Automatic paint spraying system for automobile
By integrating sensors and intelligent algorithms in automobile manufacturing, the ESRB uniform linear distribution model and the red-mouthed blue magpie algorithm are used to solve the problems of unstable quality and high cost of traditional manual spray paint, and the efficient and accurate spraying process is achieved , improves the quality of the car's appearance and production efficiency.
Patent Information
- Application Number
- CN202411157008.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-12
AI Technical Summary
The spraying quality during traditional manual spraying process is unstable, expensive and harmful to the human body. Early robot spraying trajectory generation depends on operational experience. The complexity of complex automotive surface geometry and spraying modes leads to difficulty in planning and determining spray trajectory.
A car automatic paint spraying system was designed, integrating sensors, intelligent control algorithms and automated mechanical devices, and optimizing spraying quality by establishing an ESRB uniform linear distribution model and the red-mouthed blue magpie algorithm, realizing accurate control of the spraying environment and process, reducing materials and Energy consumption.
It realizes uniform spraying of the coating, reduces color aberration, improves the appearance quality and corrosion resistance of the automobile, reduces labor costs, improves production efficiency and market competitiveness, and ensures consistency of product quality.
Smart Images

Figure CN118925967A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of automobile manufacturing and relates to an automobile automatic painting technology; specifically, it relates to an automobile automatic painting system. Background Art
[0002] With the vigorous development of automobile manufacturing industry, spraying process is a key link. In the early days, it relied on manual operation, which not only made it difficult to guarantee the quality of spraying and had a high spraying cost, but also caused great harm to the human body. Later, automatic spraying technology gradually replaced manual operation, but the early robot spraying trajectory generation also had to rely on the operator's experience to a certain extent.
[0003] In current industrial production, the electrostatic spray rotary bell (ESRB) technology has emerged. Through advanced atomization and electric field control technology, the spraying efficiency and quality have been greatly improved; however, ESRB technology still faces some challenges in practical applications. The complex geometry of the automobile surface and the complexity of the ESRB spraying pattern make spraying trajectory planning and spraying parameter determination very difficult. Summary of the invention
[0004] In view of the above problems, the purpose of the present invention is to propose an efficient and accurate automobile automatic painting technology (an automobile automatic painting system) to solve the problems of unstable quality, high cost and harm to the health of operators in the traditional manual painting process; by integrating advanced sensors, intelligent control algorithms and automated mechanical devices, precise control of the spraying environment and process can be achieved, ensuring the spraying quality while significantly reducing material and energy consumption, thereby reducing production costs, improving efficiency and market competitiveness.
[0005] The technical solution of the present invention is: an automobile automatic spraying system described in the present invention comprises a collection unit, a regulating unit, a spraying unit and a control unit which are interconnected.
[0006] Furthermore, the specific equipment includes: indoor temperature sensor, indoor humidity sensor, anemometer, camera, air conditioner and sprinkler.
[0007] Furthermore, the collection unit sends the collected indoor temperature, humidity, wind speed and product quality status to the control unit;
[0008] The regulating unit regulates indoor temperature, humidity and wind speed parameters;
[0009] The spraying unit receives the spraying or re-spraying instruction from the control unit; by establishing the ESRB uniform linear distribution model and using the red-billed blue magpie algorithm to optimize the spraying quality, the goal of spraying automation is achieved.
[0010] Furthermore, the ESRB uniform linear distribution model is established, and the model is as follows:
[0011]
[0012] Where: t is the actual thickness, t c is the thickness value at the central symmetry axis, t p is the thickest thickness of the model at the peak, r p is the peak value t p The corresponding x-coordinate, t p is 50% of the width w 50 , t p is 25% of the width w 25 .
[0013] Furthermore, during the automobile spraying process, t c ,t p ,r p ,w 50 ,w 25 The spraying parameters need to be changed frequently to meet the requirements of different areas, so it is necessary to establish a functional relationship between the parameters and the distribution model; among them, t c ,t p ,r p ,w 50 ,w 25 The main influencing factors of parameters include spraying distance H, moving speed v, spray gun flow rate Q, internal shaping air flow rate N1, and external shaping air flow rate N2.
