A production quality inspection method and device for a steering element

Abstract

The present application provides a production quality inspection method and device for steering elements, which relates to the field of quality inspection technology, including: determining multiple inspection modules for production quality inspection of steering elements; calling multiple inspection modules to perform traceability analysis of production defects, and establishing a production defect traceability analysis network; obtaining the first batch of production data sets; screening the parameters of production equipment, raw material parameters, and production environment parameters for parameter consistent clustering centers; performing quality inspection on multiple steering element inspection samples, and determining the defective sample production data of samples with unqualified quality inspection indicators; inputting the defective sample production data into the production defect traceability analysis network, and tracing the defects through the first traceability layer and the second traceability layer to generate traceability results. The present application can solve the technical problems of the management methods in the prior art due to the lack of an effective quality tracing mechanism, and achieve the technical effect of improving production efficiency and ensuring accelerated quality improvement.

Description

Technical Field

[0001] The present application relates to the technical field of quality inspection, and in particular to a production quality inspection method and device for a steering element. Background Art

[0002] In modern manufacturing, especially in the automotive industry, production quality control and management has always been a key factor in ensuring product safety, reliability and performance. With the continuous development of production technology, how to effectively improve product quality while ensuring large-scale production efficiency has become a continuous challenge for enterprises.

[0003] At present, with the increasing requirements of the automotive industry for product quality, existing technologies that simply rely on standardized control of equipment, raw materials and environment can no longer meet actual needs. In modern production processes, product quality is not only affected by production equipment and materials, but also by the combined effects of process parameters, production environment, operator skills and other factors. Existing technologies often find it difficult to comprehensively consider these multi-dimensional factors and cannot conduct comprehensive and systematic quality analysis and traceability. Although some high-end production lines have introduced intelligent detection systems, most of these systems are still in a single-point detection state, lacking comprehensive coverage and precise control of the entire production process. The lack of an effective quality traceability mechanism and refined management methods means that when quality problems occur, companies cannot quickly track the source of the problem, and thus cannot quickly take effective improvement measures. Therefore, how to achieve more efficient, intelligent and precise quality control in the production process has become a technical problem that needs to be solved urgently in the manufacturing industry.

[0004] In summary, the existing technology lacks an effective quality traceability management method, which results in the failure to fully integrate and analyze multi-dimensional factors such as process parameters and production environment during the production process, further making it difficult to timely discover and accurately trace quality problems, affecting production efficiency, product consistency and the speed of quality improvement, and even being unable to cope with the technical problems of increasingly complex production needs. Summary of the invention

[0005] The purpose of this application is to provide a production quality inspection method and device for steering elements, so as to solve the technical problem that the lack of an effective quality traceability mechanism in the prior art leads to the failure to comprehensively integrate and analyze multi-dimensional factors such as process parameters and production environment during the production process, further resulting in difficulty in timely discovery and accurate traceability of quality problems, affecting production efficiency, product consistency and the speed of quality improvement, and even being unable to cope with increasingly complex production needs.

[0006] In view of the above problems, the present application provides a method and device for detecting the production quality of a steering element.

[0007] In a first aspect, the present application provides a method for production quality inspection of a steering element, which is implemented by a production quality inspection device for a steering element, comprising: determining a plurality of inspection modules for performing production quality inspection on the steering element, wherein any inspection module is used to perform quality inspection on the steering element according to corresponding quality inspection indicators; calling the plurality of inspection modules to perform traceability analysis on production defects, and establishing a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer for process nodes and a second traceability layer for production parameters; connecting to a control terminal of a steering element production line, and receiving a first batch of production data sets, wherein the first batch of production data sets includes a first batch of production data sets. The production equipment parameters, raw material parameters and production environment parameters corresponding to any steering element produced in a batch; performing parameter consistent clustering on the production equipment parameters, raw material parameters and production environment parameters, and screening multiple steering element inspection samples at the cluster center according to the clustering results; performing quality inspection on the multiple steering element inspection samples through the multiple inspection modules, and determining the defective sample production data of the samples with unqualified corresponding quality inspection indicators; inputting the defective sample production data into the production defect traceability analysis network, performing defect traceability through the first traceability layer and the second traceability layer, generating a traceability result and sending it to the control terminal of the steering element production line for reminder.

[0008] In a second aspect, the present application further provides a production quality inspection device for a steering element, which is used to execute a production quality inspection method for a steering element as described in the first aspect, including: a detection module determination unit, which is used to determine multiple detection modules for performing production quality inspection on the steering element, wherein any detection module is used to perform quality inspection on the steering element according to corresponding quality inspection indicators; a traceability analysis unit, which is used to call the multiple detection modules to perform traceability analysis on production defects and establish a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer of process nodes and a second traceability layer of production parameters; a production data acquisition unit, which is used to connect to the control terminal of the steering element production line to receive the first batch of production data sets, wherein the first batch The secondary production data set includes production equipment parameters, raw material parameters and production environment parameters corresponding to any steering element produced in the first batch; a cluster screening unit, the cluster screening unit is used to perform parameter consistent clustering on the production equipment parameters, raw material parameters and production environment parameters, and screen multiple steering element inspection samples at the cluster center according to the clustering results; a quality inspection unit, the quality inspection unit is used to perform quality inspection on the multiple steering element inspection samples through the multiple inspection modules, and determine the defective sample production data of the samples with unqualified corresponding quality inspection indicators; a defect tracing unit, the defect tracing unit is used to input the defective sample production data into the production defect tracing analysis network, perform defect tracing through the first tracing layer and the second tracing layer, generate a tracing result and send it to the control terminal of the steering element production line for reminder.

