A method and system for enterprise product quality assessment based on multi-dimensional data

Abstract

The present invention relates to the technical field of product quality data processing, and specifically discloses a method and system for enterprise product quality assessment based on multi-dimensional data. The method determines the label information of a product to obtain a product compliance index, thereby providing basic data for product quality, and analyzing the production process of the product to timely discover factors that have a negative impact on product quality in the product production process. At the same time, the production information and product production risk index of each reference product are evaluated to obtain a product production quality index, thereby making a horizontal comparison of products to understand whether there is a competitive advantage in product quality, and then providing evaluation feedback on product quality, which is conducive to predicting the product quality level and timely adjusting the product and the product production process to improve product quality.

Description

Technical Field

[0001] The present invention relates to the technical field of product quality data processing, and in particular to a method and system for evaluating enterprise product quality based on multi-dimensional data. Background Art

[0002] In today's rapidly changing market environment, the stability and competitiveness of product quality have become key factors in determining the survival and development of enterprises. In existing product quality assessment practices, the collection of product data often fails to cover multiple key dimensions, resulting in incomplete assessment results and difficulty in accurately reflecting the true competitiveness of products in the market.

[0003] For example, the invention patent with announcement number CN114862266B discloses an industrial product production quality monitoring and analysis system based on big data. By acquiring the three-dimensional model and appearance image of each elbow pipe fitting to be monitored, the basic characteristic parameters and appearance characteristic parameters of each elbow pipe fitting to be monitored are obtained, and the basic characteristic parameter accuracy compliance ratio index and the appearance characteristic parameter influence ratio index of each elbow pipe fitting to be monitored are analyzed. At the same time, the mechanical properties of each elbow pipe fitting to be monitored are tested to obtain the mechanical property parameters of each elbow pipe fitting to be monitored, and the mechanical property compliance ratio index of each elbow pipe fitting to be monitored is analyzed. The comprehensive production quality coefficient of each elbow pipe fitting to be monitored is evaluated, thereby realizing multi-dimensional analysis of the production quality of elbow pipe fittings, avoiding the problems of excessive one-sidedness and limitations of existing methods, effectively reducing the error of the elbow pipe fitting production quality analysis results, and greatly improving the overall use quality of the later pressure pipeline.

[0004] For example, the invention patent with announcement number CN113780724B, the method for calculating the quantitative evaluation criteria of product quality batch stability includes: S1, determining the quantitative evaluation criterion indicator set; S2, designing the quantitative evaluation criterion indicator calculation method and combination application logic; determining the threshold parameters of each indicator and the indicator combination application logic in the quality inspection application to meet the quantitative evaluation needs of product quality batch stability of small sample test data sets; the above invention designs a set of quantitative evaluation criterion calculation methods for product quality batch stability evaluation, and the quantitative evaluation criterion calculation method can be used to directly form an analysis conclusion on product quality batch stability, thereby realizing the standardization and instrumentation of the product quality batch stability evaluation process and improving the efficiency and level of product quality inspection.

[0005] However, in the process of implementing the embodiments of the present application, it was found that the above-mentioned technology has at least the following technical problems: the existing product quality assessment method mainly focuses on the quality analysis of the product itself, and a single data dimension may only reflect part of the product quality, making it difficult to fully grasp the potential room for improvement of product quality in the market, and unable to ensure the continuous improvement of product quality, thereby failing to meet market demand. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a method and system for enterprise product quality assessment based on multi-dimensional data, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides an enterprise product quality assessment method based on multi-dimensional data, including: S1. Acquire multi-dimensional data of the product, extract product label information from it, and determine the product compliance index; S2. According to the multi-dimensional data of the product, match the production process of the product, collect the production process information of the product, and analyze the product production risk index; S3. Sample and extract similar products, and mark each extracted product as a reference product, collect the production information of each reference product, and evaluate the product production quality index based on the product production risk index; S4. Compare the product production quality index with the product production threshold, thereby evaluating the product quality.

[0008] As a further method, the production process of the product is matched, and the specific matching process is: according to the multi-dimensional data of the product, the production process and production time of the product are extracted, and the length of the product production cycle is analyzed to match the production process of the product.

[0009] As a further method, the production information of each reference product is collected, specifically including a plane model of each reference product at the end time of the performance test cycle.

[0010] As a further method, the evaluation process of the product production quality index is as follows: based on the plane model of each reference product at the end time of the performance test cycle, the wear area of ​​each reference product is obtained by image processing, and at the same time, based on the multi-dimensional data of the product, the plane model of the product at the end time of the performance test cycle is extracted to obtain the wear area of ​​the product, and the overall variance of the wear area of ​​the product and the wear area of ​​each reference product is analyzed to obtain the product wear degree; the wear area of ​​the product is marked as the reference wear area, and the wear area of ​​each reference product is sorted from small to large, and the number of reference products with a wear area greater than the reference wear area is counted, marked as the number of products with excessive wear, and the ratio is processed with the number of reference products to obtain the reference product wear excess ratio; the reference product corresponding to the wear area ranked first is marked as the optimal reference product, and the number of assembly parts of the optimal reference product is obtained by analysis, and the number of assembly parts of the product is extracted based on the multi-dimensional data of the product, thereby comprehensively analyzing to obtain the product production quality index.