[0014] Furthermore, the ESRB parameter distribution model is established as follows:
[0015] (1) Peak thickness t p The objective function is:
[0016] t p1 =a1Q 2 +b1Q+c1
[0017]
[0018] Where: t p_1 is the peak thickness when considering the internal shaping air flow, t p_2 is the peak thickness when considering the spraying distance, t p0 is the initial peak thickness value, t p1 is the thickness value at the peak when considering the spray gun flow rate, t p2 is the thickness value at the peak when both the spray gun flow rate and the internal shaping air flow rate are considered, t p3In order to consider the spray gun flow rate, internal shaping air flow rate and the thickness value at the peak value at the spraying distance, Q is the flow rate of the sampling spray gun, Q0 is the flow rate of the initial setting spray gun, N1 is the internal shaping air flow rate, N 1_0 is the initial setting of internal shaping air flow, H is the spraying distance, H0 is the initial setting of spraying distance, a1, a2 b1, b2, b3, c1 are all spraying parameters;
[0019] (2) Peak value t p The corresponding x coordinate r p The objective function is:
[0020]
[0021] Where: r p0 is the x-coordinate of the peak value at the initial setting, r p1 is the x-coordinate of the peak value when considering the internal shaping air flow, r p2 To consider both the internal shaping air flow and the spraying distance, the x-coordinate of the peak value, N1 is the internal shaping air flow, N 1_0 is the initial setting of the internal shaping air flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a4, a5, b4, b5, c2 are all spraying parameters;
[0022] (3) Thickness value t about the central symmetry axis c Objective function:
[0023]
[0024] Where: t c_1 is the thickness value at the central symmetry axis when considering the internal shaping air flow, t c_2 is the thickness value at the central symmetry axis when considering the spraying distance, t c1 is the thickness value at the central symmetry axis when considering the flow rate of the spray gun, t c2 is the thickness value at the central symmetry axis when considering the spray gun flow rate and internal shaping air flow rate, t c3 In order to consider the spray gun flow rate, internal shaping air flow rate and the thickness value at the central symmetry axis at the spraying distance, Q is the flow rate of the sampling spray gun, Q0 is the flow rate of the initial setting spray gun, N1 is the internal shaping air flow rate, N 1_0 is the initial setting of the internal shaping air flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a6, a7, a8, b6, b7, b8 are all spraying parameters;
[0025] (4) The width w of the peak thickness is 50% 50 Objective function:
[0026]
[0027] Where: w 50_0 The initial setting of the peak thickness is 50% of the width, w 50_1 The width of 50% of the peak thickness when considering the internal shaping air flow, w 50_2 w is the width at which the peak thickness is 50% when the internal shaping air flow and the flow of the spray gun are taken into account. 50_3 To consider the internal shaping air flow, the flow of the spray gun and the width of the peak thickness of 50% when the spray distance, N1 is the internal shaping air flow, N 1_0 is the initial setting of the internal shaping air flow, Q is the flow of the sampling spray gun, Q0 is the initial setting of the spray gun flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a9, a 10 ,a 11 ,b9,b 10 ,b 11 All are spraying parameters;
[0028] (5) The width w of the peak thickness is 25% 25 Objective function:
[0029]
[0030] Where: w 25_0 The initial setting of peak thickness is 25% of the width, w 25_1 The width w is the width of 25% of the peak thickness when considering the internal shaping air flow. 25_2 w is the width of 25% of the peak thickness when considering the internal shaping air flow and the external shaping air flow. 25_3 The width w is the value of 25% of the peak thickness when considering the internal shaping air flow, external shaping air flow and the flow of the spray gun. 25_4 To consider the internal shaping air flow, external shaping air flow, spray gun flow and spray distance, the width of the peak thickness is 25%, N1 is the internal shaping air flow, N 1_0 is the initial setting of internal shaping air flow, N2 is the external shaping air flow, N 2_0 is the initial setting of external shaping air flow, Q is the flow of the sampling spray gun, Q0 is the initial setting of the spray gun flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a 12 ,a 13 ,a 14 ,a 15 ,b 12 ,b 13 ,b 14 ,b 15 All are spraying parameters.
[0031] Furthermore, the spraying thickness is one of the important indicators to measure the spraying quality, and the spraying quality also includes standards such as coating color difference and coating thickness uniformity. In addition, the spraying quality is also affected by parameters such as temperature, humidity, and wind speed in the environment. Therefore, it is necessary to establish a corresponding evaluation function to ensure that the spraying effect meets the requirements.
[0032] Furthermore, the corresponding spraying evaluation function is established as follows:
[0033] maxY=ω1Y1+ω2Y2+ω3Y3+ω4t+ω5d+ω6Q
[0034] 1=ω1+ω2+ω3+ω4+ω5+ω6
[0035]
[0036] Wherein, Y is the spraying quality, ω1, ω2, ω3, ω4, ω5, ω6 are weight numbers, which are random numbers uniformly distributed between [0, 1], Y1 is the evaluation function characterizing the performance of matching with the target thickness, Y2 is the evaluation function characterizing the color difference of the coating, Y3 is the evaluation function of the thickness uniformity, H is the spraying distance, v is the moving speed, Q is the spray gun flow rate, N1 is the internal shaping air flow rate, N2 is the external shaping air flow rate, t is the ambient temperature, d is the ambient humidity, and Q is the ambient wind speed;
[0037] (1) Establish an evaluation function to characterize the performance of matching with the target thickness:
[0038] Y1=(T mean -T t ) 2
[0039]
[0040] Where Y1 is the actual target thickness, T mean is the average thickness, T t To set the target thickness, T i is the thickness of n sampling points;
[0041] (2) Establish an evaluation function to characterize coating color difference:
[0042] Y2=|T max -T min |
[0043] Where, Y2 is the color difference of the coating, T max is the maximum value of the sampling thickness, T min is the minimum value of sampling thickness;
[0044] (3) Establish the evaluation function of thickness uniformity:
[0045]
[0046] Where, Y3 is the thickness uniformity value, N is the number of sampling times, T t To set the target thickness, T mean is the average thickness.
