A quality inspection system for precision hardware machining

Abstract

This invention discloses a quality inspection system for precision hardware parts processing, belonging to the field of quality inspection technology. By analyzing the fluctuations of equipment operating parameters and processing parameters, and combining this with the application of a picking robot, it can accurately and promptly identify potential defect risks, providing a foundation for targeted quality inspection of precision hardware parts. The system analyzes the structure, performance, and surface of the defective parts to obtain spacing parameters, surface parameters, and performance parameters. These three parameters are then comprehensively analyzed to obtain the detection value, which is compared with a set detection threshold to output the quality inspection result. This system enables rapid and accurate detection and output of results for defective parts, improving the stability and consistency of product quality. It also helps companies track and monitor changes in equipment operating status and process parameters, allowing for timely problem detection and appropriate maintenance and adjustment measures.

Description

Technical Field

[0001] This invention relates to the field of quality inspection technology, and in particular to a quality inspection system for precision hardware parts processing. Background Technology

[0002] Precision metal parts are commonly used in various critical fields, such as aerospace, electronic instruments, automobiles, and medical devices. These industries have very high requirements for product reliability and safety. Currently, the manufacturing process control for precision metal parts is very strict, and defects in specifications can almost be avoided in the strictly controlled production process. However, some defects still exist in the production process that cannot be avoided. For example, defects in precision metal parts may be caused by abnormalities in the precision metal processing equipment or fluctuations in process parameters. Therefore, a quality inspection system for precision metal parts is indispensable.

[0003] Current quality inspection methods for precision hardware components involve random sampling or individual inspection to determine whether the appearance, internal structure, and performance of the components meet technical requirements. While individual inspection allows for comprehensive testing, it significantly reduces efficiency and cannot meet production needs. Random sampling, while improving efficiency, has limitations, only allowing inspection of a small subset of products. If defective components are not selected, they cannot be detected promptly, compromising the stability and reliability of precision hardware quality. Therefore, improving inspection efficiency while accurately identifying defective components to meet production demands is a critical technical challenge. Summary of the Invention

[0004] Therefore, it is necessary to provide a quality inspection system for precision hardware parts processing to address the problems mentioned in the background technology above.

[0005] The objective of this invention can be achieved through the following technical solution: a quality inspection system for precision hardware parts processing, comprising a data acquisition unit, a server, a processing analysis module, and a defect detection module; the data acquisition unit and the server are communicatively connected, and the data acquisition unit collects equipment operating parameters and processing parameters during the production and processing of precision hardware parts, and sends them to the server for storage; wherein the equipment operating parameters include equipment temperature value, equipment motor speed, and equipment noise value; the processing parameters include injection molding parameters and cutting parameters, the injection molding parameters include injection molding temperature, cooling temperature, and injection molding pressure; the cutting parameters include cutting speed and cutting depth;

[0006] The processing analysis module analyzes equipment operating parameters and processing parameters to determine the defect risks of precision hardware parts by analyzing equipment operating fluctuations and process parameter fluctuations, as detailed below:

[0007] S1: The specific steps for analyzing equipment operation fluctuations through equipment operating parameters are as follows:

[0008] S11: Extract the equipment temperature value and construct a graph showing the change in equipment temperature value with time as the horizontal axis and equipment temperature value as the vertical axis; analyze the graph to obtain the slope difference and the increase / decrease ratio, and record them as L1 and L2 respectively. Calculate the temperature fluctuation value LZ using the set formula LZ=a1×L1+a2×L2, where a1 and a2 are the set correction factors.

[0009] S12: Extract the motor speed of the equipment, set several speed ranges, compare and match the motor speeds of the equipment with the set speed ranges, and count the number of equipment motors in each set speed range. The range with the highest number of equipment motors is designated as the stable range, and the other ranges are combined into fluctuation ranges. The motor speeds in the fluctuation ranges are designated as the fluctuation speed Ri. The average speed of the equipment motors in the stable ranges is calculated to obtain the stable speed WR. Then, using the set formula... The speed fluctuation value RZ is calculated, where r1 and r2 are the set correction factors. This represents the average value of the fluctuating rotational speed;

[0010] S13: Extract the noise value and construct a noise spectrum with the acquisition time corresponding to the noise value as the x-axis and the noise value as the y-axis. There are two preset straight lines in the noise spectrum. The first preset straight line and the noise broken line form the high-frequency part, and the second preset straight line and the noise broken line form the low-frequency part. Calculate the area of ​​the high-frequency part and the low-frequency part respectively to obtain the high-frequency area and the low-frequency area, and record them as G1 and G2 respectively. Calculate the spectrum fluctuation value GZ using the set formula GZ=g1×G1+g2×G2, where g1 and g2 are the set correction factors.