[0011] As a further method, the product quality is evaluated and fed back, and the specific feedback process is: comparing the product production quality index with the product production quality threshold, if the product production quality index is less than the product production quality threshold, then evaluating and feeding back the product quality.

[0012] The second aspect of the present invention provides a system for an enterprise product quality assessment method based on multi-dimensional data, including: a product compliance determination module, used to obtain multi-dimensional data of products, extract product label information therefrom, and determine the product compliance index; a production risk analysis module, used to match the production process of the product based on the multi-dimensional data of the product, collect the production process information of the product, and analyze the product production risk index; a production quality assessment module, used to sample and extract similar products, mark each extracted product as a reference product, collect the production information of each reference product, and evaluate the product production quality index based on the product production risk index.

[0013] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0014] (1) The present invention provides an enterprise product quality assessment method and system based on multi-dimensional data. By determining the label information of the product, a product compliance index is obtained, thereby providing basic data for product quality. By analyzing the production process of the product, factors that have a negative impact on product quality in the production process can be discovered in a timely manner. At the same time, the production information and product production risk index of each reference product are evaluated to obtain a product production quality index. Thus, a horizontal comparison of products is performed to understand whether there is a competitive advantage in product quality, and then evaluation feedback on product quality is provided, which is conducive to predicting the product quality level and timely adjusting the product and the product production process to improve product quality.

[0015] (2) The present invention obtains a product compliance index by analyzing the proportion of environmentally friendly products, the proportion of products that comply with material composition, and the proportion of products that comply with size. This can provide in-depth insights into the production strength of an enterprise and more accurately predict the probability of product quality compliance, thereby avoiding potential product quality risks in advance.

[0016] (3) The present invention obtains the product production quality index by analyzing the product production risk index, product wear degree, reference product wear excess ratio, the number of assembly parts of the optimal reference product and the number of assembly parts of the product. It can quickly capture the changing dynamics of product production risks. Enterprises can respond quickly, adjust the operating parameters of production equipment, optimize product production processes, and ensure that product quality is significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0018] Figure 1 The figure is a schematic flow chart of the method steps of the present invention.

[0019] Figure 2 It is a schematic diagram of system module connection of the present invention.

[0020] Figure 3 It is a schematic diagram of the waste volume curve involved in the present invention.

[0021] Figure symbols: 1. Waste volume peak detection time point; 2. Waste volume valley detection time point; 3. Waste volume peak value; 4. Waste volume valley value. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] Reference Figure 1 As shown, the first aspect of the present invention provides an enterprise product quality assessment method based on multi-dimensional data, including: S1. Acquire multi-dimensional data of the product, extract the product label information therefrom, and determine the product compliance index.

[0024] In a specific embodiment, the present invention obtains a product compliance index by analyzing the proportion of environmentally friendly products, the proportion of products that comply with material composition, and the proportion of products that comply with size. This can provide in-depth insights into the production strength of the company and more accurately predict the compliance probability of product quality, thereby avoiding potential product quality risks in advance.

[0025] Specifically, the product compliance index is determined by the following process: according to the label information of each sampled product, each sampled product containing an environmentally friendly label is marked as an environmentally friendly product, the number of environmentally friendly products is counted, and the ratio is processed with the number of sampled products to obtain the proportion of environmentally friendly products; in this embodiment, the system used for the enterprise product quality assessment method based on multi-dimensional data is referred to as the product quality assessment system, and the above-mentioned environmentally friendly labels are added by the enterprise according to the requirements of market standards, including durable labels, energy-saving labels, and non-toxic and harmless labels.

[0026] The proportion of each material component of each sampled product is tested, and the difference processing is performed between the reference proportion of each material component recorded in the label information of each sampled product to obtain the deviation value of the proportion of each material component of each sampled product, which is compared with the allowable deviation value of the material component proportion respectively, and the number of sampled products whose deviation values ​​of each material component proportion are less than the allowable deviation value of the material component proportion is counted, marked as the number of products with compliant material component proportion, and the ratio processing is performed with the number of sampled products to obtain the proportion of products with compliant material component proportion; the reference proportion of each material component recorded in the label information of the above-mentioned sampled products is stipulated by the production regulations of the enterprise; the allowable deviation value of the above-mentioned material component proportion is stipulated by the product market standard, which indicates the maximum value of the allowable deviation of the material component proportion; the above-mentioned testing of the proportion of each material component of each sampled product refers to obtaining parts of each sampled product and making them into each solid Electrode, each solid electrode is analyzed by atomic emission spectroscopy, thereby obtaining the proportion of each material component of each sampled product. For example, in an example embodiment, after part of a sampled product is tested, the wavelength of the characteristic spectral line of iron element is 248.3 nanometers, the relative value of the spectral line intensity is 100, and its proportion is 58.3%. The wavelength of the characteristic spectral line of nickel element is 340.5 nanometers, the relative value of the spectral line intensity is 50, and its proportion is 23.5%. The reference proportion of iron element is 60%, and the deviation value of the proportion of iron element is 1.7%. The reference proportion of nickel element is 23%, and the deviation value of the proportion of nickel element is 0.5%. The allowable deviation value of the material component proportion is 5%. The deviation value of the proportion of iron element and the deviation value of the proportion of nickel element of the sampled product are both less than the allowable deviation value of the material component proportion. Therefore, the sampled product is a compliant product for the material component proportion.

