Quality detection method for safety valve spring

Abstract

The invention discloses a quality detection method for a safety valve spring, and relates to the technical field of spring quality detection, and the method comprises the steps: constructing an appearance detection module, and carrying out the surface defect detection and size verification of a target safety valve spring; performing performance test and performance grade evaluation on the target safety valve spring through a performance detection module; and combining a surface defect detection result, a size verification result and a performance evaluation result to carry out spring quality comprehensive evaluation, and extracting a defective finished product production number according to a quality judgment result to carry out correlation analysis and defective product traceability. The technical problem that an existing safety valve spring quality detection method is low in accuracy and reliability due to the complexity of an application environment and the diversity of performance requirements in the prior art is solved, and the purpose of detecting the quality of the safety valve spring through all-dimensional and multi-angle appearance quality detection and performance attribute detection is achieved. And the accuracy and reliability of quality detection of the safety valve spring are improved.

Description

Technical Field

[0001] The invention relates to the technical field of spring quality detection, and in particular to a quality detection method for a safety valve spring. Background Art

[0002] A safety valve is an automatic valve that can automatically open and discharge the medium when the internal pressure of the system exceeds the predetermined safety value to prevent the equipment or system from being damaged by overpressure. As the driving force source of the safety valve, the stability and accuracy of the spring performance are crucial. With the continuous development of industrial technology, the performance requirements for safety valves and their springs are getting higher and higher.

[0003] However, since safety valve springs may be used in various harsh working environments, such as high temperature, high pressure, corrosion, etc., it is necessary to avoid environmental factors interfering with the test results during the test process. At the same time, different industries and different application occasions have different performance requirements for safety valve springs, resulting in the existing spring quality testing methods being unable to meet the test accuracy requirements. Summary of the invention

[0004] The present application provides a quality inspection method for a safety valve spring, which is used to solve the technical problem in the prior art that the accuracy and reliability of the existing quality inspection method for a safety valve spring are low due to the complexity of the application environment and the diversity of performance requirements.

[0005] The present application provides a quality inspection method for a safety valve spring, the method comprising: constructing an appearance inspection module, the appearance inspection module comprising an image acquisition unit, a defect recognition unit and a dimension verification unit; performing surface defect inspection and dimension verification on a target safety valve spring through the appearance inspection module to obtain surface defect inspection results and dimension verification results; performing performance testing and performance grade evaluation on the target safety valve spring through a performance inspection module to obtain performance evaluation results, wherein the performance inspection comprises compressive stability inspection, corrosion resistance inspection and comprehensive performance correlation inspection; performing comprehensive spring quality evaluation in combination with the surface defect inspection results, the dimension verification results and the performance evaluation results to obtain a quality determination result; extracting defective finished product production numbers for correlation analysis based on the quality determination result, and tracing the defective products based on the correlation analysis results.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides a quality inspection method for a safety valve spring, which relates to the technical field of spring quality inspection. By constructing an appearance inspection module, surface defect inspection and dimension verification are performed on a target safety valve spring. By using a performance inspection module, performance testing and performance grade evaluation are performed on the target safety valve spring. The surface defect inspection results, dimension verification results and performance evaluation results are combined to conduct a comprehensive evaluation of the spring quality. Based on the quality judgment results, the production numbers of defective finished products are extracted for correlation analysis and defective product traceability. The technical problem of low accuracy and reliability of the existing safety valve spring quality inspection method in the prior art due to the complexity of the application environment and the diversity of performance requirements is solved, and the technical effect of improving the accuracy and reliability of safety valve spring quality inspection is achieved through all-round and multi-angle appearance quality inspection and performance attribute inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a quality inspection method for a safety valve spring provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a flow chart of obtaining surface defect detection results and dimension verification results in a quality inspection method for a safety valve spring provided in an embodiment of the present application;

[0011] Figure 3 A schematic diagram of a flow chart for obtaining performance evaluation results in a quality inspection method for a safety valve spring provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The present application provides a quality inspection method for a safety valve spring, which is used to solve the technical problem in the prior art that the accuracy and reliability of the existing quality inspection method for a safety valve spring are low due to the complexity of the application environment and the diversity of performance requirements.

