Automatic production line control method and device for shipbuilding

Abstract

The invention discloses an automatic production line control method and device for ship manufacturing, and relates to the technical field of intelligent control. Performing visual detection on the cut metal material to obtain a metal material image; the metal material image is compared with a preset image, if the comparison result is that cutting is abnormal, the complete metal material cut in the production line is replaced with a sample metal material, and the complete metal material originally to be cut in the production line is evenly distributed to other production lines; adjusting preset working parameters of a cutting machine for cutting the sample metal material until a comparison result of a metal material image corresponding to the cut metal material and a preset image shows that cutting is normal; the complete metal material on the cutting line is replaced with the sample metal material by discovering the cutting abnormity, and the complete metal material production task of the original plan is flexibly adjusted to other production lines, so that the situation that the whole production line is completely shut down due to a single fault is avoided, and the operation efficiency of the production line is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent control, and in particular relates to an automated production line control method and device for shipbuilding. Background Art

[0002] The traditional shipbuilding process has long relied on a large amount of manual operation, which not only makes the labor intensity extremely high, workers have to perform physical labor for a long time in a harsh working environment, but also has relatively low production efficiency, and it is difficult to ensure the consistency and quality of products. With the continuous development and progress of manufacturing automation technology, the introduction of automated production lines into the field of shipbuilding has become an important way to improve production efficiency and product quality. At present, cutting through automated production lines has been realized in shipbuilding. The application of this technology has greatly reduced the labor intensity of workers and improved production efficiency.

[0003] However, in actual operation, the automated cutting production line also encountered some challenges. In particular, when the cutting accuracy is not up to standard, the products produced by the entire cutting line may be unusable, and the production of the line must be suspended for inspection and adjustment. This kind of downtime caused by non-standard accuracy not only increases additional operating costs, but also reduces the efficiency of the production line. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that shutdowns caused by failure to meet precision standards not only increase additional operating costs but also reduce production line efficiency, and to propose an automated production line control method and device for shipbuilding.

[0005] In a first aspect of the present invention, a method for controlling an automated production line for shipbuilding is first proposed, the method comprising:

[0006] Determine the cutting speed of the cutting machine in each metal material cutting production line based on the total amount of metal material cutting, the number of production lines, the required cutting time, the size of the metal material and the material properties;

[0007] For each cutting machine, the cutting machine is started according to preset working parameters to cut the complete metal material to obtain a plurality of metal materials, and for each metal material, the metal material is visually inspected to obtain a metal material image of the metal material;

[0008] The metal material image is compared with a preset image to obtain a comparison result. If the comparison result indicates that the cutting is abnormal, the complete metal material cut in the metal material cutting production line is replaced with a sample metal material, and the complete metal materials originally to be cut in the metal material cutting production line are evenly distributed to other production lines;

[0009] The preset working parameters of the cutting machine used for cutting the sample metal material are adjusted until the comparison result between the metal material image corresponding to the metal material cut by the cutting machine after optimization and the preset image shows that the cutting is normal. The sample metal material is then replaced with a complete metal material, and the number of complete metal materials originally to be cut is reallocated to the production line.

[0010] Optionally, the cutting speed of the cutting machine in each metal material cutting production line is determined according to the total amount of metal material cutting, the number of production lines, the performance parameters of the cutting machine, the specified cutting time, the size of the metal material and the material properties, including:

[0011] Determine the cutting path length of the cutting machine according to the length and width of the target metal material, and obtain an estimated time for cutting one target metal material according to the cutting path length, the material properties of the target metal material and the maximum cutting speed of the cutting machine;

[0012] Determine a cutting cycle according to the specified cutting time, and obtain a target metal material output of each cutting cycle according to the time period of the cutting cycle, the specified cutting time and the total amount of metal material cut;

[0013] The target metal material output of each cutting cycle is divided by the number of production lines to obtain the amount of metal material that each production line needs to cut in each cutting cycle;

[0014] Calculate the cutting speed of the cutting machine in each metal material cutting production line according to the amount of metal materials, the cutting path length, the estimated time and the cutting cycle;

[0015] By formula Get the cutting speed of the cutting machine in each metal material cutting production line; where V is the cutting speed of the cutting machine, P line is the amount of metal material, L cut is the cutting path length, T cut is the estimated time, and ΔT is the cutting cycle.

[0016] Optionally, comparing the metal material image with a preset image to obtain a comparison result includes:

[0017] Preprocessing the metal material image to obtain an initial image, and extracting the edge of the initial image using a Sobel edge algorithm to obtain a target edge;

[0018] Processing the target edge by a contour detection algorithm to obtain the outer contour of the initial image;

[0019] Performing shape similarity analysis on the outer contour and the standard contour in the preset image by a shape matching algorithm to obtain a similarity value;

[0020] If the similarity value is greater than or equal to the preset similarity value, the comparison result is that the cutting is normal; if the similarity value is less than the preset similarity value, the comparison result is that the cutting is abnormal.

[0021] Optionally, adjusting preset working parameters of a cutting machine for cutting the sample metal material includes:

[0022] Step 1: the cutting machine cuts the sample metal material according to the initial working parameters to obtain the test metal material, collects the image of the test metal material to obtain the test image; analyzes the test image by the image recognition algorithm to obtain the metal material size and burr quality of the test metal material and records them as the first quality data;

[0023] Step 2, substituting the working parameters of the cutting machine into the dynamic model to obtain an acceleration signal, and obtaining the sensitive features of the cutting machine in the acceleration signal through a dynamic feature extraction algorithm;

[0024] Step 3, substituting the first quality data, the sensitive features, and the initial working parameters into the real-time characterization model of the side tool wear to obtain the cutting machine wear parameters;

[0025] Step 4, optimizing the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain target optimization parameters; the second quality data is the metal material size and the burr quality corresponding to the preset image;

[0026] Step 5, bringing the target optimization parameters back to step 1 as initial working parameters; obtaining the updated first quality data, and if the difference between the updated first quality data and the second quality data is within a preset range, ending the working parameter adjustment.

