defect risk score.

[0072] S105: Determine the target geometric area where the defect risk score exceeds a preset risk threshold as a target critical area for process inspection and allocate resources.

[0073] Specifically, the equipment inspection control system obtains the defect risk score for each target geometric area obtained in step S104 and reads a pre-set risk threshold. The defect risk score of each target geometric area is compared with the preset risk threshold one by one. When the defect risk score of a target geometric area is greater than the preset risk threshold, the target geometric area is determined as a target critical area for process inspection. After determining the target critical areas, the system allocates inspection resources to these areas according to a pre-established resource allocation strategy. For example, if the preset risk threshold is 60 points and the defect risk score of target geometric area B is 75 points, then area B is determined to be a target critical area, and the system can arrange more inspection personnel, more advanced inspection equipment, and longer inspection time to inspect this area.

[0074] Optionally, the system can utilize intelligent optimization algorithms for resource allocation. For example, using a genetic algorithm, information about the target critical area (such as defect risk score, area location, etc.) is first encoded to form an initial population. A fitness function is then defined to evaluate the performance of each individual (i.e., resource allocation plan). The fitness function can comprehensively consider factors such as inspection cost and inspection effectiveness. The population is then continuously optimized through genetic operations such as selection, crossover, and mutation, ultimately resulting in the optimal resource allocation plan. For example, after multiple iterations, the genetic algorithm determined that for a certain high-risk target critical area, three experienced inspectors and two high-precision inspection equipment should be assigned to achieve the best inspection results.

[0075] In the above-mentioned embodiment, the system dynamically divides quality batches and critical inspection areas using real-time collected process behavior data, breaking through the limitations of fixed inspection areas in traditional inspection methods. Based on actual data fluctuations during the production process, the system intelligently identifies areas that truly require focused inspection and dynamically allocates inspection resources accordingly. This data-driven dynamic inspection approach ensures that inspection resources are more precisely allocated to high-risk areas, to a certain extent avoiding over-inspection of low-risk areas, thereby improving the efficiency of inspection resource utilization.

[0076] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of a dynamic critical area process inspection method based on real-time data driving in an embodiment of the present application.

[0077] S201 , calculating parameter fluctuation values ​​corresponding to the process behavior data based on the differences between the process behavior data corresponding to all parts to be inspected and the preset ideal process behavior data.

[0078] Among them, the preset ideal process behavior data is pre-set, representing the data standard that the process behavior should present during the parts production process under ideal production conditions, and is used to measure the deviation of actual production data.

[0079] This step is performed before dividing quality batches based on the process behavior data of the parts to be inspected. It is suitable for production scenarios that require high production process stability and product quality consistency. By calculating parameter fluctuation values, you can initially assess the fluctuations in the production process and provide data for subsequent quality batch division and inspection area division.

[0080] Specifically, the equipment inspection and control system obtains the process behavior data corresponding to all parts to be inspected and simultaneously calls upon the preset ideal process behavior data. For each piece of process behavior data, it is compared with the corresponding preset ideal process behavior data and the difference between the two is calculated. For example, if the actual temperature data during production of a part to be inspected is 90°C and the preset ideal temperature data is 85°C, the fluctuation value of this temperature parameter is 90 - 85 = 5°C. By calculating the differences corresponding to all process behavior data, the corresponding parameter fluctuation values ​​are obtained, which reflect the difference between the actual production process and the ideal state.

[0081] S202: Divide the parameter fluctuation value into multiple parameter fluctuation ranges based on a preset ratio to obtain multiple corresponding parameter value ranges.

[0082] The equipment inspection and control system divides the parameter fluctuation values ​​obtained in step S201 according to a pre-set ratio. For example, the pre-set ratio divides the parameter fluctuation values ​​into three intervals: one interval for fluctuation values ​​within the range of 0-2, another interval for fluctuation values ​​between 2-5, and another interval for fluctuation values ​​greater than 5. These three intervals constitute the parameter fluctuation ranges. Based on these parameter fluctuation ranges, the corresponding parameter value ranges for the process behavior data are then determined. For example, for a temperature parameter, if the parameter fluctuation value is within the range of 0-2, the corresponding actual temperature parameter value range may be 83-87°C; if the parameter fluctuation value is within the range of 2-5, the corresponding temperature parameter value range may be 80-90°C, and so on. Furthermore, different processing area division granularities are set for different parameter value ranges. For example, for parameter value ranges with small fluctuations (corresponding to parameter fluctuation values ​​of 0-2), a larger division granularity can be used to divide the processing area into fewer but larger areas. For parameter value ranges with large fluctuations (corresponding to parameter fluctuation values ​​greater than 5), a smaller division granularity can be used to divide the processing area into more and smaller areas, allowing for more detailed inspection.

