A method for manufacturing a high-reliability pin and mother header
Through real-time monitoring and prediction model analysis, combined with deep learning algorithms, the problem of difficult time discovery of quality deviations and defects in the assembly process of needle and master row assembly is solved, and high-reliability production process and product quality control is achieved, and production efficiency is improved. stability.
Patent Information
- Application Number
- CN202410596660.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-14
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-05-14
AI Technical Summary
The quality deviations and defects caused by environmental factors and human errors during the assembly process of existing needle and master row assembly are difficult to detect and resolve in a timely manner, and there is a lack of effective simulation and debugging and parameter correction methods, which affects product quality and production efficiency.
Through the management side, the processing equipment operating parameters and image data are monitored in real time, the prediction model and deep learning algorithms are used to perform defect detection and abnormal prediction, quality evaluation and traceability tracking, and correction instructions are sent to optimize the production process.
It realizes timely discovery and accurate resolution of production defects, improves product quality control and production line efficiency, ensures product traceability and production process stability, and reduces equipment downtime and resource waste.
Smart Images

Figure CN118352862B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of circuit connection, and in particular to a method for manufacturing a high-reliability pin and mother header. Background Art
[0002] Pin headers and female headers are a pair of matching devices used to establish electrical connections in electronic components. They are usually used for plug-in connections between electronic circuit boards or between electronic components and circuit boards. Pin headers are connectors with a row of upright metal pins, and female headers usually have holes that match the pin headers for plugging into the metal pins of the pin headers. In practical applications, pin headers and female headers are often used for circuit board or system expansion, modular design, easy maintenance and upgrading, and convenience during assembly. The assembly accuracy of pin headers and female headers directly affects the quality of the final connector.
[0003] However, the existing assembly process based on pin and female headers still has some shortcomings:
[0004] 1. In the actual assembly process, due to various environmental factors, such as power fluctuations, human errors and equipment failures, various abnormal conditions may occur in the raw material transportation or assembly process of the pin and mother headers, resulting in deviations in the quality of the final processed products;
[0005] 2. When a defective workpiece appears, it is difficult to conduct specific analysis and trace the flaws of the defective workpiece. It is also affected by environmental factors, making it difficult to discover and solve potential problems in a short period of time, and it is difficult to independently perform simulation debugging and correct problem parameters. Summary of the invention
[0006] 1. Technical issues to be solved
[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides a method for manufacturing a high-reliability pin and socket header, which can effectively solve the problems of the prior art.
[0008] (II) Technical solution
[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0010] The invention discloses a method for manufacturing a high-reliability pin and mother header, comprising the following steps:
[0011] Step 1: The management side defines product specifications, including the size, shape and material grade requirements of the pin and female headers, sets quality inspection standards, establishes a quality inspection reference database, and marks the inspection objects: pin and female headers and related processing equipment;
[0012] Step 2: The processing equipment is started, and the heating, milling and cutting steps are performed. The raw materials are automatically fed to the processing equipment, and the processing equipment positions and assembles the pin headers and the female headers according to the preset specifications;
[0013] Step 3: During the processing and assembly of the pin and bus headers, the detection unit monitors the operating parameters of the processing equipment in real time, dynamically obtains the image data of the pin and bus headers during the assembly process, and performs surface defect detection, predictively verifies whether there are any doubts about the obtained operating parameters and surface defect data results, and performs performance detection on the assembled workpieces. By comparing with the reference database, the verified data is quality evaluated to obtain the quality evaluation results;
[0014] Step 4: Mark the workpieces whose quality assessment results are lower than the expected parameters as defective workpieces and remove them. Trace the associated processing equipment and raw materials, and send correction instructions to the processing equipment based on the judgment results of the intelligent algorithm.
[0015] Step 5: All pass quality inspection for cleaning, labeling and packaging, then proceed to inventory management or direct shipment.
[0016] Furthermore, the operating parameters of the processing equipment in step 3 include: temperature, pressure, speed, current and voltage.
[0017] Furthermore, in the process of surface defect detection in step 3, a high-resolution camera is used to capture an image of the object to be inspected, smoothing filtering or median filtering is used to remove noise in the image, the contrast of the image is adjusted, the defect area is separated from the background according to the brightness or color threshold, and the edge of the defect area is detected, the defect area, perimeter and main axis length are described, the contrast, uniformity and correlation characteristics described by the gray level co-occurrence matrix are obtained, and the defects of the obtained detection data are analyzed to see whether they exceed an acceptable range.
