An automotive production line safety monitoring system based on the industrial Internet

Abstract

The present invention relates to the technical field of safety monitoring, and discloses an automotive production line safety monitoring system based on the industrial Internet. According to N groups of symmetric mechanical arms on the left and right, N identification areas are divided at fixed intervals for the target vehicle frame from the front of the vehicle to the rear of the vehicle, and the nth group of mechanical arms is associated with the nth identification area; the first label is arranged on both the nth group of mechanical arms and the nth identification area; the second label is arranged on the Nth group of mechanical arms; the characteristic data of each welding point in the 1st to N-1th identification areas are obtained, and the corresponding welding points are divided into key welding points and non-key welding points based on the characteristic data; the characteristic map of the target vehicle frame at the corresponding matching moment is obtained based on the Nth group of mechanical arms, and the characteristic image is sent to the kth group of mechanical arms for priority identification; combined with the genetic algorithm, the first welding is performed on the key welding points, and the second welding is performed on the remaining welding points to obtain a welding execution plan.

Description

Technical Field

[0001] The present invention relates to the technical field of safety monitoring, and more specifically, to an automotive production line safety monitoring system based on the industrial Internet. Background Art

[0002] In the current automatic welding production line, the frame welding is jointly completed by multiple welding robotic arms symmetrically deployed on the left and right. To ensure the firmness of the frame welding, multiple robotic arms need to participate in the welding simultaneously, and there is a risk that the robotic arms may interfere with each other. For this reason, each robotic arm is equipped with an obstacle avoidance system and an identification system. The former is used to detect and avoid collisions with other robotic arms, and the latter is responsible for identifying the welding points on the frame. However, the existing technology has the following problems:

[0003] 1. Safety issues: Each robotic arm independently identifies the welding points, resulting in the welding time depending on the difficulty of identifying the welding points. The welding points that are easy to identify will be welded first, while the welding points with higher identification difficulty (usually key welding points) will be delayed, resulting in poor welding stability of the frame.

[0004] 2. Efficiency issues: The welding time of the key welding points is relatively long, and coupled with the waiting for obstacle avoidance of the robotic arms that are welded first, the overall welding time is thus greatly extended. Summary of the Invention

[0005] The present invention provides an automotive production line safety monitoring system based on the industrial Internet to solve the technical problems proposed in the background art.

[0006] The present invention provides an automotive production line safety monitoring system based on the industrial Internet, including:

[0007] A region division module, configured to divide N identification regions for a target frame at fixed intervals from the head to the tail of the vehicle according to N groups of left and right symmetric robotic arms, and associate the nth group of robotic arms with the nth identification region; wherein, 1 ≤ n ≤ N;

[0008] A label matching module, including a first label and a second label; arranging the first label on both the nth group of robotic arms and the nth identification region; arranging the second label on the Nth group of robotic arms;

[0009] A welding point grading module, configured to obtain the characteristic data of each welding point in the 1st to N-1th identification regions, and classify the corresponding welding points into key welding points and non-key welding points based on the characteristic data;

[0010] A data monitoring module, configured to, in response to the matching of the second label of the Nth group of robotic arms with the first label of the kth identification region, obtain the characteristic map of the target frame at the corresponding matching moment based on the Nth group of robotic arms, and send the characteristic image to the kth group of robotic arms for priority identification; wherein, 1 ≤ k ≤ N-1;

[0011] The welding execution module is used to respond to the matching of the first tag of the nth robotic arm and the first tag of the nth recognition area, and combine with the genetic algorithm to perform the first welding on the key welding points and the second welding on the remaining welding points to obtain a welding execution plan.

[0012] Furthermore, both the first tag and the second tag are RFID tags; among them, when the first tag matches the first tag, the welding task of the corresponding robotic arm is executed; when the second tag matches the first tag, a data link between the Nth robotic arm and the corresponding robotic arm is established.

[0013] Furthermore, the corresponding welding points are divided into key welding points and non-key welding points, including:

[0014] The characteristic data includes: the connection function L of the welding point and the safety function S of the welding point; for the target vehicle frame, a number of structural units are defined manually, and the structural units include but are not limited to: front and rear longitudinal beams, side beams and cross beams; if the welding point is used to connect any number of structural units, the connection function of the welding point is the number of connected structural units; multi-angle stress analysis is performed on the welded target vehicle frame; if the stress value of the welding point at any stress angle is greater than the preset stress threshold, the safety function of the welding point is the difference between the stress value and the preset stress threshold.