[0027] Optionally, optimizing the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain the target optimization parameters includes:

[0028] The initial working parameters include cutting speed, feed depth, spindle speed, and cutting angle; the second quality data includes target metal material size and target burr quality; the sample metal material size is recorded as the actual metal material size, and the burr quality of the sample metal material is recorded as the actual burr quality;

[0029] The absolute value of the difference between the target metal material size and the actual metal material size is calculated to obtain the size error; the absolute value of the difference between the target burr quality and the actual burr quality is calculated to obtain the burr quality error;

[0030] Determine a first weight coefficient and a second weight coefficient according to the size error and the burr quality error;

[0031] By formula

[0032]

[0033] Determine the target optimization parameters; where S is the size error, E is the burr quality error, α is the first weight coefficient, β is the second weight coefficient, S init is the actual metal material size, E init is the actual burr quality, D is the target feed depth of the cutting machine, and D init is the feed depth, N, N init are the target spindle speed of the cutting machine and the spindle speed, θ, θ init are the target cutting angle of the cutting machine and the cutting angle, S tar is the target metal material size, k1, k2, k3, m1, m2, m3 are constant coefficients.

[0034] In a second aspect of the present invention, an automated production line control device for shipbuilding is provided, comprising:

[0035] A cutting speed determination module, used to determine the cutting speed of the cutting machine in each metal material cutting production line according to the total amount of metal material cutting, the number of production lines, the specified cutting time, the size of the metal material and the material properties;

[0036] A metal material image determination module is used to start each cutting machine according to preset working parameters to cut a complete metal material to obtain a plurality of metal materials, and to visually inspect each metal material to obtain a metal material image of the metal material;

[0037] A comparison module is used to compare the metal material image with a preset image to obtain a comparison result. If the comparison result is a cutting abnormality, the complete metal material cut in the metal material cutting production line is replaced with a sample metal material, and the complete metal materials originally to be cut in the metal material cutting production line are evenly distributed to other production lines;

[0038] The optimization module is used to adjust the preset working parameters of the cutting machine for cutting the sample metal material until the comparison result between the metal material image corresponding to the metal material cut by the cutting machine after optimization and the preset image shows that the cutting is normal. Then, the sample metal material is replaced with a complete metal material, and the number of complete metal materials originally to be cut is reallocated to the production line.

[0039] Optionally, the cutting speed determination module includes:

[0040] A working time determination module, used to determine the cutting path length of the cutting machine according to the length and width of the target metal material, and to obtain an estimated time for cutting one of the target metal materials according to the cutting path length, the material properties of the target metal material and the maximum cutting speed of the cutting machine;

[0041] A target metal material output determination module is used to determine a cutting cycle according to the specified cutting time, and obtain a target metal material output of each cutting cycle according to the time period of the cutting cycle, the specified cutting time and the total amount of metal material cut;

[0042] A metal material quantity determination module is used to obtain the quantity of metal materials that each production line needs to cut in each cutting cycle by dividing the target metal material output of each cutting cycle by the number of production lines;

[0043] A cutting speed determination module, used for calculating the cutting speed of the cutting machine in each metal material cutting production line according to the amount of the metal material, the length of the cutting path, the estimated time and the cutting cycle;

[0044] By formula Get the cutting speed of the cutting machine in each metal material cutting production line; where V is the cutting speed of the cutting machine, P line is the amount of metal material, L cut is the cutting path length, T cut is the estimated time, and ΔT is the cutting cycle.

[0045] Optionally, the optimization module includes:

[0046] An edge extraction module is used to preprocess the metal material image to obtain an initial image, and extract the edge of the initial image by using a Sobel edge algorithm to obtain a target edge;

[0047] A contour extraction module, used for processing the edge of the target by a contour detection algorithm to obtain the outer contour of the initial image;

[0048] A similarity value determination module, used for performing shape similarity analysis on the outer contour and the standard contour in the preset image by a shape matching algorithm to obtain a similarity value;

[0049] The comparison result determination module is used to determine that if the similarity value is greater than or equal to a preset similarity value, the comparison result is that the cutting is normal; if the similarity value is less than the preset similarity value, the comparison result is that the cutting is abnormal.

[0050] Optionally, the optimization module further includes:

[0051] An image analysis module is used for the cutting machine to cut the sample metal material according to the initial working parameters to obtain the test metal material, collect the image of the test metal material to obtain the test image; analyze the test image by the image recognition algorithm to obtain the metal material size and burr quality of the test metal material and record them as the first quality data;

[0052] A sensitive feature extraction module is used to substitute the working parameters of the cutting machine into the dynamic model to obtain an acceleration signal, and obtain the sensitive features of the cutting machine in the acceleration signal through a dynamic feature extraction algorithm;

[0053] A wear parameter determination module, used for substituting the first quality data, the sensitive feature, and the initial working parameter into the side tool wear real-time characterization model to obtain the cutter wear parameter;

[0054] a target optimization parameter determination module, configured to optimize the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain the target optimization parameters; the second quality data is the metal material size and the burr quality corresponding to the preset image;

[0055] The quality data judgment module is used to bring the target optimization parameters back to the image analysis module as initial working parameters; obtain the updated first quality data, and if the difference between the updated first quality data and the second quality data is within a preset range, end the working parameter adjustment.