[0047] Furthermore, in the process of optimizing the spraying quality by using the red-billed blue magpie algorithm, the specific steps of the red-billed blue magpie algorithm are as follows:
[0048] (1) Establish a search agent position matrix. The matrix model is as follows:
[0049]
[0050] Where X represents the position of the generated search agent, which is the candidate solution of RBMO, which is randomly generated under the constraints of the given problem and needs to be updated after each iteration; n represents the overall size, that is, the number of groups of spraying parameters and environmental parameters, and dim represents the dimension of the problem to be solved, that is, the number of spraying parameters and environmental parameters;
[0051] x i,j =(ub-lb)×Rand1+lb
[0052] In the formula, x i,j is an element in the X matrix, ub and lb are the upper and lower bounds of the problem respectively, and Rand1 represents a random number between 0 and 1;
[0053] (2) Calculate the evaluation function to find the optimal spraying quality. The evaluation function is as follows:
[0054] maxY=ω1Y1+ω2Y2+ω3Y3+ω4t+ω5d+ω6Q
[0055] 1=ω1+ω2+ω3+ω4+ω5+ω6
[0056]
[0057] Wherein, Y is the spraying quality, ω1, ω2, ω3, ω4, ω5, ω6 are weight numbers, which are random numbers uniformly distributed between [0, 1], Y1 is the evaluation function characterizing the performance of matching with the target thickness, Y2 is the evaluation function characterizing the color difference of the coating, Y3 is the evaluation function of the thickness uniformity, H is the spraying distance, v is the moving speed, Q is the spray gun flow rate, N1 is the internal shaping air flow rate, N2 is the external shaping air flow rate, t is the ambient temperature, d is the ambient humidity, and Q is the ambient wind speed;
[0058] The expressions of Y1, Y2, and Y3 are as follows:
[0059] Y1=(T mean -T t ) 2
[0060]
[0061] Where Y1 is the actual target thickness, T mean is the average thickness, T t To set the target thickness, T i is the thickness of n sampling points;
[0062] Y2=|T max -T min |
[0063] Where, Y2 is the color difference of the coating, T max is the maximum value of the sampling thickness, T min is the minimum value of sampling thickness;
[0064]
[0065] Where, Y3 is the thickness uniformity value, N is the number of sampling times, T t To set the target thickness, T mean is the average thickness;
[0066] (3) Construct an algorithm search phase model, which aims to improve the efficiency of finding the optimal solution and simulate the habits of the red-billed blue magpie to enhance the algorithm's ability in the search space. The position update formula is as follows:
[0067]
[0068] In the formula, t represents the current iteration number, X i (t+1) represents the i-th new search agent position, i.e., the spray quality solution to be selected, p represents the number of search agents in the cluster when exploring food, X m represents the randomly selected mth individual, X i represents the i-th individual, X rs represents the randomly selected search agent in the current iteration;
[0069] (4) Construct an algorithm attack phase model, which aims to enhance the algorithm’s positioning accuracy and local search capability for the optimal solution. The position update formula is as follows:
[0070]
[0071] In the formula, t represents the current iteration number, X i (t+1) represents the i-th new search agent position, i.e., the optimal solution for spraying quality, X food (t) indicates the location of the food, Randn represents the random numbers used to generate the standard normal distribution (mean 0, standard deviation 1), p represents the number of search agents in the cluster when exploring for food;
[0072] (5) Construct the algorithm storage phase model, which is used to determine whether the target value meets the requirements. The position update formula is as follows:
[0073]
[0074] Where, iffitness old and fitness new Respectively represent the fitness values of the i-th red-billed blue magpie before and after the position update;
[0075] (6) Determine whether the spraying quality meets the standard. If so, store the data and jump to step (7). If not, return to step (3);
[0076] (7) Output the optimal objective function value.
[0077] Furthermore, the improvement step of the red-billed blue magpie algorithm is to initialize the population by Sin chaotic mapping in step (1). The Sin chaotic mapping can make the generated initial population more uniform, improve the quality of the initial population, and facilitate the global search in the early stage. The specific improvement method is as follows:
[0078] x n+1 =μsin(πx n )0≤x n ≤1
[0079] In the formula, x represents the iteration value, and μ is a random number in [0,1].
[0080] The beneficial effects of the present invention are: 1. By establishing the ESRB uniform linear distribution model and adopting the red-billed blue magpie algorithm to optimize the spraying quality, uniform spraying of the coating is achieved; compared with the traditional spraying technology, the spraying unit of the present invention can more accurately control the coating thickness, reduce color difference, improve the uniformity of spraying, and improve the appearance quality and anti-corrosion performance of the automobile; 2. Compared with other algorithms, the red-billed blue magpie algorithm has faster convergence, high adaptability and flexibility; the algorithm is designed with a mechanism to avoid falling into local optimality, which can help the ESRB uniform linear distribution model to seek the optimal solution; 3. The sin chaotic mapping is used to initialize the population, and the generated initial population is relatively uniform, which improves the quality of the initial population and is conducive to the early global search; 4. The automated spraying process reduces the dependence on manual operation, reduces labor costs, and improves production efficiency; and the automated spraying has higher quality consistency to ensure the quality of the product. BRIEF DESCRIPTION OF THE DRAWINGS
[0081] Figure 1 It is a schematic diagram of the structure of the present invention;
[0082] Figure 2 It is a work flow chart of the present invention. DETAILED DESCRIPTION
[0083] The specific technical scheme of the present invention is further described in detail below with reference to specific examples.
[0084] like Figure 1 As shown, the automatic spraying system for a car described in the present invention includes a collection unit, a regulating unit and a spraying unit.