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0015] Embodiment 1

[0016] like Figure 1 As shown, the present application provides a method for detecting the quality of a safety valve spring, the method comprising:

[0017] P10: Construct an appearance inspection module, which includes an image acquisition unit, a defect recognition unit and a size verification unit.

[0018] It should be understood that, first of all, in order to meet the appearance quality inspection requirements of the safety valve spring, an appearance quality inspection module is constructed, and the appearance inspection module includes an image acquisition unit, a defect recognition unit and a dimension verification unit. Among them, the image acquisition unit is responsible for capturing high-definition images or video data of the safety valve spring, which can be completed by a high-precision camera or image sensor to ensure that the captured image is clear and distortion-free, and can truly reflect the surface condition of the spring. In order to obtain high-quality images, the image acquisition unit needs to have high resolution, good light adaptability and stable imaging capabilities, and the installation position and angle of the camera need to be considered to ensure that all inspection surfaces of the spring can be fully covered.

[0019] The defect recognition unit is used to analyze and process the image acquired by the image acquisition unit according to image processing technology and machine learning algorithms, including image denoising, enhancement and other preprocessing, and then using pattern recognition or deep learning algorithms to detect and mark defective areas, and identify various defects on the spring surface, including cracks, scratches, rust, stains, uneven surfaces, etc. The size verification unit is responsible for verifying whether the size of the safety valve spring meets the design requirements or standard specifications. For example, non-contact measurement technology, such as laser ranging, machine vision, etc., is used to accurately measure the size of the spring, and the actual measurement value is compared with the standard value or design value to evaluate whether the size deviation of the spring is within the allowable range.

[0020] P20: Perform surface defect detection and dimension verification on the target safety valve spring through the appearance inspection module to obtain surface defect detection results and dimension verification results.

[0021] Further, such as Figure 2 As shown, step P20 of the embodiment of the present application also includes:

[0022] P21: The target safety valve spring is scanned in all directions by the image acquisition unit to obtain a multi-sensor image set, wherein the multi-sensor image set includes an acquisition device identifier, an acquisition angle identifier and a lighting condition identifier; P22: According to the defect recognition unit, defect fusion processing and defect recognition are performed based on the multi-sensor image to obtain a surface defect detection result; P23: According to the dimension verification unit, dimension deviation detection is performed based on the multi-sensor image to obtain a dimension verification result.

[0023] Optionally, the target safety valve spring is subjected to surface defect detection and size verification through the appearance inspection module. First, the target safety valve spring is scanned in all directions through the image acquisition unit to ensure that its images are captured from multiple angles and under different lighting conditions to ensure the accuracy and comprehensiveness of the extracted defect recognition images, and obtain a multi-sensor image set, which not only contains the image data of the target safety valve spring at different shooting angles and different lighting conditions, but also carries additional information such as acquisition device identification, acquisition angle identification, and lighting condition identification. These additional information help to eliminate image differences caused by different acquisition conditions, which is crucial for subsequent defect fusion processing and size deviation detection.

[0024] Furthermore, based on the multi-sensor image set, the defect recognition unit is used to perform defect fusion, including integrating defect information from images with different acquisition conditions (such as different acquisition equipment, different angles, and different lighting adjustments) to improve the accuracy and comprehensiveness of defect recognition. The defect recognition model is trained in combination with defect sample features through image processing technology and machine learning algorithms, and defect recognition is performed on the fused image to identify defects such as cracks, scratches, rust, stains, etc. on the surface of the spring, and record their location, size, and type, thereby generating surface defect detection results, including detailed descriptions of the defects and image evidence, for subsequent quality assessment.