[0011] S14: Substitute the temperature fluctuation value LZ, speed fluctuation value RZ, and spectrum fluctuation value GZ into the set formula. The operating fluctuation value LRG is calculated, where b1, b2, and b3 are the set correction factors. When the operating fluctuation value is greater than or equal to the set operating threshold, the precision hardware corresponding to the equipment operating parameters is recorded as the equipment fluctuation test piece, and the production time of the test piece is used as the equipment fluctuation test piece number. When the operating fluctuation value is less than the set threshold, S2 is executed.

[0012] S2: Perform fluctuation analysis on the processing technology of precision hardware parts through processing technology parameters to obtain the fluctuation degree. When the fluctuation degree is greater than or equal to the set degree threshold, the precision hardware parts corresponding to the equipment operating parameters are recorded as parameter fluctuation test parts. When the fluctuation degree is less than the set degree threshold, the precision hardware parts are output as qualified products.

[0013] S3: The generated equipment fluctuation test items or parameter fluctuation test items and their numbered items are integrated into defect test items and defect test item numbers, and a picking instruction is generated and sent to the picking robot; when the picking robot receives the picking instruction, it picks out the defect test items by recognizing the defect test item number.

[0014] The defect detection module performs defect detection on the part to be inspected and outputs the detection results, which include qualified and unqualified results, and implements corresponding early warning strategies based on the detection results.

[0015] In some embodiments, fluctuation analysis is performed on the machining process of precision hardware parts using machining process parameters to obtain the fluctuation degree, as follows:

[0016] 201: Extract the injection temperature, cooling temperature, injection pressure, cutting speed, and cutting depth, and denote them as C1, C2, C3, C4, and C5 respectively; use the set formula... Calculations are performed to obtain the parameter fluctuation value CZ, where v1, v2, v3, v4, and v5 are the set correction factors. The set standard injection temperature, The set standard cooling temperature, The set standard injection pressure, The set standard cutting speed, The standard cutting depth is set; and so on, to obtain the fluctuation values ​​of all parameters of the hardware part during the production and processing time, and to calculate the average parameter fluctuation value by averaging them.

[0017] 202: Extract parameter fluctuation values, compare and analyze them with the set fluctuation range to classify the parameter fluctuation values ​​into high fluctuation values, medium fluctuation values, and low fluctuation values, count the number of high fluctuation values, medium fluctuation values, and low fluctuation values ​​respectively, and record them as λ1, λ2, and λ3 respectively; substitute λ1, λ2, and λ3 into the set formula λZ=c1×(λ1 / λ3)+c2×(λ2 / λ3) to calculate the fluctuation coefficient λZ, where c1 and c2 are the set correction factors;

[0018] 203: Average parameter fluctuation value Substituting the volatility coefficient λZ into the set formula TCZ=β1×λZ× The volatility TCZ is calculated, where β1 is a set correction coefficient. Numerical analysis is then performed to obtain the volatility.

[0019] In some embodiments, defect detection is performed on the defective part to be inspected and the inspection results are output, as follows:

[0020] 301: The defective part to be inspected is scanned by a laser scanner to establish a three-dimensional model for inspection, and then paired with the point cloud data of the standard model. For each pair of paired points, the Euclidean distance between them is calculated. This process is repeated to obtain the Euclidean distance between all paired points, and the distances are summed to obtain the spacing parameter denoted as H1.