[0009] The technical solution provided in the present application has at least the following technical effects or advantages: by determining multiple detection modules for performing production quality inspection on steering elements, wherein any detection module is used to perform quality inspection on steering elements according to corresponding quality inspection indicators; calling the multiple detection modules to perform traceability analysis on production defects, and establishing a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer of process nodes and a second traceability layer of production parameters; connecting the control terminal of the steering element production line to receive the first batch of production data sets, wherein the first batch of production data sets includes production equipment parameters, raw material parameters and production environment parameters corresponding to any steering element produced in the first batch; and The raw material parameters and the production environment parameters are clustered according to parameter consistency, and a plurality of steering element inspection samples at the cluster center are screened according to the clustering results; the plurality of steering element inspection samples are quality inspected by the plurality of inspection modules, and the defective sample production data of the samples with unqualified corresponding quality inspection indicators are determined; the defective sample production data is input into the production defect traceability analysis network, and the defects are traced through the first traceability layer and the second traceability layer, and the traceability results are generated and sent to the control terminal of the steering element production line for reminder. That is to say, by realizing the technical goal of comprehensive monitoring of the production process and intelligent quality traceability, the technical effect of improving production efficiency, ensuring accelerated quality improvement and enhancing the ability to respond to complex production needs is achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of a process flow of a production quality inspection method for a steering element of the present application;

[0013] Figure 2 This is a schematic structural diagram of a production quality inspection device for a steering element according to the present application.

[0014] Description of reference numerals:

[0015] Detection module determination unit 11, traceability analysis unit 12, production data acquisition unit 13, cluster screening unit 14, quality detection unit 15, defect traceability unit 16. DETAILED DESCRIPTION

[0016] This application provides a production quality inspection method and device for steering components, which solves the problem in the prior art that the lack of an effective quality traceability mechanism leads to the failure to fully integrate and analyze multi-dimensional factors such as process parameters and production environment during the production process, further leading to the difficulty in timely discovery and accurate traceability of quality problems, affecting production efficiency, product consistency and the speed of quality improvement, and even the technical problem of being unable to cope with increasingly complex production needs. The technical goal of achieving comprehensive monitoring of the production process and intelligent quality traceability is achieved, achieving the technical effect of improving production efficiency, ensuring accelerated quality improvement and enhancing the ability to cope with complex production needs.

[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0018] For example, please refer to the attached Figure 1 The present application provides a production quality inspection method for a steering element, which is applied to a production quality inspection device for a steering element, and specifically comprises the following steps:

[0019] Step 1: Determine a plurality of detection modules for performing production quality detection on the steering element, wherein any detection module is used to perform quality detection on the steering element according to corresponding quality detection indicators.

[0020] Specifically, the steering element is the steering wheel of the car. Multiple detection modules are determined to comprehensively check various problems that may occur in the production process of the steering wheel. For example, the detection module may include an appearance detection module to check whether there are scratches, cracks and other defects on the surface of the steering wheel, which is the first line of defense to ensure the appearance quality of the steering wheel. Secondly, the function detection module can be used to check the functionality of the steering wheel, such as whether it can rotate normally and whether there is a jamming phenomenon. It is crucial to ensure the performance of the steering wheel. Then, a safety detection module can also be included to check whether the steering wheel has sufficient strength and stability to ensure that it can effectively protect the driver's safety in the event of a collision. Through multiple detection modules, every link in the production process can be carefully checked to ensure that every steering wheel shipped meets the quality standards. Finally, the data of each detection module will be comprehensively analyzed to ensure that the overall quality of the steering wheel meets the requirements and avoid safety hazards or user dissatisfaction caused by production defects. Each module will operate according to specific quality inspection indicators, which are standards or requirements for measuring whether the product meets the standards. For example, for the appearance quality inspection of the steering wheel, the quality inspection indicators that can be set include whether the surface is smooth, whether there are scratches, etc., while for the size inspection indicators, it may include whether the steering wheel diameter meets the design requirements. Each inspection module will only focus on a specific indicator during the inspection process, but the entire inspection system works together through multiple modules to ensure that the steering wheel meets quality standards in all dimensions, thereby achieving all-round quality control.

[0021] Step 2: Call the multiple detection modules to perform traceability analysis on production defects and establish a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer of process nodes and a second traceability layer of production parameters.

[0022] Specifically, by using multiple inspection modules (such as appearance inspection, functional inspection, etc.) to conduct in-depth analysis of defects found in the production process, trace the causes of their occurrence, and then establish associations based on defects and corresponding causes, respectively as the first traceability layer and the second traceability layer, and combine multiple associations to obtain a production defect traceability analysis network. The first traceability layer analyzes the relationship between process node defects and corresponding production data; the second traceability layer analyzes the relationship between production parameter defects and corresponding production data, such as defect factors such as raw material parameters and environmental parameters. Through two levels of analysis, the causes of defects can be clearly understood and guidance can be provided for improving the production process.