[0025] Furthermore, by using the dimension verification unit and the multi-sensor image set to detect dimension deviation, non-contact measurement technology such as laser ranging and machine vision can be used to accurately measure the key dimensions of the spring, including the spring's diameter, length, number of turns, free height, compressed height, etc. And by comparing the actual measured value with the standard value or design value, it is evaluated whether the dimensional deviation of the spring is within the allowable range and the dimension verification result is obtained.

[0026] Furthermore, step P22 of the embodiment of the present application also includes:

[0027] P22-1: Based on the acquisition device identification, acquisition angle identification and lighting condition identification of the multi-sensor image, the multi-sensor image is subjected to a step-by-step defect feature fusion, including first-order multi-lighting feature fusion, second-order multi-angle feature fusion and third-order multi-device feature fusion in sequence to obtain multi-level fusion defect features; P22-2: The multi-level fusion defect features are identified through a defect recognition unit to obtain the surface defect detection result.

[0028] Specifically, the specific process of defect fusion processing based on the multi-sensor image may be to perform step-by-step defect feature fusion on the multi-sensor image based on the acquisition device identifier, acquisition angle identifier and illumination condition identifier of the multi-sensor image. First, in order to eliminate the influence of illumination conditions on the defect features in the image, a first-order multi-illumination feature fusion is performed, and images from the same acquisition device and the same acquisition angle but under different illumination conditions are grouped according to the illumination condition identifier. Then, the defect features in the images in the group are fused according to the grouping, and the defect features under different illuminations are compared by image superposition and comparison, adjusting the image brightness and contrast, etc., and extracting the image with the most obvious and accurate defect features in the group of images.

[0029] Furthermore, based on the illumination feature fusion result, a second-order multi-angle feature fusion is performed to integrate defect features from different acquisition angles to obtain more comprehensive defect information. Exemplarily, based on the first-order multi-illumination feature fusion, the defect features in images from different angles are further fused according to the acquisition angle identification, and the images from different angles are aligned to the same reference coordinate system using image registration technology, and then the defect features in these images are merged to obtain the multi-angle feature fusion result.

[0030] Furthermore, based on the multi-angle feature fusion results, the third-order multi-device feature fusion is performed to eliminate the impact of acquisition device differences on defect feature recognition. According to the acquisition device identification, the defect features in the images from different acquisition devices are fused, and the image quality differences and noise levels between different devices are considered. The acquired images of different devices are corrected through algorithm optimization to ensure the consistency and comparability of the fused defect features.

[0031] Furthermore, after obtaining the multi-level fusion defect features, the multi-level fusion defect features are identified by a defect recognition unit, wherein the defect recognition unit can be obtained by collecting sample defect features as training data and combining them with a deep learning network for supervised training. Through defect recognition, surface defect detection results are obtained, and the surface defect detection results include the type, location, size, image evidence, etc. of the defect, which can reflect the outer surface quality of the target safety valve spring.

[0032] Furthermore, step P23 of the embodiment of the present application also includes:

[0033] P23-1: The dimension verification unit is embedded with a standard component simulation model; P23-2: The dimension features of the component are extracted based on the multi-sensor image to generate a finished component simulation model; P23-3: After the finished component simulation model and the standard component simulation model are aligned through multi-points, the dimension deviation of key parts is calculated to obtain the dimension deviation result, and the dimension deviation threshold is compared to generate the dimension deviation level.

[0034] It should be understood that the specific process of dimensional deviation detection may be to first construct a standard component simulation model according to the design specifications, standard dimensions and shape parameters of the safety valve spring, and embed it in the dimension verification unit. The standard component simulation model represents the spring model in an ideal state. Further, based on the multi-sensor image, the geometric dimension features of the target safety valve spring are extracted by using image processing technology and three-dimensional reconstruction algorithm, and a finished component simulation model is constructed based on these features. The finished component simulation model is a digital representation of the actual product, which contains key information such as the shape and size of the spring.