[0021] 302: The defective part to be inspected is heated and a heat distribution map is obtained using an infrared thermal imager. The heat distribution map is divided into several regions, and the RGB values ​​of each region are extracted and denoted as RGBj, where j = 1, 2, 3...n2, n2 is a positive integer, and n2 represents the total number of regions. The RGBj values ​​of each region in the heat distribution map are then substituted into a predefined formula. The performance parameter H2 is calculated, where β2 is the set correction coefficient;

[0022] 303: Acquire surface images of the defective part to be inspected using a high-definition camera. Use a photo recognition device to identify scratches and cracks in the surface image, and fill the scratches and cracks with different colors to obtain a filled image. Enlarge the filled image until only one color exists in each pixel. Count the number of pixels occupied by scratches and cracks, and multiply the number of pixels occupied by scratches and cracks by the area of ​​a single pixel to obtain the scratch area and crack area, respectively. Repeat this process to identify all scratches and cracks in the surface image of the defective part to be inspected, as well as their areas. Count the number of scratches and cracks and record them as h1 and h2, respectively. Sum the scratch area and crack area of ​​all scratches and cracks in the defective part to obtain the total scratch area and total crack area, and record them as h3 and h4, respectively. Substitute h1, h2, h3, and h4 into the set formula. The surface parameter H3 is calculated, where d1, d2, d3 and d4 are the set correction factors;

[0023] 304: Substitute the spacing parameter H1, performance parameter H2, and surface parameter H3 into the set formula HZ=d5×H1+d6×H2+d7×H3 to calculate the detection value HZ, where d5, d6, and d7 are set correction factors. When the detection value is less than the set detection threshold, the detection result of the defective part is output as qualified, and the label of the defective part is updated to qualified. When the detection value is greater than or equal to the set detection threshold, the detection result of the defective part is output as unqualified. If the defective part is a part subject to equipment fluctuation, the label of the defective part is updated to equipment fluctuation defective. If the defective part is a part subject to parameter fluctuation, the label of the defective part is updated to parameter fluctuation defective.

[0024] In some embodiments, a corresponding early warning strategy is implemented based on the detection results, as follows:

[0025] The system counts the number of defective products due to equipment fluctuations and parameter fluctuations within a preset time period, calculates the ratio between these two values ​​to obtain the set parameter ratio. The set parameter ratio is then compared and analyzed with a set ratio range to generate equipment maintenance warning signals, set parameter warning signals, or process parameter adjustment warning signals, which are then fed back to the server. The server generates corresponding warning notifications based on the type of warning signal received and sends them to the relevant technical personnel.

[0026] Compared with the prior art, the beneficial effects of the present invention are:

[0027] 1. This invention analyzes the fluctuations of equipment operating parameters and processing parameters, and combines this with the application of a picking robot to accurately and promptly identify potential defect risks, providing a foundation for targeted quality inspection of precision hardware parts.

[0028] 2. By analyzing the structure, performance, and surface of the defective part to be inspected, the spacing parameters, surface parameters, and performance parameters are obtained. The three are then comprehensively analyzed to obtain the detection value, which is compared with the set detection threshold to output the quality inspection result. This enables the quality inspection of defective parts to be inspected quickly and accurately, improving the stability and consistency of product quality, avoiding the adverse consequences of defective products, and helping enterprises track and monitor the operating status of equipment and changes in process parameters. This allows for timely detection of problems and the implementation of corresponding maintenance and adjustment measures, thereby improving production efficiency and product competitiveness.

[0029] In summary, by analyzing the fluctuations of equipment operating parameters and processing parameters during the production and processing of precision hardware parts, it is possible to determine whether there are potential defects in the precision hardware parts being produced and processed. Potential defects are then selected and inspected to achieve targeted and rapid detection, improve defect detection efficiency, and ensure timely detection and quality control in the manufacturing process. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a schematic diagram of the system module connections of the present invention;

[0032] Figure 2 This is a flowchart illustrating the implementation steps of the present invention;

[0033] Figure 3 This is a noise spectrum diagram of the device during operation according to the present invention. Detailed Implementation

[0034] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0035] First embodiment:

[0036] like Figure 1-2 As shown, a quality inspection system for precision hardware parts processing includes a data acquisition unit, a server, a processing analysis module, a defect detection module, and a coefficient optimization module.