[0018] Furthermore, in the process of whether there is any doubt about the operating parameters and surface defect data results obtained by the predictive verification in step 3, a prediction model is pre-constructed, and the reference database provides historical standard equipment operation data and image data and abnormal equipment operation data and image data, and constitutes a training sample set to be input into the prediction model for training, and defect features are extracted. If it is determined that there is a doubt, the current data is input into the prediction model, and the extracted features are analyzed by a deep learning algorithm to classify the defect type, and an abnormal prediction is performed. If the prediction result is consistent with a specified threshold, the current questionable data is judged to be abnormal data. Otherwise, the current verification data is released.
[0019] Furthermore, the performance test of the assembled workpiece in step 3 includes: electrical connectivity, mechanical strength and contact impedance.
[0020] Furthermore, the process of tracing the source in step 4 includes the following steps:
[0021] a. Obtain image data of defective workpieces before and during assembly and operating parameters of associated processing equipment;
[0022] b. Analyze whether there is interference in the image data;
[0023] c. If it exists, mark the interference area and send alarm data to the management end;
[0024] d. If it does not exist, the image data is put into the reference database and classified as abnormal data under the current processing environment;
[0025] e. Analyze whether there is interference in the operating parameters;
[0026] f. If it exists, the operation of the current associated processing equipment will be terminated and the production log will be uploaded to the management end;
[0027] g. If it does not exist, the operating parameters will be put into the reference database and classified as abnormal data under the current processing environment.
[0028] Furthermore, the interference factors of the image data in step b include: abnormal lighting conditions, abnormal vibration speed, abnormal environmental visibility, abnormal image recognition and abnormal compression transmission.
[0029] Furthermore, in the process of analyzing whether there is interference in the image data in step b, the feature vector data of the object to be verified and the feature vector data of the standard image are extracted, and the two sets of feature vector data are compared by distance, and it is calculated whether the deviation value of the feature vector data of the verification object corresponding to the feature vector data of the standard image exceeds a preset threshold, that is, whether there is interference, wherein the distance calculation formula is:
[0030]
[0031] Where T represents the distance parameter;
[0032] x is the standard image feature value;
[0033] y is the feature value of the image to be verified;
[0034] n is the total number of samples of the verified objects.
[0035] Furthermore, the interfering factors of the operating parameters in step e include: power supply fluctuation, operating temperature change, operating humidity change, abnormal mechanical wear, electromagnetic interference and improper calibration.
[0036] Furthermore, the editing process of the correction instruction in step 4 is:
[0037] Develop hypotheses about the problematic processing equipment based on existing data and identify potential processing parameters that need to be adjusted;
[0038] Build and run the adjustment model to see if the simulation results achieve the expected improvement;
[0039] If the simulation results do not meet the requirements, gradually adjust the parameters in the simulation to gradually approach the target performance indicators within the adjustment model.
[0040] For each simulation adjustment, evaluate the simulated product quality and the performance of the pin and motherboard headers to confirm whether the simulation adjustment makes the performance reach or exceed the reasonable range;
[0041] When the simulation results show that the parameters achieve the expected effects, the adjusted data will be applied to the actual processing equipment and the parameter values adjusted each time will be recorded.
[0042] (III) Beneficial effects
[0043] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects:
[0044] 1. Through the use of predictive models and deep learning algorithms, problem discovery and resolution are made more timely and accurate, reducing manual intervention and human errors, improving the operating speed of the production line and product quality control, and real-time monitoring of operating parameters and instant acquisition of image data allow the entire production process to be monitored. Using historical data and real-time data, combined with predictive models, decision analysis is performed on the production process and product quality. This method can foresee potential production defects and provide corrective instructions, optimizing the production process through data-driven decision-making.
[0045] 2. Through comprehensive quality assessment and traceability, a variety of performance indicators including electrical connectivity, mechanical strength and contact impedance are comprehensively evaluated. When problems are found in defective products, they can be quickly traced back to specific processing equipment and process parameters. Quality assessment and traceability ensure the traceability of product quality and continuous improvement of the production process.
[0046] 3. When encountering abnormalities in the production process, not only will an alarm be sounded and the equipment stopped, but preventive measures will also be taken. Through the process of simulated debugging, the problem parameters will be gradually corrected and calibrated, and then the actual application will be carried out again after verification, so as to prevent the problem from recurring, reduce the risk of equipment downtime and inefficiency, and thus increase the overall economic benefits of the product. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0048] Figure 1 It is a schematic diagram of the process of the present invention;
[0049] Figure 2 It is a schematic diagram of the process of tracing the source in the present invention. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0051] The present invention will be further described below in conjunction with the embodiments.