[0085] Furthermore, the acquisition unit includes an indoor temperature sensor, an indoor humidity sensor, an anemometer, and a camera; the temperature and humidity sensor is used to detect the indoor temperature and humidity values, and adjust the temperature and humidity values through the air conditioner; the anemometer is used to detect the indoor wind speed to ensure that the indoor wind speed meets the requirements; the camera is used to monitor whether the spraying condition meets the requirements. If not, the paint is scraped off and re-sprayed; the adjustment unit includes an air conditioner; the spraying unit includes a nozzle.
[0086] Furthermore, the collection unit sends the collected indoor temperature, humidity, wind speed and product quality status to the control unit;
[0087] The regulating unit regulates indoor temperature, humidity and wind speed parameters;
[0088] The spraying unit receives the spraying or re-spraying instruction from the control unit; by establishing the ESRB uniform linear distribution model and using the red-billed blue magpie algorithm to optimize the spraying quality, the goal of spraying automation is achieved.
[0089] like Figure 2 As shown in the figure, the process of optimizing the spraying quality using the red-billed blue magpie algorithm is as follows:
[0090] Furthermore, the ESRB uniform linear distribution model is established, and the model is as follows:
[0091]
[0092] Where: t is the actual thickness, t c is the thickness value at the central symmetry axis, t p is the thickest thickness of the model at the peak, r p is the peak value t p The corresponding x-coordinate, t p is 50% of the width w 50 , t p is 25% of the width w 25 .
[0093] Furthermore, during the automobile spraying process, t c ,t p ,r p ,w 50 ,w 25 The spraying parameters need to be changed frequently to meet the requirements of different areas, so it is necessary to establish a functional relationship between the parameters and the distribution model; among them, t c ,t p ,r p ,w 50 ,w 25 The main influencing factors of parameters include spraying distance H, moving speed v, spray gun flow rate Q, internal shaping air flow rate N1, and external shaping air flow rate N2.
[0094] Furthermore, the ESRB parameter distribution model is established as follows:
[0095] (1) Peak thickness t p The objective function is:
[0096] t p1 =a1Q 2 +b1Q+c1
[0097]
[0098] Where: t p_1 is the peak thickness when considering the internal shaping air flow, t p_2 is the peak thickness when considering the spraying distance, t p0 is the initial peak thickness value, t p1 is the thickness value at the peak when considering the spray gun flow rate, t p2 is the thickness value at the peak when both the spray gun flow rate and the internal shaping air flow rate are considered, t p3 In order to consider the spray gun flow rate, internal shaping air flow rate and the thickness value at the peak value at the spraying distance, Q is the flow rate of the sampling spray gun, Q0 is the flow rate of the initial setting spray gun, N1 is the internal shaping air flow rate, N 1_0 is the initial setting of internal shaping air flow, H is the spraying distance, H0 is the initial setting of spraying distance, a1, a2 b1, b2, b3, c1 are all spraying parameters;
[0099] (2) Peak value t p The corresponding x coordinate r p The objective function is:
[0100]
[0101] Where: r p0 is the x-coordinate of the peak value at the initial setting, r p1is the x-coordinate of the peak value when considering the internal shaping air flow, r p2 To consider both the internal shaping air flow and the spraying distance, the x-coordinate of the peak value, N1 is the internal shaping air flow, N 1_0 is the initial setting of the internal shaping air flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a4, a5, b4, b5, c2 are all spraying parameters;
[0102] (3) Thickness value t about the central symmetry axis c Objective function:
[0103]
[0104] Where: t c_1 is the thickness value at the central symmetry axis when considering the internal shaping air flow, t c_2 is the thickness value at the central symmetry axis when considering the spraying distance, t c1 is the thickness value at the central symmetry axis when considering the flow rate of the spray gun, t c2 is the thickness value at the central symmetry axis when considering the spray gun flow rate and internal shaping air flow rate, t c3 In order to consider the spray gun flow rate, internal shaping air flow rate and the thickness value at the central symmetry axis at the spraying distance, Q is the flow rate of the sampling spray gun, Q0 is the flow rate of the initial setting spray gun, N1 is the internal shaping air flow rate, N 1_0 is the initial setting of the internal shaping air flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a6, a7, a8, b6, b7, b8 are all spraying parameters;
[0105] (4) The width w of the peak thickness is 50% 50 Objective function:
[0106]
[0107] Where: w 50_0 The initial setting of the peak thickness is 50% of the width, w 50_1 The width of 50% of the peak thickness when considering the internal shaping air flow, w 50_2 w is the width at which the peak thickness is 50% when the internal shaping air flow and the flow of the spray gun are taken into account. 50_3 To consider the internal shaping air flow, the flow of the spray gun and the width of the peak thickness of 50% when the spray distance, N1 is the internal shaping air flow, N 1_0 is the initial setting of the internal shaping air flow, Q is the flow of the sampling spray gun, Q0 is the initial setting of the spray gun flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a9, a 10 ,a 11 ,b9,b 10 ,b11 All are spraying parameters;
[0108] (5) The width w of the peak thickness is 25% 25 Objective function:
[0109]
[0110] Where: w 25_0 The initial setting of peak thickness is 25% of the width, w 25_1 The width w is the width of 25% of the peak thickness when considering the internal shaping air flow. 25_2 w is the width of 25% of the peak thickness when considering the internal shaping air flow and the external shaping air flow. 25_3 The width w is the value of 25% of the peak thickness when considering the internal shaping air flow, external shaping air flow and the flow of the spray gun. 25_4 To consider the internal shaping air flow, external shaping air flow, spray gun flow and spray distance, the width of the peak thickness is 25%, N1 is the internal shaping air flow, N 1_0 is the initial setting of internal shaping air flow, N2 is the external shaping air flow, N 2_0 is the initial setting of external shaping air flow, Q is the flow of the sampling spray gun, Q0 is the initial setting of the spray gun flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a 12 ,a 13 ,a 14 ,a 15 ,b 12 ,b 13 ,b 14 ,b 15 All are spraying parameters.
