Method and system for monitoring optimization for corrosion resistant container production

Abstract

The present application belongs to the technical field of monitoring optimization, and provides a monitoring optimization method and system for corrosion-resistant container production, which comprises the following steps: using a coating thickness gauge to measure the coating thickness of each corner seam area in the container, obtaining coating thickness data of each corner seam area, analyzing and processing the coating thickness data of the corner seam area, screening out abnormal coating areas, analyzing the defect degree based on the abnormal coating areas, repairing the abnormal coating areas according to the coating defect degree, establishing a defect prediction model based on the local repair area, combining historical corner seam area coating defect degree and production environment parameter analysis, predicting the defect risk in advance according to the defect prediction model, generating an early warning signal, and iteratively analyzing and processing the coating flow based on the early warning signal to optimize the coating quality, which is conducive to timely discovering and processing potential coating problems and improving the stability and reliability of container coating production.

Description

Technical Field

[0001] This invention belongs to the field of monitoring and optimization technology, specifically a monitoring and optimization method and system for the production of corrosion-resistant containers. Background Technology

[0002] In the production of corrosion-resistant containers, due to the complex production environment and diverse material properties, traditional production monitoring methods often fall short of achieving ideal accuracy and efficiency. Existing monitoring technologies may not be able to comprehensively and in real-time capture changes in various parameters during the production process, leading to unstable product quality and low production efficiency.

[0003] In the production of corrosion-resistant containers, coating quality plays a crucial role in the container's corrosion resistance. However, current production processes still suffer from several shortcomings in monitoring coating thickness in internal corner and seam areas, as well as in predicting and repairing defects. Traditional monitoring methods are inefficient and have limited accuracy, making it difficult to accurately identify abnormal coating areas or precisely analyze the severity of defects. Furthermore, existing production monitoring systems lack the ability to predict coating defects, failing to provide early warnings and interventions before defects occur. This leads to frequent coating quality problems during production, impacting the container's corrosion resistance and service life.

[0004] Therefore, the present invention provides a monitoring and optimization method and system for the production of corrosion-resistant containers. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0006] The technical solution adopted by this invention to solve its technical problem is: a monitoring and optimization method and system for the production of corrosion-resistant containers, comprising:

[0007] Using a coating thickness gauge, the coating thickness of each corner and seam area inside the container is measured to obtain coating thickness data for each corner and seam area. The coating thickness data of the corner and seam areas is then analyzed and processed to screen out abnormal coating areas.

[0008] Based on the abnormal coating area, the degree of defect is analyzed, and the abnormal coating area is repaired according to the degree of coating defect;

[0009] Based on the local repair area, combined with the analysis of the coating defect degree in the historical corner seam area and production environment parameters, a defect prediction model is established. Based on the defect prediction model, the defect risk in production is predicted in advance, and an early warning signal is generated.

[0010] Based on the early warning signal, the coating flow rate is iteratively analyzed and processed to optimize the coating quality.

[0011] Furthermore, the process of obtaining the coating thickness data in the corner seam area is as follows:

[0012] A laser 3D scanner is used to collect 3D coordinate data of all corner and seam areas inside the container. Based on the 3D coordinate data, the corner and seam areas are divided into several sub-areas of equal size, thus obtaining the corner and seam sub-areas.

[0013] By using the grid division method, measurement points in the corner seam area are obtained. The coating thickness of the measurement points is detected by an eddy current thickness gauge to obtain the coating thickness data of the measurement points. The coating thickness data of all measurement points in the corner seam area are statistically analyzed, summed and averaged to obtain the coating thickness data of the corner seam area.

[0014] The obtained coating thickness data in the corner seam area are categorized and summarized to obtain a coating thickness database.

[0015] Furthermore, the coating thickness data in the diagonal seam area is analyzed and processed as follows:

[0016] If the coating thickness in the corner area is greater than or equal to the upper limit of the coating thickness range threshold, or if the coating thickness in the corner area is less than or equal to the lower limit of the coating thickness range threshold, then the corresponding coating sub-region will be marked as an abnormal coating sub-region.

[0017] All marked anomalous coating sub-regions were statistically analyzed for spatial continuity.

[0018] Furthermore, the spatial continuity analysis is performed as follows:

[0019] Spatially merge adjacent abnormal coating sub-regions to construct the abnormal coating region.

[0020] Furthermore, the defect severity analysis is performed as follows:

[0021] Based on the coating thickness database, the coating thickness of each abnormal coating sub-region within the abnormal coating area is obtained, and the difference between the coating thickness and the nearest coating thickness range threshold is processed to obtain the thickness difference value.