[0023] Step 3: Connect to the control terminal of the steering component production line and receive the first batch of production data sets, wherein the first batch of production data sets includes production equipment parameters, raw material parameters and production environment parameters corresponding to any steering component produced in the first batch.

[0024] Specifically, the control terminal is used to control the steering wheel production process. All relevant data of the first batch of steering wheels produced on the steering wheel production line are collected through the control terminal. The first batch of production data sets include multiple parameters involved in the production process of each steering wheel, including production equipment parameters, raw material parameters and production environment parameters corresponding to any steering wheel produced in the first batch. Production equipment parameters refer to the working status of the equipment used in the production process, such as the speed, pressure, temperature, etc. of the machine, which directly affects the quality of the production process; raw material parameters refer to the specifications, composition and quality of the raw materials used to manufacture steering wheels, such as the thickness and density of leather, plastic or metal. The quality of raw materials will also directly affect the quality of the final product; production environment parameters refer to the conditions in the production environment, such as temperature, humidity, air circulation, etc. These environmental factors also have a certain impact on the quality of the product and the stability of production. For example, if the density of the raw materials of the first batch of steering wheels is uneven during the production process, or the temperature control of the production equipment is not accurate, it may cause defects on the surface of the final steering wheel or malfunction. By collecting these data, the key factors in the production of each steering wheel can be analyzed, so as to carry out more accurate quality control and production optimization.

[0025] Step 4: performing parameter consistency clustering on the production equipment parameters, raw material parameters and production environment parameters, and selecting a plurality of steering element test samples at the cluster center according to the clustering results.

[0026] Specifically, according to the parameters of production equipment, raw materials and production environment, a consistent central point, i.e., a cluster center, is selected to represent a class of steering wheels with similar production conditions. Production equipment parameters may include the working state of the machine, such as temperature, speed and pressure; raw material parameters include the material properties used to produce steering wheels, such as thickness, density and composition; and production environment parameters involve external conditions such as temperature and humidity in the workshop. By analyzing these parameters, all steering wheels produced are classified according to these characteristics, and the steering wheels contained in each category are relatively similar in production equipment, raw materials and environmental conditions. Then, a representative cluster center is selected from each clustering result, and the parameter setting of the cluster center can better represent the overall characteristics of this type of steering wheel. By screening the cluster center, it can be ensured that the selected samples can truly reflect the quality of steering wheels under different production conditions. Finally, based on the cluster center, multiple steering wheel test samples are generated to ensure that effective quality testing can be performed on steering wheels under each production condition. In this way, the accuracy and efficiency of the test can be improved.

[0027] Step 5: Perform quality inspection on the plurality of steering element inspection samples through the plurality of inspection modules, and determine defective sample production data of samples that fail to meet corresponding quality inspection indicators.

[0028] Specifically, a number of different inspection tools and methods are used to evaluate the quality of the selected steering wheel samples. Inspection modules may include visual inspection, physical performance testing, functional testing, etc., and each module performs inspections based on different quality standards. For example, visual inspection may be used to detect scratches on the surface of the steering wheel, physical performance testing may test the strength and durability of the steering wheel, and functional testing checks the rotation flexibility of the steering wheel. Then, during the inspection process, it is identified which samples have failed quality inspection indicators and have quality problems, and the production process data of these defective samples are extracted. These production data include factors such as the working status of production equipment, the use of raw materials, and the production environment, which can effectively trace the root cause of the defect and provide a basis for subsequent production improvements and quality control.

[0029] Step six: Input the defect sample production data into the production defect traceability analysis network, perform defect traceability through the first traceability layer and the second traceability layer, generate traceability results and send them to the control terminal of the steering element production line for reminder.

[0030] Specifically, the relevant data of the production process of the identified defective samples, such as equipment parameters, raw material usage, and production environment, are input into the production defect traceability analysis network. The specific link where the defect occurs can be determined based on the input production data. The first traceability layer (process node layer) analyzes whether the defect is related to a certain process link in the production, such as problems in the surface treatment or assembly process; then, the second traceability layer (production parameter layer) further analyzes the specific parameters used in the production process, such as the temperature, speed, pressure, etc. of the machine, to see if there are any abnormalities that lead to the occurrence of defects, and then generates traceability results and sends them to the control terminal of the steering wheel production line through the control terminal to remind the staff on the production line of the possible causes of the defects and to remind the staff to take corresponding measures, such as adjusting equipment parameters, improving the quality of raw materials, or optimizing the production environment, to prevent similar problems from happening again. In this way, defects in production can be effectively traced and resolved, and the stability of the production process and product quality can be improved.

[0031] The production quality inspection method of a steering element is applied to a production quality inspection device of a steering element, which can achieve the technical goals of comprehensive monitoring and intelligent quality tracing of the production process, and achieve the technical effects of improving production efficiency, ensuring accelerated quality improvement and enhancing the ability to respond to complex production needs.