[0056] Optionally, the target optimization parameter determination module includes:

[0057] A parameter naming module, wherein the initial working parameters include cutting speed, feed depth, spindle speed, and cutting angle; the second quality data includes target metal material size and target burr quality; the sample metal material size is recorded as the actual metal material size, and the burr quality of the sample metal material is recorded as the actual burr quality;

[0058] A difference calculation module is used to calculate the absolute value of the difference between the target metal material size and the actual metal material size to obtain the size error; and calculate the absolute value of the difference between the target burr quality and the actual burr quality to obtain the burr quality error;

[0059] A target optimization parameter calculation module, used for determining a first weight coefficient and a second weight coefficient according to the size error and the burr quality error;

[0060] By formula

[0061]

[0062] Determine the target optimization parameters; where S is the size error, E is the burr quality error, α is the first weight coefficient, β is the second weight coefficient, S init is the actual metal material size, E init is the actual burr quality, D is the target feed depth of the cutting machine, and D init is the feed depth, N, N init are the target spindle speed of the cutting machine and the spindle speed, θ, θ init are the target cutting angle of the cutting machine and the cutting angle, S tar is the target metal material size, k1, k2, k3, m1, m2, m3 are constant coefficients.

[0063] Beneficial effects of the present invention:

[0064] The present invention proposes an automated production line control method for shipbuilding, which determines the cutting speed of a cutting machine in each metal material cutting production line according to the total amount of metal material cutting, the number of production lines, the specified cutting time, the size of the metal material and the material properties; for each cutting machine, the cutting machine is started according to preset working parameters to cut a complete metal material to obtain a plurality of metal materials, and for each metal material, the metal material is visually inspected to obtain a metal material image of the metal material; the metal material image is compared with a preset image to obtain a comparison result, and if the comparison result is that the cutting is abnormal, the complete metal material cut in the metal material cutting production line is replaced with a sample metal material, and the complete metal materials originally to be cut in the metal material cutting production line are evenly distributed to other production lines; the preset working parameters of the cutting machine for cutting the sample metal material are adjusted until the comparison result between the metal material image corresponding to the metal material cut by the cutting machine after optimization and the preset image is that the cutting is normal, then the sample metal material is replaced with a complete metal material again, and the number of complete metal materials originally to be cut is redistributed to the production line. By scientifically calculating and setting the optimal cutting speed of the cutting machine in each metal material cutting production line, the efficiency and stability of the cutting process are ensured, and the cutting quality problems caused by improper speed are reduced. After the cutting is completed, the metal material image detection is immediately carried out to ensure that the cutting fault can be discovered in real time. The acquired metal material image is automatically compared with the preset standard image. Once a cutting abnormality is found, such as size mismatch, rough edge, etc., the emergency response mechanism is immediately triggered. At this time, the complete metal material on the cutting line is replaced with the sample metal material, and the originally planned complete metal material production task is flexibly adjusted to other production lines to avoid the entire production line from being shut down due to a single fault, thereby greatly reducing the shutdown cost, ensuring the continuity of the production plan, and improving the operation efficiency of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The present invention will be further described below in conjunction with the accompanying drawings.

[0066] Figure 1 A flowchart of an automated production line control method for shipbuilding is provided for an embodiment of the present invention;

[0067] Figure 2 A structural schematic diagram of an automated production line control device for shipbuilding is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0068] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0069] The embodiment of the present invention provides an automated production line control method for shipbuilding. Figure 1 , Figure 1 A flowchart of an automated production line control method for shipbuilding provided by an embodiment of the present invention. The method comprises the following steps:

[0070] S101, determining the cutting speed of the cutting machine in each metal material cutting production line according to the total amount of metal material cutting, the number of production lines, the specified cutting time, the size of the metal material and the material properties.

[0071] S102, for each cutting machine, start the cutting machine according to preset working parameters to cut the complete metal material to obtain multiple metal materials, and for each metal material, perform visual inspection on the metal material to obtain a metal material image of the metal material.

[0072] S103, comparing the metal material image with the preset image to obtain a comparison result. If the comparison result is a cutting abnormality, the complete metal material cut in the metal material cutting production line is replaced with a sample metal material, and the complete metal material originally to be cut in the metal material cutting production line is evenly distributed to other production lines.

[0073] S104, adjusting the preset working parameters of the cutting machine for cutting the sample metal material until the comparison result between the metal material image corresponding to the metal material cut by the cutting machine after optimization and the preset image shows that the cutting is normal, then replacing the sample metal material with a complete metal material, and reallocating the number of complete metal materials originally to be cut to the production line.

[0074] An automated production line control method for shipbuilding provided by an embodiment of the present invention ensures high efficiency and stability of the cutting process by scientifically calculating and setting the optimal cutting speed of the cutting machine in each metal material cutting production line, reduces cutting quality problems caused by improper speed, and immediately performs metal material image detection after cutting is completed to ensure that cutting faults can be discovered in real time. The acquired metal material image is automatically compared with the preset standard image. Once cutting abnormalities such as size discrepancy, rough edges, etc. are found, an emergency response mechanism is immediately triggered. At this time, the complete metal material on the cutting line is replaced with a sample metal material, and the originally planned complete metal material production task is flexibly adjusted to other production lines to avoid the entire production line from being shut down due to a single fault, thereby greatly reducing the shutdown cost, ensuring the continuity of the production plan, and improving the operation efficiency of the production line.

[0075] In one implementation, by timely detecting cutting anomalies and adjusting cutting machine parameters, downtime due to equipment failure or poor cutting can be reduced. The cutting speed is determined based on the total amount of metal material cut, the number of production lines, the specified cutting time, the size of the metal material and the material properties, which can improve the work efficiency of each production line.

[0076] In one implementation, the metal material may be an alloy plate, an aluminum plate, a copper plate, a lead plate, a nickel plate, a zinc plate, a titanium plate, a magnesium plate, or the like.