[0037] The data acquisition unit collects the equipment operating parameters and processing parameters for each precision hardware part during production and sends them to the server for storage. The equipment operating parameters include equipment temperature, motor speed, and noise level. The processing parameters include injection molding parameters and cutting parameters. Injection molding parameters include injection temperature, cooling temperature, and injection pressure. Cutting parameters include cutting speed and depth of cut. Cutting speed refers to the speed of the cutting tool's contact point relative to the tool's movement, usually expressed as the tool's linear speed per minute (m / min). It should be noted that while higher cutting speeds can improve processing efficiency, excessively high speeds can lead to premature tool wear, increased vibration, and heat buildup, thus affecting processing accuracy. Depth of cut refers to the depth to which the tool cuts the workpiece surface in each cut, usually expressed as a percentage of the tool's dimensions or in specific length units. It should be noted that a large depth of cut can lead to tool vibration, decreased processing quality, and increased surface roughness, thus affecting processing accuracy.

[0038] The processing analysis module uses in-depth analysis of equipment operating parameters and processing parameters to determine the defect risks of precision hardware parts, as detailed below:

[0039] S1: By conducting in-depth analysis of equipment operating parameters to determine the impact of equipment operation on the machining of precision hardware parts, specifically:

[0040] S11: Extract equipment temperature values ​​and construct a temperature change graph with time on the x-axis and equipment temperature values ​​on the y-axis. Input the equipment temperature values ​​into the graph in chronological order of their acquisition times. Record the positions of the equipment temperature values ​​in the graph as equipment temperature points. Connect adjacent equipment temperature points to obtain equipment temperature lines. Calculate the slope of the equipment temperature lines using the least squares method. Take two adjacent slopes, calculate the difference between them, and take the absolute value to obtain the slope difference. It should be noted that the larger the slope difference, the greater the change between the two adjacent equipment temperature lines. Sum the slope differences to obtain the difference value, denoted as L1.

[0041] When the slope is greater than zero, it indicates that the equipment temperature at the two sampling points corresponding to the equipment temperature line is in a heating state, and this slope is recorded as the temperature increase slope. When the slope is less than zero, it indicates that the equipment temperature at the two sampling points corresponding to the equipment temperature line is in a cooling state, and this slope is recorded as the temperature decrease slope. The temperature increase slope is summed to obtain the temperature increase degree, and the temperature decrease slope is summed to obtain the absolute value of the sum to obtain the temperature decrease degree. The temperature increase degree is then divided by the temperature decrease degree to obtain the increase / decrease ratio, which is recorded as L2. It should be noted that the greater the increase / decrease ratio deviates from 1, the more obvious the temperature fluctuation.

[0042] The slope difference is denoted as L1 and the increase / decrease ratio L2 is calculated using the set formula LZ=a1×L1+a2×L2 to obtain the temperature fluctuation value LZ, where a1 and a2 are set correction factors respectively.

[0043] S12: Extract the motor speed of the equipment, measured in revolutions per second (RPS). Set several speed ranges, compare and analyze the motor speeds within each range, and count the number of motors in each range. The range containing the highest number of motors is designated as the stable range, and the other ranges are grouped into fluctuation ranges. The motor speeds within these fluctuation ranges are denoted as fluctuation speeds Ri, where i = 1, 2, 3…n1, n1 is a positive integer representing the total number of fluctuation speeds, and i represents the fluctuation speed number. The average motor speeds within the stable ranges are calculated to obtain the stable speed, denoted as WR. The set formula is then used… The speed fluctuation value RZ is calculated, where r1 and r2 are the set correction factors. This represents the average value of the fluctuating rotational speed. It should be noted that the motor is one of the main power sources for driving machining tools such as cutting tools, drill bits, and grinding heads. Fluctuations in motor operation directly affect the cutting and machining accuracy of precision hardware parts.

[0044] S13: Extract noise values ​​and construct a noise spectrum with the acquisition time corresponding to the noise value as the x-axis and the noise value as the y-axis. Input the noise values ​​into the noise spectrum in the order of their corresponding acquisition times and connect them sequentially to obtain a noise polyline; for example... Figure 3 As shown, there are two preset straight lines in the noise spectrum. The first preset straight line and the noise broken line constitute the high-frequency part, and the second preset straight line and the noise broken line constitute the low-frequency part. It should be noted that the first preset straight line and the second preset straight line are set by those skilled in the art. The areas of the high-frequency and low-frequency parts are calculated to obtain the high-frequency area and the low-frequency area, and they are denoted as G1 and G2 respectively. The spectral fluctuation value GZ is calculated using the set formula GZ=g1×G1+g2×G2, where g1 and g2 are set correction factors.