[0015] Calculate the key score for the welding point, and the calculation formula is as follows:

[0016] ;

[0017] Among them, represents the key score of the welding point, represents the first weight, represents the second weight;

[0018] If , the corresponding welding point is divided into a key welding point, otherwise it is divided into a non-key welding point.

[0019] Furthermore, send the characteristic image to the kth group of robotic arms for priority recognition, including:

[0020] Send the characteristic images obtained by the left and right robotic arms in the Nth group of robotic arms to the left and right robotic arms in the kth group of robotic arms respectively;

[0021] The left and right robotic arms in the kth group of robotic arms identify the characteristic image based on a preset recognition model to obtain the positions of several welding points in the kth recognition area at the matching moment of the first tag of the kth group of robotic arms and the first tag of the kth recognition area.

[0022] Further, performing the first welding on the key solder joints includes:

[0023] Obtaining the key solder joints on the left and right sides in the k-th recognition area, and the score of each key solder joint;

[0024] Based on the scores of the key solder joints, sorting the key solder joints on the left and right sides in the k-th recognition area from large to small respectively to obtain the first left welding sorting and the first right welding sorting;

[0025] And performing the first welding on the key solder joints in the k-th recognition area based on the first left welding sorting and the first right welding sorting.

[0026] Further, performing the second welding on the remaining solder joints includes:

[0027] Obtaining the non-key solder joints on the left and right sides in the n-th recognition area;

[0028] Initializing and generating R second welding sortings in the n-th recognition area that meet the constraint conditions; where the second welding sorting includes: the second left welding sorting and the second right welding sorting;

[0029] The constraint conditions are as follows: each solder joint is welded only once;

[0030] Performing the second welding on the non-key solder joints in the n-th recognition area based on the R second welding sortings.

[0031] Further, obtaining the welding execution plan includes:

[0032] Step 71, based on the first welding of N sub-areas and the R second weldings, respectively establishing R groups of motion interference simulations, and each group of motion interference simulations includes the first welding and the r-th second welding; 1 ≤ r ≤ R;

[0033] Step 72, running the R groups of motion interference simulations based on digital twin, including:

[0034] Setting the recognition time of the corresponding feature image by the N-th robotic arm to U;

[0035] At the matching moment T1 of the first label of the k-th robotic arm and the first label of the k-th recognition area, synchronously performing the first left welding sorting and the first right welding sorting in the k-th recognition area; after the first left welding sorting and the first right welding sorting are completed, continue to perform the second left welding sorting and the second right welding sorting;

[0036] At the matching moment T1 of the first label of the N-th robotic arm and the first label of the k-th recognition area, after the recognition time U, performing the second left welding sorting and the second right welding sorting in the N-th recognition area;

[0037] Among them, the moving paths of the robotic arm from the starting point to the welding point, from the welding point to the welding point, and from the welding point to the end point are all Euclidean distance paths, and the moving speed of each robotic arm is V;

[0038] Spatial constraints include: if there is a j-th robotic arm on the moving path of the i-th robotic arm, avoidance is required; among them, the avoidance time is Tr; where i≠j, 1≤i≤N, 1≤j≤N;

[0039] Time constraints include: obtaining the welding time required for each welding point, and the robotic arm staying at any welding point for the corresponding welding time required;

[0040] Step 73, based on the spatial constraints and time constraints, obtain the completion time T2 of the motion interference simulation for each of the R groups of motions, and the welding time corresponding to each group of motion interference simulations is T2 - T1;

[0041] Step 74, take the welding time of T2 - T1 as the fitness value of the R second weldings;

[0042] Step 76, sort the R second weldings from small to large based on the fitness value to obtain a fitness ranking; retain a preset number of second weldings from the front to the back of the fitness ranking, and perform random crossover and mutation on the second welding rankings corresponding to the remaining second weldings to obtain updated R second weldings;

[0043] Step 77, repeat steps 72 - 76 until a preset number of times is reached to obtain the second welding with the first position in the fitness ranking;

[0044] Step 78, execute the first welding and the second welding to obtain a welding execution plan.