[0032] Furthermore, the present application also includes: extracting any detection module from the multiple detection modules, and any corresponding detection indicator; collecting a historical negative detection sample set with the any detection indicator as a constraint, wherein any negative detection sample in the historical negative detection sample set includes an indicator defect detection feature and a defect factor; performing a correlation analysis of defective process nodes with the indicator defect detection feature and the defect factor as samples, and establishing the first traceability layer; performing a correlation analysis of defective production parameters with the indicator defect detection feature and the defect factor as samples, and establishing the second traceability layer; and constructing the production defect traceability analysis network with the first traceability layer and the second traceability layer.

[0033] Specifically, a module is randomly selected from multiple inspection modules for analysis, and the module corresponds to an inspection indicator. Any inspection module refers to a tool or system used to check a certain aspect of quality during the production quality inspection process, and the corresponding inspection indicator is a standard or value used to measure the quality of that aspect. For example, if the appearance inspection module is selected, the corresponding inspection indicator may be no scratches on the surface.

[0034] Next, based on any inspection indicator, a historical negative inspection sample set is collected, that is, past inspection data is collected and defect samples that occurred during the inspection are recorded. Among them, any negative inspection sample in the historical negative inspection sample set includes indicator defect detection characteristics and defect factors. Negative inspection samples refer to samples that meet defect conditions, and defect factors are the causes of defects, such as the length of surface scratches and excessive humidity in the production environment, which are then used to more deeply analyze the causes and patterns of defects.

[0035] Then, by analyzing the correlation between process defects and corresponding production parameters, the correlation relationship is used as the first traceability layer. For example, scratches may be related to the missing steps of the steering wheel surface treatment, and then the first traceability layer is established to record the process node where the defect occurs.

[0036] Next, by analyzing the defect factors in the historical negative detection sample set, negative detection samples whose defect factors are production parameters are selected. Among them, defective production parameters include raw material parameters, environmental parameters, etc. Using the defect factors as production parameter defects and the corresponding production data, the correlation is trained to generate the second traceability layer.

[0037] Finally, the first traceability layer and the second traceability layer are combined to build a production defect traceability analysis network. The production defect traceability analysis network helps identify and track the causes of defects that may occur in production by linking process nodes and production parameters, thereby achieving more accurate quality control.

[0038] The production defect traceability analysis network helps to obtain the source and formation process of quality defects, providing data support for subsequent quality control and production process improvement.

[0039] Furthermore, the present application also includes: using the defect factor as a constraint to screen negative detection samples whose defect factor is a process defect in the historical negative detection sample set to generate a first sample set; using the first sample set to train the correlation between the indicator defect detection characteristics of any detection indicator and the defective process node to generate the first traceability layer.

[0040] Specifically, in the historical negative detection sample set, defect samples caused by process problems are screened out according to defect factors, and then the first sample set is constructed. For example, scratches are detected on the surface of the steering wheel, and historical data shows that scratches are mostly caused by excessive temperature during the production process, so the data sample can be screened as a negative detection sample of process defects.

[0041] Next, the first sample set that has been screened is used for training to analyze the relationship between the defect characteristics of each defect indicator and the specific process nodes, thereby generating the first traceability layer. The training process is to find out the correlation between the occurrence of defects and process links through data analysis. For example, scratches may be related to defects in the surface treatment link of the production line. The results after training can help confirm that the surface treatment process is an important process node that causes the defect. Finally, the generation of the first traceability layer is to form a traceable production quality control layer by analyzing the correlation between defect characteristics and process nodes, which helps to clarify the source of each defect so that every link in the production process can be effectively monitored and optimized.

[0042] Furthermore, the present application also includes: configuring a production equipment parameter consistency threshold, a raw material parameter consistency threshold and a production environment parameter consistency threshold; clustering the production equipment parameters, raw material parameters and production environment parameters corresponding to any steering element according to the production equipment parameter consistency threshold, the raw material parameter consistency threshold and the production environment parameter consistency threshold to generate multiple clustering clusters; determining a preset sample sampling ratio coefficient, and determining the number of sampling samples based on the total number of steering elements produced in the first batch; and screening the multiple clustering clusters based on the number of sampling samples with the cluster centroid as the center to generate the multiple steering element detection samples.

[0043] Specifically, a standard range is set for the equipment parameters, raw material parameters, and production environment parameters in the production process, that is, the acceptable allowable error value for each parameter. The production equipment parameter consistency threshold refers to the allowable working state fluctuation range when the equipment is running, such as the temperature, speed or pressure of the equipment, etc., which is considered abnormal if it exceeds this range; the raw material parameter consistency threshold refers to the quality range of the raw materials, such as density, thickness, composition, etc., and changes in these parameters may affect the quality of the final product; the production environment parameter consistency threshold is the tolerance range of the environment, such as the temperature and humidity of the workshop. By setting these thresholds, it can be ensured that each link in the production process fluctuates within the allowable range, thereby reducing quality problems.

