Rearview mirror paint baking system and working method

Abstract

The invention discloses a rearview mirror paint baking system and a working method thereof. A transmission mechanism is sequentially connected with a pretreatment mechanism, a spraying mechanism, a drying mechanism, a data acquisition mechanism, a quality prediction mechanism and a control feedback mechanism. The preprocessing mechanism is responsible for preprocessing the surface of the rearview mirror. The spraying mechanism completes spraying by controlling the spraying angle, the spraying speed and the coating amount, the drying mechanism is used for heating the rearview mirror, and it is ensured that a coating is evenly cured. The data acquisition mechanism acquires the thickness, glossiness and color uniformity of the coating in real time, generates an input vector, and transmits the input vector to the quality prediction mechanism based on the neural network for coating quality prediction. And the control feedback module compares a predicted value with an actual value, calculates an error, adjusts process parameters and optimizes the spraying quality. And the technological parameters are continuously adjusted in the circulating process until the set coating quality standard is reached, so that the coating thickness uniformity, the surface glossiness and the color uniformity are accurately controlled, and the coating quality of the rearview mirror is improved.

Description

Technical Field

[0001] The invention relates to the field of rearview mirror manufacturing, and in particular to a rearview mirror baking paint system and a working method. Background Art

[0002] In the process of automobile manufacturing, rearview mirrors need to go through multiple process flows such as pretreatment, spraying, and drying to ensure that their surfaces have good gloss and coating thickness. In the existing production process, the spraying process of rearview mirrors is mainly manual using simple mechanical spraying. During the spraying process, the angle, speed, and spray volume of the spray gun are usually manually adjusted by workers, so the spraying conditions cannot be accurately controlled, resulting in problems such as missing coating, sagging, and inconsistent film thickness on the coating of the rearview mirror. At the same time, the drying process cannot be accurately adjusted according to the specific shape of the rearview mirror and the coating thickness, which will lead to insufficient or over-curing of the coating, further affecting the adhesion and durability of the coating. Since the traditional method relies on the operating level of the workers and lacks real-time monitoring of quality parameters such as coating thickness and gloss, the defects in the process are not discovered until the final quality inspection process, resulting in rework and material waste. Therefore, in order to solve the above problems, a rearview mirror baking paint system and working method are needed. Summary of the invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides a rearview mirror baking paint system and a working method.

[0004] Among them, a specific technical solution of a rearview mirror painting system is as follows:

[0005] A rearview mirror painting system, characterized by:

[0006] It includes a transmission mechanism, along which a pretreatment mechanism, a spraying mechanism, a drying mechanism, a data collection mechanism, a quality prediction mechanism and a control feedback mechanism are sequentially distributed;

[0007] The data collection mechanism and the quality prediction mechanism are connected to the control feedback mechanism;

[0008] The pre-treatment mechanism is used to polish, degrease and remove dust from the rearview mirror;

[0009] The spraying mechanism is used to control the spraying angle, spraying speed and coating amount of the spray gun;

[0010] The drying mechanism is used to uniformly heat the sprayed rearview mirror to ensure uniform curing of the coating;

[0011] The data collection mechanism collects the coating thickness, glossiness and color parameters of the rearview mirror in real time;

[0012] The quality prediction mechanism is used to receive the parameters transmitted by the data acquisition mechanism to predict the coating quality;

[0013] The control feedback mechanism is used to analyze the error between the actual coating quality index and the predicted index, and adjust the process parameters based on the error size feedback to optimize the rearview mirror coating quality.

[0014] To better realize the present invention, it can be further:

[0015] The data acquisition mechanism includes a multispectral camera and a laser thickness gauge. The multispectral camera detects surface defects in the spraying process in real time, and the laser thickness gauge collects the coating thickness of the rearview mirror in real time.

[0016] Further:

[0017] The quality prediction mechanism includes a prediction model based on a neural network.

[0018] Further:

[0019] The pretreatment mechanism adopts an automatic spray cleaning machine, the spraying mechanism adopts a six-axis spraying robot, and the drying mechanism adopts an infrared curing furnace.

[0020] A specific technical solution of a working method of a rearview mirror baking paint system is:

[0021] A working method of a rearview mirror painting system, characterized in that:

[0022] S1: The transmission mechanism drives the rearview mirror to be processed by the pretreatment mechanism, the spraying mechanism, and the drying mechanism in sequence. The pretreatment mechanism pre-treats the rearview mirror, the spraying mechanism sprays the rearview mirror with a spray gun, and the drying mechanism is used to heat and cure the coating on the rearview mirror;

[0023] S2: The transmission mechanism transmits the rearview mirror into the collection area, and the data collection mechanism collects the coating thickness T, glossiness G and color uniformity C of the rearview mirror in real time to form an input vector X:

[0024] X=[TGC]

[0025] S3: the data acquisition mechanism transmits the input vector X to the quality prediction mechanism for predicting the coating quality of the rearview mirror;