[0045] The beneficial effects of the present invention are as follows: By integrating technologies such as industrial Internet, RFID tags, digital twin simulation, and genetic algorithm, refined zoning and intelligent scheduling of the entire process of frame welding are achieved, effectively solving problems in traditional production such as untimely processing of key welding points and chaotic welding sequences caused by the independent operation of robotic arms, thereby significantly improving production efficiency and ensuring the welding quality of the frame. Description of the Drawings

[0046] Figure 1 is a module diagram of an automotive production line safety monitoring system based on the industrial Internet of the present invention;

[0047] Figure 2 is a schematic diagram of the welding production line of the present invention. Detailed Embodiments

[0048] Reference will now be made to exemplary embodiments to discuss the subject matter described herein. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein, and the functions and arrangements of the elements discussed can be changed without departing from the scope of protection of the content of this specification. Each example can omit, substitute, or add various processes or components as needed. Additionally, the features described for some examples can also be combined in other examples.

[0049] As Figures 1 to 2 shown, an industrial Internet-based safety monitoring system for an automobile production line includes:

[0050] A region division module, configured to divide N identification regions for a target vehicle frame from the head to the tail of the vehicle at fixed intervals according to N groups of symmetrically arranged robotic arms on the left and right, and associate the nth group of robotic arms with the nth identification region; where 1 ≤ n ≤ N;

[0051] A tag matching module, including a first tag and a second tag; arranging the first tag on both the nth group of robotic arms and the nth identification region; arranging the second tag on the Nth group of robotic arms;

[0052] A solder joint grading module, configured to obtain the characteristic data of each solder joint in the 1st to N - 1th identification regions, and classify the corresponding solder joints into critical solder joints and non-critical solder joints based on the characteristic data;

[0053] A data monitoring module, configured to, in response to the matching of the second tag of the Nth group of robotic arms with the first tag of the kth identification region, obtain the characteristic map of the target vehicle frame at the corresponding matching moment based on the Nth group of robotic arms, and send the characteristic image to the kth group of robotic arms for priority identification; where 1 ≤ k ≤ N - 1;

[0054] A welding execution module, configured to, in response to the matching of the first tag of the nth group of robotic arms with the first tag of the nth identification region, and in combination with a genetic algorithm, perform first welding on the critical solder joints and second welding on the remaining solder joints to obtain a welding execution plan.

[0055] In an embodiment of the present invention, both the first tag and the second tag are RFID tags; when the first tag matches the first tag, the welding task of the corresponding robotic arm is executed; when the second tag matches the first tag, a data link between the Nth robotic arm and the corresponding robotic arm is established.

[0056] Specifically, the RFID (Radio Frequency Identification) technology enables the automatic matching of the robotic arm with the identification area, ensures the intelligent execution of the welding task, and enables data sharing between robotic arms. A first tag is installed on each robotic arm and each identification area. When the first tag on the robotic arm enters its corresponding identification area (i.e., the first tag is matched), the robotic arm is activated to perform the welding task. Robotic arm A enters identification area 1, and its first tag recognizes the first tag in this area. The system confirms that robotic arm A should perform the welding task and activates this robotic arm. When the second tag is matched with the first tag in a certain identification area, the Nth group of robotic arms obtains the solder joint data of this area and transmits it to the previous robotic arms. The previous robotic arms can obtain complete welding information before starting welding, improving production efficiency. Robotic arm N enters identification area 3, and its second tag recognizes the first tag in this area. Robotic arm N collects the frame feature image of this area and sends it to the previous robotic arms 1 and 2. A data sharing mechanism is formed between robotic arms, reducing task waiting time and enhancing the overall production efficiency.

[0057] In an embodiment of the present invention, the corresponding solder joints are divided into key solder joints and non-key solder joints, including:

[0058] The feature data includes: the connection function L of the solder joint and the safety function S of the solder joint; based on manual definition, several structural units are defined for the target frame, and the structural units include but are not limited to: front and rear longitudinal beams, side beams, and cross beams; if the solder joint is used to connect any number of structural units, the connection function of the solder joint is the number of connected structural units; multi-angle stress analysis is performed on the welded target frame; if the stress value of the solder joint at any stress angle is greater than the preset stress threshold, the safety function of the solder joint is the difference between the stress value and the preset stress threshold.