[0035] Furthermore, in order to accurately compare the standard component simulation model and the finished component simulation model, multi-point alignment is first required. Specifically, multiple key points on the model (such as endpoints, intersections, center points, etc.) are selected, and these key points are aligned in three-dimensional space through an algorithm. After alignment, the two models will be in the same coordinate system, which is convenient for subsequent comparison and analysis. Furthermore, on the basis of multi-point alignment, the dimensional deviation of the key parts of the standard component simulation model and the finished component simulation model is calculated, including measuring the dimensional difference between the two models at the corresponding positions and calculating the deviation value. The deviation value can be expressed as an absolute deviation or a relative deviation, depending on the evaluation requirements.

[0036] Furthermore, the calculated dimensional deviation result is compared with a preset dimensional deviation threshold, which can be set according to product performance requirements. According to the size and range of the deviation value, the dimensional deviation is divided into different levels, such as qualified, slight deviation, severe deviation, etc. This helps to quickly determine whether the dimensional quality of the safety valve spring meets the requirements and provide a basis for subsequent production decisions.

[0037] P30: Through the performance detection module, the target safety valve spring is subjected to performance testing and performance level evaluation to obtain a performance evaluation result, wherein the performance detection includes pressure stability detection, corrosion resistance detection and comprehensive performance correlation detection.

[0038] Further, such as Figure 3 As shown, step P30 of the embodiment of the present application also includes:

[0039] P31: Based on the spring triggering record of the target safety valve in the real-time working environment, high-frequency triggering conditions are collected; P32: Based on the high-frequency triggering conditions, high-frequency triggering pressure values ​​and high-frequency environmental corrosion characteristics are extracted; P33: According to the high-frequency triggering pressure values ​​and high-frequency environmental corrosion characteristics, parameters are randomly combined to generate a variety of test conditions; P34: Based on the multiple test conditions, the performance test and performance level evaluation of the target safety valve spring are performed through the performance detection module to obtain the performance evaluation result.

[0040] Optionally, the performance test and performance level evaluation of the target safety valve spring is performed through the performance detection module. First, according to the spring triggering record of the target safety valve in the real-time working environment, the spring triggering data under different working conditions are collected, and the triggering frequency is counted to obtain high-frequency triggering conditions. These working conditions may include but are not limited to multiple triggerings in a short period of time, rapid changes in high pressure, etc.

[0041] Furthermore, based on the high-frequency triggering condition, the high-frequency triggering pressure value and the high-frequency environmental corrosion characteristics are extracted by performing a centralized trend analysis on the triggering pressure values ​​and the environmental corrosion characteristics of multiple high-frequency triggering conditions. The extracted high-frequency triggering pressure value and the high-frequency environmental corrosion characteristics are paired by using a random combination of parameters to generate a variety of different test conditions, that is, to create a series of test conditions simulating actual conditions, which are used to comprehensively evaluate the performance of the target safety valve spring under different conditions.

[0042] Furthermore, the performance detection module is used to perform multiple performance tests on the target safety valve spring according to the multiple test conditions, including the spring's compressive stability, corrosion resistance, and the comprehensive correlation between these properties. After the test is completed, the performance level of the spring is evaluated according to the performance test results, for example, by comparing the spring's performance test results with various performance test thresholds to perform a level evaluation and give the corresponding performance level evaluation results. This result will provide an important basis for subsequent product improvements, quality control, and production decisions.

[0043] Furthermore, step P34 of the embodiment of the present application also includes:

[0044] P34-1: The performance detection module includes a spring performance testing module and a spring performance evaluation module; P34-2: Based on the spring performance testing module, according to the multiple test conditions, the spring compressive performance simulation test, environmental corrosion simulation test and corrosion-compression correlation test are carried out respectively, wherein the compressive performance simulation test includes a compressive stability test and a yield strength stability test.

[0045] It should be understood that the performance detection module includes a spring performance test module and a spring performance evaluation module, wherein the spring performance test module is responsible for performing specific performance test experiments, including simulating spring behavior under different working conditions, and is equipped with high-precision test equipment and control systems, and can accurately measure and record various performance parameters of the spring during the test. The spring performance evaluation module is responsible for processing and analyzing the test data and evaluating the performance level of the spring.