[0045] S14: The temperature fluctuation value LZ, speed fluctuation value RZ, and spectrum fluctuation value GZ are calculated using a predefined formula. The operating fluctuation value LRG is calculated, where b1, b2, and b3 are the set correction factors. As can be seen from the formula, the larger the temperature fluctuation value, the larger the speed fluctuation value, and the larger the spectrum fluctuation value, the larger the operating fluctuation value, indicating that the equipment is more unstable, which has a greater impact on the processing of precision hardware parts and a greater potential risk of defects in the processed precision hardware parts.

[0046] The operating fluctuation value is compared and analyzed with the set operating threshold. When the operating fluctuation value is greater than or equal to the set operating threshold, it indicates that the fluctuation of the equipment will have a significant impact on the precision hardware parts, resulting in a high potential risk of defects in the precision hardware parts produced. In this case, the precision hardware parts corresponding to the equipment operating parameters are recorded as the equipment fluctuation test pieces, and the production time of the test pieces is used as the equipment fluctuation test piece number, where the production time includes the production date and the production time. When the operating fluctuation value is less than the set threshold, it indicates that the fluctuation of the equipment will have a minor impact on the precision hardware parts and can be ignored. In this case, S2 is executed.

[0047] S2: Stability analysis of the machining process of precision hardware parts is performed through machining process parameters, specifically:

[0048] S21: Extract the injection temperature, cooling temperature, injection pressure, cutting speed, and cutting depth, and label them as C1, C2, C3, C4, and C5 respectively; use the set formula... Calculations are performed to obtain the parameter fluctuation value CZ, where v1, v2, v3, v4, and v5 are the set correction factors. The set standard injection temperature, The set standard cooling temperature, The set standard injection pressure, The set standard cutting speed, This refers to the set standard cutting depth. It should be noted that the standard injection temperature, standard cooling temperature, standard injection pressure, standard cutting speed, and standard cutting depth refer to standard parameters under optimal conditions. This process is repeated to obtain the fluctuation values ​​of all parameters for the hardware part during the production and processing period, and the average value is calculated to obtain the average parameter fluctuation value, denoted as [value missing]. ;

[0049] S22: Extract all parameter fluctuation values ​​of the hardware part during the production and processing process, compare and analyze the parameter fluctuation values ​​with the set fluctuation range. When the parameter fluctuation value is greater than the maximum value in the set fluctuation range, it indicates that the parameter fluctuation at that moment is large and has a significant impact on the precision of the hardware part. In this case, the parameter fluctuation value is recorded as a high fluctuation value. When the parameter fluctuation value is within the set fluctuation range, it is recorded as a medium fluctuation value. When the parameter fluctuation value is less than the minimum value in the set fluctuation range, it indicates that the parameter fluctuation value at that moment has a small impact on the precision hardware part and can be ignored. In this case, the parameter fluctuation value is recorded as a low fluctuation value. Count the number of high, medium, and low fluctuation values ​​during the production and processing of the precision hardware part and record them as λ1, λ2, and λ3, respectively. Calculate the fluctuation coefficient λZ using the set formula λZ=c1×(λ1 / λ3)+c2×(λ2 / λ3), where c1 and c2 are the set correction factors.

[0050] S23: Average parameter fluctuation value The fluctuation coefficient λZ is calculated using the established formula TCZ=c3×λZ× The fluctuation range TCZ is calculated, where c3 is the set correction coefficient. The fluctuation range is compared with the set threshold. When the fluctuation range is greater than or equal to the set threshold, it indicates that the fluctuation of the process parameters in the production and processing of the precision hardware part will have a significant impact on its production and processing. The precision hardware part corresponding to the equipment operating parameters is then recorded as the parameter fluctuation test part. When the fluctuation range is less than the set threshold, it indicates that the fluctuation of the process parameters in the production and processing of the precision hardware part will have a very small impact on its production and processing and can be ignored. The precision hardware part is then output as a qualified product.

