A digital processing system and method for the end of an air-conditioning compressor housing
By working collaboratively with the main control center and the height unit, point cloud data is acquired using sensors and scanning equipment. This data is then used to correct and cluster the height of the air conditioner compressor casing, constructing a collaborative processing map. This solves the problems of accuracy and efficiency in detecting the height of the air conditioner compressor casing, achieving a high-precision and high-efficiency processing process.
Patent Information
- Application Number
- CN202411131956.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-19
AI Technical Summary
In existing technologies, it is difficult to maintain the accuracy of height detection for the air conditioner compressor casing over a long period of time. Mechanical measuring instruments are affected by wear and tear, and the reliability of single-dimensional detection is low. As a result, it is difficult to detect defective products in a timely manner, and it is difficult to achieve equipment linkage adjustment during the production process, resulting in a high defect rate.
By combining the main control center with the first and second height units, point cloud data is acquired through front-end sensors and preset scanning equipment. Height correction and clustering are performed to construct a collaborative processing map, enabling real-time feedback and adjustment, thereby improving measurement accuracy and processing efficiency.
It improves the accuracy and consistency of air conditioner compressor casing height measurement, reduces the defect rate, enhances the flexibility and adaptability of the production process, and realizes closed-loop control and real-time optimization of the processing process.
Smart Images

Figure CN118732602B_ABST
Abstract
Description
Technical Field
[0001] The present specification relates to the field of intelligent production technology, and in particular to a system and method for digitally processing the end of an air-conditioning compressor casing. Background Art
[0002] The air-conditioning compressor plays the role of compressing and driving the refrigerant in the air-conditioning refrigerant circuit. The refrigerant is extracted from the low-pressure area, compressed, and sent to the high-pressure area for cooling and condensation, and then the heat is dissipated into the air through the heat sink, thereby achieving the cooling effect. The air-conditioning compressor housing is the external protection and support structure of the air-conditioning compressor. It is usually made of metal materials, such as stainless steel, aluminum alloy, etc., to withstand internal pressure, protect the internal structure and ensure the stable operation of the air-conditioning compressor. The air-conditioning compressor itself plays the role of refrigerant buffer in the refrigeration system, and the housing further enhances the realization of these functions. Since the height of the air-conditioning compressor housing affects the stability and safety of the accumulator operation, in the production and processing of the air-conditioning compressor housing, the accurate detection of the housing height, that is, the length, and the adoption of corresponding measures for subsequent disposal based on the height detection results are the key links to ensure the overall quality and operational stability of the produced accumulator.
[0003] At present, in the production and processing of air-conditioning compressor housings, the end-sealing forming device in the production line is generally tested based on a mechanical height measuring instrument. However, this method is often affected by factors such as wear or looseness of mechanical transmission parts, making it difficult to maintain measurement accuracy for a long time. This method of measuring by positioning may also cause unnecessary wear on the air-conditioning compressor housing during the measurement process. In addition, although the current detection method based on rangefinders can achieve higher accuracy and efficiency detection, the reliability of single-dimensional detection is low, and the products that fail the current height detection are generally detected after production. This lagging detection cannot timely detect possible defective products during the production process, and it is also difficult to achieve linkage between subsequent production equipment to adjust subsequent tool parameters to reduce wear and the generation of defective products. Summary of the invention
[0004] In order to solve the above-mentioned technical problems, one or more embodiments of the present specification provide a system and method for digitally processing the end of an air-conditioning compressor casing.
[0005] One or more embodiments of this specification adopt the following technical solutions:
[0006] One or more embodiments of this specification provide a digital intelligent treatment system for the end of an air-conditioning compressor housing, the system comprising:
[0007] The main control center includes a first height unit connected to the main control center, and each operation module control subsystem connected to the main control center based on a preset communication interface, and also includes a second height detection unit connected to the first height unit and the main control center;
[0008] The first height unit is used to obtain the workpiece height of the current air-conditioning compressor housing through the front sensor corresponding to the current operation module, so as to start the second height unit based on the detection result corresponding to the workpiece height;
[0009] The second height unit is used to obtain point cloud data corresponding to the current air-conditioning compressor housing through a preset scanning device, so as to correct the workpiece height based on the point cloud data to obtain an actual workpiece height;
[0010] The main control center is used to perform clustering processing on the historical processing events of each air-conditioning compressor housing, and determine the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events;
[0011] Determine the collaborative factors of the associated triggering event based on the data characteristics of the tool adjustment parameters to construct a collaborative processing map of the associated triggering event;
[0012] Receive the actual workpiece height fed back by the second height unit, and determine the designated collaborative processing map corresponding to the current air-conditioning compressor housing based on the actual workpiece height and the degree of matching between the basic processing data of the current operating module and the historical processing data, so as to perform feedback adjustment on the current operating unit based on the control subsystems of each operating module in combination with the designated collaborative processing map.
[0013] Optionally, in one or more embodiments of this specification, the first height unit is specifically used to:
[0014] Acquire an effective detection range of a front sensor corresponding to a current operation module, so as to acquire a workpiece height of the current air-conditioning compressor housing detected by the front position sensor when the current air-conditioning compressor housing reaches the effective detection range;
[0015] Determine a target workpiece height and a target error range based on the current order information of the air-conditioning compressor housing, and obtain a plurality of historical processing data matching the target workpiece height and the target error range;
[0016] Determine the height range of the current operation module according to the sorting and rejection quantity of the current operation module corresponding to the plurality of historical processing data;
[0017] Determining a workpiece height coverage range of the current air-conditioning compressor housing based on the workpiece height and an error value of the front sensor;
[0018] Determine a first detection result based on the overlap between the workpiece height coverage range and the height range of the current operation module; wherein the first detection result includes: qualified and unqualified;
[0019] If qualified, the current air-conditioning compressor housing is transmitted to the current operation module for processing;
[0020] If it fails, the second height unit is activated.