[0027] Dimension detection areas are randomly arranged on the surface of each sampled product, and the area, circumference, transmission shaft diameter and spring outer diameter of each dimension detection area are measured. The difference is processed with the reference area, reference circumference, reference transmission shaft diameter and reference spring outer diameter recorded in the label information of each sampled product to obtain the dimensional deviation value of each sampled product, which is compared with the allowable dimensional deviation value respectively. The number of sampled products with each dimensional deviation value less than the allowable dimensional deviation value is counted and marked as the number of size-qualified products. The ratio is processed with the number of sampled products to obtain the proportion of size-compliant products; the above-mentioned allowable dimensional deviation value is specified by the product market standard and represents the maximum value of the allowable dimensional deviation; the reference area, reference circumference, reference transmission shaft diameter and reference spring outer diameter recorded in the label information of the above-mentioned sampled products are specified by the enterprise production specification The above measurements obtain the area, circumference, drive shaft diameter and spring outer diameter of each size detection area, which can be measured and analyzed using a vernier caliper. For example, in an example embodiment, the drive shaft diameter of a sampled product is 25.2 mm, and the reference drive shaft diameter is 25 mm. The drive shaft size deviation value of the sampled product is 0.2 mm. The spring outer diameter of the sampled product is 8.98 mm, and the reference spring outer diameter is 9 mm. The spring outer diameter size deviation value of the sampled product is 0.02 mm, and the allowable size deviation value is 0.25 mm. The drive shaft size deviation value and the spring outer diameter size deviation value of the sampled product are both smaller than the allowable size deviation value. If the area size deviation value and the circumference size deviation value of the sampled product are both smaller than the allowable size deviation value, the sampled product can be called a size-compliant product.

[0028] The product compliance index is obtained through comprehensive analysis. In this embodiment, the product compliance index is obtained through comprehensive analysis of the proportion of environmentally friendly products, the proportion of products with compliant material composition, and the proportion of products with compliant dimensions. It refers to a value used to predict the probability of product quality compliance. The specific expression is as follows:

[0029]

[0030] Among them, Λ is the product compliance index. The higher the proportion of environmentally friendly products, the more reliable the quality of the company's historical products is and the more in line with the trend of sustainable development. As a result, the company can ensure that the material composition meets the product production requirements during the production process. The higher the proportion of compliant products with material composition, the foundation for product quality compliance is laid. The higher the proportion of dimensional compliant products, the higher the product manufacturing precision, which can jointly improve the degree of product quality compliance and reduce unnecessary waste of resources. Therefore, a comprehensive analysis of the proportion of environmentally friendly products, the proportion of compliant products with material composition and the proportion of compliant products with size can comprehensively evaluate the company's production level and predict the probability of product quality compliance, thereby enhancing the market competitiveness of the product.

[0031] Eco_P is the proportion of environmentally friendly products. A high proportion of environmentally friendly products reflects that the company's historical production process is more in line with market standards, thus ensuring the reliability of the product source and stable quality.

[0032] CM_R is the proportion of products with compliant material composition. A high proportion of products with compliant material composition indicates that the company strictly controls the proportion, use and inspection of raw materials used in the products to ensure reliable product quality, which helps reduce product quality defects caused by material problems.

[0033] CP_R is the proportion of products with dimensional compliance. A high proportion of products with dimensional compliance indicates that the company has strong capabilities in precise control and management of product dimensions during the production process, which helps to improve the overall quality of the product and meet user needs.

[0034] hm 1 is the impact factor corresponding to the unit value of the environmentally friendly product ratio, hm 2 The impact factor corresponding to the unit value of the material composition ratio of compliant products, hm 3 It is the impact factor corresponding to the unit value of the proportion of dimensional compliant products; the impact factor corresponding to the unit value of the above-mentioned environmentally-friendly product proportion represents the numerical value of the influence of the unit value of the environmentally-friendly product proportion on the product compliance index, and its numerical range is 20% to 32%, and it is 30% in this embodiment; the impact factor corresponding to the unit value of the above-mentioned material composition proportion compliant product proportion represents the numerical value of the influence of the unit value of the material composition proportion compliant product proportion on the product compliance index, and its numerical range is 38% to 42%, and it is 40% in this embodiment; the impact factor corresponding to the unit value of the above-mentioned size compliant product proportion represents the numerical value of the influence of the unit value of the size compliant product proportion on the product compliance index, and its numerical range is 25% to 38%, and it is 30% in this embodiment.

[0035] In this embodiment, the change table of the above product compliance index and its corresponding parameters is shown in Table 1:

[0036] Table 1 Product compliance index and its corresponding parameter changes

[0037]

[0038]

[0039] In this embodiment, as shown in Table 1, when the proportion of environmentally friendly products, the proportion of products with compliant material composition ratio, and the proportion of products with compliant size are all the smallest, the product compliance index is the lowest, indicating that the product is more likely to be an unqualified product. As the proportion of environmentally friendly products, the proportion of products with compliant material composition ratio, and the proportion of products with compliant size increase, the product compliance index also increases, indicating that the probability of compliance of product quality is getting higher and higher.