[0051] S3: The generated equipment fluctuation test items or parameter fluctuation test items and their numbered items are integrated into defect test items and defect test item numbers, and a picking instruction is generated and sent to the picking robot; when the picking robot receives the picking instruction, it picks out the defect test items by recognizing the defect test item number.

[0052] By analyzing the fluctuations of equipment operating parameters and processing parameters during the production and processing of precision hardware parts, it is possible to determine whether there are potential defects in the precision hardware parts being produced and processed. Those with potential defects are then selected, which can accurately and timely identify potential defect risk analysis and provide a basis for targeted quality inspection of precision hardware parts.

[0053] The defect detection module performs defect detection on the part to be inspected and outputs the detection results, which include qualified and unqualified results. The defect detection process is as follows:

[0054] A laser scanner is used to scan the defective part to be inspected, collecting a large amount of point cloud data. A 3D model is then built based on this point cloud data to obtain the 3D model of the defective part, denoted as the inspection 3D model. Point cloud registration algorithms (such as the nearest neighbor algorithm) are used to pair the point cloud data of the inspection model with the point cloud data of the standard model. For each point in the inspection model, the closest point in the standard model is found as the pairing point. For each pair of paired points, the Euclidean distance between them is calculated. The Euclidean distance is the straight-line distance between points; the larger the Euclidean distance, the farther the distance between the paired points. This process is repeated to obtain the Euclidean distances between all paired points, and these distances are summed to obtain the spacing parameter, denoted as H1. It should be noted that the standard 3D model is a model built by scanning standard precision hardware parts. The main purpose of 3D modeling is to detect the differences between the external and internal structures of the defective part and the standard precision hardware parts.

[0055] The defective part to be inspected is heated and a heat distribution map is obtained using an infrared thermal imager. It should be noted that an infrared thermal imager is a device capable of detecting infrared radiation within the electromagnetic wave range, converting the infrared radiation from an object's surface into a visible thermal image. During the heating of the defective metal part, significant temperature differences will appear in different areas. These differences will be captured by the infrared thermal imager and reflected on the heat distribution map. The heat distribution map uses colors to represent the temperature of different areas; the higher the RGB value of a color, the higher the temperature of that area. The heat distribution map is divided into several regions, and the RGB value of each region is extracted and denoted as RGBj, where j = 1, 2, 3…n2, and n2 is a positive integer representing the total number of regions. Using a predefined formula… The performance parameter H2 is calculated, where β2 is the set correction coefficient. As can be seen from the formula, the greater the difference in RGB values ​​between different regions, the greater the performance parameter, indicating that the defect detection part has a greater potential risk of some local performance parameter problems, such as uneven heat conduction, loose structure, or surface damage, which may cause abnormal hot spots or local overheating during use, thus affecting its normal operation.

[0056] A high-definition camera is used to acquire surface images of the defective part to be inspected. A photo recognition device is used to identify scratches and cracks in the surface images, and different colors are used to fill the scratches and cracks to obtain filled images. The filled images are magnified until only one color exists in each pixel. The number of pixels occupied by scratches and cracks is counted, and the number of pixels occupied by scratches and cracks is multiplied by the area of ​​a single pixel to obtain the scratch area and crack area, respectively. This process is repeated to identify all scratches and cracks in the surface images of the defective part, as well as their areas. The number of scratches and cracks is counted and recorded as h1 and h2, respectively. The scratch area and crack area of ​​all scratches and cracks in the defective part are summed to obtain the total scratch area and total crack area, recorded as h3 and h4, respectively. A pre-defined formula is then used to calculate the total scratch area and crack area. The surface parameter H3 is calculated, where d1, d2, d3 and d4 are the set correction factors;