[0052] Example 1
[0053] A method for manufacturing a high-reliability pin and female header according to this embodiment is as follows: Figure 1 As shown, the following steps are included:
[0054] Step 1: The management side defines product specifications, including the size, shape and material grade requirements of the pin and female headers, sets quality inspection standards, establishes a quality inspection reference database, and marks the inspection objects: pin and female headers and related processing equipment;
[0055] Step 2: The processing equipment is started, and the heating, milling and cutting steps are performed. The raw materials are automatically fed to the processing equipment, and the processing equipment positions and assembles the pin headers and the female headers according to the preset specifications;
[0056] Step 3: During the processing and assembly of the pin header and the mother header, the detection unit monitors the operating parameters of the processing equipment in real time. The operating parameters of the processing equipment include: temperature, pressure, speed, current and voltage, dynamically obtains the image data of the pin header and the mother header during the assembly process, and performs surface defect detection;
[0057] In the process of surface defect detection, a high-resolution camera is used to capture the image of the object to be detected, and the noise in the image is removed by smoothing filtering or median filtering. The contrast of the image is adjusted, the defect area is separated from the background according to the brightness or color threshold, and the edge of the defect area is detected. The defect area, perimeter and main axis length are described, and the contrast, uniformity and correlation characteristics described by the gray level co-occurrence matrix are obtained. The defects of the obtained detection data are analyzed to see whether they exceed the acceptable range;
[0058] Whether there are any doubts about the operating parameters and surface defect data obtained by predictive verification, and the performance of the assembled workpiece is tested. The performance test of the assembled workpiece includes: electrical connectivity, mechanical strength and contact impedance. By comparing with the reference database, the quality of the verified data is evaluated to obtain the quality evaluation results;
[0059] In the process of predictive verification of whether there is any doubt about the operating parameters and surface defect data results, a prediction model is pre-built, and the reference database provides historical standard equipment operation data and image data and abnormal equipment operation data and image data, and constitutes a training sample set to be put into the prediction model for training, and the defect features are extracted. If it is determined that there is a doubt, the current data is put into the prediction model, and the extracted features are analyzed by the deep learning algorithm to classify the defect type, and abnormal prediction is performed. If the prediction result is consistent with a higher than the specified threshold, the current questionable data is judged to be abnormal data, otherwise, the current verification data is released;
[0060] Step 4: Mark the workpieces whose quality assessment results are lower than the expected parameters as defective workpieces and remove them. Trace the associated processing equipment and raw materials, and send correction instructions to the processing equipment based on the judgment results of the intelligent algorithm.
[0061] Step 5: All pass quality inspection for cleaning, labeling and packaging, then proceed to inventory management or direct shipment.
[0062] Compared with the existing technology, the intelligent algorithm and deep learning technology are used to realize real-time monitoring and defect detection in the production process of pin and mother headers, thereby improving the quality and reliability of the product. At the same time, the predictive verification method is used to analyze the operating parameters and surface defect data, which can timely identify and correct abnormal data, ensuring the stability and reliability of the product production process. In addition, by tracing the defective workpieces and sending correction instructions, this method can also improve the efficiency of the production process and reduce resource waste. In general, compared with the existing technology, this production method has a higher level of intelligence and automation, which can effectively improve product quality and production efficiency and reduce production costs.
[0063] Example 2
[0064] At other levels, this embodiment also provides a process for tracing the source of defective workpieces, such as Figure 2 As shown in the figure, the traceability process includes the following steps:
[0065] a. Obtain image data of defective workpieces before and during assembly and operating parameters of associated processing equipment;
[0066] b. Analyze whether there is interference in the image data. The interference factors of image data include: abnormal lighting conditions, abnormal vibration speed, abnormal environmental visibility, abnormal image recognition and abnormal compression transmission;
[0067] c. If it exists, mark the interference area and send alarm data to the management end;
[0068] d. If it does not exist, the image data is put into the reference database and classified as abnormal data under the current processing environment;
[0069] e. Analyze whether there is interference in the operating parameters. The interference factors of the operating parameters include: power supply fluctuations, operating temperature changes, operating humidity changes, abnormal mechanical wear, electromagnetic interference and improper calibration;
[0070] f. If it exists, the operation of the current associated processing equipment will be terminated and the production log will be uploaded to the management end;
[0071] g. If it does not exist, the operating parameters will be put into the reference database and classified as abnormal data under the current processing environment.