[0021] Optionally, in one or more embodiments of this specification, the second height unit is specifically used for:
[0022] Acquire point cloud data corresponding to the current air-conditioning compressor housing through a preset scanning device, and obtain a point cloud minimum bounding box corresponding to the current air-conditioning compressor housing based on the three-axis maximum and minimum values of the point cloud data;
[0023] Based on the region growing algorithm, the point cloud data within the minimum bounding box of the point cloud is screened to obtain the point cloud data to be identified;
[0024] Projecting the point cloud data to be identified into a two-dimensional space based on the intrinsic parameter matrix and the extrinsic parameter matrix of the preset scanning device to obtain two-dimensional projection data corresponding to the point cloud data;
[0025] Performing edge detection on the two-dimensional projection data based on a preset edge detection algorithm to obtain edge data of the current air-conditioning compressor housing, and converting the edge data into a parameter space to identify straight line data of the current air-conditioning compressor housing based on a peak point of the parameter space;
[0026] The straight line data is fitted based on the least square method, so as to correct the workpiece height based on the fitted straight line data to obtain the actual workpiece height.
[0027] Optionally, in one or more embodiments of the present specification, edge detection is performed on the two-dimensional projection data based on a preset edge detection algorithm to obtain edge data of the current air-conditioning compressor housing, and the edge data is converted into a parameter space to identify straight line data of the current air-conditioning compressor housing based on a peak point of the parameter space, specifically including:
[0028] Acquire the gradients of the two-dimensional projection data in multiple directions based on a preset multi-directional gradient operator, so as to determine a gradient map corresponding to the two-dimensional projection data based on the gradients in the multiple directions;
[0029] Acquire local maximum data in each direction of the gradient map as initial edge data, filter the initial edge data based on a preset bilateral filter, and obtain edge data of the current air-conditioning compressor housing;
[0030] Mapping the edge data to a parameter space, recording each edge data in the parameter space based on the accumulator data, determining a peak point in the parameter space, and converting the parameter corresponding to the peak point to a space corresponding to the two-dimensional projection data, to obtain initial straight line data of the current air-conditioning compressor housing;
[0031] The initial straight line data is filtered based on the height detection direction of the current air-conditioning compressor housing to obtain straight line data corresponding to the height detection direction.
[0032] Optionally, in one or more embodiments of the present specification, clustering is performed on the historical processing events of each air-conditioning compressor housing to determine the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events, specifically including:
[0033] Based on multiple data sources, historical processing events of each air-conditioning compressor housing are obtained, and the historical processing events are evenly divided according to a preset number of cluster centers to obtain multiple historical processing event groups, so as to randomly determine the historical processing events in each of the historical processing event groups as initial cluster centers;
[0034] Traversing the historical processing events in each of the historical processing event groups to determine the Euclidean distance between the historical processing events in each of the historical processing event groups and the initial cluster center, and clustering each of the historical processing events based on the Euclidean distance to obtain a plurality of cluster clusters;
[0035] Re-determining the location of the cluster center based on the historical processing events in each of the clusters, so as to iteratively obtain the clustering results of the historical processing events, and determine the optimal cluster corresponding to the clustering results;
[0036] Based on the historical processing events in each of the optimal clusters and the tool adjustment parameters corresponding to the historical processing events, the tool adjustment parameters corresponding to each of the historical processing events and the associated triggering events are determined.
[0037] Optionally, in one or more embodiments of the present specification, determining the collaborative factors of the associated triggering event based on the data characteristics of the tool adjustment parameters to construct a collaborative processing map of the associated triggering event specifically includes:
[0038] The tool adjustment parameters are collected, and the tool adjustment parameters are sorted based on a plurality of attribute information corresponding to the tool adjustment parameters to obtain a multi-dimensional tool adjustment parameter sequence; wherein the attribute information at least includes: adjustment object, time sequence, and spatial position;
[0039] Converting the multidimensional tool adjustment parameter sequence corresponding to the same associated trigger event into a multidimensional tool adjustment parameter distribution diagram, and determining the first coordination factor of the associated trigger event based on the overlap of the attribute information of the multidimensional tool adjustment parameter distribution diagram;
[0040] Determining a second coordination factor triggering the associated triggering event based on the operation device logic log corresponding to each associated triggering event;
[0041] Aggregate the first collaborative factor and the second collaborative factor as the collaborative factors of the associated trigger event, use the collaborative factors as graph edges and the associated trigger event as nodes to construct a collaborative processing graph of the associated trigger event; wherein the collaborative processing graph is one or more connected graphs.
[0042] Optionally, in one or more embodiments of the present specification, based on the actual workpiece height and the matching degree between the basic processing data of the current operation module and the historical processing data, determining the designated collaborative processing map corresponding to the current air-conditioning compressor housing specifically includes:
[0043] Filtering the first historical processing data corresponding to the actual workpiece height in the historical processing data;
[0044] Determining matching historical processing data corresponding to the basic processing data according to a matching degree between the basic processing data and the first historical processing data;
[0045] The historical processing events corresponding to the matching historical processing data are obtained to determine the designated collaborative processing map corresponding to the current air-conditioning compressor housing according to the collaborative factors included in the historical processing events.
[0046] Optionally, in one or more embodiments of this specification, the main control center is also used for:
[0047] If it is determined that the current air-conditioning compressor housing has completed the production and processing of the current operating unit, the current operating unit is restored based on the standard tool parameters stored in the operating module control subsystem;
[0048] Determining whether the defective rate of the current air-conditioning compressor housing is lower than a preset defective rate value;
[0049] If so, the tool adjustment parameters of the current operating unit are recorded, and the tool adjustment parameters of the current operating unit are marked based on the actual workpiece height of the current air-conditioning compressor housing and the corresponding designated collaborative processing map.
[0050] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:
[0051] Through the cooperation of the first height unit and the second height unit, the actual workpiece height of the current air-conditioning compressor housing can be obtained more accurately. The workpiece height is first obtained by the front sensor, and then the point cloud data is obtained by the preset scanning device for correction, which improves the accuracy of height measurement. It also avoids the problem of high defective rate and ineffective equipment processing cost loss caused by re-detection after production. The main control center clusters the historical processing events of each air-conditioning compressor housing, determines the tool adjustment parameters and associated trigger events, and constructs a collaborative processing map, which makes full use of historical data, provides valuable reference for current processing, and helps to improve the efficiency and quality of processing. After considering the collaborative factors of tool adjustment parameters and associated trigger events to construct the collaborative processing map, the specified collaborative processing map is determined according to the actual workpiece height and the matching degree between the basic processing data of the current operation module and the historical processing data, and the personalized feedback adjustment of the current operation unit is realized. It can better adapt to the characteristics and processing requirements of different workpieces, and improve the adaptability and flexibility of processing. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:
[0053] Figure 1 A schematic diagram of a digital intelligent treatment system for the end of an air-conditioning compressor housing provided in an embodiment of this specification;
[0054] Figure 2 A processing schematic diagram of a digital intelligent processing system for an end portion of an air-conditioning compressor housing in an application scenario provided by an embodiment of this specification;
[0055] Figure 3 A schematic diagram of a process for determining a collaborative processing map provided in an embodiment of this specification;
[0056] Figure 4 A schematic flow chart of a method for digitally processing the end of an air-conditioning compressor casing provided in an embodiment of this specification. DETAILED DESCRIPTION
[0057] The embodiments of this specification provide a system and method for digitally processing the end of an air-conditioning compressor casing.