[0040] Furthermore, the specific analysis process of the label information of the product is as follows: based on the multi-dimensional data of the product, the label information of the product is extracted and each product of the batch to which the product belongs is located, and each sampled product is randomly selected from each product to thereby obtain the label information of each sampled product; the above-mentioned extraction of the label information of the product and locating each product of the batch to which the product belongs refers to the product quality assessment system entering the label information of all products, the label information includes the batch number of the product, and by obtaining the batch number of the product, all products belonging to the batch number can be queried through the product quality assessment system.

[0041] S2. Based on the multi-dimensional data of the product, match the production process of the product, collect the production process information of the product, and analyze the product production risk index.

[0042] Specifically, the analysis of the product production risk index includes the following specific analysis process: based on the product production process information, extract the duration of each operation error of the production equipment to which the product belongs within the product production cycle, accumulate the total duration of operation errors of the production equipment to which the product belongs within the product production cycle, and perform ratio processing with the duration corresponding to the product production cycle, thereby obtaining the operation error rate of the production equipment to which the product belongs; the above-mentioned product production cycle is formulated by the enterprise based on the production process of the product, and refers to the total duration from the beginning of product processing to output, and the duration will change according to different actual conditions; the above-mentioned duration of each operation error can be extracted from the information recorded in the production operation log of the production equipment.

[0043] Randomly select each product produced by the production equipment to which the product belongs within the product production cycle, mark them as each production sample of the production equipment, obtain each geometric feature of each production sample, compare and verify with the geometric features of each template preset by the production equipment, count the number of production samples whose geometric features are equal to the geometric features of each template preset by the production equipment, mark them as the number of qualified production samples, and perform ratio processing with the number of production samples to obtain the production consistency rate of the production equipment to which the product belongs; the above-mentioned geometric features of each production sample are obtained, wherein each geometric feature includes torsion, curvature, perimeter, surface area and symmetry; the above-mentioned template geometric features preset by the production equipment are specified by the enterprise production; in an example embodiment, locate the center point of a certain position of a production sample, measure the change of the reflection angle of the center point of the position by laser scanning method, so as to obtain the curvature of the production sample; at the same time, use three-dimensional scanning technology to obtain a three-dimensional model of the production sample, analyze the surface area of ​​the production sample by Geometry Magic reverse engineering software, and compare them with the template curvature and template surface area preset by the production equipment respectively. If they are equal, the production sample is a qualified production sample.

[0044] According to the production process information of the product, the waste volume curve of the production equipment to which the product belongs within the product production cycle is extracted, the highest point of the waste volume curve is located, and the horizontal axis corresponding to the highest point of the waste volume curve is marked as the waste volume peak detection time point, and the vertical axis is marked as the waste volume peak value. At the same time, the lowest point of the waste volume curve is located, and the horizontal axis corresponding to the lowest point of the waste volume curve is marked as the waste volume valley detection time point, and the vertical axis is marked as the waste volume valley value. Through data processing, the functions to which the waste volume peak detection time point, the waste volume valley detection time point, the waste volume peak value and the waste volume valley value belong are obtained, and the slope of the function is extracted and marked as the net waste treatment rate of the production equipment to which the product belongs; the above-mentioned waste volume curve of the production equipment to which the product belongs within the product production cycle is extracted, wherein the waste volume curve is as follows Figure 3 The figure shown is generated by the Fanruan intelligent reporting software belonging to the product quality assessment system based on the data in the production operation log of the production equipment. The horizontal axis is the waste volume detection time point in hours, and the vertical axis is the waste volume in cubic meters. The peak value of the waste volume is Figure 3 Arrow 3 in the figure shows the waste volume valley value. Figure 3 Arrow 4 in the figure indicates the time point of waste volume peak detection. Figure 3 Arrow 1 in the figure indicates the time point of waste volume valley detection. Figure 3 Arrow 2 in the figure shows the slope of the above extraction function. Figure 3 The coordinates (the value corresponding to arrow 1, the value corresponding to arrow 3) and the coordinates (the value corresponding to arrow 2, the value corresponding to arrow 4) can constitute a two-variable linear function. The absolute value of the slope of the two-variable linear function is the net waste processing rate of the production equipment to which the product belongs. If the absolute value of the slope is larger, it indicates that the production equipment has a faster waste processing speed, which can reduce equipment failures caused by waste blockage, thereby improving the production efficiency and production accuracy of the production equipment.