[0059] Calculate the key score for the solder joint, and the calculation formula is as follows:

[0060] ;

[0061] Wherein, represents the key score of the solder joint, represents the first weight, represents the second weight;

[0062] If , then the corresponding solder joint is divided into a key solder joint, otherwise it is divided into a non-key solder joint.

[0063] Specifically, by calculating the key scores of solder joints, the solder joints are classified into: critical solder joints (which must be welded first) and non-critical solder joints (which can be welded later). The goal of this method is to determine which solder joints are crucial for the frame structure strength, ensure priority welding, and improve the frame stability. Optimize the welding sequence to avoid low welding efficiency and insufficient solder joint strength caused by random welding. Evaluate the importance of solder joints through two key parameters: connection function (L): measure whether the solder joint is used to connect multiple key structural units (such as longitudinal beams and cross beams). Safety function (S): measure the force-bearing situation of the solder joint, and select the solder joints with greater force in multiple directions. By assigning different weight parameters respectively, the key score of each solder joint is obtained.

[0064] In an embodiment of the present invention, the feature image is sent to the kth group of robotic arms for priority recognition, including:

[0065] The feature images obtained by the left and right robotic arms in the Nth group of robotic arms are correspondingly sent to the left and right robotic arms in the kth group of robotic arms;

[0066] The left and right robotic arms in the kth group of robotic arms recognize the feature image based on a preset recognition model to obtain the positions of several solder joints in the kth recognition area at the matching moment of the first label of the kth group of robotic arms and the first label of the kth recognition area.

[0067] This method realizes information sharing between robotic arms through the process of image acquisition → transmission → recognition → task execution, so as to optimize the welding process through pre-recognition. Specifically, the preset recognition models are all prior arts. It can be an open-source model with multimodality, such as Chatgpt or Tongyi Qianwen.

[0068] The comparison between the present invention and the prior art is as follows:

[0069] Traditional welding method: The robotic arm scans and recognizes one by one.

[0070] Priority recognition of solder joints in the present invention: Pre-recognized by the rear-end robotic arm.

[0071] Traditional welding method: The robotic arm recognizes independently.

[0072] Priority recognition of solder joints in the present invention: Image sharing mechanism.

[0073] Traditional welding method: Scan first and then weld.

[0074] Priority recognition of solder joints in the present invention: Obtain data first and directly execute welding.

[0075] Traditional welding method: Low (time-consuming for the robotic arm to scan one by one).

[0076] Priority recognition of solder joints in the present invention: High (reduce scanning time and improve welding efficiency).

[0077] In one embodiment of the present invention, the first welding is performed on key solder joints, including:

[0078] Obtain the key solder joints on the left and right sides in the nth recognition area, and the score of each key solder joint;

[0079] Based on the scores of the key solder joints, the key solder joints on the left and right sides in the nth recognition area are sorted from large to small respectively to obtain the first left welding sorting and the first right welding sorting;

[0080] And perform the first welding on the key solder joints in the nth recognition area based on the first left welding sorting and the first right welding sorting.

[0081] Specifically, ensure the priority welding of key solder joints to improve the structural strength and production efficiency of frame welding. Priority welding of key solder joints: First weld the solder joints that are most critical to the structural strength to ensure the stability of the frame. Solder joint score sorting: Adopt a scoring mechanism to determine the priority of solder joints and ensure that the most important solder joints are welded first. Synchronous sorting on both left and right sides: Independently sort the solder joints on both left and right sides to optimize the welding sequence and improve the collaborative efficiency of the robotic arm.

[0082] In one embodiment of the present invention, the second welding is performed on the remaining solder joints, including:

[0083] Obtain the non-key solder joints on the left and right sides in the nth recognition area;

[0084] Initialize and generate R second welding sortings in the nth recognition area that meet the constraint conditions; where the second welding sorting includes: the second left welding sorting and the second right welding sorting;

[0085] The constraint conditions are as follows: Each solder joint is welded only once;

[0086] Perform the second welding on the non-key solder joints in the nth recognition area based on the R second welding sortings.