[0022] The mean thickness difference is obtained by summing the thickness difference values ​​of each sub-region of abnormal coating within the abnormal coating area, taking the absolute value, and then calculating the standard deviation.

[0023] The coefficient of variation is used to obtain the coating thickness dispersion coefficient in the abnormal coating area;

[0024] By using three-dimensional coordinate data, the total area of ​​the corner seam region where the abnormal coating is located is obtained. The ratio of the area of ​​the abnormal coating region to the total area of ​​the corner seam region is then calculated to obtain the abnormal region proportion coefficient.

[0025] Furthermore, the defect severity analysis is performed as follows:

[0026] The coating thickness dispersion coefficient is added to the abnormal area proportion coefficient to obtain the coating defect degree value;

[0027] If the coating defect severity value is greater than or equal to the coating defect severity threshold, the corresponding coating area will be marked as the overall repair area;

[0028] If the coating defect severity value is less than the coating defect severity threshold, the corresponding coating area is marked as a local repair area.

[0029] Furthermore, the process of establishing the defect prediction model is as follows:

[0030] Acquire historical coating defect data in corner seam areas, classify and organize the historical defect data, categorize them according to defect type, and calculate the defect rate of each defect type in the same location.

[0031] Compare the defect rates of all defect types and identify the defect type with the highest defect rate as the most likely defect type for the corresponding location.

[0032] A correlation analysis was performed on humidity and defect type. The Pearson correlation coefficient between humidity and defect type and defect rate was calculated, and the absolute value was taken to obtain the synchronization coefficient.

[0033] If the synchronization coefficient is greater than or equal to the synchronization coefficient threshold, it indicates that there is a correlation between humidity and defect type / defect rate.

[0034] A defect prediction model was obtained by fitting the humidity and defect rate using the least squares method.

[0035] Based on historical monitoring data, the coating adjustment range for each coating defect repair under the same humidity was obtained.

[0036] Furthermore, the process of predicting defects in production in advance and generating early warning signals is as follows:

[0037] During production process monitoring, the humidity of the current environment is obtained and input into the defect prediction model to predict the types of coating defects that may occur.

[0038] If the humidity reaches the humidity warning value, the corresponding defect type will be output and a warning signal will be sent.

[0039] Furthermore, the iterative analysis of the coating flow rate is performed as follows:

[0040] The coating flow rate is adjusted according to the defect type, and the coating quality is optimized through iterative analysis and processing of the coating flow rate.

[0041] In the first iteration, the current paint flow rate is obtained, and adjustments are made based on the minimum value of the paint adjustment range.

[0042] After debugging, the coating thickness is tested to observe whether the thickness tends to approach the standard range;

[0043] If the coating thickness shows a trend toward the standard range, continue to fine-tune the current adjustment range until the coating thickness stabilizes within the standard range.

[0044] If the coating thickness does not show a trend toward the standard range, a second iteration is performed, adjusting according to the maximum value of the coating thickness range until the coating thickness stabilizes within the standard range.

[0045] A monitoring and optimization system for the production of corrosion-resistant containers includes the following modules:

[0046] Data Acquisition and Screening Module: Using a coating thickness gauge, the coating thickness of each corner and seam area inside the container is measured to obtain coating thickness data for each corner and seam area. The coating thickness data of the corner and seam areas is then analyzed and processed to screen out abnormal coating areas.

[0047] Analysis and Repair Module: Based on the abnormal coating area, analyze the degree of defect and repair the abnormal coating area according to the degree of coating defect;

[0048] Predictive Analysis Module: Combining historical coating defect severity in corner seams with production environment parameter analysis, a defect prediction model is established. Based on the defect prediction model, the defect risk in production is predicted in advance, and early warning signals are generated.

[0049] Iterative optimization module: Based on the early warning signal, iteratively analyzes and processes the coating flow rate to optimize the coating quality.

[0050] The beneficial effects of this invention are as follows:

[0051] (1) Obtain the coating thickness data of the corner seam area, process and analyze the coating thickness data, screen out abnormal coating areas, and based on the abnormal coating areas, perform difference processing on the corresponding coating thickness and the coating thickness range threshold to obtain the thickness difference value for defect degree analysis, and repair the abnormal coating areas according to the defect degree to provide a location basis for subsequent targeted repair measures. By constructing abnormal coating areas through spatial continuity analysis, we can more comprehensively grasp the distribution range and severity of coating defects and avoid ignoring the overall correlation due to the separate analysis of each abnormal coating sub-region.