[0077] In one implementation, the preset working parameters are determined by a technician, and the sample metal material is the same metal material as the complete metal material.

[0078] In one implementation, when the comparison result is a cutting abnormality, the quantity of all metal materials to be completed in the current execution cycle will be evenly distributed to the remaining production lines. After this production line is repaired, all production lines will still cut according to the cutting speed of the cutting machine in each metal material cutting production line.

[0079] In one implementation, the metal material is visually inspected to obtain a metal material image of the metal material, specifically an image captured by an industrial camera at a frame rate 10 times the speed of a production line, and the clearest and most complete image is used as the metal material image.

[0080] In one implementation, each metal material is inspected by a visual inspection system and compared with a preset image, which can ensure that the cutting quality of each metal material meets the standard and reduce defective products. The cutting machine parameters are adjusted according to the comparison results, which can continuously optimize the cutting quality and ensure the accuracy of the size and shape of the metal material.

[0081] In one implementation, timely detection and correction of abnormal cutting problems can reduce waste caused by poor cutting, thereby reducing the cost of raw materials and waste processing. By allocating metal materials from abnormal production lines to other production lines, the production load can be balanced and the utilization and efficiency of the overall production line can be improved.

[0082] In one implementation, when cutting abnormalities are found, the sample metal material can be quickly replaced with the complete metal material and the production plan can be adjusted. This flexibility can quickly respond to changes in production. By adjusting and optimizing different production lines, it can better adapt to various metal material cutting needs and changes in metal material specifications.

[0083] In one embodiment, determining the cutting speed of the cutting machine in each metal material cutting production line according to the total amount of metal material cutting, the number of production lines, the performance parameters of the cutting machine, the specified cutting time, the size of the metal material and the material properties includes:

[0084] Determine the cutting path length of the cutting machine according to the length and width of the target metal material, and obtain an estimated time for cutting one target metal material according to the cutting path length, the material properties of the target metal material and the maximum cutting speed of the cutting machine;

[0085] Determine the cutting cycle according to the specified cutting time, and obtain the target metal material output of each cutting cycle according to the time period of the cutting cycle, the specified cutting time and the total amount of metal material cut;

[0086] The target metal material output of each cutting cycle is divided by the number of production lines to obtain the amount of metal material that each production line needs to cut in each cutting cycle;

[0087] The cutting speed of the cutting machine in each metal material cutting production line is calculated based on the amount of metal materials, the length of the cutting path, the estimated time and the cutting cycle;

[0088] By formula Get the cutting speed of the cutting machine in each metal material cutting production line; where V is the cutting speed of the cutting machine, P line is the material property of the target metal material, L cut is the cutting path length, T cut is the estimated time, and ΔT is the cutting cycle.

[0089] In one implementation, by calculating the cutting speed of the cutting machine, it is possible to ensure that the cutting machine operates at an optimal speed to meet production needs, thereby improving production efficiency. Determining the cutting path length based on the length and width of the target metal material helps to reduce unnecessary time in the cutting process and further improve efficiency.

[0090] In one implementation, the cutting path length is the circumference of the target metal material, and the target metal material is the metal material ultimately required. The cutting cycle is determined by a technician based on the specified cutting time. For example, if the entire specified cutting time is 12 days, but three machine inspections are required, the cutting cycle is four days per cycle.

[0091] In one implementation, the formula Get the estimated time of the target metal material; where T cut is the estimated time, γ is the durability factor of the cutting machine, δ is the correction factor of the material, L cut is the cutting path length, V max is the maximum cutting speed; the durability coefficient of the cutting machine is the ratio of the first rate to the second rate, the first rate is the rate at which the cutting machine cuts the target metal material with the default power half a year before the current time, and the second rate is the rate at which the cutting machine cuts the target metal material with the default power at the current time; the correction coefficient is half of the ratio of the cutting speed at a Brinell hardness of 120HB to the cutting speed at the current material.

[0092] In one implementation, the target metal material output of each cutting cycle is obtained based on the time period of the cutting cycle, the specified cutting time and the total amount of metal material cut. Specifically, it is determined by multiplying the total amount of metal material cut by the time period of the cutting cycle and dividing it by the specified cutting time.

[0093] In one implementation method, the amount of metal material that needs to be cut on each production line is calculated based on the target metal material output of each cutting cycle and the number of production lines, so that the production load is evenly distributed among the production lines to avoid overloading or idleness of a single production line. By understanding the target metal material output of each cutting cycle, the production rhythm and schedule can be better adjusted to ensure the smooth implementation of the production plan.

[0094] In one implementation, by accurately calculating the cutting speed, increased energy consumption due to excessive acceleration or deceleration of the cutting machine is avoided, thereby reducing production costs.

[0095] In one embodiment, comparing the metal material image with a preset image to obtain a comparison result includes:

[0096] The metal material image is preprocessed to obtain an initial image, and the edge of the initial image is extracted by the Sobel edge algorithm to obtain the target edge;

[0097] The outer contour of the initial image is obtained by processing the edge of the target through the contour detection algorithm;

[0098] The shape similarity analysis between the outer contour and the standard contour in the preset image is performed by a shape matching algorithm to obtain a similarity value;

[0099] If the similarity value is greater than or equal to the preset similarity value, the comparison result is normal cutting; if the similarity value is less than the preset similarity value, the comparison result is abnormal cutting.

[0100] In one implementation, the Sobel edge detection algorithm can effectively identify edge features in an image, thereby providing an accurate outline of the metal material. This is the basis for detecting cutting quality. By processing the edge image with the contour detection algorithm, the outer contour of the metal material can be accurately extracted, ensuring that important features in the detection process are correctly captured.

[0101] In one implementation, the contour detection algorithm is findContours in OpenCV, the shape matching algorithm is matchShapes in OpenCV, and the preset similarity value is determined by a technician.