[0083] Optionally, the system can configure preset ratios and corresponding parameter value range rules in the rule engine. For example, when the parameter fluctuation value is less than or equal to 2, the corresponding parameter value range has a lower limit of the ideal value - 3 and an upper limit of the ideal value + 3; when the parameter fluctuation value is greater than 2 and less than or equal to 5, the corresponding parameter value range has a lower limit of the ideal value - 5 and an upper limit of the ideal value + 5, and so on. The calculated parameter fluctuation value is then input into the rule engine, which automatically divides the parameter fluctuation range according to the preset rules and determines the corresponding parameter value range. Finally, the division results are stored in the database for subsequent use.

[0084] In the above example, the system calculates the degree of deviation between process behavior data and ideal data, establishing a mechanism for aligning different parameter value ranges with different processing area granularity. This multi-level granularity, based on actual processing parameter fluctuations, allows for more targeted inspection area division, allowing for the selection of appropriate inspection granularity based on the actual processing status of different product batches, avoiding resource waste caused by overly coarse or overly detailed granularity.

[0085] S203. Based on the processing feature size and processing accuracy requirements of the parts, construct a multi-level fine-grained division level of the processing area.

[0086] The equipment inspection and control system acquires information about the part's machining feature dimensions and machining accuracy requirements. For example, for a precision shaft part, the machining feature dimensions may include the shaft diameter and length, and the machining accuracy requirement may be a diameter tolerance within ±0.01mm. Based on this information, the system constructs a multi-level, fine-grained classification system for the machining area. Assuming three levels are constructed, Level 1 corresponds to larger area divisions and is suitable for areas with relatively low machining accuracy requirements and small variations in machining feature dimensions; Level 2 has the next highest divisions; and Level 3 corresponds to the smallest area divisions and is used for areas with extremely high machining accuracy requirements and critical machining feature dimensions. For shaft parts, non-critical parts of the shaft might be classified as Level 1, with the machining area divided according to a larger size range; critical areas, such as those near bearing mating points, might be classified as Level 3, with smaller size ranges to ensure more detailed inspection of the machining accuracy of these critical areas.

[0087] S204: Setting a preset parameter range corresponding to each fine-grained division level based on parameter fluctuation value distribution characteristics in historical processing data.

[0088] Specifically, the equipment inspection and control system collects and organizes historical processing data, extracting parameter fluctuations. It then performs statistical analysis on these parameter fluctuations, calculating their distribution characteristics, such as the mean and standard deviation, and observing the distribution pattern. For example, it is found that the parameter fluctuations of a certain type of part in a certain processing area exhibit a normal distribution, with a mean of 3 and a standard deviation of 1. Based on these distribution characteristics and in conjunction with the fine-grained classification levels established in step S203, preset parameter ranges are set for each level. For level 1 (coarser granularity), the preset parameter range can be set to mean ± 2 times the standard deviation, i.e., 1 - 5; for level 2, the range is set to mean ± 1.5 times the standard deviation, i.e., 1.5 - 4.5; and for level 3 (finest granularity), the range is set to mean ± 1 times the standard deviation, i.e., 2 - 4. In this way, different fine-grained classification levels correspond to different preset parameter ranges. This allows for a more accurate assessment of the quality status of the processing area during subsequent inspections by comparing actual process behavior data with the preset parameter ranges.

[0089] S205 , calculating the overlap ratio of the parameter fluctuation values ​​within each parameter value range in the preset parameter range; and determining the fine-grained division level corresponding to the preset parameter range with the largest overlap ratio as the fine-grained division level corresponding to the parameter value range.