[0052] (2) By combining the analysis of the degree of coating defects in the historical corner seam area and the production environment parameters, a defect prediction model is established. The defect prediction model can predict the defect risk in advance, generate early warning signals, and perform iterative analysis and processing of the coating flow to optimize the coating quality. This is conducive to improving the stability and reliability of container coating production, reducing the rework rate and maintenance costs caused by coating defects, monitoring coating thickness changes in real time, and timely detection and handling of potential coating problems. Attached Figure Description

[0053] The invention will now be further described with reference to the accompanying drawings.

[0054] Figure 1 This is a flowchart of the monitoring and optimization method for the production of corrosion-resistant containers as described in an embodiment of the present invention;

[0055] Figure 2 This is a logic analysis diagram of the monitoring and optimization method for the production of corrosion-resistant containers as described in the embodiments of the present invention;

[0056] Figure 3 This is a flowchart of the monitoring and optimization system for the production of corrosion-resistant containers as described in an embodiment of the present invention. Detailed Implementation

[0057] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0058] Example 1: Please refer to Figure 1 - Figure 2 As shown in the embodiment of the present invention, the monitoring and optimization method for the production of corrosion-resistant containers includes:

[0059] Step 1: Use a coating thickness gauge to measure the coating thickness in each corner and seam area inside the container, obtain coating thickness data for each corner and seam area, analyze and process the coating thickness data for the corner and seam areas, and screen out abnormal coating areas.

[0060] In some embodiments, a coating thickness gauge (such as an eddy current thickness gauge) is used to measure the coating thickness in various corner and seam areas of the container. The specific process is as follows:

[0061] A laser 3D scanner is used to collect 3D coordinate data of all corner and seam areas inside the container. Based on the 3D coordinate data, the corner and seam areas are divided into several sub-areas of equal size, thus obtaining the corner and seam sub-areas.

[0062] It should be noted that the division method is a planar division, which divides the plane into the plane containing the x and y axes, the plane containing the x and z axes, and the plane containing the y and z axes, namely the xy plane, the xz plane, and the yz plane.

[0063] Measurement points in the corner seam area are obtained by dividing the grid equally.

[0064] The coating thickness is measured at the measurement points using an eddy current thickness gauge to obtain the coating thickness data at the corresponding measurement points. The coating thickness data of all measurement points in the corner seam area are statistically analyzed, and the summation and average are taken to obtain the coating thickness data of the corner seam area.

[0065] The obtained coating thickness data in the corner seam area are categorized and summarized to obtain a coating thickness database.

[0066] For example, based on the obtained three-dimensional coordinate data, the corner seam area in the xy plane is divided into several sub-regions of equal area to obtain the corner seam sub-regions. The coating thickness of the corner seam sub-regions on the xy plane is measured using an eddy current thickness gauge. During the measurement process, for each corner seam area on the xy plane, measurement points are arranged according to a preset grid spacing to ensure that the measurement points are evenly distributed in order to obtain the coating thickness of the corresponding area.

[0067] It should be noted that the preset grid spacing is set by dividing the corner area into several equal parts in the horizontal and vertical directions using the grid equal division method to form a grid structure, and setting measurement points at the intersection of each grid.

[0068] It should also be noted that the purpose of obtaining coating thickness data for each corner and seam area is to provide reliable data for optimizing the coating process in the subsequent production of corrosion-resistant containers through accurate measurement and data analysis of coating thickness. In actual production, based on this coating thickness data, it can be determined whether the current coating process meets the corrosion resistance requirements. If it is found that the coating thickness in some corner and seam areas does not meet the standard, the coating spraying parameters, such as spraying pressure, spraying time, and paint flow rate, can be adjusted in time to ensure that the coating thickness of each part of the container is uniform and meets the standard, thereby improving the overall corrosion resistance of the container, extending its service life, and reducing maintenance costs and safety risks caused by corrosion. At the same time, by analyzing a large amount of coating thickness data, it is also possible to summarize the variation law of coating thickness under different production conditions, providing data support for further optimizing the production process and improving production efficiency.

[0069] The coating thickness of each corner seam area within the obtained coating thickness database is analyzed, and the specific process is as follows:

[0070] The coating thickness in the corner seam area is compared with the coating thickness range threshold;

[0071] If the coating thickness in the corner area is greater than or equal to the upper limit of the coating thickness range threshold, or if the coating thickness in the corner area is less than or equal to the lower limit of the coating thickness range threshold, then the corresponding coating sub-region will be marked as an abnormal coating sub-region.