[0058] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.
[0059] like Figure 1 As shown, the embodiment of this specification provides a schematic diagram of a digital intelligent treatment system for the end of an air-conditioning compressor housing. Figure 1 It can be known that in one or more embodiments of the present specification, a digital intelligent disposal system for the end of an air-conditioning compressor housing is provided, and the system includes: a first height unit connected to the main control center by a main control center, and each operation module control subsystem connected to the main control center based on a preset communication interface, and also includes a second height detection unit connected to the first height unit and the main control center. Among them, the first height unit is used to obtain the workpiece height of the current air-conditioning compressor housing through the front sensor corresponding to the current operation module, so that the detection result corresponding to the workpiece height determines whether to start the second height unit. If the height is determined to be not in compliance with the requirements based on the detection result, in order to determine that the detection result is reliable and reduce the loss rate, the second unit will be started at this time, and the second height unit is used to obtain the point cloud data corresponding to the current air-conditioning compressor housing through a preset scanning device, so as to correct the workpiece height according to the point cloud data to obtain the actual workpiece height. By introducing the second height detection unit and the preset scanning device to obtain the point cloud data and correct the workpiece height, the measurement accuracy of the workpiece height is greatly improved. This high-precision measurement ensures the accuracy and consistency in the subsequent processing process and reduces the scrap rate caused by dimensional errors.
[0060] The main control unit in the system is used to cluster the historical processing events of each air-conditioning compressor housing, and determine the tool adjustment parameters and associated trigger events corresponding to each historical processing event. It should be noted that the historical processing events of each air-conditioning compressor housing in the process include detailed information of each processing event, such as processing time, tool type; tool adjustment parameters such as cutting speed, feed rate, cutting depth, etc.; processing results, such as dimensional accuracy, surface quality. And any possible associated trigger events, such as tool wear, machine tool failure, material change, etc. And these historical processing events have undergone data preprocessing stages such as data cleaning, data formatting, and data standardization. The historical processing events obtained for clustering processing can be grouped according to the similarity of tool adjustment parameters and associated trigger events based on clustering algorithms such as K-means, hierarchical clustering, DBSCAN, etc. For example, if a series of processing events are very close in tool adjustment parameters and are accompanied by similar associated trigger events such as tool wear to a certain extent, then these events may be classified into the same category. Then, the main control center will determine the synergistic factors of the associated trigger events based on the data characteristics of the tool adjustment parameters, and then according to the synergistic processing map of the associated trigger events. Collaborative factors refer to those factors that can affect the occurrence of multiple associated trigger events at the same time. They may include adjustment objects, time sequence, spatial position, and processing conditions such as temperature and humidity, and machine tool status such as stability and accuracy. Based on the above analysis, a collaborative processing map is constructed. This map is a visual representation that shows the complex relationship between different processing events, tool adjustment parameters, associated trigger events, and collaborative factors. This facilitates the processing adjustment of the operation module in advance based on the collaborative processing map, reducing the processing defective products of the air-conditioning compressor housing.
[0061] Then, in order to solve the problem that it is difficult to realize real-time feedback in the existing technology, the main control center cannot realize the linkage disposal between equipment based on the detection results, resulting in the problem that the highly unqualified air-conditioning compressor casing is not detected until after production. The main control center will receive the actual workpiece height feedback from the second height unit based on the connection relationship with the second height unit, and determine the designated collaborative processing map corresponding to the current air-conditioning compressor casing based on the actual workpiece height and the matching degree between the basic processing data of the current operation module and the historical processing data, so as to feedback and adjust the current operation unit according to the control subsystem of each operation module combined with the designated collaborative processing map. Based on the real-time reception and processing of feedback information during the workpiece processing process, the system can dynamically adjust the processing strategy to realize the closed-loop control and real-time optimization of the air-conditioning compressor casing processing process, and improve the production efficiency while ensuring the quality of the workpiece based on the automatic adjustment of the collaborative operation module.
[0062] Specifically, in one or more embodiments of the present specification, the first height unit is specifically used to: obtain the effective detection range of the front sensor corresponding to the current operation module, so that when the current air-conditioning compressor housing reaches the effective detection range, the workpiece height of the current air-conditioning compressor housing detected by the front position sensor is obtained. The limitation based on the effective detection range of the front sensor can ensure that the measurement is started only when the workpiece enters this range, thereby avoiding the generation of invalid measurements and erroneous data. Through the detection of the front position sensor, the detection process is advanced to the disposal of the operation module, so as to facilitate the adjustment of the tool parameters of the operation module based on the feedback of the detection results and thus reduce the defective rate of the air-conditioning compressor housing. Then, based on the order information of the current air-conditioning compressor housing, the target workpiece height and the target error range are determined, and multiple historical processing data matching the target workpiece height and the target error range are obtained. Setting the target height and error range according to the specific order requirements makes the production process more flexible and can meet the needs of different customers. Using historical data to guide current production can reduce the trial and error cost by relying on historical experience, and improve production efficiency and success rate. Then, since the unqualified air-conditioning compressor shell may be sorted and removed before the processing of the operating module, the air-conditioning compressor shell may be eliminated or related processing may be performed based on other operating modules. Therefore, in order to more scientifically set the height range of the current operating module to reduce the probability of unqualified products, the height range of the current operating module will be determined according to the sorting and rejection number of the current operating module corresponding to multiple historical processing data, that is, the height range of the current operating module is determined by the average of the workpiece height ranges in multiple historical processing data that are less than the preset sorting and rejection number value according to the sorting and rejection number. Then, in order to consider the influence of the measurement error on the result, the final height detection is made more accurate and reliable. According to the error value between the workpiece height and the front sensor, the workpiece height coverage range of the current air-conditioning compressor shell is determined by adding the error value to the workpiece height of the current air-conditioning compressor shell. For example: the height of the workpiece of the current air-conditioning compressor shell detected is 270mm, and the error value of the front sensor is within 3mm, then the height coverage range of the workpiece of the current air-conditioning compressor shell is 267mm-273mm. Then, the first detection result is determined based on the overlap between the workpiece height coverage range and the height range of the current operating module, that is, whether the height range of the current operating module is within the workpiece height coverage range of the current air-conditioning compressor housing. It should be noted that the first detection result includes: qualified and unqualified. If qualified, the current air-conditioning compressor housing is transferred to the current operating module for processing. If unqualified, the second height unit is started. By directly transferring qualified workpieces to the current operating module for processing, pre-processing detection is achieved, which avoids invalid processing of the current operating module and improves production efficiency.For unqualified workpieces, the second height unit is activated for further testing to ensure product quality. Through diversion processing, the flexibility of the automated production and processing process is improved while ensuring product quality.