[0026] S4: The quality prediction mechanism predicts the input vector X based on the neural network model f in the following manner:

[0027] Q = f(W, X)

[0028] Where Q is the predicted coating quality obtained by the neural network model f according to the current process parameters;

[0029] W is the weight matrix of the neural network;

[0030] X is the coating parameter matrix obtained by the data acquisition agency;

[0031] S5: The control feedback module receives the predicted value Q of the quality prediction mechanism, and compares the predicted value Q with the actual value Y detected by the data acquisition mechanism, and calculates the error e between the two using the following formula:

[0032] e=YQ

[0033] S6: The control feedback mechanism adjusts the process parameter P according to the error e to reduce the error and optimize the coating quality:

[0034] P′=P-αe

[0035] Among them, α is the parameter adjustment step, P is the process parameter, and P′ is the adjusted process parameter;

[0036] S7: the control feedback mechanism inputs the new process parameter P′ into the spraying mechanism, and transmits it to the quality prediction mechanism again to predict the new process parameter P′;

[0037] S8: Repeat S1 to S7 until the error between the optimized process parameters and the predicted value of the quality prediction structure is within a set range.

[0038] To better realize the present invention, it can be further:

[0039] The control feedback mechanism uses a rule-based control model to adjust control parameters according to the error value.

[0040] The beneficial effects of the present invention are as follows: the present invention realizes intelligent control of rearview mirror coating through efficient cooperation of pretreatment mechanism, spraying mechanism, drying mechanism, data collection mechanism, quality prediction mechanism and control feedback mechanism. The cleanliness and smoothness of the rearview mirror surface are ensured by the pretreatment mechanism, the spraying angle, speed and coating amount are accurately controlled by the spraying mechanism, the parameters of the rearview mirror coating are acquired in real time by the data collection mechanism, and the quality prediction mechanism accurately predicts the coating quality based on the collected coating parameters through the neural network model, which can identify possible problems in advance and effectively evaluate the coating quality. At the same time, the feedback mechanism compares the predicted value with the actual detection value, calculates the error and makes adjustments, ensuring that the process parameters can be dynamically adjusted according to the deviation in real-time production, thereby improving the accuracy in production. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is the overall block diagram of the present invention;

[0042] Figure 2 It is the work flow chart of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In the description of the present invention, it should be noted that the terms "vertical", "upper", "lower", "horizontal", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention. In addition, "first", "second", "third", and "fourth" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0045] like Figure 1 As shown:

[0046] A specific technical solution of a rearview mirror painting system is as follows:

[0047] Among them, a specific technical solution of a rearview mirror painting system is as follows:

[0048] A rearview mirror paint baking system comprises a transmission mechanism, along which a pretreatment mechanism, a spraying mechanism, a drying mechanism, a data collection mechanism, a quality prediction mechanism and a control feedback mechanism are sequentially distributed, wherein the data collection mechanism and the quality prediction mechanism are connected to the control feedback mechanism.

[0049] The pretreatment mechanism adopts an automated spray cleaning machine, which is used to polish, degrease and remove dust from the rearview mirror. The spraying mechanism adopts a six-axis spraying robot, which is used to control the spraying angle, spraying speed and coating amount of the spray gun. The drying mechanism adopts an infrared curing furnace, which is used to uniformly heat the sprayed rearview mirror to ensure uniform curing of the coating. The data acquisition mechanism collects the coating thickness, glossiness and color parameters of the rearview mirror in real time.

[0050] The quality prediction mechanism is used to receive the parameters transmitted by the data acquisition mechanism to predict the coating quality, wherein the quality prediction mechanism includes a prediction model based on a neural network, the neural network model uses a multi-layer feedforward neural network, uses ReLU as an activation function, and the neural network model uses a back propagation algorithm to update parameters.

[0051] The data acquisition mechanism includes a multispectral camera and a laser thickness gauge. The multispectral camera detects surface defects in the spraying process in real time, and the laser thickness gauge collects the coating thickness of the rearview mirror in real time.

[0052] The control feedback mechanism is used to analyze the error between the actual coating quality index and the predicted index, and adjust the process parameters based on the error size feedback to optimize the rearview mirror coating quality.

[0053] like Figure 2 As shown, a specific technical solution of a working method of a rearview mirror painting system is:

[0054] A working method of a rearview mirror painting system comprises the following steps:

[0055] S1: The transmission mechanism drives the rearview mirror to be processed by the pretreatment mechanism, the spraying mechanism, and the drying mechanism in sequence. The pretreatment mechanism pre-treats the rearview mirror, the spraying mechanism sprays the rearview mirror with a spray gun, and the drying mechanism is used to heat and cure the coating on the rearview mirror;

[0056] S2: The transmission mechanism transmits the rearview mirror into the collection area, and the data collection mechanism collects the coating thickness T, glossiness G and color uniformity C of the rearview mirror in real time to form an input vector X:

[0057] X=[TGC]