[0087] Specifically, in the actual production process, the number of non-key solder joints is much larger than that of key solder joints. If welded in the traditional order, it will lead to a long welding path and an extended welding time, thus reducing the production efficiency. Therefore, through the welding sequence generation method of the genetic algorithm, the welding path of non-key solder joints is optimized, thereby improving the welding efficiency. This method performs welding sorting that meets the constraint conditions on non-key solder joints to obtain a class code, which further supports the optimization of the subsequent genetic algorithm.

[0088] In one embodiment of the present invention, obtaining the welding execution plan includes:

[0089] Step 71: Based on the first welding of N sub-regions and the R second weldings, establish R groups of motion interference simulations respectively. Each group of motion interference simulations includes the first welding and the r-th second welding; 1 ≤ r ≤ R;

[0090] Step 72: Run the R groups of motion interference simulations based on digital twin, including:

[0091] Set the recognition time of the corresponding feature image by the N-th robotic arm to U;

[0092] At the matching moment T1 between the first label of the k-th robotic arm and the first label of the k-th recognition region, perform the first left welding sorting and the first right welding sorting synchronously in the k-th recognition region; after the first left welding sorting and the first right welding sorting are completed, continue to perform the second left welding sorting and the second right welding sorting;

[0093] At the matching moment T1 between the first label of the N-th robotic arm and the first label of the k-th recognition region, after the recognition time U, perform the second left welding sorting and the second right welding sorting in the N-th recognition region;

[0094] Wherein, the moving paths of the robotic arm moving from the starting point to the welding point, from the welding point to the welding point, and from the welding point to the end point are all Euclidean distance paths, and the moving speed of each robotic arm is V;

[0095] The space constraint includes: if there is a j-th robotic arm on the moving path of the i-th robotic arm, then avoid it; wherein, the avoidance time is Tr; wherein, i ≠ j, 1 ≤ i ≤ N, 1 ≤ j ≤ N;

[0096] The time constraint includes: obtain the welding time required for each welding point, and the robotic arm stays at any welding point for the corresponding welding time required;

[0097] Step 73: Based on the space constraint and the time constraint, obtain the completion time T2 of the R groups of motion interference simulations respectively, then the welding time corresponding to each group of motion interference simulations is T2 - T1;

[0098] Step 74: Take the welding time T2 - T1 as the fitness value of the R second weldings;

[0099] Step 76: Sort the R second weldings from small to large based on the fitness value to obtain the fitness sorting; retain a preset number of second weldings from front to back in the fitness sorting, and perform random crossover and mutation on the second welding sorting corresponding to the remaining second weldings to obtain the updated R second weldings;

[0100] Step 77: Repeat Step 72 - Step 76 until reaching the preset number of times to obtain the second welding with the first position in the fitness sorting;

[0101] Step 78, perform the first welding and the second welding to obtain a welding execution plan.

[0102] Specifically, traditional welding methods usually rely on manual setting of the welding sequence, but this method is prone to low welding efficiency and long operating paths of the robotic arms. The present invention uses digital twin simulation + genetic algorithm optimization to generate and optimize the welding execution plan, making the arrangement of welding tasks more intelligent and precise.

[0103] The execution process of the present invention can be divided into the following steps:

[0104] Establish R groups of motion interference simulations: Before performing welding, the system first establishes R groups of motion interference simulations. This simulation is based on the division of the welding area of the vehicle frame (N sub-areas), and respectively simulates: the first welding of key welds (determined part) and the second welding of non-key welds (part to be optimized by the genetic algorithm). Evaluate the total welding time under the R groups of motion interference simulations before actual welding to ensure that the optimized welding plan can minimize the interference between robotic arms to the greatest extent and improve welding efficiency.

[0105] Set the recognition time U: Since the Nth group of robotic arms still needs to recognize the vehicle frame welds before performing welding (the 1st to N - 1th groups of robotic arms recognize in advance), the time U from recognition to welding of the robotic arms is set in the simulation.