[0063] In another embodiment of the present specification, Figure 2 As shown, after the current air-conditioning compressor housing is loaded, the first height unit is specifically used to obtain the workpiece height of the current air-conditioning compressor housing through the front sensor and the rear sensor corresponding to the current operating module, such as the chamfering machine equipment, so as to feedback and adjust the current operating unit based on the workpiece height. Specifically, in this embodiment, the first height unit obtains the effective detection range of the front sensor corresponding to the current operating module, so that when the current air-conditioning compressor housing reaches the effective detection range, the first workpiece height of the current air-conditioning compressor housing detected by the front sensor is obtained, and then the second workpiece height detected by the rear sensor of the chamfering machine is obtained. It should be noted that during the detection process, the current air-conditioning compressor housing can be grabbed by a double-station robot arm to the current operating module, for example, by a double-station robot arm to the chamfering machine equipment. Then, based on the order information of the current air-conditioning compressor housing, the target workpiece height and the target error range are determined, and multiple historical processing data matching the target workpiece height and the target error range are obtained; the height range of the current operating module is determined according to the sorting and rejection quantity of the current operating module corresponding to the multiple historical processing data; the workpiece height coverage range of the current air-conditioning compressor housing is determined based on the workpiece height and the error value of the front sensor, and the second workpiece height is compared with the workpiece height coverage range to determine whether the current air-conditioning compressor housing meets the requirements, and if so, continue with subsequent processing. If not, the processing height of the current operating module is determined based on the first workpiece height and the second workpiece height, and the adjustment height of the processing height relative to the workpiece height coverage range is determined, so as to feedback and adjust the current operating module based on the adjustment height.
[0064] In this embodiment, the height of the workpiece of the air-conditioning compressor housing is detected by the front and rear sensors, which can significantly improve the accuracy of height measurement. This dual detection mechanism helps to reduce measurement errors and ensure more accurate dimensional control during processing. At the same time, the automated detection and adjustment process improves processing efficiency and reduces the need for manual intervention. The system can automatically retrieve and match relevant historical processing data based on the target workpiece height and target error range in the order information. This flexibility enables the system to quickly adjust to different order requirements, enhancing the adaptability and flexibility of the production line. Supporting the use of dual-station robotic arms allows the system to process multiple workpieces at the same time, further improving the flexibility and capacity of the production line.
[0065] Specifically, in one or more embodiments of this specification, in order to improve product processing accuracy and facilitate feedback adjustment in subsequent processing, the second height unit is specifically used to:
[0066] First, the second height unit obtains the point cloud data corresponding to the current air-conditioning compressor housing through the preset scanning device, and then obtains the point cloud minimum bounding box corresponding to the current air-conditioning compressor housing according to the three-axis maximum and minimum values of the point cloud data. For example, point cloud data 1 is (150, 200, 300), point cloud data 2 is (400, 250, 200), point cloud data 3 is (50, 100, 400), and point cloud data 4 is (300, 350, 100). Then traversing these points can get the following boundary values X-axis: minX=50, maxX=400; Y-axis: minY=100, maxY=350; Z-axis: minZ=100, maxZ=400. Based on these boundary values, the coordinates of each vertex can be determined in turn, for example: lower left corner: (minX, minY, minZ), lower right corner: (minX, maxY, minZ), upper left corner: (maxX, minY, maxZ), etc. Based on these vertices, a cuboid parallel to the coordinate axis can be obtained as the minimum bounding box. Then, according to the region growing algorithm, points with similar attributes are combined to filter the point cloud data within the minimum bounding box of the point cloud, that is, to confirm that all points are within this range to obtain the point cloud data to be identified. Among them, the region growing algorithm is an image segmentation or point cloud segmentation technology based on the similarity of pixel or point cloud data. The basic idea is to start from a set of predefined seed points, and gradually add adjacent pixels or points with similar attributes to the corresponding area to form a larger area until a certain stop condition is met. The region growing algorithm will not be described in detail here.
[0067] Then, in order to facilitate the detection of the actual workpiece height, the second height unit determines the conversion relationship from three-dimensional to two-dimensional through the internal parameter matrix and external parameter matrix of the preset scanning device, thereby projecting the point cloud data to be identified into the two-dimensional space to obtain the two-dimensional projection data corresponding to the point cloud data. Then, the two-dimensional projection data is edge detected based on the preset edge detection algorithm to obtain the edge data of the current air-conditioning compressor housing, and the edge data is converted to the parameter space to identify the straight line data of the current air-conditioning compressor housing based on the peak point of the parameter space. Then, the straight line data is fitted according to the least squares method to correct the workpiece height based on the fitted straight line data to obtain the actual workpiece height. In this process, the regional growing algorithm and the edge detection algorithm can process incomplete or blurred scanning data to a certain extent, and can adapt to the environmental noise and complex background in the production process, and the fitting of the straight line data based on the least squares method can smooth the small fluctuations in the data and improve the stability of the results.