[0072] If the coating thickness in the corner seam area is within the coating thickness range threshold, then the corresponding corner seam area is marked as a normal coating sub-area.

[0073] It should be noted that the coating thickness range threshold is determined by a combination of factors, including the container's operating environment, corrosion resistance requirements, and the performance of the coating material. In actual production, through extensive experiments and data analysis, a coating thickness range has been obtained that ensures both the container's corrosion resistance and production efficiency and cost. This range threshold can serve as an important basis for judging whether the coating quality is up to standard. When the coating thickness in the corner seam area exceeds this range, it means that the coating in that area may have quality problems and requires further inspection and treatment.

[0074] All marked anomalous coating sub-regions were statistically analyzed for spatial continuity, as follows:

[0075] Adjacent abnormal coating sub-regions are spatially merged to construct an abnormal coating region. The adjacency methods include horizontal adjacency, vertical adjacency, and diagonal adjacency.

[0076] It should be noted that the purpose of obtaining abnormal coating areas is to locate areas where the coating quality does not meet the standards during the container production process, providing a location basis for subsequent targeted repair measures. By constructing abnormal coating areas through spatial continuity analysis, we can more comprehensively grasp the distribution range and severity of coating defects, and avoid ignoring the overall correlation by analyzing each abnormal coating sub-region separately.

[0077] Following this, once the abnormal coating area is identified, its location and extent can be analyzed in conjunction with the container manufacturing process to determine the possible causes of the coating abnormality. For example, if there are many abnormal coating areas in a specific region, it may be due to environmental factors (such as temperature, humidity, dust, etc.) affecting the area during spraying, or unreasonable parameter settings of the spraying equipment in that area. Based on the analyzed causes, corresponding repair plans can be developed. For minor coating abnormalities, local repair methods can be used, re-spraying with the same material as the original coating. For severe coating abnormalities, it may be necessary to remove the entire coating in that area and redo the surface treatment and spraying.

[0078] Step 2: Based on the abnormal coating area, analyze the degree of defect and repair the abnormal coating area according to the degree of coating defect;

[0079] Based on the coating thickness database, the coating thickness of each abnormal coating sub-region within the abnormal coating area is obtained, and the coating thickness is compared with the nearest coating thickness range threshold limit to obtain the thickness difference value. The coating thickness range threshold limit includes an upper limit and a lower limit.

[0080] If the thickness difference value is positive, it indicates that the coating thickness of the corresponding abnormal coating sub-region is too thick.

[0081] If the thickness difference value is negative, it indicates that the coating thickness of the corresponding abnormal coating sub-region is too thin.

[0082] For example, the coating thickness of the abnormal coating sub-region is 0.6 mm, the upper limit of the coating thickness range threshold is 0.5 mm, and the thickness difference is (0.6-0.5=0.1). The thickness of the abnormal sub-region is 0.3 mm, the lower limit of the coating thickness range threshold is 0.4 mm, and the thickness difference is (0.3-0.4=-0.1).

[0083] It should be noted that the purpose of obtaining the thickness difference value is to: quantify the degree of coating defect in each abnormal coating sub-region by calculating the thickness difference value. This value can intuitively reflect the degree to which the coating thickness deviates from the standard range, providing objective and accurate data basis for subsequent defect level classification. In addition, by statistically analyzing the thickness difference values ​​of a large number of abnormal coating sub-regions, the distribution pattern and trend of coating defects can be summarized, providing strong data support for further optimizing the coating process and improving coating quality.

[0084] The mean thickness difference is obtained by summing the thickness difference values ​​of each sub-region of abnormal coating within the abnormal coating area, taking the absolute value, and then calculating the standard deviation.

[0085] The coefficient of variation is used to obtain the coating thickness dispersion coefficient in the abnormal coating area;

[0086] By using three-dimensional coordinate data, the total area of ​​the corner seam region where the abnormal coating is located is obtained. The ratio of the area of ​​the abnormal coating region to the total area of ​​the corner seam region is processed to obtain the abnormal region proportion coefficient.

[0087] The obtained coating thickness dispersion coefficient is added to the abnormal area proportion coefficient to obtain the coating defect degree value, and then compared with the coating defect degree threshold.