[0072] In the process of analyzing whether there is interference in the image data in step b, the feature vector data of the object to be verified and the feature vector data of the standard image are extracted, and the two sets of feature vector data are compared by distance, and the deviation value of the feature vector data of the verification object corresponding to the feature vector data of the standard image is calculated to determine whether there is interference, wherein the distance calculation formula is:
[0073]
[0074] Where T represents the distance parameter;
[0075] x is the standard image feature value;
[0076] y is the feature value of the image to be verified;
[0077] n is the total number of samples of the verified objects.
[0078] Compared with the existing technology, by analyzing image data and operating parameters, the possible interference factors in the processing process can be automatically identified, and the problem can be quickly located without human intervention. Once interference is found in image data or operating parameters, alarm data can be sent to the management end immediately, so that the problem can be discovered and handled in time to avoid further affecting production. The abnormal data is put into the reference database and classified, which is helpful to establish a more complete abnormal situation database, providing a reference basis for the handling of similar problems in the future. The characteristic vector data is used to compare the deviation value. This method is more objective and accurate, and can quickly determine whether there is interference, thereby improving the accuracy and efficiency of the judgment.
[0079] Example 3
[0080] The editing process of the correction instruction provided in this embodiment is:
[0081] Develop hypotheses about the problematic processing equipment based on existing data and identify potential processing parameters that need to be adjusted;
[0082] Build and run the adjustment model to see if the simulation results achieve the expected improvement;
[0083] If the simulation results do not meet the requirements, gradually adjust the parameters in the simulation to gradually approach the target performance indicators within the adjustment model.
[0084] For each simulation adjustment, evaluate the simulated product quality and the performance of the pin and motherboard headers to confirm whether the simulation adjustment makes the performance reach or exceed the reasonable range;
[0085] When the simulation results show that the parameters achieve the expected effects, the adjusted data will be applied to the actual processing equipment and the parameter values adjusted each time will be recorded.
[0086] In this embodiment, by constructing and running the adjustment model, the impact of parameter adjustment on product quality and performance can be observed in a simulated environment, avoiding direct trial and error on actual equipment, reducing the actual impact on production equipment and products, and taking the method of gradually adjusting the parameters in the simulation and gradually approaching the target performance indicators. This helps to refine the adjustment and improve the accuracy and efficiency of the adjustment. The product quality and performance after each simulation adjustment are evaluated to confirm whether the simulation adjustment has brought the performance into a reasonable range, which helps to verify the rationality of the adjustment effect. Recording the parameter value of each adjustment helps to establish a historical record of parameter adjustments, providing a reference for handling similar problems in the future.
[0087] In summary, the present invention uses intelligent algorithms and deep learning technology to achieve real-time monitoring and defect detection of the pin and socket production process, greatly improving product quality and reliability. At the same time, the predictive verification method is used to deeply analyze the operating parameters and surface defect data, and abnormal data can be quickly identified and corrected, ensuring the stability and reliability of the product production process. In addition, by tracing the source of defective workpieces and sending correction instructions, this method can also improve production efficiency and reduce resource waste.
[0088] The present invention can automatically identify possible interference factors in the processing process by carefully analyzing image data and operating parameters, and quickly locate the problem. Once the image data or operating parameters are found to be abnormal, the system can immediately send an alarm to the management end, so that the problem can be dealt with in time to avoid further impact on production. At the same time, the abnormal data is included in the reference database for classification, which provides strong support for the establishment of a more complete abnormal database and provides a valuable reference for the handling of similar problems in the future. By using feature vector data to compare deviation values, the objectivity and accuracy of the judgment are improved, making the problem judgment more rapid and accurate.
[0089] By constructing and running the adjustment model, the present invention can observe the impact of parameter adjustment on product quality and performance in a simulated environment, avoid trial and error on actual equipment, and reduce the potential impact on production equipment and products. By taking the method of gradually adjusting the simulation parameters, the target performance indicators are gradually approached, which helps to achieve refined adjustment and improve the accuracy and efficiency of the adjustment. At the same time, the product quality and performance after each simulation adjustment are evaluated to ensure that the simulation adjustment can bring the performance into a reasonable range, verify the rationality of the adjustment effect, and record the parameter value of each adjustment, providing a basis for establishing a parameter adjustment history record.