[0111] Furthermore, the spraying thickness is one of the important indicators to measure the spraying quality, and the spraying quality also includes standards such as coating color difference and coating thickness uniformity. In addition, the spraying quality is also affected by parameters such as temperature, humidity, and wind speed in the environment. Therefore, it is necessary to establish a corresponding evaluation function to ensure that the spraying effect meets the requirements.
[0112] Furthermore, the corresponding spraying evaluation function is established as follows:
[0113] maxY=ω1Y1+ω2Y2+ω3Y3+ω4t+ω5d+ω6Q
[0114] 1=ω1+ω2+ω3+ω4+ω5+ω6
[0115]
[0116] Wherein, Y is the spraying quality, ω1, ω2, ω3, ω4, ω5, ω6 are weight numbers, which are random numbers uniformly distributed between [0, 1], Y1 is the evaluation function characterizing the performance of matching with the target thickness, Y2 is the evaluation function characterizing the color difference of the coating, Y3 is the evaluation function of the thickness uniformity, H is the spraying distance, v is the moving speed, Q is the spray gun flow rate, N1 is the internal shaping air flow rate, N2 is the external shaping air flow rate, t is the ambient temperature, d is the ambient humidity, and Q is the ambient wind speed;
[0117] (1) Establish an evaluation function to characterize the performance of matching with the target thickness:
[0118] Y1=(T mean -T t ) 2
[0119]
[0120] Where Y1 is the actual target thickness, T mean is the average thickness, T t To set the target thickness, T i is the thickness of n sampling points;
[0121] (2) Establish an evaluation function to characterize coating color difference:
[0122] Y2=|T max -T min |
[0123] Where, Y2 is the color difference of the coating, T max is the maximum value of the sampling thickness, T min is the minimum value of sampling thickness;
[0124] (3) Establish the evaluation function of thickness uniformity:
[0125]
[0126] Where, Y3 is the thickness uniformity value, N is the number of sampling times, T t To set the target thickness, T mean is the average thickness.
[0127] Furthermore, in the process of optimizing the spraying quality by using the red-billed blue magpie algorithm, the specific steps of the red-billed blue magpie algorithm are as follows:
[0128] (1) Establish a search agent position matrix. The matrix model is as follows:
[0129]
[0130] Where X represents the position of the generated search agent, which is the candidate solution of RBMO, which is randomly generated under the constraints of the given problem and needs to be updated after each iteration; n represents the overall size, that is, the number of groups of spraying parameters and environmental parameters, and dim represents the dimension of the problem to be solved, that is, the number of spraying parameters and environmental parameters;
[0131] x i,j =(ub-lb)×Rand1+lb
[0132] In the formula, x i,j is an element in the X matrix, ub and lb are the upper and lower bounds of the problem respectively, and Rand1 represents a random number between 0 and 1;
[0133] (2) Calculate the evaluation function to find the optimal spraying quality. The evaluation function is as follows:
[0134] max Y=ω1Y1+ω2Y2+ω3Y3+ω4t+ω5d+ω6Q
[0135] 1=ω1+ω2+ω3+ω4+ω5+ω6
[0136]
[0137] Wherein, Y is the spraying quality, ω1, ω2, ω3, ω4, ω5, ω6 are weight numbers, which are random numbers uniformly distributed between [0, 1], Y1 is the evaluation function characterizing the performance of matching with the target thickness, Y2 is the evaluation function characterizing the color difference of the coating, Y3 is the evaluation function of the thickness uniformity, H is the spraying distance, v is the moving speed, Q is the spray gun flow rate, N1 is the internal shaping air flow rate, N2 is the external shaping air flow rate, t is the ambient temperature, d is the ambient humidity, and Q is the ambient wind speed;
[0138] The expressions of Y1, Y2, and Y3 are as follows:
[0139] Y1=(T mean -T t ) 2
[0140]
[0141] Where Y1 is the actual target thickness, T mean is the average thickness, T t To set the target thickness, T i is the thickness of n sampling points;
[0142] Y2=|T max -T min |
[0143] Where, Y2 is the color difference of the coating, Tmax is the maximum value of the sampling thickness, T min is the minimum value of sampling thickness;
[0144]
[0145] Where, Y3 is the thickness uniformity value, N is the number of sampling times, T t To set the target thickness, T mean is the average thickness;
[0146] (3) Construct an algorithm search phase model, which aims to improve the efficiency of finding the optimal solution and simulate the habits of the red-billed blue magpie to enhance the algorithm's ability in the search space. The position update formula is as follows:
[0147]
[0148] In the formula, t represents the current iteration number, X i (t+1) represents the i-th new search agent position, i.e., the spray quality solution to be selected, p represents the number of search agents in the cluster when exploring food, X m represents the randomly selected mth individual, X i represents the i-th individual, X rs represents the randomly selected search agent in the current iteration;
[0149] (4) Construct an algorithm attack phase model, which aims to enhance the algorithm’s positioning accuracy and local search capability for the optimal solution. The position update formula is as follows:
[0150]
[0151] In the formula, t represents the current iteration number, X i (t+1) represents the i-th new search agent position, i.e., the optimal solution for spraying quality, X food (t) indicates the location of the food, Randn represents the random numbers used to generate the standard normal distribution (mean 0, standard deviation 1), p represents the number of search agents in the cluster when exploring for food;
[0152] (5) Construct the algorithm storage phase model, which is used to determine whether the target value meets the requirements. The position update formula is as follows:
[0153]
[0154] Where, iffitness old and fitness new Respectively represent the fitness values of the i-th red-billed blue magpie before and after the position update;
[0155] (6) Determine whether the spraying quality meets the standard. If so, store the data and jump to step (7). If not, return to step (3);
[0156] (7) Output the optimal objective function value.