[0106] Synchronously execute welding tasks: The robotic arms perform the first welding (key welds) at the matching moment T1 in the 1st to N - 1th recognition areas. After the first welding is completed, the second welding sequence (non-key welds) is continued in sequence. However, for the Nth recognition area, it needs to wait for the recognition time U. Since there are no key welds set in the Nth recognition area, the second welding is directly performed in the Nth recognition area.

[0107] Optimize the welding path: When the robotic arms perform welding, the Euclidean distance path (that is, directly reaching from point to point) is adopted to ensure that the movement path of the robotic arms during welding is the shortest and avoid ineffective movements.

[0108] Optimize the welding time based on spatial constraints and time constraints.

[0109] Spatial constraints: Set the movement paths of different robotic arms to ensure that when the jth robotic arm exists on the path of the ith robotic arm, the ith robotic arm can actively stop and wait for the jth robotic arm to leave the path of the ith robotic arm before the ith robotic arm continues to move. The avoidance time is set to Tr. Since each robotic arm has a corresponding recognition area (welding area), the avoidance situation of the robotic arms only exists when both the ith robotic arm and the jth robotic arm are on the path, rather than during the welding process. Therefore, when the moving speeds are the same at V, the avoidance times are also the same at Tr.

[0110] Time constraint: Set the welding time required for each solder joint (the welding time required is obtained based on historical data. Since welding is performed by a robotic arm, the welding time for each solder joint is basically the same), and ensure that the residence time of the robotic arm at each solder joint is the corresponding welding time required. Thus, simulate the real welding process in the motion interference simulation to obtain the real welding time.

[0111] Optimize the welding sequence. The system uses a genetic algorithm for iterative optimization: Use the welding time T2 - T1 as the evaluation index to calculate the fitness values of different welding sequences. The shorter the welding time, the higher the fitness value. Sort the fitness of the second welding plan of group R, and select the top N optimal plans. Randomly cross and mutate the remaining plans to generate new welding plans for the next round of optimization. Iterate multiple times to obtain the optimal welding plan: After multiple rounds of optimization, the system finally obtains the optimal welding sequence, that is, the welding plan with the first fitness ranking. After completing the simulation and optimization, the system sends the optimal welding plan to the production line to perform the final welding task. Since the welding sequence has been optimized, therefore: the welding time is the shortest, the interference of the robotic arm is the smallest, and the welding quality is the highest.

[0112] The above describes the embodiments of this example, but this example is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative and not restrictive. Under the inspiration of this example, those of ordinary skill in the art can also make many forms, all of which fall within the protection scope of this example.

Claims

1. An automobile production line safety monitoring system based on industrial Internet, characterized in that: include: The area division module is used to divide the target vehicle frame into N identification areas from the front to the rear at fixed intervals according to N groups of bilaterally symmetrical mechanical arms, and associate the nth group of mechanical arms with the nth identification area; wherein 1≤n≤N; The tag matching module includes a first tag and a second tag; the first tag is arranged on the nth group of mechanical arms and the nth identification area; the second tag is arranged on the Nth group of mechanical arms; The solder joint classification module is used to obtain the characteristic data of each solder joint in the 1st to N-1th identification areas, and classify the corresponding solder joints into key solder joints and non-key solder joints based on the characteristic data, including: The characteristic data includes: the connection function L of the welding point and the safety function S of the welding point; a number of structural units are manually defined for the target frame, and the structural units include but are not limited to: front and rear longitudinal beams, side beams and cross beams; if the welding point is used to connect any number of structural units, the connection function of the welding point is the number of connected structural units; a multi-angle force analysis is performed on the welded target frame; if the stress value of the welding point at any stress angle is greater than the preset stress threshold, the safety function of the welding point is the difference between the stress value and the preset stress threshold; The critical score is calculated for the solder joints using the following formula: ； in, Indicates the critical score of the solder joint, represents the first weight, represents the second weight; like , the corresponding solder joint is classified as a critical solder joint, otherwise it is classified as a non-critical solder joint; A data monitoring module, for responding to the matching of the second label of the Nth group of mechanical arms with the first label of the kth identification area, obtaining a feature image of the target vehicle frame at the corresponding matching time based on the Nth group of mechanical arms, and sending the feature image to the kth group of mechanical arms for priority identification; wherein 1≤k≤N-1; The welding execution module is used to respond to the matching of the first tag of the nth group of robot arms with the first tag of the nth identification area, and in combination with the genetic algorithm, perform the first welding on the key welding points and perform the second welding on the remaining welding points to obtain a welding execution plan.