[0046] First, based on the spring performance test module, tests are performed for the various test conditions, including spring compression performance simulation test, environmental corrosion simulation test and corrosion-compression correlation test. The compression performance simulation test includes a compression stability test and a yield strength stability test. Among them, the compression stability test can simulate the stability performance of the target safety valve spring under continuous or periodic pressure. During the test, the deformation, rebound speed and other parameters of the spring at different pressure levels are recorded to evaluate its compression stability and recovery ability. The yield strength stability test can further test the stability of the yield strength of the spring when it reaches the yield point, that is, the stability of the compression resistance of the spring under plastic deformation.

[0047] At the same time, the environmental corrosion simulation test can simulate the performance changes of the target safety valve spring in different corrosive environments. By controlling the temperature, humidity, corrosive media and other factors of the test environment, the corrosion conditions and performance changes on the spring surface are observed and recorded to evaluate its corrosion resistance. The corrosion-compression resistance correlation test combines the compression resistance simulation test and the environmental corrosion simulation test to evaluate the impact of corrosion on the compression resistance of the spring. After the corrosion test, a compression resistance test is performed immediately or after a certain period of recovery, and the changes in the compression resistance of the spring before and after corrosion are compared to reveal the correlation between corrosion and compression resistance. Through the implementation of the above-mentioned specific test methods, the performance of the target safety valve spring under different working conditions can be understood more comprehensively and in-depth, providing strong data support for its performance level evaluation and subsequent product improvements.

[0048] Furthermore, step P34-2 of the embodiment of the present application also includes:

[0049] P34-21: Based on the multiple test conditions, randomly extract the first test condition; P34-22: According to the first test condition, perform a spring pressurization test on the first test sample group to obtain a first pressure resistance performance test result; P34-23: According to the first test condition, perform an environmental corrosion simulation test on the second test sample group to obtain a first corrosion resistance test result; P34-24: According to the first test condition, perform a corrosion-pressure resistance correlation test on the third test sample group to obtain a first comprehensive performance test result; P34-25: Based on the first pressure resistance performance test result, the first corrosion resistance test result, and the first comprehensive performance test result, combined with the target working environment of the target safety valve spring, perform a comprehensive evaluation of the spring performance to obtain the first performance test result under the first test condition; P34-26: Traverse the multiple test conditions, obtain multiple pressure resistance performance test results, multiple corrosion resistance test results, and multiple comprehensive performance test results, and perform a performance level evaluation to constitute the performance evaluation result.

[0050] Specifically, the specific process of performing a performance test on the target safety valve spring may be to randomly extract any one of the test conditions as the first test condition from the multiple test conditions. And according to the working requirements of the first test condition, a spring pressure test is performed on the first test sample group (i.e., a group of representative safety valve spring samples). During the test, key parameters such as the deformation, rebound speed, and yield load of the spring are recorded to obtain the first compressive performance test result. Similarly, based on the requirements of the first test condition, an environmental corrosion simulation test is performed on the second test sample group. By controlling factors such as the temperature, humidity, and corrosive media of the test environment, the corrosion conditions in the target working environment are simulated, and the corrosion conditions, mass loss, etc. on the spring surface are observed and recorded to obtain the first corrosion resistance test result. At the same time, a corrosion-compression correlation test is performed on the third test sample group. First, an environmental corrosion simulation test is performed, and then a spring pressure test is performed immediately after the corrosion test or after a certain period of recovery. By comparing the changes in the compressive performance of the spring before and after corrosion, the first comprehensive performance test result is obtained.

[0051] Furthermore, based on the first compressive performance test result, the first corrosion resistance test result and the first comprehensive performance test result, combined with the target working environment of the target safety valve spring, including but not limited to the properties of the working medium (such as corrosiveness, temperature, pressure, etc.), the temperature and humidity conditions of the working environment, vibration or impact conditions, etc., a comprehensive evaluation of the spring performance is performed, and a series of performance indicator thresholds or standards can be set, and the performance test results can be compared with them to derive the pros and cons of each spring performance, and give the first performance test result under the first test condition, which can reflect the reliability, durability and safety of the spring in actual applications.