[0157] Furthermore, the improvement step of the red-billed blue magpie algorithm is to initialize the population by Sin chaotic mapping in step (1). The Sin chaotic mapping can make the generated initial population more uniform, improve the quality of the initial population, and facilitate the global search in the early stage. The specific improvement method is as follows:
[0158] x n+1 =μsin(πx n )0≤x n ≤1
[0159] In the formula, x represents the iteration value, and μ is a random number in [0,1].
[0160] Furthermore, to obtain a set of data of better spraying quality, adjust the temperature, humidity, wind speed, and conduct spraying tests. If it does not meet the spraying requirements - peeling, wrinkling, uneven spraying, etc., remove it and re-spray it.
[0161] Implementation scenario: This technology provides a systematic automatic spraying technology, which is mainly used for workshop spraying. During the spraying process, this technology can monitor the workshop working environment in real time through data collection to ensure the smooth progress of the spraying work. When spraying, this technology helps operators to carry out the spraying work through accurate data analysis and model prediction, taking into account high quality while saving manpower, reducing the risk of poor spraying quality, and thus achieving the goal of energy saving.
[0162] Implementable cases: The present invention can be applied to automobile manufacturing plants; spraying is an important link in the automobile manufacturing process, and the present invention can significantly improve spraying efficiency and product quality; the system integrates advanced sensors and intelligent algorithms to achieve precise control of the spraying environment; through real-time monitoring and data analysis, the system can automatically adjust the spraying parameters to ensure that the coating is uniform and has no color difference; in addition, the automated spraying process reduces labor costs and improves production efficiency; the system can also be applied to furniture manufacturing, toy manufacturing, sports equipment and other links that require spraying, providing effective spraying technology for the manufacturing industry.
Claims
1. Automobile automatic painting system, characterized in that: It includes a control unit, a collection unit, a regulating unit and a spraying unit which are interconnected; The acquisition unit includes an indoor temperature sensor for controlling temperature, an indoor humidity sensor for controlling humidity, a camera for observing the spraying condition, and an anemometer for testing wind speed; The conditioning unit includes an air conditioner; The spraying unit includes a spray head.
2. The automobile automatic painting system according to claim 1, characterized in that: The collection unit sends the collected indoor temperature, humidity, wind speed and product quality status to the control unit; The regulating unit regulates indoor temperature, humidity and wind speed parameters; The spraying unit receives the spraying or re-spraying instruction from the control unit; by establishing the ESRB uniform linear distribution model and using the red-billed blue magpie algorithm to optimize the spraying quality, the goal of spraying automation is achieved.
3. The automobile automatic painting system according to claim 2, characterized in that: The process of the ESRB uniform linear motion spray distribution model is as follows: (1) Establish the piecewise mathematical expression of the general uniform linear distribution model: Where: a, b, c, d are the coefficients of the polynomial, determined according to the characteristic points; A is the coefficient of the normal distribution function, σ is the standard deviation of the normal distribution function, which is used to adjust the shape of the curve so that the model is at x = r p The rest of the decline; (2) According to the shape of the model, the five important characteristic parameters are determined as follows: the thickness value t at the central symmetry axis c , the thickest thickness value of the model at the peak value t p , peak value t p The corresponding x coordinate r p , t p Width w at half thickness 50 , t p Width w at 25% thickness 25 ; make t(0) = t c , t(r p ) = t p , t'(0) = 0, t'(r p ) = 0, it can be obtained that: c=0 d=t c Let x = r p is the symmetry axis of the Gaussian function, we can get: A=t p μ=r p In order for the Gaussian function to strictly pass and These two points need to change their standard deviation σ value; when x = r p And A=t p When 50 and w 25 Uniquely correspond to σ 50 and σ 25 ; you can get: σ=kσ 50 +(1-k)σ 25 Where: 50 , σ 25 They are the standard deviation at 50% thickness and the standard deviation at 25% thickness respectively. The larger the standard deviation, the greater the difference between the data points; the smaller the standard deviation, the closer the data points are to the mean value; (3) Finally, the piecewise mathematical expression of the ESRB uniform linear distribution model is obtained: Where: t is the actual thickness, t c is the thickness value at the central symmetry axis, t p is the thickest thickness of the model at the peak, r p is the peak value t p The corresponding x-coordinate, t p is 50% of the width w 50 , t p is 25% of the width w 25 .