[0044] Next, by collecting the equipment, raw materials and environmental parameter data of each steering wheel during the production process, comparing these data with the preset thresholds, these steering wheels are divided into different groups according to similarity, i.e. clustering, and multiple clusters are generated. Clusters are groups formed based on the similarity of these parameters. The production conditions of the steering wheels in each group are similar, and then accurately analyzing which production conditions may lead to quality problems.

[0045] Then, determine the preset sample sampling ratio coefficient, that is, the ratio of the steering wheel samples to be sampled. The ratio coefficient helps us scientifically select the number of samples to be tested under limited resources. Combined with the total number of steering wheels produced in the first batch, determine the number of samples to be sampled. For example, if the ratio coefficient is set to 5%, and 300 steering wheels are produced in the first batch, then 15 steering wheels need to be sampled for testing.

[0046] Finally, based on the determined number of random inspection samples, samples are selected from each cluster for testing. The centroid of each cluster is taken as the center, that is, the central point in the cluster that best represents the group of data. Some samples are screened around the center point as multiple steering wheel inspection samples. This helps to ensure that the selected samples can cover various situations that may occur in the production process, thereby improving the representativeness and accuracy of the inspection.

[0047] Through cluster analysis, steering wheels produced under different conditions are grouped, and the number of samples that need to be tested is determined based on the sampling ratio. Samples are selected for testing through the cluster centroid. This allows representative steering wheels to be efficiently and systematically screened for quality inspection, ensuring that every link in the production process can be reasonably monitored and optimized.

[0048] Furthermore, the present application also includes: determining the number of cluster steering elements corresponding to the multiple clusters, uniformly distributing the sampled samples in combination with the number of spot checks, and determining the number of spot checks within the multiple clusters; spot checking samples within the multiple clusters with the cluster centroid as the center according to the number of spot checks within the multiple clusters, and uniformly distributing the surrounding sampled samples to generate the multiple steering element detection samples.

[0049] Specifically, determine the number of steering wheels contained in each cluster, and determine the number of samples to be drawn from each cluster based on the number of samples to be drawn as a whole, as the number of sampling within multiple clusters, to ensure that a certain number of samples can be fairly selected from each cluster. For example, if there are 1,000 steering wheels in total, divided into 5 clusters, each cluster may contain a different number of steering wheels. Then, according to the proportion of steering wheels in the cluster, the number of samples to be drawn from each cluster is proportionally allocated to ensure the uniformity of sample selection.

[0050] Next, in each cluster, based on the number of random inspections determined for each cluster, the samples are selected with the centroid of the cluster as the center. The centroid refers to a representative point in the cluster that best represents the other steering wheel data in the cluster. The samples are evenly distributed based on the centroid, that is, samples are selected from around the centroid to generate multiple steering wheel test samples, ensuring that the selected samples can cover different situations within the cluster and will not be biased towards a specific data, so that the steering wheels under different conditions within the cluster can be fully tested to ensure the representativeness and comprehensiveness of the test results.

[0051] By determining the number of samples to be extracted from each cluster, and selecting evenly distributed samples based on this number, the sample selection is then performed using the cluster centroid as the center to ensure that the samples in each cluster can represent the overall situation in the cluster, which helps to extract representative samples from steering wheels under different production conditions for testing, thereby effectively analyzing and controlling production quality.

[0052] Furthermore, the present application also includes: parsing the traceability results, calculating the proportion coefficients corresponding to different defect factors; sorting the different defect factors in descending order of the proportion coefficients to generate a defect factor sequence; sending the defect factor sequence to the control terminal of the steering element production line for defect factor troubleshooting and taboo reminders.

[0053] Specifically, after obtaining the defect traceability results, calculate the proportion of each defect factor in the total defects as the proportion coefficient. Defect factors refer to various factors that lead to defects, such as problems with production equipment, unqualified raw material quality, or unsuitable production environment. The proportion coefficient is the percentage of each factor in all defects, which helps determine which factor has the greatest impact on the defect.

[0054] Next, according to the proportion coefficient of each defect factor, arrange the defect factors from large to small to form a priority order and generate a defect factor sequence to help focus on the factors that have the greatest impact on the defects, so as to give priority to solving them.

[0055] Finally, the defect factor sequence is sent to the control terminal of the steering wheel production line for defect factor screening and taboo reminders. Further screening is carried out based on the sorting results to confirm whether the defect factor still exists in actual production and take measures to correct it. Taboo reminders mean that if certain defect factors are particularly critical, warnings are issued to remind production personnel to avoid similar problems in production, such as reminding production personnel to check whether the temperature and pressure of the equipment meet the requirements.

[0056] By analyzing the traceability results, the proportion of each defect factor to the total defects is calculated to find out the most critical defect factor; then, these defect factors are sorted according to the proportion coefficient, and those factors with high proportion and great impact are solved first; finally, the generated defect factor sequence will be sent to the control terminal of the production line for defect investigation and taboo reminders, so as to effectively prevent quality problems in production, help production managers focus on key issues, and improve production efficiency and product quality.

[0057] Furthermore, the present application also includes: parsing the traceability results, locating defective process nodes whose defect factors are process nodes; collecting the original process parameters used to produce defective samples corresponding to the defective process nodes; connecting the process parameter optimization library to optimize the original process parameters, wherein the process parameter optimization library includes multiple pairs of optimization parameter groups, wherein any pair of optimization parameter groups includes the process parameters before optimization and the process parameters after optimization and defect optimization feature labels, and based on the original process parameters and the defect characteristics of the defective samples, the optimized process parameters are matched in the multiple pairs of optimization parameter groups.