[0052] By analogy, by repeating the above steps, traversing the various test conditions, performing performance tests respectively, obtaining multiple pressure resistance test results, multiple corrosion resistance test results and multiple comprehensive performance test results, collecting and sorting the pressure resistance test results, corrosion resistance test results and comprehensive performance test results under all test conditions. And based on these results, the performance level of the target safety valve spring is evaluated. For example, the multiple test results obtained under each condition are quantified, such as converting the test results into performance scores, and each performance indicator is graded according to preset evaluation standards or industry standards. For example, the pressure resistance can be divided into four levels: "excellent", "good", "qualified" and "unqualified". Taking all performance indicators into consideration, the spring performance under each test condition is evaluated as a whole, and the corresponding performance level is given to construct a comprehensive and accurate performance evaluation result as an important basis for product improvement, quality control and production decision-making.

[0053] Furthermore, step P34-22 of the embodiment of the present application also includes:

[0054] P34-221: According to the first test condition, a spring compression test is performed on the first test sample group to obtain a first compressive resistance data series set and a first yield strength set; P34-222: A plurality of first compressive resistance change curves are drawn according to the first compressive resistance data series set, and a first compressive resistance stability is obtained according to the first compressive resistance change curves; P34-223: A yield strength concentration trend analysis is performed through the first yield strength set to obtain a first yield strength stability; P34-224: Based on the first compressive resistance stability and the first yield strength stability, a first compressive resistance performance test result is obtained.

[0055] Optionally, the specific process of performing a spring pressure test on the first test sample group for the first test condition may be, first, performing a spring pressure test on the first test sample group according to the requirements of the first test condition. During the test, the deformation, rebound speed and other parameters of different spring samples under different pressure levels are recorded to form a first compression resistance data sequence set. At the same time, the pressure value when the spring reaches the yield point is recorded to form a first yield strength set.

[0056] Further, according to the first set of compression resistance data series, with the pressure change as the independent variable and the spring deformation as the dependent variable, a plurality of first compression resistance change curves are drawn, which show the trend of the spring deformation changing with the pressure. By observing the smoothness of the curve, the position of the inflection point and other characteristics, calculating the slope change rate of the curve, analyzing the fluctuation range of the curve, etc., the compression stability of the spring is evaluated. At the same time, statistical methods (such as mean, standard deviation, median, etc.) are used to perform a central tendency analysis on the first yield strength set to understand the distribution of the yield strength of multiple spring samples, and then evaluate their stability. For example, a smaller standard deviation indicates that the yield strength is more concentrated and the stability is higher, whereas a smaller standard deviation indicates that the yield strength distribution is more scattered and the stability is lower.

[0057] Furthermore, based on the evaluation results of the first compressive stability and the first yield strength stability, they are combined according to preset weights, which can be adjusted according to actual application requirements to obtain the first compressive performance test result. This result reflects the compressive performance of the spring under the first test condition, providing a basis for subsequent comprehensive performance evaluation.

[0058] P40: Based on the surface defect detection results, the dimension verification results and the performance evaluation results, a comprehensive evaluation of the spring quality is performed to obtain a quality determination result.

[0059] Specifically, a comprehensive evaluation of the spring quality is performed by combining the surface defect detection results, the dimension verification results and the performance evaluation results to comprehensively evaluate the overall quality level of the spring. Exemplarily, the surface defect detection results are first summarized, including information such as defect type, quantity, location and severity. The dimension verification results are collected to confirm whether the actual size of the spring meets the design requirements or tolerance range. The performance evaluation results are obtained, including the results of compression resistance, corrosion resistance and corrosion-compression correlation tests.