[0045] The comprehensive analysis thus obtained results in the product production risk index. In this embodiment, the product production risk index is obtained by comprehensive analysis of the operation error rate, production consistency rate, and net waste treatment speed of the production equipment to which the product belongs. The index refers to a value used to determine the degree of product production risk. The specific expression is as follows:

[0046]

[0047] Among them, Θ is the product production risk index. The higher the operating error rate of the production equipment to which the product belongs, the lower the stability of the production equipment in the production process, the larger the production error, which leads to a decrease in production consistency. Unqualified products often need to be discarded, which will increase the volume of waste and processing time, thereby reducing the net waste processing rate. Therefore, the operating error rate, production consistency rate and net waste processing rate are integrated and analyzed. When these parameters change, the product production risk index will also change accordingly, thereby timely reflecting the changes in product production risks, thereby adjusting the production parameters of the production equipment and optimizing the process flow of the production equipment to improve product quality.

[0048] OE_R is the operational error rate of the production equipment to which the product belongs. The level of the operational error rate directly affects the quality and production efficiency of the product. A high operational error rate may result in the product being unable to be produced according to the prescribed production process, thereby causing huge structural deviations and reducing product quality.

[0049] PC_R is the production consistency rate of the production equipment to which the product belongs. The higher the production consistency rate, the more accurately the production equipment can produce according to the preset parameters, and the higher the stability and reliability of product quality.

[0050] WD_V is the net waste treatment rate of the production equipment to which the product belongs. A higher net waste treatment rate indicates that the production equipment has a higher adjustment capacity, which can reduce the adverse negative impact on the product production process, thereby ensuring the stability of the product production process and thus ensuring the stability of product production quality.

[0051] p 1 is the impact factor corresponding to the unit value of the operation error rate, p 2 is the impact factor corresponding to the unit value of production consistency rate, p 3 It is the impact factor corresponding to the unit value of the net waste treatment speed; the impact factor corresponding to the above-mentioned unit value of the operation error rate represents the numerical value of the influence of the unit value of the operation error rate on the product production risk index, and its numerical range is 10% to 30%, and it is 20% in this embodiment; the impact factor corresponding to the above-mentioned unit value of the production consistency rate represents the numerical value of the influence of the unit value of the production consistency rate on the product production risk index, and its numerical range is 20% to 40%, and it is 30% in this embodiment; the impact factor corresponding to the above-mentioned unit value of the net waste treatment speed represents the numerical value of the influence of the unit value of the net waste treatment speed on the product production risk index, and its numerical range is 32% to 48%, and it is 40% in this embodiment.

[0052] In this embodiment, the variation table of the above product production risk index and its corresponding parameters is shown in Table 2:

[0053] Table 2 Changes of product production risk index and its corresponding parameters

[0054]

[0055] In this embodiment, as shown in Table 2, the operational error rate has the greatest impact on the product production risk index. When the operational error rate is the maximum value of 6 in the table, the product production risk index is also the maximum value in the table, highlighting the importance of operational errors in the production process. A high operational error rate may not only lead to reduced production efficiency, but also increase the risk of production accidents, thereby significantly improving the overall product production risk index.

[0056] Furthermore, the production process of the product is matched, and the specific matching process is: according to the multi-dimensional data of the product, the production process and production time of the product are extracted, and the duration of the product production cycle is analyzed to match the production process of the product; the specific matching process is as follows: according to the multi-dimensional data of the product, the label information of the product is extracted, and the label information records the production time of the product, which is the end time point of the product production cycle, and the duration of the product production cycle is obtained according to the product production process recorded in the label information, thereby calculating the start time point of the product production cycle, and obtaining the production operation log of the production equipment to which the product belongs during the product production cycle, that is, matching the production process of the product.

[0057] S3. Sample and extract similar products, mark each extracted product as a reference product, collect the production information of each reference product, and evaluate the product production quality index based on the product production risk index.

[0058] In a specific embodiment, the present invention obtains a product production quality index by analyzing the product production risk index, product wear, reference product wear excess ratio, the number of assembly parts of the optimal reference product, and the number of assembly parts of the product. It can quickly capture the changing dynamics of product production risks, and the enterprise can respond quickly, adjust the operating parameters of the production equipment, optimize the product production process, and ensure that the product quality is significantly improved.

[0059] Specifically, the product production quality index is obtained by comprehensively analyzing the product production risk index, product wear degree, reference product wear excess ratio, the number of assembly parts of the optimal reference product, and the number of assembly parts of the product in this embodiment. It refers to a value used to predict the quality of product production. The specific expression is:

[0060]

[0061] Among them, Φ is the product production quality index. When the risk level of product production increases, the stability of the production process fluctuates significantly and the product quality cannot be guaranteed. Especially for products with a large number of assembly parts, the complex production process makes the product more prone to wear during the manufacturing process, which makes the wear area after a period of use significantly increase compared with similar products, thereby reducing the excess wear rate of the reference product. Comprehensive evaluation of the above parameters makes it possible to predict product quality.

[0062] Θ is the product production risk index, which is a value obtained through comprehensive analysis of the operating error rate, production consistency rate and net waste treatment rate of the production equipment to which the product belongs, and is used to determine the degree of product production risk.

[0063] F_R is the product wear degree, which is used to evaluate the degree of wear of the product relative to the reference product. The lower the wear degree, the stricter the quality control of the product during the production process.

[0064] MA_D c It is the ratio of excessive wear of the reference product. The higher the ratio of excessive wear of the reference product, the smaller the wear area of ​​the test product and the higher the quality level among similar reference products.