[0088] If the coating defect severity value is greater than or equal to the coating defect severity threshold, the corresponding coating area will be marked as the overall repair area;

[0089] If the coating defect severity value is less than the coating defect severity threshold, the corresponding coating area is marked as a local repair area.

[0090] It is understandable that the physical meaning of the coating defect severity value is as follows: the coating defect severity value is obtained by adding the coating thickness dispersion coefficient and the abnormal area proportion coefficient. The coating thickness dispersion coefficient reflects the dispersion of the coating thickness of each abnormal coating sub-region within the abnormal coating area. The higher the dispersion coefficient, the more uneven the coating thickness. The abnormal area proportion coefficient reflects the proportion of the abnormal coating area to the corner seam area. The larger the abnormal area proportion value, the more obvious the abnormal coating phenomenon in the corner seam area. For example, the higher the defect severity and the smaller the abnormal area proportion value, the more it indicates that the defect occurs locally and requires local repair.

[0091] Based on the labeling results of the overall and local repair areas, a targeted repair strategy is formulated.

[0092] For the corner seam areas marked as areas requiring overall repair, a full repair approach is adopted, and the specific process is as follows:

[0093] The corner seam area is surface treated to remove the original substandard coating. Based on the corrosion resistance requirements of the container and the usage environment, a suitable coating material is selected and the parameters of the spraying equipment, such as spraying pressure, spraying speed, and paint flow rate, are adjusted before re-spraying. During the spraying process, the spraying process must be strictly controlled to ensure that the coating thickness is uniform and meets the standard requirements.

[0094] For the corner seam areas marked as local repair areas, local repairs are carried out on the abnormal coating areas based on the thickness difference value and defect distribution. The same material as the original coating is used to re-spray the defective areas. During the local repair process, attention should be paid to the transition between the repaired area and the surrounding normal coating to avoid problems such as obvious repair marks and uneven coating thickness.

[0095] After the repair is completed, the repaired area is inspected for quality. The coating thickness of the repaired area is measured again using a coating thickness gauge to ensure that the thickness of the repaired coating meets the standard requirements.

[0096] Example 2: Please refer to Figure 1 - Figure 2 As shown in the embodiment of the present invention, the monitoring and optimization method for the production of corrosion-resistant containers includes:

[0097] Step 3: Based on the local repair area, combined with the analysis of the coating defect degree in the historical corner seam area and production environment parameters, establish a defect prediction model, predict the defect risk in production in advance based on the defect prediction model, and generate early warning signals;

[0098] In step three, historical coating defect data for corner seam areas are obtained. The specific process is as follows:

[0099] Retrieve information on coating defects in corner seams recorded during past production processes from historical databases, including but not limited to the location of defects, defect type (such as coating too thin or too thick), and defect severity.

[0100] The acquired historical defect data is classified and organized, categorized according to defect type, and the defect rate of each defect type in the same location is calculated, which is the ratio of the number of times a single defect type occurs to the total number of times a defect occurs in the corresponding location.

[0101] Compare the defect rates of all defect types, identify the defect type with the highest defect rate as the most likely defect type for the corresponding location, and obtain the corresponding production environment parameters (such as humidity).

[0102] A correlation analysis was conducted between humidity and defect type. A coordinate system was established with humidity as the x-axis and defect rate as the y-axis. Defect rate data under different humidity environments were marked in the coordinate system and plotted from left to right to obtain a correlation curve.

[0103] By observing the changing trend of the correlation curve, we can analyze the influence of humidity on the defect rate. For example, if the defect rate of the coating being too thin increases significantly with increasing humidity, it can be preliminarily judged that a high humidity environment is more likely to cause the coating to be too thin.

[0104] Calculate the Pearson correlation coefficient between humidity and defect rate (too thin coating), and take the absolute value to obtain the synchronization coefficient;

[0105] If the synchronization coefficient is greater than or equal to the synchronization coefficient threshold, it indicates that there is a correlation between humidity and the coating thinning defect rate.

[0106] If the synchronization coefficient is less than the synchronization coefficient threshold, it indicates that there is no correlation between humidity and the coating thinning defect rate.

[0107] It should be noted that the synchronization coefficient threshold is set to determine whether there is a correlation between humidity and the coating thinness defect rate. The synchronization coefficient threshold can be set according to actual engineering needs. For example, the synchronization coefficient threshold can be set to 0.75.

[0108] Based on the correlation, the least squares method is used to fit the humidity and defect rate to obtain a defect prediction model;

[0109] When monitoring the production process, the humidity of the current environment is obtained and input into the defect prediction model to predict the types of coating defects that may occur.