[0068] Further, the second height unit performs edge detection on the two-dimensional projection data based on a preset edge detection algorithm to obtain edge data of the current air-conditioning compressor housing, and converts the edge data into a parameter space to identify straight line data of the current air-conditioning compressor housing based on a peak point of the parameter space, specifically including the following process:
[0069] In order to capture edge information more comprehensively and improve the accuracy of subsequent height detection, in the embodiment of this specification, the gradient of the two-dimensional projection data in multiple directions is obtained based on the preset multi-directional gradient operator, so that the gradient map corresponding to the two-dimensional projection data is determined according to the gradient of multiple directions. The preset multi-directional gradient operator is used to obtain the multi-directional gradient, so that the edge information can be detected from multiple directions, avoiding the information omission that may be caused by single-direction detection, thereby more comprehensively capturing edge features and improving the accuracy of subsequent edge detection and height detection. In the edge detection process, noise may interfere with the accurate detection of the edge, and the traditional filtering method may cause the loss of edge details. Therefore, in order to highlight the main features of the edge, the local maximum value data of each direction of the gradient map is obtained as the initial edge data in the embodiment of this specification, so that the initial edge data is filtered according to the preset bilateral filter to obtain the edge data of the current air-conditioning compressor housing. By filtering with the preset bilateral filter, the detailed information of the edge can be better retained while removing the noise, so that the obtained edge data is more accurate and reliable. Then, in order to obtain the straight line features and mine the potential straight line features at the same time, the second height unit in the embodiment of this specification first maps the edge data to the parameter space, so as to record each edge data in the parameter space according to the accumulator data, determine the peak point in the parameter space, and convert the parameters corresponding to the peak point to the space corresponding to the two-dimensional projection data, and obtain the initial straight line data of the current air-conditioning compressor housing. By converting the edge data to the parameter space and recording it using the accumulator data in this way, the straight line features can be more effectively detected and represented. Since the peak point corresponds to the most significant straight line in the image, the peak point in the parameter space is further determined so as to achieve both accurate identification of potential straight line information and certain robustness to noise and occlusion, thereby providing strong support for subsequent height detection. Then, in order to remove the straight line information irrelevant to the detection direction, further reduce false detection and missed detection, improve the pertinence and accuracy of detection, and make the final straight line data more in line with actual needs, after identifying the straight line features, the initial straight line data will be filtered based on the height detection direction of the current air-conditioning compressor housing to obtain the straight line data corresponding to the height detection direction.
[0070] Specifically, in one or more embodiments of the present specification, clustering is performed on the historical processing events of each air-conditioning compressor housing to determine the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events, specifically including:
[0071] The main control center obtains the historical processing events of each air-conditioning compressor housing according to multiple data sources. In order to avoid the problem that the clustering results lack interpretability due to the random selection of clustering centers, in the embodiment of this specification, the main control center divides the historical processing events equally according to the preset number of clustering centers to obtain multiple historical processing event groups, thereby randomly determining the historical processing events in each historical processing event group as the initial clustering center. In this process, the historical processing events are evenly divided and the initial clustering center is randomly determined, which can avoid the adverse effects of the randomness of the initial center selection on the clustering results to a certain extent, and provide a relatively reasonable starting point for the subsequent clustering process. Then, the historical processing events in each historical processing event group are traversed to determine the Euclidean distance between the historical processing events in each historical processing event group and the initial clustering center, so as to cluster each historical processing event based on the Euclidean distance to obtain multiple cluster clusters. Clustering based on the Euclidean distance can classify similar historical processing events into one category, which is helpful to discover the potential patterns and laws in the data. Then, the position of the clustering center is re-determined based on the historical processing events in each clustering cluster, and then the clustering results of the historical processing events are iteratively obtained, and the optimal clustering cluster corresponding to the clustering results is determined. By continuously iterating and updating the position of the cluster center, the clustering results are made more accurate and stable. Determining the optimal clustering cluster can help find the most representative and discriminative clustering results, providing valuable information for subsequent analysis and application. After obtaining the optimal clustering cluster, the tool adjustment parameters and associated trigger events corresponding to each historical processing event are determined based on the historical processing events in each optimal clustering cluster and the tool adjustment parameters corresponding to the historical processing events. Combining the clustering results with the tool adjustment parameters and associated triggering events can provide an in-depth understanding of the relationship between different types of historical processing events and tool adjustments. This helps to make tool adjustments more accurately based on historical experience in the actual processing process, thereby improving processing quality and efficiency. The problem that the existing technology lacks an effective combination of historical processing events with tool adjustment parameters and associated triggering events, which makes it difficult to optimize based on historical experience in actual processing, is solved. By determining the relationship between historical processing events in the optimal clustering cluster and tool adjustment parameters and associated triggering events, a more targeted basis is provided for closed-loop adjustment in actual processing.
[0072] Specifically, in one or more embodiments of the present specification, the collaborative factors of the associated triggering events are determined based on the data characteristics of the tool adjustment parameters to construct a collaborative processing map of the associated triggering events, specifically including:
[0073] When processing tool adjustment parameters, the existing technology may only focus on data of a single dimension or a few dimensions, ignoring the multi-dimensional correlation and complexity between the data, and lacking the ability to comprehensively collect and analyze multiple attribute information of the tool adjustment parameters, such as adjustment objects, time sequence, spatial position, etc., resulting in the inability to accurately reflect the actual state of the tool during the processing. Therefore, in the embodiment of this specification, the tool adjustment parameters are collected to sort the tool adjustment parameters based on the multiple attribute information corresponding to the tool adjustment parameters to obtain a multi-dimensional tool adjustment parameter sequence; it should be noted that the attribute information includes at least: adjustment object, time sequence, and spatial position. Based on this method, various information in the tool adjustment process can be fully captured, providing a rich data basis for subsequent analysis.