[0057] The spacing parameter H1, performance parameter H2, and surface parameter H3 are calculated using the set formula HZ=d5×H1+d6×H2+d7×H3 to obtain the detection value HZ, where d5, d6, and d7 are set correction factors. The detection value is compared with the set detection threshold. When the detection value is less than the set detection threshold, it indicates that the defective part meets the requirements, and the detection result of the defective part is output as qualified, and the label of the defective part is updated to qualified. When the detection value is greater than or equal to the set detection threshold, it indicates that the defective part does not meet the requirements, and the label of the defective part is output as qualified. If the test result of the test piece is unqualified, and the defective test piece is a test piece for equipment fluctuation, then the label of the defective test piece is updated to "Equipment Fluctuation Defective Product"; if the defective test piece is a test piece for parameter fluctuation, then the label of the defective test piece is updated to "Parameter Fluctuation Defective Product". The number of equipment fluctuation defective products and parameter fluctuation defective products within a preset time period are counted separately, and the ratio of the two is calculated to obtain the ratio of the number of equipment fluctuation defective products to parameter fluctuation defective products, which is recorded as the preset reference value. It should be noted that the preset time period is 30 minutes or 60 minutes, etc., which can be set by those skilled in the art.

[0058] When the set reference ratio is greater than the maximum value in the set ratio range, an equipment maintenance warning signal is generated; when the set reference ratio is within the set ratio range, a setting parameter warning signal is generated; when the set reference ratio is less than the minimum value in the set ratio range, a process parameter adjustment warning signal is generated. The generated equipment maintenance warning signal, setting parameter warning signal, and process parameter adjustment warning signal are fed back to the server. When the server receives the equipment maintenance warning signal, it sends an equipment maintenance notification to the equipment technicians. When the server receives the setting parameter warning signal, it sends an equipment maintenance notification and a process parameter adjustment notification to both the equipment technicians and process technicians. When the server receives the process parameter adjustment warning signal, it sends a process parameter adjustment notification to the process technicians.

[0059] By analyzing the structure, performance, and surface of the defective part to be inspected, spacing parameters, surface parameters, and performance parameters are obtained. These three parameters are then comprehensively analyzed to obtain the detection value, which is compared with the set detection threshold. This enables quality inspection of the defective part, allowing for rapid and accurate detection and output of test results. This improves the stability and consistency of product quality, avoids the adverse consequences of defective products, and also helps enterprises track and monitor the operating status of equipment and changes in process parameters. This allows for timely detection of problems and the implementation of corresponding maintenance and adjustment measures, thereby improving production efficiency and product competitiveness.

[0060] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0061] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A quality inspection system for precision hardware parts processing, comprising a data acquisition unit and a server, wherein the data acquisition unit acquires equipment operating parameters and processing parameters respectively, and sends them to the server for storage; Its features are, Also includes: Processing analysis module and defect detection module; The processing analysis module analyzes equipment operating parameters and processing parameters to determine the defect risks of precision hardware parts by analyzing equipment operating fluctuations and process parameter fluctuations, as detailed below: S1: The specific steps for analyzing equipment operation fluctuations through equipment operating parameters are as follows: S11: Extract the equipment temperature value, construct a graph of equipment temperature value change relationship with time as the horizontal axis and equipment temperature value as the vertical axis; analyze the temperature value change relationship graph to obtain the slope difference and the increase / decrease ratio, and perform numerical analysis on the two to obtain the temperature fluctuation value; S12: Extract the motor speed of the equipment, set several speed ranges, compare and match the motor speeds of the equipment with the set speed ranges, and count the number of equipment motors in each set speed range. The range with the highest number of equipment motors is designated as the stable range, and the other ranges are combined into fluctuation ranges. The motor speeds in the fluctuation ranges are designated as fluctuation speeds Ri, where i represents the fluctuation speed number (i = 1, 2, 3, ..., n1), and n1 represents the total number of fluctuation speeds. The average of the motor speeds in the stable ranges is calculated to obtain the stable speed, denoted as WR. Then, using the set formula... The speed fluctuation value RZ is calculated, where r1 and r2 are the set correction factors. This represents the average value of the fluctuating rotational speed; S13: Extract noise values ​​and construct a noise spectrum with the acquisition time corresponding to the noise value as the horizontal axis and the noise value as the vertical axis. Perform graphical analysis based on the noise spectrum to obtain the spectrum fluctuation value. S14: Normalize the temperature fluctuation value, speed fluctuation value, and spectrum fluctuation value and take their values. Analyze the values ​​to obtain the operating fluctuation value. When the operating fluctuation value is greater than or equal to the set operating threshold, the precision hardware part corresponding to the equipment operating parameter is recorded as the equipment fluctuation test part, and the production time of the test part is used as the equipment fluctuation test part number. When the operating fluctuation value is less than the set threshold, execute S2. S2: Perform fluctuation analysis on the processing technology of precision hardware parts through processing technology parameters to obtain the fluctuation degree. When the fluctuation degree is greater than or equal to the set degree threshold, the precision hardware parts corresponding to the equipment operating parameters are recorded as parameter fluctuation test parts. When the fluctuation degree is less than the set degree threshold, the precision hardware parts are output as qualified products. S3: The generated equipment fluctuation test items or parameter fluctuation test items and their numbered items are integrated into defect test items and defect test item numbers, and a picking instruction is generated and sent to the picking robot; when the picking robot receives the picking instruction, it picks out the defect test items by recognizing the defect test item number. The defect detection module performs defect detection on the part to be inspected and outputs the detection results, which include qualified and unqualified results, and implements corresponding early warning strategies based on the detection results.