[0102] In one implementation, shape similarity analysis is performed through an algorithm to achieve automated cutting quality detection, reducing the time and labor intensity of manual inspection. It can quickly process metal material images and provide comparison results, which helps to promptly detect and correct cutting anomalies and improve the response speed of the production line.

[0103] In one implementation, a standardized shape matching algorithm is used to ensure that the cutting quality of each metal material meets the set standards, thereby improving product consistency and reliability.

[0104] In one embodiment, adjusting preset working parameters of a cutting machine for cutting a sample metal material includes:

[0105] Step 1: the cutting machine cuts the sample metal material according to the initial working parameters to obtain the test metal material, collects the image of the test metal material to obtain the test image; the test image is analyzed by the image recognition algorithm to obtain the metal material size and burr quality of the test metal material and record them as the first quality data;

[0106] Step 2, substituting the working parameters of the cutting machine into the dynamic model to obtain the acceleration signal, and obtaining the sensitive features of the cutting machine in the acceleration signal through the dynamic feature extraction algorithm;

[0107] Step 3, substituting the first quality data, sensitive features, and initial working parameters into the real-time characterization model of side tool wear to obtain the wear parameters of the cutting machine;

[0108] Step 4, optimizing the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain the target optimization parameters; the second quality data is the metal material size and the burr quality corresponding to the preset image;

[0109] Step 5, bringing the target optimization parameters back to step 1 as initial working parameters; obtaining the updated first quality data, and if the difference between the updated first quality data and the second quality data is within a preset range, ending the working parameter adjustment.

[0110] In one implementation, by testing the size and burr quality of metal materials and combining the acceleration signal characteristics of the dynamic model, the working state and wear of the cutting machine can be accurately evaluated, thereby improving the cutting quality.

[0111] In one implementation, the real-time characterization model for edge tool wear can be a BiGRU model, an LSTM model, a GRU model, etc., the image recognition algorithm can be a convolutional neural network, YOLO, Faster R-CNN, etc., and the dynamic feature extraction algorithm can be time domain analysis, frequency domain analysis, wavelet transform, etc.; the sensitive feature is the acceleration peak, and the preset range is determined by the technician.

[0112] In one implementation, the analysis of the dynamic model and acceleration signal provides real-time monitoring of the cutting machine's operating status, which helps to detect problems and make adjustments in a timely manner. The working parameters are dynamically optimized based on the actual operating data, and the cutting machine's operating status can be adjusted at any time to adapt to different cutting conditions and requirements.

[0113] In one implementation, by optimizing working parameters, downtime and adjustment time caused by cutting quality problems are reduced, thereby improving the overall efficiency of the production line.

[0114] In one implementation, the wear of the cutting machine is quantitatively analyzed through a real-time characterization model of side tool wear, providing data support for optimizing parameters.

[0115] In one embodiment, the initial working parameters of the cutting machine are optimized according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain the target optimization parameters, including:

[0116] The initial working parameters include cutting speed, feed depth, spindle speed, and cutting angle; the second quality data includes target metal material size and target burr quality; the sample metal material size is recorded as the actual metal material size, and the burr quality of the sample metal material is recorded as the actual burr quality;

[0117] The absolute value of the difference between the target metal material size and the actual metal material size is calculated to obtain the size error; the absolute value of the difference between the target burr quality and the actual burr quality is calculated to obtain the burr quality error;

[0118] Determine a first weight coefficient and a second weight coefficient according to the size error and the burr quality error;

[0119] By formula

[0120]

[0121] Determine the target optimization parameters; where S is E is the burr quality error size error, E is E is the burr quality error burr quality error, α is the first weight coefficient, β is the second weight coefficient, S init E is the actual metal material size of the burr quality error, E init E is the actual burr quality error, D is the target feed depth of the cutting machine, and D is the burr quality error. init E is the cutting depth of the burr quality error, N, N init E is the target spindle speed of the cutting machine for the burr quality error and E is the spindle speed for the burr quality error, θ, θ init E is the target cutting angle of the burr quality error cutting machine and E is the burr quality error cutting angle, S tar E is the target metal material size of the burr quality error, and k1, k2, k3, m1, m2, and m3 are constant coefficients.

[0122] In one implementation, by calculating the absolute value of the difference between the target metal material size and the actual metal material size, the size error can be determined, thereby accurately adjusting the parameters of the cutting machine to reduce the cutting error. By calculating the absolute value of the difference between the target burr quality and the actual burr quality, the burr problem can be accurately evaluated, the cutting process can be optimized, and the generation of burrs can be reduced.

[0123] In one implementation, all the target optimization parameters (D, N, θ) solved by the formula are substituted into the formula S pred =k1D+k2N+k3θ to get the first optimization parameter, substitute it into formula E pred =w1D+w2N+w3θ to get the second optimization parameter, and use the formula f(D, N, θ)=|S0-S pred | 2 +|E0-E pred | 2 , determine (D, N, θ) corresponding to the minimum value f(D, N, θ) as the target optimization parameter, where S0 is the standard metal material size corresponding to the final qualified metal material, and E0 is the standard burr quality corresponding to the final qualified metal material.

[0124] In one implementation method, the size error and the burr quality error are respectively normalized by minimum-maximum normalization to obtain the size error planning value and the burr quality error planning value, and the sum of the size error planning value and the burr quality error planning value is calculated and recorded as the total planning value; the size error planning value divided by the total planning value is recorded as the first weight coefficient, and the burr quality error planning value divided by the total planning value is recorded as the second weight coefficient. If the first weight coefficient is greater than or equal to the second weight coefficient, k1, k2, k3, m1, m2, and m3 are 1.13, 1.1, 1.12, 1.06, 1.0, and 1.06, respectively. If the first weight coefficient is less than the second weight coefficient, k1, k2, k3, m1, m2, and m3 are 1.0, 1.06, 1.06, 1.1, 1.13, and 1.12, respectively.