[0074] In the existing method, when the height detection fails during the production process, it is generally detected after production, and it is difficult to identify it before passing through the operating unit and adjust the subsequent processing based on the detected height. Therefore, in order to achieve the adjustment of production and processing in the embodiment of this specification, the associated operations corresponding to each processing event related to the height are determined. In the embodiment of this specification, the multidimensional tool adjustment parameter sequence corresponding to the same associated trigger event is subsequently converted into a multidimensional tool adjustment parameter distribution map, so as to determine the first synergistic factor of the associated trigger event based on the overlap of the attribute information of the multidimensional tool adjustment parameter distribution map. The multidimensional tool adjustment parameter sequence is converted into a distribution map, which intuitively shows the distribution of parameters in different dimensions. This visualization method helps to quickly identify the correlation and change trend between parameters, and provides an intuitive reference for the subsequent determination of synergistic factors. By analyzing the overlap of the attribute information of the multidimensional tool adjustment parameter distribution map, the direct factors that cause the associated trigger event can be accurately identified. This method is based on the inherent correlation of data, avoids the interference of subjective judgment, and improves the accuracy and reliability of synergistic factor identification. Then, in order to increase the impact of environmental factors and the processing process, the main control center determines the second synergistic factor that triggers the associated trigger event based on the operating equipment logic log corresponding to each associated trigger event. By combining the operating equipment logic log, it can gain an in-depth understanding of the equipment's operating status and the operator's behavior patterns during the processing process. This helps to identify other external factors that may affect the associated trigger event in addition to tool adjustment parameters. This method takes into account multiple factors such as equipment, operation, and environment, making the determination of synergistic factors more comprehensive and in-depth. Then, Figure 3As shown, the first collaborative factor and the second collaborative factor are summarized as collaborative factors of the associated trigger event, and the collaborative factors are used as graph edges and the associated trigger event is used as a node to construct a collaborative processing graph of the associated trigger event; wherein the collaborative processing graph is one or more connected graphs. The constructed collaborative processing graph not only shows the association between different trigger events, but also reveals the collaborative factors that cause these events. Through the connectivity of the graph, the mutual influence and dependency of each link in the entire processing process can be intuitively understood, which provides strong support for optimizing the processing process and improving production efficiency. It solves the problem that the prior art cannot fully understand the interaction and dependency of each link in the processing process, resulting in limited implementation effect and low efficiency in the production and processing process based on manual scheduling adjustment or experience-based adjustment and optimization.
[0075] Specifically, in one or more embodiments of the present specification, the main control center is used to determine the designated collaborative processing map corresponding to the current air-conditioning compressor housing based on the actual workpiece height and the matching degree between the basic processing data of the current operation module and the historical processing data, specifically including the following process:
[0076] First, the first historical processing data corresponding to the actual workpiece height in the historical processing data is screened. Then, according to the matching degree between the basic processing data and the first historical processing data, the matching historical processing data corresponding to the basic processing data is determined. Then, the historical processing events corresponding to the matching historical processing data are obtained to determine the specified collaborative processing map corresponding to the current air-conditioning compressor housing according to the collaborative factors contained in the historical processing events. By matching the actual workpiece height with the historical processing data, similar or identical processing cases can be quickly found, so that the most suitable processing map can be customized for the current workpiece based on the parameter settings of these successful cases. This helps to reduce the trial and error process and improve processing accuracy and efficiency. In this process, by automatically screening, matching and determining the processing map, manual intervention is reduced, and the flexibility and response speed of the production line are improved. At the same time, using the matching degree between the basic processing data and the historical processing data to determine the optimal processing path is a typical application of data-driven decision-making. This method can make full use of historical experience, avoid repeated errors, and improve the scientificity and accuracy of decision-making. The process can also flexibly respond to air-conditioning compressor casings of different heights and specifications. By dynamically matching historical data, it can find the most suitable processing map for each event and size of air-conditioning compressor casing. This highly adaptable feature enables the production line to handle a more diverse range of products to meet market demand.
[0077] Specifically, in one or more embodiments of this specification, the main control center is also used for:
[0078] If it is determined that the current air-conditioning compressor housing has completed the production and processing of the current operating unit, the current operating unit is restored based on the standard tool parameters stored in the operating module control subsystem. After the production and processing of the current operating unit is completed, the operating unit is restored based on the standard tool parameters, which helps to ensure that the operating unit is in a standard initial state during the next processing, and provides a guarantee for the accuracy and consistency of subsequent processing. Then it is determined whether the defective rate of the current air-conditioning compressor housing is lower than the preset defective rate value. If it is lower than the preset defective rate value, the tool adjustment parameters of the current operating unit are recorded, and the tool adjustment parameters of the current operating unit are marked based on the actual workpiece height of the current air-conditioning compressor housing and the corresponding designated collaborative processing map. When the defective rate is lower than the preset value, the tool adjustment parameters of the current operating unit are recorded. These data realize the experience accumulation and can provide valuable reference for subsequent production, which helps to further optimize the tool parameters and improve the processing accuracy and efficiency. The tool adjustment parameters of the current operating unit are marked based on the actual workpiece height and the corresponding designated collaborative processing map, realizing the personalized customization of the parameters. This marking helps to quickly identify and apply tool parameters suitable for specific workpieces and processing maps in subsequent production, improving the flexibility and adaptability of production. Through the above process, the entire disposal process of the end digital disposal system forms a closed-loop process that can be continuously improved. By continuously checking the defective rate, recording and adjusting tool parameters, and marking based on actual production data, the main control center can continuously optimize the production process and improve production efficiency and product quality.
[0079] like Figure 4 As shown, one or more embodiments of the present specification provide a method for digitally intelligently handling the end of an air-conditioning compressor housing, which is applied to a main control center and a first height unit connected to the main control center, and each operation module control subsystem connected to the main control center based on a preset communication interface, and also includes an end digitally intelligent handling system consisting of a second height detection unit connected to the first height unit and the main control center, and the method includes:
[0080] S401: The first height unit obtains the workpiece height of the current air-conditioning compressor housing through the front sensor corresponding to the current operation module, so as to start the second height unit based on the detection result corresponding to the workpiece height;
[0081] S402: the second height unit acquires point cloud data corresponding to the current air-conditioning compressor housing through a preset scanning device, so as to correct the workpiece height based on the point cloud data to obtain an actual workpiece height;
[0082] S403: the main control center performs clustering processing on the historical processing events of each air-conditioning compressor housing, and determines the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events;
[0083] S404: The main control center determines the collaborative factors of the associated triggering event based on the data characteristics of the tool adjustment parameters to construct a collaborative processing map of the associated triggering event;
[0084] S405: The main control center receives the actual workpiece height fed back by the second height unit, and determines the designated collaborative processing map corresponding to the current air-conditioning compressor casing based on the actual workpiece height and the degree of matching between the basic processing data of the current operating module and the historical processing data, so as to perform feedback adjustment on the current operating unit based on the control subsystems of each operating module in combination with the designated collaborative processing map.