[0065] TPI c is the number of assembly parts of the optimal reference product, and TPI is the number of assembly parts of the product. If the number of assembly parts of the optimal reference product is greater than the number of assembly parts of the product, it means that the assembly process in the product production process is optimized to ensure the stability of the product structure.

[0066] mt is the weight factor corresponding to the product production risk index, which represents the influence coefficient of the product production risk index on the production quality index. The relationship between the product production risk index and the product production quality index is analyzed by the least squares method to obtain the weight factor corresponding to the product production risk index, and its value range is 0.7 to 0.88.

[0067] bm 1 bm is the impact factor corresponding to the unit value of product wear, 2 bm is the influence factor corresponding to the unit value of the product wear excess ratio, 3It is the influence factor corresponding to the unit value of the number of assembly part deviations; the influence factor corresponding to the unit value of the above-mentioned product wear degree represents the influence of the unit value of the product wear degree on the product production quality index, and its value range is 0.21 to 0.30; the influence factor corresponding to the unit value of the above-mentioned reference product wear excess ratio represents the influence of the unit value of the reference product wear excess ratio on the product production quality index, and its value range is 0.28 to 0.35; the influence factor corresponding to the unit value of the above-mentioned assembly part deviations represents the influence of the unit value of the assembly part deviations on the product production quality index, and its value range is 0.26 to 0.34.

[0068] Specifically, the production information of each reference product is collected, including the plane model of each reference product at the end time of the performance test cycle. The specific collection process is: capturing the three-dimensional model of each reference product at the end time of the performance test cycle by a three-dimensional scanner, and then converting the three-dimensional model into a two-dimensional image by ray tracing technology, thereby obtaining the plane model of each reference product at the end time of the performance test cycle.

[0069] Furthermore, the evaluation process of the product production quality index is as follows: based on the plane model of each reference product at the end time of the performance test cycle, the wear area of ​​each reference product is obtained by image processing, and at the same time, based on the multi-dimensional data of the product, the plane model of the product at the end time of the performance test cycle is extracted to obtain the wear area of ​​the product, and the overall variance of the wear area of ​​the product and the wear area of ​​each reference product is analyzed to obtain the product wear degree; the above-mentioned performance test cycle refers to the time period for analyzing product performance, which is formulated by quality assessment experts based on product performance, and the duration of the performance test cycle will vary according to actual conditions; the above-mentioned wear area of ​​each reference product obtained by image processing , refers to identifying and analyzing the pixels of the wear area of ​​the plane model of each reference product at the end time of the performance test cycle through a threshold segmentation algorithm, thereby calculating the wear area of ​​each reference product; the above-mentioned extraction of the plane model of the product at the end time of the performance test cycle is the same as the plane model acquisition process of each reference product at the end time of the performance test cycle; the above-mentioned analysis of the overall variance of the wear area of ​​the product and the wear area of ​​each reference product refers to first performing a mean analysis on the wear area of ​​the product and the wear area of ​​each reference product to obtain the average wear area, and then calculating the sum of the squares of the difference between the wear area of ​​the product and the wear area of ​​each reference product and the average wear area, thereby obtaining the product wear degree.

[0070] Mark the wear area of ​​the product as the reference wear area, sort the wear area of ​​each reference product from small to large, count the number of reference products with a wear area larger than the reference wear area, mark it as the number of products with excessive wear, and perform ratio processing with the number of reference products to obtain the ratio of excessive wear of reference products; the above-mentioned number of reference products with a wear area larger than the reference wear area can be used to judge the quality level of the product in the market. If the number of products with excessive wear is small, it indicates that the product quality is relatively inferior among similar reference products on the market. It also means that the wear resistance of the product is lower than that of similar reference products, resulting in insufficient competitiveness of the product in the market.

[0071] The reference product corresponding to the wear area ranked first is marked as the optimal reference product, and the number of assembly parts of the optimal reference product is analyzed. The number of assembly parts of the product is extracted based on the multi-dimensional data of the product, and the product production quality index is obtained through comprehensive analysis; the number of assembly parts of the optimal reference product obtained by the above analysis refers to the three-dimensional model of each reference product at the end time of the performance test cycle, the three-dimensional model of the optimal reference product at the end time of the performance test cycle is extracted, and the object detection and segmentation technology based on convolutional neural network is used to identify and count the number of assembly parts of the optimal reference product; the method for obtaining the number of assembly parts of the product is the same as the method for obtaining the number of assembly parts of the optimal reference product.

[0072] S4. Compare the product production quality index with the product production threshold, and provide evaluation feedback on the product quality.

[0073] Specifically, the evaluation and feedback of product quality is as follows: comparing the product production quality index with the product production quality threshold, if the product production quality index is less than the product production quality threshold, the product quality is evaluated and fed back; the above-mentioned product production quality threshold refers to the minimum value of the product production quality index, which is formulated by quality assessment experts based on the performance of products produced historically by the enterprise; if the product production quality index is less than the product production threshold, it means that the result predicted by the product quality assessment method in the product quality assessment system shows that the product quality may not meet the standards due to unqualified material ratios in the production process or the production process is not carried out according to the target, and the product cannot meet the expectations and industry standards; if the product production quality index is greater than or equal to the product production quality threshold, it means that the result predicted by the product quality assessment method in the product quality assessment system shows that the product quality meets the standards and no evaluation feedback is required; the above-mentioned evaluation and feedback of product quality refers to the product quality assessment system adding warning information to the product label information, and the quality assessment experts inspect and rework the product based on the warning information, and adjust the parameters of the production equipment to which the product belongs, thereby continuously improving the reliability of the enterprise's production and ensuring the quality of the products produced by the enterprise.