[0110] For example, the current humidity is input into the defect prediction model. If the humidity reaches the humidity warning value, the corresponding defect type is output and a warning signal is sent. The humidity warning value can be obtained from the data in the cross-tabulation analysis method. For example, the average of the last 5% of the humidity data can be taken as the benchmark.

[0111] Based on historical monitoring data, the coating adjustment range for each coating defect repair under the same humidity was obtained.

[0112] It should be noted that the purpose of establishing a defect prediction model is to predict potential coating defects in advance by using historical data and current production environment parameters, and to take corresponding preventive measures, thereby effectively reducing the occurrence of coating defects during the production process, improving product quality and production efficiency. The prediction results can be dynamically adjusted according to different production conditions and environmental changes, providing timely and accurate decision support for production personnel. In practical applications, the defect prediction model can be integrated with the production management system to achieve automated early warning and parameter adjustment, further reducing the error and cost of human intervention. At the same time, through continuous optimization and updating of the model, its prediction accuracy and applicability can be continuously improved, providing a strong guarantee for the continuous improvement of corrosion-resistant container production.

[0113] Step 4: Based on the early warning signal, perform iterative analysis and processing of the coating flow rate to optimize the coating quality;

[0114] Based on the warning signal, extract the signal data, including: the container corner gap area determined by the three-dimensional coordinate data and the humidity data that triggered the warning;

[0115] Input humidity into the defect prediction model and output the predicted defect type;

[0116] Obtain the corresponding process parameters (such as paint flow rate) and adjust the paint flow rate according to the defect type;

[0117] For example, when humidity is input into the defect prediction model, the predicted defect type is "coating too thin". The coating flow rate is then iteratively analyzed to optimize the coating too thin defect.

[0118] In the first iteration, the current paint flow rate is obtained, and adjustments are made based on the minimum value of the paint adjustment range.

[0119] After debugging, the coating thickness is tested to observe whether the thickness tends to approach the standard range;

[0120] If the coating thickness shows a trend toward the standard range, continue to fine-tune the current adjustment range until the coating thickness stabilizes within the standard range.

[0121] If the coating thickness does not show a trend toward the standard range, a second iteration is performed, adjusting according to the maximum value of the coating thickness range until the coating thickness stabilizes within the standard range.

[0122] Working principle of the invention:

[0123] The coating thickness data of the corner seam area is obtained and processed and analyzed to screen out abnormal coating areas. Based on the abnormal coating areas, the difference between the corresponding coating thickness and the coating thickness range threshold is processed to obtain the thickness difference value for defect degree analysis. The abnormal coating areas are repaired according to the defect degree, providing a location basis for subsequent targeted repair measures. By constructing abnormal coating areas through spatial continuity analysis, the distribution range and severity of coating defects can be more comprehensively grasped, avoiding the neglect of the overall correlation due to the analysis of individual abnormal coating sub-regions.

[0124] By combining the analysis of historical coating defect levels in corner seam areas and production environment parameters, a defect prediction model is established. The defect prediction model can predict defect risks in advance, generate early warning signals, and iteratively analyze and process coating flow to optimize coating quality. This is beneficial to improving the stability and reliability of container coating production, reducing rework rate and maintenance costs caused by coating defects, and monitoring coating thickness changes in real time to promptly detect and address potential coating problems.

[0125] Example 3: Please refer to Figure 3 As shown in the embodiment of the present invention, the monitoring and optimization system for the production of corrosion-resistant containers includes:

[0126] Data Acquisition and Screening Module: Using a coating thickness gauge, the coating thickness of each corner and seam area inside the container is measured to obtain coating thickness data for each corner and seam area. The coating thickness data of the corner and seam areas is then analyzed and processed to screen out abnormal coating areas.

[0127] Analysis and Repair Module: Based on the abnormal coating area, analyze the degree of defect and repair the abnormal coating area according to the degree of coating defect;

[0128] Predictive Analysis Module: Based on the local repair area, combined with the analysis of the coating defect degree in the historical corner seam area and production environment parameters, a defect prediction model is established. Based on the defect prediction model, the defect risk in production is predicted in advance, and an early warning signal is generated.