4. The automobile automatic painting system according to claim 3, characterized in that: In the process of automobile spraying, t c ,t p ,r p ,w 50 ,w 25 The spraying parameters need to be changed frequently to meet the requirements of different areas, so the ESRB parameter distribution model is established; Among them, t c ,t p ,r p ,w 50 ,w 25 The influencing factors of the parameters include spraying distance H, moving speed v, spray gun flow rate Q, internal shaping air flow rate N1, and external shaping air flow rate N2.
5. The automobile automatic painting system according to claim 4, characterized in that: The ESRB parameter distribution model is as follows: (1) Peak thickness t p The objective function is: t p1 =a1Q 2 +b1Q+c1 Where: t p_1 is the peak thickness when considering the internal shaping air flow, t p_2 is the peak thickness when considering the spraying distance, t p0 is the initial peak thickness value, t p1 is the thickness value at the peak when considering the spray gun flow rate, t p2 is the thickness value at the peak when both the spray gun flow rate and the internal shaping air flow rate are considered, t p3 In order to consider the spray gun flow rate, internal shaping air flow rate and the thickness value at the peak value at the spraying distance, Q is the flow rate of the sampling spray gun, Q0 is the flow rate of the initial setting spray gun, N1 is the internal shaping air flow rate, N 1_0 is the initial setting of internal shaping air flow, H is the spraying distance, H0 is the initial setting of spraying distance, a1, a2b1, b2, b3, c1 are all spraying parameters; (2) Peak value t p The corresponding x coordinate r p The objective function is: Where: r p0 is the x-coordinate of the peak value at the initial setting, r p1 is the x-coordinate of the peak value when considering the internal shaping air flow, r p2 To consider both the internal shaping air flow and the spraying distance, the x-coordinate of the peak value, N1 is the internal shaping air flow, N 1_0 is the initial setting of the internal shaping air flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a4, a5, b4, b5, c2 are all spraying parameters; (3) Thickness value t about the central symmetry axis c Objective function: Where: t c_1 is the thickness value at the central symmetry axis when considering the internal shaping air flow, t c_2 is the thickness value at the central symmetry axis when considering the spraying distance, t c1 is the thickness value at the central symmetry axis when considering the flow rate of the spray gun, t c2 is the thickness value at the central symmetry axis when considering the spray gun flow rate and internal shaping air flow rate, t c3 In order to consider the spray gun flow rate, internal shaping air flow rate and the thickness value at the central symmetry axis at the spraying distance, Q is the flow rate of the sampling spray gun, Q0 is the flow rate of the initial setting spray gun, N1 is the internal shaping air flow rate, N 1_0 is the initial setting of the internal shaping air flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a6, a7, a8, b6, b7, b8 are all spraying parameters; (4) The width w of the peak thickness is 50% 50 Objective function: Where: w 50_0 The initial setting of the peak thickness is 50% of the width, w 50_1 The width of 50% of the peak thickness when considering the internal shaping air flow, w 50_2 w is the width at which the peak thickness is 50% when the internal shaping air flow and the flow of the spray gun are taken into account. 50_3 To consider the internal shaping air flow, the flow of the spray gun and the width of the peak thickness of 50% when the spray distance, N1 is the internal shaping air flow, N 1_0 is the initial setting of the internal shaping air flow, Q is the flow of the sampling spray gun, Q0 is the initial setting of the spray gun flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a9, a 10 ,a 11 ,b9,b 10 ,b 11 All are spraying parameters; (5) The width w of the peak thickness is 25% 25 Objective function: In the formula, w 25_0 The initial setting of peak thickness is 25% of the width, w 25_1 The width w is the width of 25% of the peak thickness when considering the internal shaping air flow. 25_2 w is the width of 25% of the peak thickness when considering the internal shaping air flow and the external shaping air flow. 25_3 The width w is the value of 25% of the peak thickness when considering the internal shaping air flow, external shaping air flow and the flow of the spray gun. 25_4 To consider the internal shaping air flow, external shaping air flow, spray gun flow and spray distance, the width of the peak thickness is 25%, N1 is the internal shaping air flow, N 1_0 is the initial setting of internal shaping air flow, N2 is the external shaping air flow, N 2_0 is the initial setting of external shaping air flow, Q is the flow of the sampling spray gun, Q0 is the initial setting of the spray gun flow, H is the spraying distance, H0 is the initial setting of the spraying distance, a 12 ,a 13 ,a 14 ,a 15 ,b 12 ,b 13 ,b 14 ,b 15 All are spraying parameters.
6. The automobile automatic painting system according to claim 5, characterized in that: The spraying thickness is used to measure the spraying quality; The spraying quality also includes coating color difference and coating thickness uniformity; in addition, the spraying quality is also affected by the temperature, humidity and wind speed in the environment; therefore, a corresponding evaluation function is established to ensure that the spraying effect meets the requirements.