[0074] In a specific embodiment, the present invention provides an enterprise product quality assessment method and system based on multi-dimensional data, and obtains a product compliance index by determining the label information of the product, thereby providing basic data for product quality. By analyzing the production process of the product, factors that have a negative impact on product quality in the production process can be discovered in a timely manner. At the same time, the production information and product production risk index of each reference product are evaluated to obtain a product production quality index, thereby making a horizontal comparison of products to understand whether there is a competitive advantage in product quality, and then evaluating and feeding back the product quality, which is conducive to predicting the product quality level and timely adjusting the product and the product production process to improve product quality.

[0075] Reference Figure 2 As shown, the second aspect of the present invention provides a system for an enterprise product quality assessment method based on multi-dimensional data, including: a product compliance determination module, a production risk analysis module, a production quality assessment module and a product quality feedback module.

[0076] The product compliance determination module is connected to the production risk analysis module, the production risk analysis module is connected to the production quality assessment module, and the production quality assessment module is connected to the product quality feedback module.

[0077] The product compliance determination module is used to obtain multi-dimensional data of the product, extract the product label information therefrom, and determine the product compliance index.

[0078] The production risk analysis module is used to match the production process of the product based on the multi-dimensional data of the product, collect the production process information of the product, and analyze the production risk index of the product.

[0079] The production quality assessment module is used to sample and extract similar products, mark each extracted product as a reference product, collect production information of each reference product, and evaluate the product production quality index based on the product production risk index.

[0080] The product quality feedback module is used to compare the product production quality index with the product production threshold, thereby providing evaluation feedback on the product quality.

[0081] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A method for evaluating enterprise product quality based on multi-dimensional data, characterized in that: include: S1. Obtain multi-dimensional data of the product, extract the product label information from it, and determine the product compliance index. The product compliance index refers to a value obtained by comprehensive analysis of the proportion of environmentally friendly products, the proportion of compliant products in terms of material composition, and the proportion of compliant products in terms of size, and is used to predict the probability of product quality compliance; S2. Based on the multi-dimensional data of the product, the production process of the product is matched, and the production process information of the product is collected to analyze the product production risk index. The product production risk index refers to a value obtained by comprehensively analyzing the operation error rate, production consistency rate and net waste treatment speed of the production equipment to which the product belongs, and is used to determine the degree of product production risk; S3. Sample and extract similar products, mark each extracted product as a reference product, collect production information of each reference product, and evaluate the product production quality index based on the product production risk index. The product production quality index refers to a value obtained by comprehensive analysis of the product production risk index, product wear, reference product wear excess ratio, the number of assembly parts of the best reference product, and the number of assembly parts of the product, which is used to predict the quality of product production; S4. Compare the product production quality index with the product production threshold, thereby providing evaluation feedback on product quality; The specific analysis process of analyzing the product production risk index is as follows: According to the production process information of the product, the duration of each operation error of the production equipment to which the product belongs in the product production cycle is extracted, and the total duration of the operation error of the production equipment to which the product belongs in the product production cycle is accumulated to obtain the total duration of the operation error of the production equipment to which the product belongs in the product production cycle, and the ratio is processed with the duration corresponding to the product production cycle, thereby obtaining the operation error rate of the production equipment to which the product belongs; Randomly select each product produced by the production equipment to which the product belongs within the product production cycle, mark them as each production sample of the production equipment, obtain each geometric feature of each production sample, compare and verify with the geometric features of each template preset by the production equipment, count the number of production samples whose geometric features are equal to the geometric features of each template preset by the production equipment, mark them as the number of qualified production samples, perform ratio processing with the number of production samples, and obtain the production consistency rate of the production equipment to which the product belongs; According to the production process information of the product, the waste volume curve of the production equipment to which the product belongs during the product production cycle is extracted, the highest point of the waste volume curve is located, and the horizontal axis corresponding to the highest point of the waste volume curve is marked as the waste volume peak detection time point, and the vertical axis is marked as the waste volume peak value. At the same time, the lowest point of the waste volume curve is located, and the horizontal axis corresponding to the lowest point of the waste volume curve is marked as the waste volume valley detection time point, and the vertical axis is marked as the waste volume valley value. Through data processing, the functions of the waste volume peak detection time point, the waste volume valley detection time point, the waste volume peak value and the waste volume valley value are obtained, and the slope of the function is extracted and marked as the net waste treatment speed of the production equipment to which the product belongs. The product production risk index is obtained through comprehensive analysis, and the specific expression is as follows: Among them, Θ is the product production risk index, p1 is the impact factor corresponding to the unit value of the operation error rate, p2 is the impact factor corresponding to the unit value of the production consistency rate, p3 is the impact factor corresponding to the unit value of the net waste treatment rate, WD_V is the net waste treatment rate of the production equipment to which the product belongs, PC_R is the production consistency rate of the production equipment to which the product belongs, and OE_R is the operation error rate of the production equipment to which the product belongs.