[0060] Furthermore, different quality indicators are assigned corresponding weights according to the specific application requirements, industry standards or customer requirements of the spring. For example, for certain high-precision or high-safety application scenarios, performance evaluation results and dimensional verification results may have higher weights. Then, a quantitative score is given for each quality indicator, and then a weighted sum is performed according to the assigned weight to obtain a comprehensive score of the spring quality. The scoring method can be flexibly designed according to actual conditions, such as using a percentage system, a grade system or other quantitative standards.

[0061] Furthermore, the quality of the spring is judged based on the comprehensive score and the preset quality judgment standards (such as qualified line, excellent line, etc.). The judgment results may include qualified, unqualified, pending (such as needing rework or further testing), etc. The quality judgment results and related evaluation data are recorded for subsequent tracking and analysis.

[0062] P50: Based on the quality determination results, the production numbers of the defective finished products are extracted for correlation analysis, and the defective products are traced based on the correlation analysis results.

[0063] It should be understood that, according to the quality judgment result, the production number of the defective finished product is extracted, and the springs judged as defective products are further traced. Exemplarily, all springs judged as defective products are screened out from the quality judgment result. The production numbers of these defective products are extracted, and these numbers are usually associated with information such as the production batch, production line, and production time of the product. The production number of the defective product is associated with the records of each link in the production process, including the procurement of raw materials, processing, equipment status, operators, environmental conditions, etc. By analyzing these associated data, common factors or abnormal points that may cause product defects are identified. Based on the results of the association analysis, the specific reasons for the production of defective products are determined, such as raw material quality problems, production equipment failures, improper process parameter settings, operator errors, and other aspects. Each reason is analyzed in depth, its impact and probability of occurrence are evaluated, and the priority and corrective measures are determined. Thereby timely discovering and solving problems in the production process, improving product quality and production efficiency, and enhancing customer satisfaction and market competitiveness.

[0064] In summary, the embodiments of the present application have at least the following technical effects:

[0065] This application constructs an appearance inspection module to perform surface defect inspection and dimensional verification on the target safety valve spring, and uses a performance inspection module to perform performance testing and performance level evaluation on the target safety valve spring. Combined with the surface defect inspection results, dimensional verification results and performance evaluation results, a comprehensive evaluation of the spring quality is performed, and based on the quality judgment results, the production numbers of defective finished products are extracted for correlation analysis and defective product traceability.

[0066] The technical effect of improving the accuracy and reliability of safety valve spring quality inspection through all-round and multi-angle appearance quality inspection and performance attribute inspection has been achieved.

[0067] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying 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.

[0068] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0069] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A quality inspection method for a safety valve spring, characterized in that: The method comprises: Constructing an appearance inspection module, wherein the appearance inspection module includes an image acquisition unit, a defect recognition unit, and a size verification unit; Through the appearance inspection module, surface defect inspection and dimension verification are performed on the target safety valve spring to obtain surface defect inspection results and dimension verification results; Through the performance detection module, the target safety valve spring is subjected to performance testing and performance level evaluation to obtain a performance evaluation result, wherein the performance detection includes pressure stability detection, corrosion resistance detection and comprehensive performance correlation detection; Combine the surface defect detection result, the dimension verification result and the performance evaluation result to conduct a comprehensive evaluation of the spring quality and obtain a quality determination result; According to the quality determination result, the production number of the defective finished product is extracted for association analysis, and the defective product is traced according to the association analysis result.

2. A method for quality inspection of a safety valve spring according to claim 1, characterized in that: Through the appearance inspection module, the target safety valve spring is subjected to surface defect inspection and dimension verification, and the surface defect inspection result and dimension verification result are obtained, including: Performing an all-round scan of the target safety valve spring by the image acquisition unit to obtain a multi-sensor image set, wherein the multi-sensor image set includes an acquisition device identifier, an acquisition angle identifier, and an illumination condition identifier; According to the defect recognition unit, defect fusion processing and defect recognition are performed based on the multi-sensor image to obtain a surface defect detection result; The dimension verification unit performs dimension deviation detection according to the multi-sensor image to obtain a dimension verification result.