7. The automobile automatic painting system according to claim 6, characterized in that: The corresponding spraying evaluation function is established: For multi-objective parameter optimization, the linear weighted method is used to optimize, and the six optimization objectives are combined into an objective function according to different weights; maxY=ω1Y1+ω2Y2+ω3Y3+ω4t+ω5d+ω6Q 1=ω1+ω2+ω3+ω4+ω5+ω6 Wherein, Y is the spraying quality, ω1, ω2, ω3, ω4, ω5, ω6 are weight numbers, which are random numbers uniformly distributed between [0, 1], Y1 is the evaluation function that characterizes the performance of matching with the target thickness, Y2 is the evaluation function that characterizes the color difference of the coating, Y3 is the evaluation function of the thickness uniformity, H is the spraying distance, v is the moving speed, Q is the spray gun flow rate, N1 is the internal shaping air flow rate, N2 is the external shaping air flow rate, t is the ambient temperature, d is the ambient humidity, and Q is the ambient wind speed; (1) Establish an evaluation function to characterize the performance of matching with the target thickness: Y1=(T mean -T t ) 2 Where Y1 is the actual target thickness, T mean is the average thickness, T t To set the target thickness, T i is the thickness of n sampling points; (2) Establish an evaluation function to characterize coating color difference: Y2=|T max -T min | Where, Y2 is the color difference of the coating, T max is the maximum value of the sampling thickness, T min is the minimum value of sampling thickness; (3) Establish the evaluation function of thickness uniformity: Where, Y3 is the thickness uniformity value, N is the number of sampling times, T t To set the target thickness, T mean The average thickness.
8. The automobile automatic painting system according to claim 2, characterized in that: In the above-mentioned optimization of spraying quality by using the red-billed blue magpie algorithm, the steps of the red-billed blue magpie algorithm are as follows: (1) Establish a search agent position matrix. The matrix model is as follows: Where X represents the position of the generated search agent, which is the candidate solution of RBMO, which is randomly generated under the constraints of the given problem and needs to be updated after each iteration; n represents the overall size, that is, the number of groups of spraying parameters and environmental parameters, and dim represents the dimension of the problem to be solved, that is, the number of spraying parameters and environmental parameters; x i,j =(ub-lb)×Rand1+lb In the formula, x i,j is an element in the X matrix, ub and lb are the upper and lower bounds of the problem respectively, and Rand1 represents a random number between 0 and 1; (2) Calculate the evaluation function to find the optimal spraying quality. The evaluation function is as follows: maxY=ω1Y1+ω2Y2+ω3Y3+ω4t+ω5d+ω6Q 1=ω1+ω2+ω3+ω4+ω5+ω6 Wherein, Y is the spraying quality, ω1, ω2, ω3, ω4, ω5, ω6 are weight numbers, which are random numbers uniformly distributed between [0, 1], Y1 is the evaluation function that characterizes the performance of matching with the target thickness, Y2 is the evaluation function that characterizes the color difference of the coating, Y3 is the evaluation function of the thickness uniformity, H is the spraying distance, v is the moving speed, Q is the spray gun flow rate, N1 is the internal shaping air flow rate, N2 is the external shaping air flow rate, t is the ambient temperature, d is the ambient humidity, and Q is the ambient wind speed; The expressions of Y1, Y2, and Y3 are as follows: Y1=(T mean -T t ) 2 Where Y1 is the actual target thickness, T mean is the average thickness, T t To set the target thickness, T i is the thickness of n sampling points; Y2=|T max -T min | Where, Y2 is the color difference of the coating, T max is the maximum value of the sampling thickness, T min is the minimum value of sampling thickness; Where, Y3 is the thickness uniformity value, N is the number of sampling times, T t To set the target thickness, T mean is the average thickness; (3) Constructing the algorithm search phase model; (4) Constructing the algorithm attack stage model; (5) Construct the algorithm storage stage model; (6) Determine whether the spraying quality meets the standard. If so, store the data and jump to step (7). If not, return to step (3); (7): The optimal objective function value is output, that is, the optimal solution for spraying quality.
9. The automobile automatic painting system according to claim 8, characterized in that: In step (3), the algorithm search phase model is constructed to improve the efficiency of finding the optimal solution, and the ability of the algorithm in the search space is enhanced by simulating the habits of the red-billed blue magpie. The position update formula is as follows: In the formula, t represents the current iteration number, X i (t+1) represents the i-th new search agent position, i.e., the spray quality solution to be selected, p represents the number of search agents in the cluster when exploring food, X m represents the randomly selected mth individual, X i represents the i-th individual, X rs represents the randomly selected search agent in the current iteration; In step (4), the algorithm attack phase model is constructed to enhance the algorithm's positioning accuracy and local search capability for the optimal solution. The position update formula is as follows: In the formula, t represents the current iteration number, X i (t+1) represents the i-th new search agent position, i.e., the optimal solution for spraying quality, X food (t) indicates the location of the food, Randn represents the random numbers used to generate the standard normal distribution (mean 0, standard deviation 1), p represents the number of search agents in the cluster when exploring for food; In step (5), the algorithm storage phase model is constructed to determine whether the target value meets the requirements. The position update formula is as follows: Where, iffitness old and fitness new They respectively represent the fitness values of the i-th red-billed blue magpie before and after the position is updated.
10. The automobile automatic painting system according to claim 8, characterized in that: The step of improving the red-billed blue magpie algorithm is to initialize the population by Sin chaotic mapping in step (1). The initial population generated by Sin chaotic mapping fills the entire solution space, which is beneficial to the global search in the early stage. The specific improvement method is as follows: x n+1 =μsin(πx n )0≤x n ≤1 In the formula, x represents the iteration value, and μ is a random number in [0,1].