[0125] In one implementation, the cutting speed, feed depth, spindle speed and cutting angle are comprehensively considered and combined with weight coefficients to optimize target parameters and achieve the best performance of the cutting machine.

[0126] Based on the same inventive concept, the present invention also provides an automated production line control device for shipbuilding. Figure 2 , Figure 2 A schematic diagram of a structure of an automated production line control device for shipbuilding provided by an embodiment of the present invention includes:

[0127] A cutting speed determination module, used to determine the cutting speed of the cutting machine in each metal material cutting production line according to the total amount of metal material cutting, the number of production lines, the specified cutting time, the size of the metal material and the material properties;

[0128] A metal material image determination module is used to start each cutting machine according to preset working parameters to cut a complete metal material to obtain a plurality of metal materials, and to visually inspect each metal material to obtain a metal material image of the metal material;

[0129] A comparison module is used to compare the metal material image with a preset image to obtain a comparison result. If the comparison result is a cutting abnormality, the complete metal material cut in the metal material cutting production line is replaced with a sample metal material, and the complete metal material originally to be cut in the metal material cutting production line is evenly distributed to other production lines;

[0130] The optimization module is used to adjust the preset working parameters of the cutting machine for cutting the sample metal material until the comparison result between the metal material image corresponding to the metal material cut by the cutting machine after optimization and the preset image shows that the cutting is normal. Then, the sample metal material is replaced with a complete metal material, and the number of complete metal materials originally to be cut is reallocated to the production line.

[0131] An automated production line control device for shipbuilding provided by an embodiment of the present invention ensures the efficiency and stability of the cutting process and reduces cutting quality problems caused by improper speed by scientifically calculating and setting the optimal cutting speed of the cutting machine in each metal material cutting production line. After the cutting is completed, metal material image detection is immediately performed to ensure that cutting faults can be discovered in real time. The acquired metal material image is automatically compared with the preset standard image. Once cutting abnormalities such as size discrepancy, rough edges, etc. are found, the emergency response mechanism is immediately triggered. At this time, the complete metal material on the cutting line is replaced with a sample metal material, and the originally planned complete metal material production task is flexibly adjusted to other production lines to avoid the entire production line from being shut down due to a single fault, thereby greatly reducing the shutdown cost, ensuring the continuity of the production plan, and improving the operation efficiency of the production line.

[0132] In one embodiment, the cutting speed determination module includes:

[0133] A working time determination module is used to determine the cutting path length of the cutting machine according to the length and width of the target metal material, and to obtain an estimated time for cutting a target metal material according to the cutting path length, the material properties of the target metal material and the maximum cutting speed of the cutting machine;

[0134] A target metal material output determination module is used to determine the cutting cycle according to the specified cutting time, and obtain the target metal material output of each cutting cycle according to the time period of the cutting cycle, the specified cutting time and the total amount of metal material cut;

[0135] A metal material quantity determination module is used to obtain the quantity of metal materials that each production line needs to cut in each cutting cycle by dividing the target metal material output of each cutting cycle by the number of production lines;

[0136] A cutting speed determination module, used to calculate the cutting speed of the cutting machine in each metal material cutting production line according to the amount of metal materials, the length of the cutting path, the estimated time and the cutting cycle;

[0137] By formula Get the cutting speed of the cutting machine in each metal material cutting production line; where V is the cutting speed of the cutting machine, P line is the amount of metal material, L cut is the cutting path length, T cut is the estimated time, and ΔT is the cutting cycle.

[0138] In one embodiment, the optimization module includes:

[0139] An edge extraction module is used to preprocess the metal material image to obtain an initial image, and extract the edge of the initial image by using the Sobel edge algorithm to obtain a target edge;

[0140] The contour extraction module is used to process the edge of the target through the contour detection algorithm to obtain the outer contour of the initial image;

[0141] A similarity value determination module, used for performing shape similarity analysis on the outer contour and the standard contour in the preset image through a shape matching algorithm to obtain a similarity value;

[0142] The comparison result determination module is used to determine that if the similarity value is greater than or equal to the preset similarity value, the comparison result is normal cutting; if the similarity value is less than the preset similarity value, the comparison result is abnormal cutting.

[0143] In one embodiment, the optimization module further includes:

[0144] An image analysis module is used for the cutting machine to cut the sample metal material according to the initial working parameters to obtain the test metal material, collect the image of the test metal material to obtain the test image; analyze the test image by the image recognition algorithm to obtain the metal material size and burr quality of the test metal material and record them as the first quality data;

[0145] A sensitive feature extraction module is used to substitute the working parameters of the cutting machine into the dynamic model to obtain the acceleration signal, and obtain the sensitive features of the cutting machine in the acceleration signal through the dynamic feature extraction algorithm;

[0146] A wear parameter determination module, used for substituting the first quality data, the sensitive features, and the initial working parameters into the side tool wear real-time characterization model to obtain the cutter wear parameters;

[0147] A target optimization parameter determination module is used to optimize the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain the target optimization parameters; the second quality data is the metal material size and the burr quality corresponding to the preset image;

[0148] The quality data judgment module is used to bring the target optimization parameters back to the image analysis module as initial working parameters; obtain the updated first quality data, and if the difference between the updated first quality data and the second quality data is within a preset range, end the working parameter adjustment.