[0090] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for manufacturing a high-reliability pin and female header, characterized in that: The following steps are involved: Step 1: The management side defines product specifications, including the size, shape and material grade requirements of the pin and female headers, sets quality inspection standards, establishes a quality inspection reference database, and marks the inspection objects: pin and female headers and related processing equipment; Step 2: The processing equipment is started, and the heating, milling and cutting steps are performed. The raw materials are automatically fed to the processing equipment, and the processing equipment positions and assembles the pin headers and the female headers according to the preset specifications; Step 3: During the processing and assembly of the pin and bus headers, the detection unit monitors the operating parameters of the processing equipment in real time, dynamically obtains the image data of the pin and bus headers during the assembly process, and performs surface defect detection, predictively verifies whether there are any doubts about the obtained operating parameters and surface defect data results, and performs performance detection on the assembled workpieces. By comparing with the reference database, the verified data is quality evaluated to obtain the quality evaluation results; Step 4: Mark the workpieces whose quality assessment results are lower than the expected parameters as defective workpieces and remove them. Trace the associated processing equipment and raw materials, and send correction instructions to the processing equipment based on the judgment results of the intelligent algorithm. Step 5: All products that have passed quality inspection are cleaned, labeled and packaged, and then go into inventory management or ship directly; The operating parameters of the processing equipment in step 3 include: temperature, pressure, speed, current and voltage; In the process of surface defect detection in step 3, a high-resolution camera is used to capture an image of the object to be detected, a smoothing filter or a median filter is used to remove noise in the image, the contrast of the image is adjusted, the defect area is separated from the background according to the brightness or color threshold, and the edge of the defect area is detected, the defect area, perimeter and main axis length are described, the contrast, uniformity and correlation characteristics described by the gray level co-occurrence matrix are obtained, and the defects of the obtained detection data are analyzed to see whether they exceed the acceptable range; In the process of whether there is any doubt about the operating parameters and surface defect data results obtained by the predictive verification in step 3, a prediction model is pre-built, and the historical standard equipment operation data and image data and abnormal equipment operation data and image data are provided by the reference database, and a training sample set is formed to be put into the prediction model for training, and defect features are extracted. If it is determined that there is a doubt, the current data is put into the prediction model, and the extracted features are analyzed by the deep learning algorithm and the defect type is classified to perform abnormal prediction. If the prediction result is consistent with a higher than a specified threshold, the current questionable data is judged to be abnormal data, otherwise, the current verification data is released; The performance test of the assembled workpiece in step 3 includes: electrical connectivity, mechanical strength and contact impedance; The process of tracing the source in step 4 includes the following steps: a. Obtain image data of defective workpieces before and during assembly and operating parameters of associated processing equipment; b. Analyze whether there is interference in the image data; c. If it exists, mark the interference area and send alarm data to the management end; d. If it does not exist, the image data is put into the reference database and classified as abnormal data under the current processing environment; e. Analyze whether there is interference in the operating parameters; f. If it exists, the operation of the current associated processing equipment will be terminated and the production log will be uploaded to the management end; g. If it does not exist, the operating parameters will be put into the reference database and classified as abnormal data under the current processing environment.
2. The method for manufacturing a high-reliability pin and female header according to claim 1, characterized in that: The interference factors of the image data in step b include: abnormal lighting conditions, abnormal vibration speed, abnormal environmental visibility, abnormal image recognition and abnormal compression transmission.
3. The method for manufacturing a high-reliability pin and female header according to claim 1, characterized in that: In the process of analyzing whether there is interference in the image data in step b, the feature vector data of the object to be verified and the feature vector data of the standard image are extracted, and the two sets of feature vector data are compared by distance, and it is calculated whether the deviation value of the feature vector data of the verification object corresponding to the feature vector data of the standard image exceeds a preset threshold, that is, whether there is interference, wherein the distance calculation formula is: T= ; Where T represents the distance parameter; is the standard image feature value; is the feature value of the image to be verified; n is the total number of samples of the verified objects.
4. The method for manufacturing a high-reliability pin and female header according to claim 1, characterized in that: The interfering factors of the operating parameters in step e include: power supply fluctuation, operating temperature change, operating humidity change, abnormal mechanical wear, electromagnetic interference and improper calibration.
5. The method for manufacturing a high-reliability pin and female header according to claim 1, characterized in that: The editing process of the correction instruction in step 1 is as follows: Develop hypotheses about the problematic processing equipment based on existing data and identify potential processing parameters that need to be adjusted; Build and run the adjustment model to see if the simulation results achieve the expected improvement; If the simulation results do not meet the requirements, gradually adjust the parameters in the simulation to gradually approach the target performance indicators within the adjustment model. For each simulation adjustment, evaluate the simulated product quality and the performance of the pin and motherboard headers to confirm whether the simulation adjustment makes the performance reach or exceed the reasonable range; When the simulation results show that the parameters achieve the expected effects, the adjusted data will be applied to the actual processing equipment and the parameter values adjusted each time will be recorded.