[0085] Further, in one or more embodiments of the present specification, clustering is performed on the historical processing events of each air-conditioning compressor housing to determine the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events, specifically including:
[0086] Based on multiple data sources, historical processing events of each air-conditioning compressor housing are obtained, and the historical processing events are evenly divided according to a preset number of cluster centers to obtain multiple historical processing event groups, so as to randomly determine the historical processing events in each of the historical processing event groups as initial cluster centers;
[0087] Traversing the historical processing events in each of the historical processing event groups to determine the Euclidean distance between the historical processing events in each of the historical processing event groups and the initial cluster center, and clustering each of the historical processing events based on the Euclidean distance to obtain a plurality of cluster clusters;
[0088] Re-determining the location of the cluster center based on the historical processing events in each of the clusters, so as to iteratively obtain the clustering results of the historical processing events, and determine the optimal cluster corresponding to the clustering results;
[0089] Based on the historical processing events in each of the optimal clusters and the tool adjustment parameters corresponding to the historical processing events, the tool adjustment parameters corresponding to each of the historical processing events and the associated triggering events are determined.
[0090] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the method embodiment, since it is basically similar to the system embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0091] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0092] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.
Claims
1. A digital intelligent treatment system for the end of an air-conditioning compressor housing, characterized in that: The system comprises: a main control center and a first height unit connected to the main control center, and each operation module control subsystem connected to the main control center based on a preset communication interface, and also comprises a second height detection unit connected to the first height unit and the main control center; The first height unit is used to obtain the workpiece height of the current air-conditioning compressor housing through the front sensor corresponding to the current operation module, so as to start the second height unit based on the detection result corresponding to the workpiece height; The second height unit is used to obtain point cloud data corresponding to the current air-conditioning compressor housing through a preset scanning device, so as to correct the workpiece height based on the point cloud data to obtain an actual workpiece height; The main control center is used to perform clustering processing on the historical processing events of each air-conditioning compressor housing, and determine the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events; Determine the collaborative factors of the associated triggering event based on the data characteristics of the tool adjustment parameters to construct a collaborative processing map of the associated triggering event; Receive the actual workpiece height fed back by the second height unit, and determine the designated collaborative processing map corresponding to the current air-conditioning compressor housing based on the actual workpiece height and the matching degree between the basic processing data of the current operation module and the historical processing data, so as to feedback and adjust the current operation unit based on each operation module control subsystem in combination with the designated collaborative processing map; Wherein, determining the collaborative factors of the associated triggering events based on the data characteristics of the tool adjustment parameters to construct the collaborative processing map of the associated triggering events specifically includes: The tool adjustment parameters are collected, and the tool adjustment parameters are sorted based on a plurality of attribute information corresponding to the tool adjustment parameters to obtain a multi-dimensional tool adjustment parameter sequence; wherein the attribute information at least includes: adjustment object, time sequence, and spatial position; Converting the multidimensional tool adjustment parameter sequence corresponding to the same associated trigger event into a multidimensional tool adjustment parameter distribution diagram, and determining the first coordination factor of the associated trigger event based on the overlap of the attribute information of the multidimensional tool adjustment parameter distribution diagram; Determining a second coordination factor triggering the associated triggering event based on the operation device logic log corresponding to each associated triggering event; Aggregate the first collaborative factor and the second collaborative factor as the collaborative factors of the associated trigger event, use the collaborative factors as graph edges and the associated trigger event as nodes to construct a collaborative processing graph of the associated trigger event; wherein the collaborative processing graph is one or more connected graphs.
2. The end digital processing system of the air-conditioning compressor housing according to claim 1 is characterized in that: The first height unit is specifically used for: Acquire an effective detection range of a front sensor corresponding to a current operation module, so as to acquire a workpiece height of the current air-conditioning compressor housing detected by the front position sensor when the current air-conditioning compressor housing reaches the effective detection range; Determine a target workpiece height and a target error range based on the current order information of the air-conditioning compressor housing, and obtain a plurality of historical processing data matching the target workpiece height and the target error range; Determine the height range of the current operation module according to the sorting and rejection quantity of the current operation module corresponding to the plurality of historical processing data; Determining a workpiece height coverage range of the current air-conditioning compressor housing based on the workpiece height and an error value of the front sensor; Determine a first detection result based on the overlap between the workpiece height coverage range and the height range of the current operation module; wherein the first detection result includes: qualified and unqualified; If qualified, the current air-conditioning compressor housing is transmitted to the current operation module for processing; If it fails, the second height unit is activated.
3. The end digital processing system of the air-conditioning compressor housing according to claim 1 is characterized in that: The second height unit is specifically used for: Acquire point cloud data corresponding to the current air-conditioning compressor housing through a preset scanning device, and obtain a point cloud minimum bounding box corresponding to the current air-conditioning compressor housing based on the three-axis maximum and minimum values of the point cloud data; Based on the region growing algorithm, the point cloud data within the minimum bounding box of the point cloud is screened to obtain the point cloud data to be identified; Projecting the point cloud data to be identified into a two-dimensional space based on the intrinsic parameter matrix and the extrinsic parameter matrix of the preset scanning device to obtain two-dimensional projection data corresponding to the point cloud data; Performing edge detection on the two-dimensional projection data based on a preset edge detection algorithm to obtain edge data of the current air-conditioning compressor housing, and converting the edge data into a parameter space to identify straight line data of the current air-conditioning compressor housing based on a peak point of the parameter space; The straight line data is fitted based on the least square method, so as to correct the workpiece height based on the fitted straight line data to obtain the actual workpiece height.
4. The end digital processing system of the air-conditioning compressor housing according to claim 3 is characterized in that: Performing edge detection on the two-dimensional projection data based on a preset edge detection algorithm to obtain edge data of the current air-conditioning compressor housing, and converting the edge data into a parameter space to identify straight line data of the current air-conditioning compressor housing based on a peak point of the parameter space, specifically comprising: Acquire the gradients of the two-dimensional projection data in multiple directions based on a preset multi-directional gradient operator, so as to determine a gradient map corresponding to the two-dimensional projection data based on the gradients in the multiple directions; Acquire local maximum data in each direction of the gradient map as initial edge data, filter the initial edge data based on a preset bilateral filter, and obtain edge data of the current air-conditioning compressor housing; Mapping the edge data to a parameter space, recording each edge data in the parameter space based on the accumulator data, determining a peak point in the parameter space, and converting the parameter corresponding to the peak point to a space corresponding to the two-dimensional projection data, to obtain initial straight line data of the current air-conditioning compressor housing; The initial straight line data is filtered based on the height detection direction of the current air-conditioning compressor housing to obtain straight line data corresponding to the height detection direction.