2. According to the industrial Internet-based automobile production line safety monitoring system of claim 1, it is characterized in that: The first tag and the second tag are both RFID tags; when the first tag matches the first tag, the welding task of the corresponding robotic arm is executed; when the second tag matches the first tag, a data link between the Nth robotic arm and the corresponding robotic arm is established.

3. According to the industrial Internet-based automobile production line safety monitoring system of claim 2, it is characterized in that: Send the feature image to the kth group of robotic arms for priority recognition, including: The feature images acquired by the left and right robotic arms in the Nth group of robotic arms are sent to the left and right robotic arms in the kth group of robotic arms respectively; The left robotic arm and the right robotic arm in the kth group of robotic arms recognize the feature image based on a preset recognition model to obtain the positions of several welding points in the kth identification area at the moment when the first label of the kth group of robotic arms matches the first label of the kth identification area.

4. According to the industrial Internet-based automobile production line safety monitoring system of claim 3, it is characterized in that: Perform the first weld on the critical weld points, including: Obtain the key solder joints on the left and right sides of the nth recognition area, and the score of each key solder joint; Based on the scores of the key welds, the key welds on the left and right sides of the nth identification area are sorted from large to small to obtain a first left welding sort and a first right welding sort; And performing the first welding on the key welding points in the nth identified area based on the first left welding sequence and the first right welding sequence.

5. According to the industrial Internet-based automobile production line safety monitoring system of claim 4, it is characterized in that: Perform a second weld on the remaining weld points, including: Obtain non-critical welding points on the left and right sides of the nth identification area; Initialize and generate a second welding sequence in R n-th identification areas that meet the constraint conditions; wherein the second welding sequence includes: a second left welding sequence and a second right welding sequence; The constraints are as follows: each solder joint is soldered only once; The second welding is performed on the non-critical welding points in the nth identified area based on the R second welding rankings.

6. The automotive production line safety monitoring system based on industrial Internet according to claim 5 is characterized in that: Get a welding execution plan, including: Step 61, based on the first welding and R second welding of the N sub-areas, respectively establish R groups of motion interference simulation, each group of motion interference simulation includes the first welding and the rth second welding; 1≤r≤R; Step 62, running the R group motion interference simulation based on the digital twin, including: Set the recognition time of the feature image corresponding to the Nth group of robot arms to U; At the matching time T1 of the first tag of the kth group of robot arms and the first tag of the kth identification area, the first left welding sequence and the first right welding sequence are synchronously executed in the kth identification area; after the first left welding sequence and the first right welding sequence are completed, the second left welding sequence and the second right welding sequence are continued to be executed; At the matching time T1 of the first tag of the Nth group of robot arms and the first tag of the kth identification area, after the identification time U, the second left welding sequence and the second right welding sequence are performed in the Nth identification area; Among them, the moving paths of the robot arm from the starting point to the welding point, from the welding point to the welding point, and from the welding point to the end point are all Euclidean distance paths, and the moving speed of each robot arm is V; The spatial constraints include: if there is a jth robot on the moving path of the ith robot, avoid it; the avoidance time is Tr; i≠j, 1≤i≤N, 1≤j≤N; Time constraints include: obtaining the welding time required for each welding point, and the welding time required for the robot arm to stay at any welding point; Step 63, based on the space constraint and the time constraint, respectively obtain the completion time T2 of the motion interference simulation of the R motion groups, and the welding time corresponding to each motion interference simulation group is T2-T1; Step 64, taking the welding time T2-T1 as the fitness value of the R second welding; Step 65, sorting the R second welds from small to large based on the fitness values ​​to obtain a fitness sorting; retaining a preset number of second welds from the front to the back of the fitness sorting, and performing random crossover and mutation on the second weld sortings corresponding to the remaining second welds to obtain updated R second welds; Step 66, repeating steps 62 to 65 for a preset number of times to obtain a second welding with a ranking of 1 in the fitness ranking; Step 67, performing the first welding and the second welding to obtain a welding execution plan.

Images