[0090] This step is performed after completing the construction of the multi-level fine-grained division level of the processing area (S203), setting the preset parameter range corresponding to each fine-grained division level (S204), and determining the parameter value range (S202).

[0091] Specifically, for each parameter value range determined in step S202, the equipment inspection and control system obtains all parameter fluctuation values ​​within that range. These parameter fluctuation values ​​are then compared with the preset parameter ranges set for each fine-grained division level in step S204. For example, assuming there are 100 parameter fluctuation values ​​within a parameter value range, 60 of which fall within the preset parameter range of level 1, 30 fall within the preset parameter range of level 2, and 10 fall within the preset parameter range of level 3, then the overlap percentages of this parameter value range with the preset parameter ranges of levels 1, 2, and 3 are 60%, 30%, and 10%, respectively. The system calculates the overlap percentages of all parameter value ranges with each preset parameter range and determines the fine-grained division level corresponding to the preset parameter range with the largest overlap percentage as the fine-grained division level corresponding to that parameter value range. For example, if a parameter value range has the largest overlap percentage with the preset parameter range of level 2, then level 2 is determined as the fine-grained division level corresponding to that parameter value range. This ensures that the regional division granularity is more aligned with current production conditions.

[0092] In the above example, the system established a multi-level, fine-grained classification hierarchy based on the part's machining feature dimensions and precision requirements, and determined the optimal classification hierarchy through historical data analysis. This adaptive regional division approach considers both the product's technical requirements and the distribution characteristics of actual production data, making regional division more scientific and reasonable and better guiding the allocation of inspection resources.

[0093] S206 , obtaining production trajectory data of the target part; calibrating the part processing positions of the target part corresponding to different acquisition time stamps based on the production trajectory data to obtain the calibrated part processing positions.

[0094] The equipment inspection and control system acquires the target part's production trajectory data through a communication interface or data storage system with the production equipment. This data may be stored as files, database records, or real-time data streams. The system then reads the motion trajectory and processing speed information contained in this production trajectory data. For example, it obtains the X, Y, and Z coordinate changes of the machining tool relative to the target part over a certain period of time, along with the corresponding speed data. The production trajectory data is then correlated with the part's processing position data based on the acquisition timestamp. Because the accuracy of part processing position data may be affected by factors such as equipment vibration and measurement errors in actual production, the system uses a specific algorithm to calibrate the part processing positions corresponding to different acquisition timestamps based on the motion trajectory and speed information in the production trajectory data. For example, the measured part processing position is corrected based on the changing patterns of processing speed and motion trajectory. The resulting calibrated part processing position is more accurate, laying the foundation for the subsequent establishment of a precise mapping between process behavior data and processing areas.

[0095] Optionally, the system can also utilize sensor fusion technology and algorithm compensation. First, a variety of sensors, such as position sensors, speed sensors, etc., are installed on the production equipment to collect the production trajectory data of the target parts in real time. Then, the data collected by these sensors are fused and processed to remove noise and outliers. For example, the Kalman filter algorithm is used to fuse multiple sensor data to improve the accuracy of the data. Then, based on the fused data, combined with the pre-established equipment motion model and error model, the part processing position data is calibrated. For example, by analyzing factors such as transmission error and positioning error in the equipment motion model, the measured part processing position is compensated and adjusted to obtain the calibrated part processing position.

[0096] S207. After determining the target critical area for process inspection, obtain the candidate critical area and non-critical area determined in the design phase of the part to be inspected; and adjust the first spatial overlap portion of the target critical area and the non-critical area to the candidate critical area.

[0097] Specifically, after determining the target critical area for process inspection, the equipment inspection and control system obtains the information of the selected critical area and non-critical area of ​​the part to be inspected from the relevant documents, databases or systems in the design stage. Then, the first spatial overlapping part of the target critical area and the non-critical area is determined through a spatial analysis algorithm or a related geometric calculation method. For example, the spatial analysis function in a three-dimensional modeling software or a spatial database is used to find the overlapping part of the two areas in space. For this overlapping area, the system adjusts it to a candidate critical area, which means that in the subsequent inspection process, this area will be subject to stricter inspection and attention, changing the inspection strategy that was originally defined as a non-critical area in the design stage, so that the division of the inspection area is more in line with the quality risk situation in actual production.