5. The digital intelligent treatment system for the end of the air-conditioning compressor housing according to claim 1 is characterized in that: Clustering is performed on the historical processing events of each air-conditioning compressor housing to determine the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events, specifically including: Based on multiple data sources, historical processing events of each air-conditioning compressor housing are obtained, and the historical processing events are evenly divided according to a preset number of cluster centers to obtain multiple historical processing event groups, so as to randomly determine the historical processing events in each of the historical processing event groups as initial cluster centers; Traversing the historical processing events in each of the historical processing event groups to determine the Euclidean distance between the historical processing events in each of the historical processing event groups and the initial cluster center, and clustering each of the historical processing events based on the Euclidean distance to obtain a plurality of cluster clusters; Re-determining the location of the cluster center based on the historical processing events in each of the clusters, so as to iteratively obtain the clustering results of the historical processing events, and determine the optimal cluster corresponding to the clustering results; Based on the historical processing events in each of the optimal clusters and the tool adjustment parameters corresponding to the historical processing events, the tool adjustment parameters corresponding to each of the historical processing events and the associated triggering events are determined.
6. The end digital processing system of the air-conditioning compressor housing according to claim 1 is characterized in that: Based on the actual workpiece height and the matching degree between the basic processing data of the current operation module and the historical processing data, the designated collaborative processing map corresponding to the current air-conditioning compressor housing is determined, specifically including: Filtering the first historical processing data corresponding to the actual workpiece height in the historical processing data; Determining matching historical processing data corresponding to the basic processing data according to a matching degree between the basic processing data and the first historical processing data; The historical processing events corresponding to the matching historical processing data are obtained to determine the designated collaborative processing map corresponding to the current air-conditioning compressor housing according to the collaborative factors included in the historical processing events.
7. The end digital processing system of the air-conditioning compressor housing according to claim 1 is characterized in that: The main control center is also used for: If it is determined that the current air-conditioning compressor housing has completed the production and processing of the current operating unit, the current operating unit is restored based on the standard tool parameters stored in the operating module control subsystem; Determining whether the defective rate of the current air-conditioning compressor housing is lower than a preset defective rate value; If so, the tool adjustment parameters of the current operating unit are recorded, and the tool adjustment parameters of the current operating unit are marked based on the actual workpiece height of the current air-conditioning compressor housing and the corresponding designated collaborative processing map.
8. A method for digitally processing the end of an air-conditioning compressor housing, characterized in that: The method includes: applying to a first height unit connected to the main control center and each operation module control subsystem connected to the main control center based on a preset communication interface, and also including an end digital intelligent disposal system consisting of a second height detection unit connected to the first height unit and the main control center. The first height unit obtains the workpiece height of the current air-conditioning compressor housing through the front sensor corresponding to the current operation module, so as to start the second height unit based on the detection result corresponding to the workpiece height; The second height unit acquires point cloud data corresponding to the current air-conditioning compressor housing through a preset scanning device, so as to correct the workpiece height based on the point cloud data to obtain an actual workpiece height; The main control center performs clustering processing on the historical processing events of each air-conditioning compressor housing, and determines the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events; The main control center determines the collaborative factors of the associated triggering event based on the data characteristics of the tool adjustment parameters to construct a collaborative processing map of the associated triggering event; The main control center receives the actual workpiece height fed back by the second height unit, and determines the designated collaborative processing map corresponding to the current air-conditioning compressor housing based on the actual workpiece height and the matching degree between the basic processing data of the current operation module and the historical processing data, so as to perform feedback adjustment on the current operation unit based on each operation module control subsystem in combination with the designated collaborative processing map; Wherein, determining the collaborative factors of the associated triggering events based on the data characteristics of the tool adjustment parameters to construct the collaborative processing map of the associated triggering events specifically includes: The tool adjustment parameters are collected, and the tool adjustment parameters are sorted based on a plurality of attribute information corresponding to the tool adjustment parameters to obtain a multi-dimensional tool adjustment parameter sequence; wherein the attribute information at least includes: adjustment object, time sequence, and spatial position; Converting the multidimensional tool adjustment parameter sequence corresponding to the same associated trigger event into a multidimensional tool adjustment parameter distribution diagram, and determining the first coordination factor of the associated trigger event based on the overlap of the attribute information of the multidimensional tool adjustment parameter distribution diagram; Determining a second coordination factor triggering the associated triggering event based on the operation device logic log corresponding to each associated triggering event; Aggregate the first collaborative factor and the second collaborative factor as the collaborative factors of the associated trigger event, use the collaborative factors as graph edges and the associated trigger event as nodes to construct a collaborative processing graph of the associated trigger event; wherein the collaborative processing graph is one or more connected graphs.
9. The method for digitally processing the end of an air-conditioning compressor housing according to claim 8, characterized in that: Clustering is performed on the historical processing events of each air-conditioning compressor housing to determine the tool adjustment parameters and associated triggering events corresponding to each of the historical processing events, specifically including: Based on multiple data sources, historical processing events of each air-conditioning compressor housing are obtained, and the historical processing events are evenly divided according to a preset number of cluster centers to obtain multiple historical processing event groups, so as to randomly determine the historical processing events in each of the historical processing event groups as initial cluster centers; Traversing the historical processing events in each of the historical processing event groups to determine the Euclidean distance between the historical processing events in each of the historical processing event groups and the initial cluster center, and clustering each of the historical processing events based on the Euclidean distance to obtain a plurality of cluster clusters; Re-determining the location of the cluster center based on the historical processing events in each of the clusters, so as to iteratively obtain the clustering results of the historical processing events, and determine the optimal cluster corresponding to the clustering results; Based on the historical processing events in each of the optimal clusters and the tool adjustment parameters corresponding to the historical processing events, the tool adjustment parameters corresponding to each of the historical processing events and the associated triggering events are determined.