2. The enterprise product quality assessment method based on multi-dimensional data according to claim 1, characterized in that: The label information of the product, the specific analysis process is as follows: According to the multi-dimensional data of the product, the label information of the product is extracted and each product of the batch to which the product belongs is located, and each sampled product is randomly selected from each product to obtain the label information of each sampled product.

3. The enterprise product quality assessment method based on multi-dimensional data according to claim 2 is characterized by: The specific determination process of determining the product compliance index is as follows: According to the label information of each sampled product, each sampled product with an environmentally friendly label is marked as an environmentally friendly product, the number of environmentally friendly products is counted, and the ratio is processed with the number of sampled products to obtain the proportion of environmentally friendly products; Detect the proportion of each material component of each sampled product, perform difference processing with the reference proportion of each material component recorded in the label information of each sampled product, and obtain the deviation value of each material component proportion of each sampled product. Compare them with the allowable deviation value of the material component proportion respectively, and count the number of sampled products whose deviation values ​​of each material component proportion are less than the allowable deviation value of the material component proportion, mark them as the number of products with compliant material component proportion, and perform ratio processing with the number of sampled products to obtain the proportion of products with compliant material component proportion; Size inspection areas are randomly arranged on the surface of each sampled product, and the area, circumference, drive shaft diameter and spring outer diameter of each size inspection area are measured. The difference is processed with the reference area, reference circumference, reference drive shaft diameter and reference spring outer diameter recorded in the label information of each sampled product to obtain the size deviation value of each sampled product, which are compared with the allowable size deviation value respectively. The number of sampled products with each size deviation value less than the allowable size deviation value is counted and marked as the number of size-qualified products. The ratio is processed with the number of sampled products to obtain the proportion of size-compliant products, and the product compliance index is obtained through comprehensive analysis.

4. The enterprise product quality assessment method based on multi-dimensional data according to claim 1 is characterized by: The production process of matching products, the specific matching process is: Based on the multi-dimensional data of the product, the production process and production time of the product are extracted, and the length of the product production cycle is analyzed to match the production process of the product.

5. The enterprise product quality assessment method based on multi-dimensional data according to claim 1 is characterized by: The collecting of production information of each reference product specifically includes a plane model of each reference product at the end time of the performance test cycle.

6. The enterprise product quality assessment method based on multi-dimensional data according to claim 5 is characterized by: The specific evaluation process of evaluating the product production quality index is as follows: According to the plane model of each reference product at the end of the performance test cycle, the wear area of ​​each reference product is obtained through image processing. At the same time, according to the multi-dimensional data of the product, the plane model of the product at the end of the performance test cycle is extracted to obtain the wear area of ​​the product. The overall variance of the wear area of ​​the product and the wear area of ​​each reference product is analyzed to obtain the wear degree of the product. The wear area of ​​the product is marked as the reference wear area, and the wear areas of the reference products are sorted from small to large. The number of reference products with wear areas larger than the reference wear area is counted and marked as the number of products with excessive wear. The number is then compared with the number of reference products to obtain the ratio of excessive wear of the reference products. The reference product corresponding to the wear area ranked first is marked as the optimal reference product. The number of assembly parts of the optimal reference product is analyzed and the number of assembly parts of the product is extracted based on the multi-dimensional data of the product. The product production quality index is obtained through comprehensive analysis.

7. The enterprise product quality assessment method based on multi-dimensional data according to claim 6 is characterized by: The product production quality index is specifically expressed as: Among them, Φ is the product production quality index, Θ is the product production risk index, F_R is the product wear degree, MA_D c To refer to the product wear excess ratio, TPI c is the number of assembly parts of the optimal reference product, TPI is the number of assembly parts of the product, mt is the weight factor corresponding to the product production risk index, bm1 is the impact factor corresponding to the unit value of the product wear degree, bm2 is the impact factor corresponding to the unit value of the reference product wear excess ratio, and bm3 is the impact factor corresponding to the unit value of the number of assembly part deviations.

8. The enterprise product quality assessment method based on multi-dimensional data according to claim 7 is characterized by: The specific feedback process for product quality evaluation is as follows: The product production quality index is compared with the product production quality threshold. If the product production quality index is less than the product production quality threshold, an evaluation feedback is given on the product quality.

9. A system for enterprise product quality assessment method based on multi-dimensional data, used to execute the enterprise product quality assessment method based on multi-dimensional data as claimed in any one of claims 1 to 8, characterized in that: include: The product compliance determination module is used to obtain multi-dimensional data of products, extract product label information from it, and determine the product compliance index; The production risk analysis module is used to match the production process of the product based on the multi-dimensional data of the product, collect the production process information of the product, and analyze the production risk index of the product; The production quality assessment module is used to sample and extract similar products, mark each extracted product as a reference product, collect production information of each reference product, and evaluate the product production quality index based on the product production risk index.

Images