2. The quality inspection system for precision hardware machining according to claim 1, characterized in that, The fluctuation degree of the machining process of precision hardware parts is obtained by analyzing the fluctuation of the machining process parameters, as follows: 201: Extract the injection temperature, cooling temperature, injection pressure, cutting speed, and cutting depth, and combine them with standard injection temperature, standard cooling temperature, standard injection pressure, standard cutting speed, and standard cutting depth for numerical analysis to obtain parameter fluctuation values; and so on to obtain all parameter fluctuation values ​​of the hardware part during the production and processing period, and calculate the average value of the average parameter fluctuation value. 202: Extract parameter fluctuation values, compare and analyze the parameter fluctuation values ​​with the set fluctuation range to divide the parameter fluctuation values ​​into high fluctuation values, medium fluctuation values ​​and low fluctuation values, count the number of high fluctuation values, medium fluctuation values ​​and low fluctuation values ​​respectively, and perform numerical analysis on the three to obtain the fluctuation coefficient; 203: Numerical analysis of the average parameter fluctuation value and fluctuation coefficient is performed to obtain the volatility.

3. The quality inspection system for precision hardware machining according to claim 1, characterized in that, The defect detection process involves inspecting the defective part and outputting the results, as detailed below: 301: The defective part to be inspected is scanned by a laser scanner to establish a three-dimensional model for inspection, and then paired with the point cloud data of the standard model. For each pair of paired points, the Euclidean distance between them is calculated, and so on to obtain the Euclidean distance between all paired points. The distances are then summed to obtain the spacing parameter. 302: By heating the defective part to be inspected and using an infrared thermal imager to acquire a heat distribution map, the heat distribution map is divided into several regions, and the RGB value of each region is extracted. The RGB values ​​of each region in the heat distribution map are analyzed to obtain performance parameters. 303: Acquire surface images of the defective part to be inspected using a high-definition camera, identify scratches and cracks in the surface images using a photo recognition device, fill the scratches and cracks with different colors to obtain a filled image, and perform quantitative analysis on the filled image to obtain surface parameters. 304: The spacing parameters, surface parameters, and performance parameters are numerically processed to obtain the detection value. When the detection value is less than the set detection threshold, the detection result of the defective part is output as qualified, and the label of the defective part is updated to qualified. When the detection value is greater than or equal to the set detection threshold, the detection result of the defective part is output as unqualified. If the defective part is a part with equipment fluctuation, the label of the defective part is updated to equipment fluctuation defective. If the defective part is a part with parameter fluctuation, the label of the defective part is updated to parameter fluctuation defective.

4. The quality inspection system for precision hardware machining according to claim 3, characterized in that, Based on the test results, corresponding early warning strategies will be implemented, as follows: The number of equipment fluctuation defects and parameter fluctuation defects within a preset time period is counted, and the ratio of the two is calculated to obtain the ratio of the number of equipment fluctuation defects to parameter fluctuation defects, which is recorded as the set parameter ratio. The set parameter ratio is compared and analyzed with the set ratio range to generate equipment maintenance early warning signal, set parameter early warning signal or process parameter adjustment early warning signal, and then fed back to the server. The server generates a corresponding warning notification based on the type of warning signal received and sends it to the relevant technical personnel.

Images