[0058] Specifically, in the results obtained through traceability analysis, find out the specific production links that lead to quality defects, especially problems in the process links. The process node refers to each specific operation step or link in the production process, such as the assembly, surface treatment or painting of the steering wheel. The defective process node refers to the specific step where problems occur in these production links and cause defects. If a certain production link is found through traceability analysis, such as the equipment temperature is too high during the surface treatment process, resulting in cracks on the steering wheel surface, then this link is a defective process node.

[0059] Next, collect the original process parameters used to produce defective samples corresponding to the defective process nodes, that is, collect the original production parameters related to the determined defective process nodes. The original process parameters refer to the specific technical indicators or control parameters used in this production link, such as temperature, pressure, speed, etc. If it is found that the equipment temperature is too high during the surface treatment process, causing defects, then it is necessary to collect the specific data of temperature control in this link to understand whether the temperature setting exceeds the reasonable range and causes quality problems.

[0060] Then, the collected process parameter data is compared and connected with the process parameter optimization library, which contains multiple pairs of optimization parameter groups, that is, the verified optimal process parameter settings, which are used to improve the quality of the production process. By comparing the collected process parameters with the recommended parameters in the optimization library, the parameters that need to be adjusted are identified, such as temperature, humidity or pressure settings that are too high or too low and need to be adjusted to the appropriate range, so that the production process can be continuously improved and the occurrence of quality defects can be reduced.

[0061] Each pair of optimization parameter groups contains the process parameters before optimization and the process parameters after optimization. The process parameters before optimization refer to the parameter settings before adjustment, while the process parameters after optimization refer to the settings after adjustment or improvement. In addition, defect optimization feature labels are included to identify the defect type and its improvement effect, helping to better evaluate whether the optimization measures are effective. For example, a defect feature label may be marked as "surface defect", indicating that the original defect has been eliminated through optimization. Based on the original process parameters and the defect characteristics of the defective samples, the optimization process parameters are matched in multiple pairs of optimization parameter groups. The original process parameters in actual production are compared with the defective samples (referring to defective products), and the characteristics of the defects are analyzed to find the appropriate optimization parameter combination in the optimization library. According to the characteristics of the defects, the most suitable optimization parameter group is selected for adjustment to improve the defect performance. For example, if it is found that the defects of a batch of products are caused by the temperature setting being too high, then the optimized temperature parameters will be selected for production to avoid the same defects from happening again.

[0062] By analyzing the traceability results, the specific process link that causes the defects can be located, and then the production parameters of this link can be collected. Finally, these parameters can be adjusted and optimized by connecting to the process parameter optimization library. This can effectively improve the accuracy of each link in the production process, avoid quality defects caused by process problems, and thus improve product quality and production efficiency.

[0063] In summary, the production quality inspection method of a steering element provided in the present application has the following technical effects: by determining multiple inspection modules for performing production quality inspection on the steering element, wherein any inspection module is used to perform quality inspection on the steering element according to corresponding quality inspection indicators; calling the multiple inspection modules to perform traceability analysis on production defects, and establishing a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer for process nodes and a second traceability layer for production parameters; connecting to the control terminal of the steering element production line, receiving the first batch of production data sets, wherein the first batch of production data sets includes production equipment parameters, raw material parameters and production environment parameters corresponding to any steering element produced in the first batch; The equipment parameters, raw material parameters and production environment parameters are clustered according to parameter consistency, and a plurality of steering element inspection samples at the cluster center are screened according to the clustering results; quality inspection is performed on the plurality of steering element inspection samples through the plurality of inspection modules, and defective sample production data of samples with unqualified corresponding quality inspection indicators are determined; the defective sample production data is input into the production defect traceability analysis network, and defect traceability is performed through the first traceability layer and the second traceability layer, and a traceability result is generated and sent to the control terminal of the steering element production line for reminder. That is to say, by achieving the technical goal of comprehensive monitoring of the production process and intelligent quality traceability, the technical effect of improving production efficiency, ensuring accelerated quality improvement and enhancing the ability to respond to complex production needs is achieved.

[0064] Embodiment 2: Based on the production quality inspection method of a steering element in the above embodiment, the present application also provides a production quality inspection device for a steering element, as shown in the attached Figure 2, including: a detection module determination unit 11, the detection module determination unit 11 is used to determine multiple detection modules for production quality detection of steering elements, wherein any detection module is used to perform quality detection of steering elements according to corresponding quality detection indicators; a traceability analysis unit 12, the traceability analysis unit 12 is used to call the multiple detection modules to perform traceability analysis of production defects and establish a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer of process nodes and a second traceability layer of production parameters; a production data acquisition unit 13, the production data acquisition unit 13 is used to connect to the control terminal of the steering element production line, receive the first batch of production data sets, wherein the first batch of production data sets includes the production equipment corresponding to any steering element produced in the first batch equipment parameters, raw material parameters and production environment parameters; a cluster screening unit 14, the cluster screening unit 14 is used to perform parameter consistent clustering on the production equipment parameters, raw material parameters and production environment parameters, and screen multiple steering element inspection samples at the cluster center according to the clustering results; a quality inspection unit 15, the quality inspection unit 15 is used to perform quality inspection on the multiple steering element inspection samples through the multiple inspection modules, and determine the defective sample production data of the samples with unqualified corresponding quality inspection indicators; a defect tracing unit 16, the defect tracing unit 16 is used to input the defective sample production data into the production defect tracing analysis network, perform defect tracing through the first tracing layer and the second tracing layer, generate a tracing result and send it to the control terminal of the steering element production line for reminder.