[0149] In one embodiment, the target optimization parameter determination module includes:

[0150] The parameter naming module is used for the initial working parameters including cutting speed, feed depth, spindle speed, and cutting angle; the second quality data includes the target metal material size and the target burr quality; the sample metal material size is recorded as the actual metal material size, and the burr quality of the sample metal material is recorded as the actual burr quality;

[0151] The difference calculation module is used to calculate the absolute value of the difference between the target metal material size and the actual metal material size to obtain the size error; calculate the absolute value of the difference between the target burr quality and the actual burr quality to obtain the burr quality error;

[0152] A target optimization parameter calculation module, used for determining a first weight coefficient and a second weight coefficient according to a size error and a burr quality error;

[0153] By formula

[0154]

[0155] Determine the target optimization parameters; where S is the size error, E is the burr quality error, α is the first weight coefficient, β is the second weight coefficient, S init is the actual metal material size, E init is the actual burr quality, D is the target feed depth of the cutting machine, and D init is the feed depth, N, N init are the target spindle speed of the cutting machine and the spindle speed, θ, θ init are the target cutting angle of the cutting machine and the cutting angle, S tar is the target metal material size, k1, k2, k3, m1, m2, m3 are constant coefficients.

[0156] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for controlling an automated production line for shipbuilding, characterized in that: The method comprises: Determine the cutting speed of the cutting machine in each metal material cutting production line based on the total amount of metal material cutting, the number of production lines, the required cutting time, the size of the metal material and the material properties; For each cutting machine, the cutting machine is started according to preset working parameters to cut the complete metal material to obtain a plurality of metal materials, and for each metal material, the metal material is visually inspected to obtain a metal material image of the metal material; The metal material image is compared with a preset image to obtain a comparison result. If the comparison result indicates that the cutting is abnormal, the complete metal material cut in the metal material cutting production line is replaced with a sample metal material, and the complete metal materials originally to be cut in the metal material cutting production line are evenly distributed to other production lines; The preset working parameters of the cutting machine used for cutting the sample metal material are adjusted until the comparison result between the metal material image corresponding to the metal material cut by the cutting machine after optimization and the preset image shows that the cutting is normal. The sample metal material is then replaced with a complete metal material, and the number of complete metal materials originally to be cut is reallocated to the production line.

2. The method for controlling an automated production line for shipbuilding according to claim 1, characterized in that: The cutting speed of the cutting machine in each metal material cutting production line is determined based on the total amount of metal material cutting, the number of production lines, the performance parameters of the cutting machine, the specified cutting time, the size of the metal material and the material characteristics, including: Determine the cutting path length of the cutting machine according to the length and width of the target metal material, and obtain an estimated time for cutting one target metal material according to the cutting path length, the material properties of the target metal material and the maximum cutting speed of the cutting machine; Determine a cutting cycle according to the specified cutting time, and obtain a target metal material output of each cutting cycle according to the time period of the cutting cycle, the specified cutting time and the total amount of metal material cut; The target metal material output of each cutting cycle is divided by the number of production lines to obtain the amount of metal material that each production line needs to cut in each cutting cycle; Calculate the cutting speed of the cutting machine in each metal material cutting production line according to the amount of metal materials, the cutting path length, the estimated time and the cutting cycle; By formula Get the cutting speed of the cutting machine in each metal material cutting production line; where V is the cutting speed of the cutting machine, P line is the amount of metal material, L cut is the cutting path length, T cut is the estimated time, and ΔT is the cutting cycle.

3. The method for controlling an automated production line for shipbuilding according to claim 1, characterized in that: The metal material image is compared with the preset image to obtain comparison results including: Preprocessing the metal material image to obtain an initial image, and extracting the edge of the initial image using a Sobel edge algorithm to obtain a target edge; Processing the target edge by a contour detection algorithm to obtain the outer contour of the initial image; Performing shape similarity analysis on the outer contour and the standard contour in the preset image by a shape matching algorithm to obtain a similarity value; If the similarity value is greater than or equal to the preset similarity value, the comparison result is that the cutting is normal; if the similarity value is less than the preset similarity value, the comparison result is that the cutting is abnormal.

4. The method for controlling an automated production line for shipbuilding according to claim 1, characterized in that: Adjusting the preset working parameters of the cutting machine for cutting the sample metal material includes: Step 1: the cutting machine cuts the sample metal material according to the initial working parameters to obtain the test metal material, collects the image of the test metal material to obtain the test image; analyzes the test image by the image recognition algorithm to obtain the metal material size and burr quality of the test metal material and records them as the first quality data; Step 2, substituting the working parameters of the cutting machine into the dynamic model to obtain an acceleration signal, and obtaining the sensitive features of the cutting machine in the acceleration signal through a dynamic feature extraction algorithm; Step 3, substituting the first quality data, the sensitive features, and the initial working parameters into the real-time characterization model of the side tool wear to obtain the cutting machine wear parameters; Step 4, optimizing the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain target optimization parameters; the second quality data is the metal material size and the burr quality corresponding to the preset image; Step 5, bringing the target optimization parameters back to step 1 as initial working parameters; obtaining the updated first quality data, and if the difference between the updated first quality data and the second quality data is within a preset range, ending the working parameter adjustment.

5. The method for controlling an automated production line for shipbuilding according to claim 4, characterized in that: The target optimization parameters obtained by optimizing the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material include: The initial working parameters include cutting speed, feed depth, spindle speed, and cutting angle; the second quality data includes target metal material size and target burr quality; the sample metal material size is recorded as the actual metal material size, and the burr quality of the sample metal material is recorded as the actual burr quality; The absolute value of the difference between the target metal material size and the actual metal material size is calculated to obtain the size error; the absolute value of the difference between the target burr quality and the actual burr quality is calculated to obtain the burr quality error; Determine a first weight coefficient and a second weight coefficient according to the size error and the burr quality error; By formula Determine the target optimization parameters; where S is the size error, E is the burr quality error, α is the first weight coefficient, β is the second weight coefficient, S init is the actual metal material size, E init is the actual burr quality, D is the target feed depth of the cutting machine, and D init is the feed depth, N, N init are the target spindle speed of the cutting machine and the spindle speed, θ, θ init are the target cutting angle of the cutting machine and the cutting angle, S tar is the target metal material size, k1, k2, k3, m1, m2, m3 are constant coefficients.