[0058] S3: the data acquisition mechanism transmits the input vector X to the quality prediction mechanism for predicting the coating quality of the rearview mirror;

[0059] S4: The quality prediction mechanism predicts the input vector X based on the neural network model f in the following manner:

[0060] Q=f(W,X)

[0061] Where Q is the predicted coating quality obtained by the neural network model f according to the current process parameters;

[0062] W is the weight matrix of the neural network;

[0063] X is the coating parameter matrix obtained by the data acquisition agency;

[0064] S5: The control feedback module receives the predicted value Q of the quality prediction mechanism, and the control feedback module compares the predicted value Q with the actual value Y detected by the data acquisition mechanism, and calculates the error e between the two in the following way:

[0065] e=YQ

[0066] S6: The control feedback mechanism adjusts the process parameter P according to the error e to reduce the error and optimize the coating quality. Specifically, the control feedback mechanism uses a rule-based control model to adjust the control parameter according to the error value.

[0067] P′=P-αe

[0068] Among them, α is the parameter adjustment step, P is the process parameter, and P′ is the adjusted process parameter;

[0069] S7: the control feedback mechanism inputs the new process parameter P′ into the spraying mechanism, and transmits it to the quality prediction mechanism again to predict the new process parameter P′;

[0070] S8: Repeat S1 to S7 until the error between the optimized process parameters and the predicted value of the quality prediction structure is within a set range.

[0071] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0072] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A rearview mirror paint system, characterized in that: It includes a transmission mechanism, along which a pretreatment mechanism, a spraying mechanism, a drying mechanism, a data collection mechanism, a quality prediction mechanism and a control feedback mechanism are sequentially distributed; The data collection mechanism and the quality prediction mechanism are connected to the control feedback mechanism; The pre-treatment mechanism is used to polish, degrease and remove dust from the rearview mirror; The spraying mechanism is used to control the spraying angle, spraying speed and coating amount of the spray gun; The drying mechanism is used to uniformly heat the sprayed rearview mirror to ensure uniform curing of the coating; The data collection mechanism collects the coating thickness, glossiness and color parameters of the rearview mirror in real time; The quality prediction mechanism is used to receive the parameters transmitted by the data acquisition mechanism to predict the coating quality; The control feedback mechanism is used to analyze the error between the actual coating quality index and the predicted index, and adjust the process parameters based on the error size feedback to optimize the rearview mirror coating quality.

2. A rearview mirror painting system according to claim 1, characterized in that: The data acquisition mechanism includes a multispectral camera and a laser thickness gauge. The multispectral camera detects surface defects in the spraying process in real time, and the laser thickness gauge collects the coating thickness of the rearview mirror in real time.

3. A rearview mirror painting system according to claim 2, characterized in that: The quality prediction mechanism includes a prediction model based on a neural network.

4. A rearview mirror painting system according to claim 3, characterized in that: The pretreatment mechanism adopts an automatic spray cleaning machine, the spraying mechanism adopts a six-axis spraying robot, and the drying mechanism adopts an infrared curing furnace.

5. A working method of a rearview mirror painting system according to claim 4, characterized in that: The steps include: S1: The transmission mechanism drives the rearview mirror to be processed by the pretreatment mechanism, the spraying mechanism, and the drying mechanism in sequence. The pretreatment mechanism pre-treats the rearview mirror, the spraying mechanism sprays the rearview mirror with a spray gun, and the drying mechanism is used to heat and cure the coating on the rearview mirror; S2: The transmission mechanism transmits the rearview mirror into the collection area, and the data collection mechanism collects the coating thickness T, glossiness G and color uniformity C of the rearview mirror in real time to form an input vector X: X=[TGC] S3: the data acquisition mechanism transmits the input vector X to the quality prediction mechanism for predicting the coating quality of the rearview mirror; S4: The quality prediction mechanism predicts the input vector X based on the neural network model f in the following manner: Q=f(W,X) Where Q is the predicted coating quality obtained by the neural network model f according to the current process parameters; W is the weight matrix of the neural network; X is the coating parameter matrix obtained by the data acquisition agency; S5: The control feedback module receives the predicted value Q of the quality prediction mechanism, and compares the predicted value Q with the actual value Y detected by the data acquisition mechanism, and calculates the error e between the two using the following formula: e=YQ S6: The control feedback mechanism adjusts the process parameter P according to the error e to reduce the error and optimize the coating quality: P′=P-αe Among them, α is the parameter adjustment step, P is the process parameter, and P′ is the adjusted process parameter; S7: the control feedback mechanism inputs the new process parameter P′ into the spraying mechanism, and transmits it to the quality prediction mechanism again to predict the new process parameter P′; S8: Repeat S1 to S7 until the error between the optimized process parameters and the predicted value of the quality prediction structure is within a set range.

6. A working method of a rearview mirror painting system according to claim 5, characterized in that: The control feedback mechanism uses a rule-based control model to adjust control parameters according to the error value.

Images