3. A method for quality inspection of a safety valve spring according to claim 2, characterized in that: According to the defect recognition unit, defect fusion processing and defect recognition are performed based on the multi-sensor image to obtain a surface defect detection result, including: Based on the acquisition device identifier, acquisition angle identifier and illumination condition identifier of the multi-sensor image, performing step-by-step defect feature fusion on the multi-sensor image, including multi-illumination feature fusion, multi-angle feature fusion and multi-device feature fusion, to obtain multi-level fusion defect features; The multi-level fusion defect features are identified through a defect identification unit to obtain the surface defect detection result.

4. A quality inspection method for a safety valve spring according to claim 2, characterized in that: By means of the size verification unit, size deviation detection is performed according to the multi-sensor image to obtain a size verification result, including: The dimension verification unit is embedded with a standard component simulation model; Extracting component size features based on the multi-element sensor image to generate a finished component simulation model; After the finished component simulation model and the standard component simulation model are aligned through multiple points, the dimension deviation of key parts is calculated to obtain the dimension deviation result, and the dimension deviation threshold is compared to generate the dimension deviation level.

5. A method for quality inspection of a safety valve spring according to claim 1, characterized in that: Through the performance detection module, the target safety valve spring is subjected to performance testing and performance level evaluation to obtain performance evaluation results, including: Collect high-frequency triggering conditions based on the spring triggering records of the target safety valve in the real-time working environment; Based on the high-frequency triggering working condition, extracting the high-frequency triggering pressure value and the high-frequency environmental corrosion characteristics; According to the high-frequency trigger pressure value and the high-frequency environmental corrosion characteristics, parameters are randomly combined to generate a variety of test conditions; Based on the multiple test conditions, the performance test and performance level evaluation are performed on the target safety valve spring through the performance detection module to obtain the performance evaluation result.

6. A method for quality inspection of a safety valve spring as claimed in claim 5, characterized in that: Based on the multiple test conditions, the target safety valve spring is subjected to a performance test by the performance detection module, including: The performance detection module includes a spring performance testing module and a spring performance evaluation module; Based on the spring performance test module, according to the multiple test conditions, spring compressive performance simulation test, environmental corrosion simulation test and corrosion-compression correlation test are respectively carried out, wherein the compressive performance simulation test includes a compressive stability test and a yield strength stability test.

7. A method for testing the quality of a safety valve spring according to claim 6, characterized in that: Based on the spring performance test module, according to the multiple test conditions, a spring compression performance simulation test, an environmental corrosion simulation test and a corrosion-compression correlation test are respectively performed, including: Based on the multiple test conditions, randomly extracting a first test condition; According to the first test condition, a spring pressure test is performed on the first test sample group to obtain a first compression resistance test result; According to the first test condition, an environmental corrosion simulation test is performed on the second test sample group to obtain a first corrosion resistance test result; According to the first test condition, a corrosion-compression correlation test is performed on the third test sample group to obtain a first comprehensive performance test result; Based on the first compression resistance test result, the first corrosion resistance test result, and the first comprehensive performance test result, combined with the target working environment of the target safety valve spring, a comprehensive evaluation of the spring performance is performed to obtain a first performance test result under a first test condition; The plurality of test conditions are traversed to obtain a plurality of compression resistance test results, a plurality of corrosion resistance test results and a plurality of comprehensive performance test results, and a performance level evaluation is performed to form the performance evaluation result.

8. A method for testing the quality of a safety valve spring according to claim 7, characterized in that: According to the first test condition, a spring pressure test is performed on the first test sample group to obtain a first compression resistance test result, including: According to the first test condition, a spring compression test is performed on the first test sample group to obtain a first compression data sequence set and a first yield strength set; Draw a plurality of first pressure resistance change curves according to the first pressure resistance data sequence set, and obtain a first pressure resistance stability according to the first pressure resistance change curves; Performing a yield strength concentration trend analysis on the first yield strength set to obtain a first yield strength stability; Based on the first compressive stability and the first yield strength stability, a first compressive performance test result is obtained.

Images