[0098] Optionally, the system can utilize computer-aided design (CAD) software in conjunction with a data analysis system. First, the part model from the design phase (including information on candidate critical and non-critical areas) is imported into the CAD software. Next, the target critical area data determined by the equipment inspection and control system is also imported into the software. Using the CAD software's spatial analysis tools, the first spatial overlap between the target critical area and the non-critical area is accurately calculated. Finally, through interaction with the data analysis system, the attribute information of this overlapping area is updated as a candidate critical area and stored in the corresponding database for subsequent inspection process invocation.

[0099] S208. Divide the regional priorities corresponding to different target geometric areas in the selected key areas according to the risk assessment results of the part to be inspected in the design phase.

[0100] The equipment inspection control system obtains the risk assessment results of the parts to be inspected during the design phase. These results are typically stored in documents, tables, or database records. It then prioritizes each target geometric area within the candidate critical areas based on the risk assessment results. For example, if the risk assessment indicates that a target geometric area involves the core functionality of the part and has a high probability of quality issues, the priority of that area is assigned higher. The target geometric area corresponding to the first spatial overlap is assigned the lowest priority, regardless of its risk assessment during the design phase. This is because these areas were originally designed as non-critical areas. Although they have been reclassified as candidate critical areas due to actual production conditions, they are still considered to have a lower risk than other areas designated as critical during the design phase, and therefore are given the lowest priority. In this way, the system establishes a clear inspection priority order for each target geometric area within the candidate critical areas, providing a basis for the rational allocation of subsequent inspection resources.

[0101] S209 , adjusting the region priority according to the second spatial overlapping portion between the target key region and the selected key region, so that the region corresponding to the second spatial overlapping portion has the highest priority.

[0102] The equipment inspection control system first determines the second spatial overlapping part of the target key area and the key area to be selected. This can be achieved through spatial analysis algorithms or related tools, such as using the Boolean operation function in the three-dimensional modeling software to find the intersection of the two area sets. For this part of the second spatial overlapping area, no matter how much priority it is assigned in step S208, the system adjusts its area priority to the highest. For example, in the previous priority division, a target geometric area originally had a medium priority, but it is in the second spatial overlapping part, then the system raises its priority to the highest. This is done because this part of the area not only meets the definition of the key area in the design stage, but is also identified as a high-risk area in actual production, so it needs to be given the highest inspection priority to ensure that this part of the area receives the most adequate inspection resources and focus, and minimizes quality risks.

[0103] In the above example, the system introduced a dynamic adjustment mechanism for regional priorities. By analyzing the spatial overlap of different types of key areas, it achieved intelligent allocation of inspection priorities. This multi-dimensional prioritization approach ensures that inspection resources can maximize coverage of high-risk areas, further improving inspection efficiency.

[0104] The device inspection control system according to the embodiment of the present invention is applied to electronic equipment. Figure 3 A schematic diagram of the architecture of an electronic device suitable for implementing an embodiment of the present invention is shown.

[0105] It should be noted that Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0106] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions (computer programs) or by controlling related hardware through instructions (computer programs), and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein the storage medium stores a plurality of instructions, which can be loaded by the processor to execute any step of the method provided in the embodiment of the present invention.

[0107] Specifically, the storage medium and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these elements can be electrically connected to each other via one or more signal lines. The storage medium stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium. The storage medium can be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The storage medium is used to store programs, and the processor executes the programs after receiving the execution instructions.