[0065] Furthermore, the production quality inspection device for a steering element is also used to: extract any inspection module from the multiple inspection modules, and any corresponding inspection index; collect a historical negative inspection sample set with the any inspection index as a constraint, wherein any negative inspection sample in the historical negative inspection sample set includes an indicator defect detection feature and a defect factor; perform correlation analysis of defective process nodes with the indicator defect detection feature and the defect factor as samples, and establish the first traceability layer; perform correlation analysis of defective production parameters with the indicator defect detection feature and the defect factor as samples, and establish the second traceability layer; and construct the production defect traceability analysis network with the first traceability layer and the second traceability layer.

[0066] Furthermore, the production quality inspection device for a steering element is also used to: use the defect factor as a constraint to screen negative side inspection samples whose defect factor is a process defect in the historical negative side inspection sample set to generate a first sample set; use the first sample set to train the correlation between the indicator defect detection feature of any detection indicator and the defective process node to generate the first traceability layer.

[0067] Furthermore, the production quality inspection device for steering elements is also used to: configure a production equipment parameter consistency threshold, a raw material parameter consistency threshold and a production environment parameter consistency threshold; cluster the production equipment parameters, raw material parameters and production environment parameters corresponding to any steering element according to the production equipment parameter consistency threshold, the raw material parameter consistency threshold and the production environment parameter consistency threshold to generate multiple clustering clusters; determine a preset sample sampling ratio coefficient, and determine the number of sampling samples based on the total number of steering elements produced in the first batch; and screen the multiple clustering clusters with the cluster centroid as the center according to the number of sampling samples to generate the multiple steering element inspection samples.

[0068] Furthermore, the production quality inspection device for steering elements is also used to: determine the number of clustered steering elements corresponding to the multiple clusters, uniformly distribute the inspection samples in combination with the number of random inspection samples, and determine the number of random inspections within the multiple clusters; according to the number of random inspections within the multiple clusters, random inspection samples are carried out within the multiple clusters with the cluster centroid as the center, and uniform distribution screening of the surrounding inspection samples is performed to generate the multiple steering element inspection samples.

[0069] Furthermore, the production quality inspection device for steering elements is also used to: analyze the traceability results and calculate the proportion coefficients corresponding to different defect factors; sort the different defect factors in descending order of the proportion coefficients to generate a defect factor sequence; and send the defect factor sequence to the control terminal of the steering element production line for defect factor troubleshooting and taboo reminders.

[0070] Furthermore, the production quality inspection device for a steering element is also used to: analyze the traceability results and locate defective process nodes whose defect factors are process nodes; collect original process parameters used to produce defective samples corresponding to the defective process nodes; connect to a process parameter optimization library to optimize the original process parameters, wherein the process parameter optimization library includes multiple pairs of optimization parameter groups, wherein any pair of optimization parameter groups includes process parameters before optimization and process parameters after optimization and defect optimization feature labels, and based on the original process parameters and the defect features of the defective samples, the optimized process parameters are matched among the multiple pairs of optimization parameter groups.

[0071] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The production quality inspection method for a steering element and the specific examples in the aforementioned embodiment 1 are also applicable to a production quality inspection device for a steering element in this embodiment. Through the aforementioned detailed description of the production quality inspection method for a steering element, those skilled in the art can clearly know the production quality inspection device for a steering element in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0072] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0073] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting the production quality of a steering element, characterized in that: include: Determining a plurality of detection modules for performing production quality detection on the steering element, wherein any detection module is used to perform quality detection on the steering element according to a corresponding quality detection index; Calling the multiple detection modules to perform traceability analysis of production defects and establishing a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer of process nodes and a second traceability layer of production parameters; A control terminal connected to a steering component production line receives a first batch of production data sets, wherein the first batch of production data sets includes production equipment parameters, raw material parameters, and production environment parameters corresponding to any steering component produced in the first batch; Performing parameter consistency clustering on the production equipment parameters, raw material parameters and production environment parameters, and selecting a plurality of steering element test samples at the cluster center according to the clustering results; Performing quality inspection on the plurality of steering element inspection samples by using the plurality of inspection modules, and determining defective sample production data of samples corresponding to unqualified quality inspection indicators; Inputting the defect sample production data into the production defect traceability analysis network, tracing the defects through the first traceability layer and the second traceability layer, generating a traceability result and sending it to the control terminal of the steering component production line for reminder; The multiple detection modules are called to perform the traceability analysis of production defects, and a production defect traceability analysis network is established, wherein the production defect traceability analysis network includes a first traceability layer of process nodes and a second traceability layer of production parameters, including: Extracting any detection module from the multiple detection modules and any corresponding detection indicator; Collecting a historical negative detection sample set with any of the detection indicators as a constraint, wherein any negative detection sample in the historical negative detection sample set includes indicator defect detection features and defect factors; Performing correlation analysis of defective process nodes using the indicator defect detection features and the defect factors as samples to establish the first traceability layer; Performing correlation analysis of defective production parameters using the indicator defect detection features and the defect factors as samples to establish the second traceability layer; The production defect traceability analysis network is constructed using the first traceability layer and the second traceability layer.