[0129] Iterative optimization module: Based on the early warning signal, iteratively analyzes and processes the paint flow rate to optimize the coating quality;

[0130] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring optimization for corrosion resistant container production, characterized by: The method comprises the following steps: Coating thickness of each corner joint area in the container is measured by a coating thickness gauge, coating thickness data of each corner joint area is obtained, and the coating thickness data of the corner joint area is analyzed and processed to screen out abnormal coating areas; Three-dimensional coordinate data of all corner joint areas in the container is collected by a laser three-dimensional scanner, the corner joint area is divided into a plurality of sub-areas of equal size according to the three-dimensional coordinate data, and the corner joint sub-area is obtained; If the coating thickness of the corner joint sub-area is greater than or equal to the upper limit value of the coating thickness range threshold or the coating thickness of the corner joint sub-area is less than or equal to the lower limit value of the coating thickness range threshold, the corresponding coating sub-area is marked as an abnormal coating sub-area; Based on the abnormal coating area, the defect degree is analyzed, and the abnormal coating area is repaired according to the coating defect degree; Based on the local repair area, a defect prediction model is established by combining historical corner joint area coating defect degree and production environment parameter analysis, the defect risk in production is predicted in advance according to the defect prediction model, and a warning signal is generated; Based on the warning signal, the coating flow is iteratively analyzed and processed to optimize the coating quality; The process of the defect degree analysis is as follows: The coating thickness of each abnormal coating sub-area in the abnormal coating area is obtained from the coating thickness database, and the coating thickness is difference processed with the nearest coating thickness range threshold limit value to obtain a thickness difference value; The thickness difference values of each abnormal coating sub-area in the abnormal coating area are summed and averaged to obtain a thickness difference mean value and take the absolute value, and the standard deviation is calculated; The coating thickness dispersion coefficient of the abnormal coating area is obtained by calculating the coefficient of variation; The total area of the corner joint area where the abnormal coating is located is obtained from the three-dimensional coordinate data, and the abnormal coating area is ratio processed with the total area of the corner joint area to obtain an abnormal area ratio coefficient; The coating thickness dispersion coefficient and the abnormal area ratio coefficient are added to obtain a coating defect degree value; If the coating defect degree value is greater than or equal to the coating defect degree threshold, the corresponding coating area is marked as a whole repair area; If the coating defect degree value is less than the coating defect degree threshold, the corresponding coating area is marked as a local repair area; The process of establishing the defect prediction model is as follows: Historical corner joint area coating defect data is obtained, the historical defect data is classified and arranged, and the defect rate of each defect type in the same position is counted according to the defect type; The defect rates of all defect types are compared in size, and the defect type with the largest defect rate is taken as the easy-to-occur defect type at the corresponding position; The correlation between humidity and defect type is analyzed, the Pearson correlation coefficient of humidity and defect type defect rate is calculated, and the absolute value is taken to obtain a synchronization coefficient; If the synchronization coefficient is greater than or equal to the synchronization coefficient threshold, it indicates that there is a correlation between humidity and defect type defect rate; The least square method is used to fit the humidity and the defect rate to obtain the defect prediction model; And the coating adjustment amplitude of each coating defect repair under the same humidity is obtained from the historical monitoring data to obtain a coating amplitude interval.

2. The method for monitoring optimization of corrosion resistant container production according to claim 1, characterized in that: The coating thickness measurement of each corner seam area in the container interior obtains the coating thickness data of each corner seam area, and the process is as follows: Collect all the three-dimensional coordinate data of the corner seam area in the container interior by using a laser three-dimensional scanner, divide the corner seam area into a plurality of equal size sub-areas according to the three-dimensional coordinate data, and obtain the corner seam sub-area; By grid equal division method, the measurement points of the corner seam sub-area are obtained, the coating thickness of the measurement points is detected by using the eddy current thickness gauge, the coating thickness data of all measurement points in the corner seam sub-area is counted, summed and averaged to obtain the coating thickness data of the corner seam sub-area; The obtained coating thickness data of the corner seam sub-area is classified and summarized to obtain a coating thickness database.

3. The method for monitoring optimization of corrosion resistant container production according to claim 2, characterized in that: The coating thickness data of the corner seam area is analyzed and processed as follows: If the coating thickness of the corner seam sub-area is greater than or equal to the upper limit value of the coating thickness range threshold value, or the coating thickness of the corner seam sub-area is less than or equal to the lower limit value of the coating thickness range threshold value, the corresponding coating sub-area is marked as an abnormal coating sub-area; All the marked abnormal coating sub-areas are counted and analyzed for spatial continuity.