6. An automated production line control device for shipbuilding, characterized in that: The device comprises: A cutting speed determination module, used to determine the cutting speed of the cutting machine in each metal material cutting production line according to the total amount of metal material cutting, the number of production lines, the specified cutting time, the size of the metal material and the material properties; A metal material image determination module is used to start each cutting machine according to preset working parameters to cut a complete metal material to obtain a plurality of metal materials, and to visually inspect each metal material to obtain a metal material image of the metal material; A comparison module is used to compare the metal material image with a preset image to obtain a comparison result. If the comparison result is a cutting abnormality, the complete metal material cut in the metal material cutting production line is replaced with a sample metal material, and the complete metal materials originally to be cut in the metal material cutting production line are evenly distributed to other production lines; The optimization module is used to adjust the preset working parameters of the cutting machine for cutting the sample metal material until the comparison result between the metal material image corresponding to the metal material cut by the cutting machine after optimization and the preset image shows that the cutting is normal. Then, the sample metal material is replaced with a complete metal material, and the number of complete metal materials originally to be cut is reallocated to the production line.

7. The automatic production line control device for shipbuilding according to claim 6 is characterized in that: The cutting speed determination module comprises: A working time determination module, used to determine the cutting path length of the cutting machine according to the length and width of the target metal material, and to obtain an estimated time for cutting one of the target metal materials according to the cutting path length, the material properties of the target metal material and the maximum cutting speed of the cutting machine; A target metal material output determination module is used to determine a cutting cycle according to the specified cutting time, and obtain a target metal material output of each cutting cycle according to the time period of the cutting cycle, the specified cutting time and the total amount of metal material cut; A metal material quantity determination module is used to obtain the quantity of metal materials that each production line needs to cut in each cutting cycle by dividing the target metal material output of each cutting cycle by the number of production lines; A cutting speed determination module, used for calculating the cutting speed of the cutting machine in each metal material cutting production line according to the amount of the metal material, the length of the cutting path, the estimated time and the cutting cycle; By formula Get the cutting speed of the cutting machine in each metal material cutting production line; where V is the cutting speed of the cutting machine, P line is the amount of metal material, L cut is the cutting path length, T cut is the estimated time, and ΔT is the cutting cycle.

8. The automatic production line control device for shipbuilding according to claim 6 is characterized in that: The optimization module includes: An edge extraction module is used to preprocess the metal material image to obtain an initial image, and extract the edge of the initial image by using a Sobel edge algorithm to obtain a target edge; A contour extraction module, used for processing the edge of the target by a contour detection algorithm to obtain the outer contour of the initial image; A similarity value determination module, used for performing shape similarity analysis on the outer contour and the standard contour in the preset image by a shape matching algorithm to obtain a similarity value; The comparison result determination module is used to determine that if the similarity value is greater than or equal to a preset similarity value, the comparison result is that the cutting is normal; if the similarity value is less than the preset similarity value, the comparison result is that the cutting is abnormal.

9. The automatic production line control device for shipbuilding according to claim 6, characterized in that: The optimization module also includes: An image analysis module is used for the cutting machine to cut the sample metal material according to the initial working parameters to obtain the test metal material, collect the image of the test metal material to obtain the test image; analyze the test image by the image recognition algorithm to obtain the metal material size and burr quality of the test metal material and record them as the first quality data; A sensitive feature extraction module is used to substitute the working parameters of the cutting machine into the dynamic model to obtain an acceleration signal, and obtain the sensitive features of the cutting machine in the acceleration signal through a dynamic feature extraction algorithm; A wear parameter determination module, used for substituting the first quality data, the sensitive feature, and the initial working parameter into the side tool wear real-time characterization model to obtain the cutter wear parameter; a target optimization parameter determination module, configured to optimize the initial working parameters of the cutting machine according to the wear parameters of the cutting machine, the initial working parameters, the second quality data, the metal material size and the burr quality of the sample metal material to obtain the target optimization parameters; the second quality data is the metal material size and the burr quality corresponding to the preset image; The quality data judgment module is used to bring the target optimization parameters back to the image analysis module as initial working parameters; obtain the updated first quality data, and if the difference between the updated first quality data and the second quality data is within a preset range, end the working parameter adjustment.

10. The automatic production line control device for shipbuilding according to claim 9, characterized in that: The target optimization parameter determination module includes: A parameter naming module, wherein the initial working parameters include cutting speed, feed depth, spindle speed, and cutting angle; the second quality data includes target metal material size and target burr quality; the sample metal material size is recorded as the actual metal material size, and the burr quality of the sample metal material is recorded as the actual burr quality; A difference calculation module is used to calculate the absolute value of the difference between the target metal material size and the actual metal material size to obtain the size error; and calculate the absolute value of the difference between the target burr quality and the actual burr quality to obtain the burr quality error; A target optimization parameter calculation module, used for determining a first weight coefficient and a second weight coefficient according to the size error and the burr quality error; By formula Determine the target optimization parameters; where S is the size error, E is the burr quality error, α is the first weight coefficient, β is the second weight coefficient, S init is the actual metal material size, E init is the actual burr quality, D is the target feed depth of the cutting machine, and D init is the feed depth, N, N init are the target spindle speed of the cutting machine and the spindle speed, θ, θ init are the target cutting angle of the cutting machine and the cutting angle, S tar is the target metal material size, k1, k2, k3, m1, m2, m3 are constant coefficients.

Images