2. A method for detecting production quality of a steering element according to claim 1, characterized in that: Using the indicator defect detection features and the defect factors as samples, a correlation analysis of defective process nodes is performed to establish the first traceability layer, including: Using the defect factor as a constraint, in the historical reverse surface inspection sample set, negative surface inspection samples whose defect factor is a process defect are selected to generate a first sample set; The first sample set is used to train the correlation between the indicator defect detection characteristics of any detection indicator and the defective process node to generate the first traceability layer.

3. A method for detecting production quality of a steering element according to claim 1, characterized in that: The production equipment parameters, raw material parameters and production environment parameters are clustered according to parameter consistency, and a plurality of steering element test samples at the cluster center are selected according to the clustering results, including: Configure the production equipment parameter consistency threshold, raw material parameter consistency threshold and production environment parameter consistency threshold; According to the production equipment parameter consistency threshold, the raw material parameter consistency threshold and the production environment parameter consistency threshold, the production equipment parameter, the raw material parameter and the production environment parameter corresponding to any steering element are clustered to generate multiple clusters; Determine the preset sample sampling ratio coefficient, and determine the number of samples for sampling based on the total number of steering components produced in the first batch; According to the number of samples randomly inspected, the plurality of clusters are screened with the cluster centroid as the center to generate the plurality of steering element detection samples.

4. A method for detecting production quality of a steering element according to claim 3, characterized in that: According to the number of samples randomly inspected, the plurality of clusters are screened with the cluster centroid as the center to generate the plurality of steering element detection samples, including: Determine the number of clustering steering elements corresponding to the plurality of clusters, evenly distribute the sampled samples in combination with the number of sampled samples, and determine the number of sampled samples within the plurality of clusters; According to the number of random inspections within the multiple clusters, samples are randomly inspected within the multiple clusters with the cluster centroid as the center, and uniform distribution screening is performed on the surrounding random inspection samples to generate the multiple steering element detection samples.

5. A method for detecting production quality of a steering element according to claim 3, characterized in that: After the traceability results are generated, they also include: Analyze the traceability results and calculate the corresponding proportion coefficients of different defect factors; The different defect factors are sorted in descending order according to the proportion coefficients to generate a defect factor sequence; The defect factor sequence is sent to the control terminal of the steering element production line for defect factor troubleshooting and taboo reminders.

6. A method for detecting production quality of a steering element according to claim 5, characterized in that: After the traceability results are generated, they also include: Analyze the traceability results to locate defective process nodes whose defect factors are process nodes; Collecting original process parameters used by the defective process node to produce defective samples; The original process parameters are optimized by connecting to a process parameter optimization library, wherein the process parameter optimization library includes multiple pairs of optimization parameter groups, wherein any pair of optimization parameter groups includes the process parameters before optimization and the process parameters after optimization and defect optimization feature labels, and based on the original process parameters and the defect features of the defective samples, the optimized process parameters are matched in the multiple pairs of optimization parameter groups.

7. A production quality inspection device for a steering element, characterized in that: The steps for implementing the production quality inspection method of a steering element according to any one of claims 1 to 6 include: A detection module determination unit, the detection module determination unit is used to determine a plurality of detection modules used to perform production quality detection on the steering element, wherein any detection module is used to perform quality detection on the steering element according to a corresponding quality detection index; A traceability analysis unit, the traceability analysis unit is used to call the multiple detection modules to perform traceability analysis on production defects and establish a production defect traceability analysis network, wherein the production defect traceability analysis network includes a first traceability layer of process nodes and a second traceability layer of production parameters; A production data acquisition unit, the production data acquisition unit is used to connect to the control terminal of the steering component production line and receive a first batch of production data sets, wherein the first batch of production data sets includes production equipment parameters, raw material parameters and production environment parameters corresponding to any steering component produced in the first batch; A cluster screening unit, the cluster screening unit is used to perform parameter consistency clustering on the production equipment parameters, raw material parameters and production environment parameters, and screen a plurality of steering element detection samples at the cluster center according to the clustering result; A quality inspection unit, the quality inspection unit is used to perform quality inspection on the plurality of steering element inspection samples through the plurality of inspection modules, and determine defective sample production data of samples corresponding to unqualified quality inspection indicators; A defect tracing unit is used to input the defect sample production data into the production defect tracing analysis network, perform defect tracing through the first tracing layer and the second tracing layer, generate tracing results and send them to the control terminal of the steering element production line for reminder.

Images