[0108] Furthermore, the software programs and modules in the above-mentioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip having signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which may implement or execute the various methods, steps, and logic flow diagrams disclosed in this embodiment. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0109] Since the instructions stored in the storage medium can execute the steps of any method provided in the embodiments of the present invention, the beneficial effects of any method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0110] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A dynamic key area process inspection method based on real-time data drive, applied to equipment inspection control system, characterized in that: The method comprises: Calculating the parameter fluctuation value corresponding to the process behavior data according to the difference between the process behavior data corresponding to all parts to be inspected and the preset ideal process behavior data; Dividing the parameter fluctuation value into a plurality of parameter fluctuation ranges based on a preset ratio to obtain a plurality of corresponding parameter value ranges, wherein the processing area division granularities corresponding to different parameter value ranges are not all the same; Based on the machining feature size and machining accuracy requirements of the parts, a multi-level fine-grained division level of the machining area is constructed, each of the fine-grained division levels corresponds to a different area division size; Setting a preset parameter range corresponding to each of the fine-grained division levels based on parameter fluctuation value distribution characteristics in historical processing data; Calculate the overlap ratio of the parameter fluctuation values ​​within each parameter value range within the preset parameter range; Determine the fine-grained division level corresponding to the preset parameter range with the largest overlap ratio as the fine-grained division level corresponding to the parameter value range; Divide the parts to be inspected into different quality batches based on the parameter value range of the process behavior data corresponding to the parts to be inspected. The process behavior data is collected during the production process of the parts to be inspected by multiple types of sensors deployed on production equipment. Different quality batches correspond to different processing area division rules; In the same quality batch, a mapping relationship between the process behavior data and the processing area of ​​the target part is established based on the process behavior data of the target part produced in the same time period and the part processing positions corresponding to multiple acquisition time stamps of the process behavior data, where the processing area includes multiple processing positions; Based on the mapping relationship, target processing regions whose fluctuation characteristics of process behavior data corresponding to the acquisition timestamps exceed a preset threshold are selected from the multiple processing regions corresponding to the target part to construct a target geometric region set, including: based on the mapping relationship, constructing a process behavior data sequence corresponding to each of the continuous acquisition timestamps according to one or more continuous acquisition timestamps corresponding to each processing region; when it is detected that the fluctuation characteristics of any process behavior data sequence corresponding to the processing region exceed a preset threshold, marking the processing region as a target processing region; and constructing a target geometric region set based on all the target processing regions, wherein the fluctuation characteristics include fluctuation frequency, fluctuation amplitude, and fluctuation trend; Inputting the process behavior data corresponding to each target geometric area in the target geometric area set into a preset risk prediction model, and outputting a defect risk score corresponding to each target geometric area, wherein the risk prediction model is trained based on historical process behavior data and corresponding historical defect risk scores; The target geometric area whose defect risk score exceeds a preset risk threshold is determined as a target critical area for process inspection for resource allocation.

2. The method according to claim 1, characterized in that Before the step of establishing a mapping relationship between the process behavior data and the processing area of ​​the target part according to the process behavior data of the target part produced in the same time period and the part processing positions corresponding to the multiple acquisition time stamps of the process behavior data in the same quality batch, the method further includes: Acquiring production trajectory data of the target part, the production trajectory data including a motion trajectory and a processing speed of a processing tool of a production equipment relative to the target part; The part processing positions of the target part corresponding to different acquisition time stamps are calibrated based on the production trajectory data to obtain the calibrated part processing positions.

3. The method according to claim 1, characterized in that After the step of determining the target geometric area having the defect risk score exceeding the preset risk threshold as a target critical area for process inspection and allocating resources, the method further includes: Obtaining the candidate critical areas and non-critical areas determined during the design phase of the part to be inspected; A first spatial overlap portion between the target key area and the non-key area is adjusted to be the to-be-selected key area.

4. The method according to claim 3, characterized in that After the step of adjusting the first spatial overlap portion between the target key area and the non-key area as the key area to be selected, the method further includes: Dividing the regional priorities corresponding to different target geometric areas in the selected key area according to the risk assessment result of the part to be inspected in the design phase, wherein the area corresponding to the first spatial overlapping portion has the lowest priority; The region priority is adjusted according to a second spatial overlap portion between the target key region and the selected key region, so that the region priority corresponding to the second spatial overlap portion is the highest.

5. An equipment inspection control system, characterized in that: The equipment inspection control system includes: one or more processors and memory; The memory is coupled to the one or more processors, and is used to store computer program codes, where the computer program codes include computer instructions. The one or more processors call the computer instructions to enable the equipment inspection control system to execute the method according to any one of claims 1 to 4.

6. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on an equipment inspection control system, the equipment inspection control system is caused to execute the method according to any one of claims 1 to 4.

7. A computer program product, characterized in that When the computer program product is run on an equipment inspection control system, the equipment inspection control system is caused to execute the method according to any one of claims 1 to 4.

Images