4. The method for monitoring optimization of corrosion resistant container production according to claim 3, characterized in that: The spatial continuity analysis process is as follows: Adjacent abnormal coating sub-areas are combined in space to construct an abnormal coating area.

5. The method for monitoring optimization of corrosion resistant container production according to claim 1, characterized in that: The process of early prediction of defect risk in production and generation of warning signal is as follows: When monitoring the production process, the humidity in the current environment is obtained and input into the defect prediction model to predict the possible coating defect type; If the humidity reaches the humidity warning value, the corresponding defect type is output and a warning signal is sent.

6. The method for monitoring optimization of corrosion resistant container production according to claim 1, characterized in that: The process of iterative analysis and processing of coating flow is as follows: According to the defect type, the coating flow is adjusted, the coating quality is optimized by iterative analysis and processing of the coating flow; First iteration, the current coating flow is obtained, and the coating flow is adjusted by the minimum value of the coating amplitude interval; After debugging, the coating thickness is detected to observe whether the thickness shows a trend of approaching the standard range; If the coating thickness shows a trend of approaching the standard range, the current adjustment amplitude is continued to be fine-tuned until the coating thickness is stable in the standard range; If the coating thickness does not show a trend of approaching the standard range, secondary iteration is performed, the coating flow is adjusted according to the maximum value of the coating amplitude interval, and the coating thickness is stable in the standard range.

7. A monitoring optimization system for corrosion resistant container production, characterized by: The following modules are included: The collection and screening module uses a coating thickness gauge to measure the coating thickness of each corner seam area in the container interior to obtain the coating thickness data of each corner seam area, and analyzes and processes the coating thickness data of the corner seam area to screen out abnormal coating areas; Collect all the three-dimensional coordinate data of the corner seam area in the container interior by using a laser three-dimensional scanner, divide the corner seam area into a plurality of equal size sub-areas according to the three-dimensional coordinate data, and obtain the corner seam sub-area; If the coating thickness of the corner seam sub-area is greater than or equal to the upper limit value of the coating thickness range threshold value, or the coating thickness of the corner seam sub-area is less than or equal to the lower limit value of the coating thickness range threshold value, the corresponding coating sub-area is marked as an abnormal coating sub-area; The analysis repair module: based on the abnormal coating area, the defect degree is analyzed, and the abnormal coating area is repaired according to the coating defect degree; The prediction analysis module: combining the historical corner gap area coating defect degree and the production environment parameter analysis, a defect prediction model is established, the defect risk in production is predicted in advance according to the defect prediction model, and a warning signal is generated; The iterative optimization module: based on the warning signal, the coating flow is iteratively analyzed and processed, and the coating quality is optimized; The process of defect degree analysis is as follows: According to the coating thickness database, the coating thickness of each abnormal coating sub-area in the abnormal coating area is obtained, and the coating thickness is differentially processed with the nearest coating thickness range threshold limit value to obtain the thickness difference value; The thickness difference value of each abnormal coating sub-area in the abnormal coating area is summed to obtain the thickness difference mean value and the absolute value, and the standard deviation is calculated; The coating thickness dispersion coefficient of the abnormal coating area is obtained by calculating the coefficient of variation; The total area of the corner gap area where the abnormal coating is located is obtained through the three-dimensional coordinate data, and the abnormal coating area is compared with the total area of the corner gap area to obtain the abnormal area ratio coefficient; The coating thickness dispersion coefficient and the abnormal area ratio coefficient are added to obtain the coating defect degree value; If the coating defect degree value is greater than or equal to the coating defect degree threshold value, the corresponding coating area is marked as a whole repair area; If the coating defect degree value is less than the coating defect degree threshold value, the corresponding coating area is marked as a local repair area; The process of establishing the defect prediction model is as follows: Obtain the historical corner gap area coating defect data, classify and arrange the historical defect data, classify according to the defect type, and count the defect rate of each defect type at the same position; Compare the defect rates of all defect types, and take the defect type with the largest defect rate as the easy-to-occur defect type at the corresponding position; The correlation analysis of humidity and defect type is carried out, the Pearson correlation coefficient of humidity and defect type defect rate is calculated, and the absolute value is taken to obtain the synchronization coefficient; If the synchronization coefficient is greater than or equal to the synchronization coefficient threshold value, it means that there is a correlation between humidity and defect type defect rate; The least square method is used to fit the humidity and the defect rate to obtain the defect prediction model; And according to the historical monitoring data, the coating adjustment amplitude of each coating defect repair under the same humidity is obtained to obtain the coating amplitude interval.

Images