Method and device for controlling a coating operation

Abstract

The application discloses a coating operation control method and device. The method comprises the following steps: obtaining a first value range of at least one first parameter; wherein the first value range can make a coating task performed by a coating device according to the first value range satisfy at least one optimization condition, and the first parameter comprises a coating operation parameter associated with the task optimization condition; obtaining a second value range of at least one second parameter according to the first value range; wherein the first value range and the second value range can make the coating task satisfy the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition; and controlling the coating device to perform the coating task according to the first value range and the second value range.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coating operation, in particular to a control method and device of coating operation. BACKGROUND

[0002] In the process of coating operation on the device shell, the setting of various operation parameters of the coating operation is specified according to the standard requirements. For example, the swing of the paint, the stirring time, the room temperature, the spray gun pressure, the angle, the baking time, the baking temperature, etc.

[0003] At present, the operation parameters of the coating operation process can be adjusted to achieve the optimization target. For example, by adjusting the paint mixing ratio, increasing the mixing paint stirring time, reducing the pre-opening swing and single paint stirring time after opening the barrel, the optimization target of ensuring energy saving can be achieved.

[0004] However, while achieving the optimization target, the coating operation quality may be affected, and the adhesion of the coating may be reduced. SUMMARY

[0005] Therefore, the present application provides a control method and device of coating operation as follows:

[0006] A control method of coating operation, comprising:

[0007] obtaining a first value range of at least one first parameter; wherein the first value range can make the coating task performed by the coating device according to the first value range meet at least one optimization condition, and the first parameter includes a coating operation parameter associated with the task optimization condition;

[0008] obtaining a second value range of at least one second parameter according to the first value range; wherein the first value range and the second value range can make the coating task meet the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition;

[0009] controlling the coating device to perform the coating task according to the first value range and the second value range.

[0010] The above method, preferably, the first value range corresponds to a parameter extreme value, and the parameter extreme value can make the coating task meet the optimization extreme value in the task optimization condition;

[0011] wherein the obtaining a second value range of at least one second parameter according to the first value range comprises:

[0012] According to the parameter extreme value corresponding to the first value range, all parameter values of the second parameter are traversed by using the quality model to obtain a second value range of the second parameter, and the parameter value in the second value range and the parameter extreme value corresponding to the first value range make the target quality parameter output by the quality model satisfy the task quality condition.

[0013] The quality model is used to output a predicted quality parameter for the first parameter and the second parameter, and the predicted quality parameter represents the quality of the coating task.

[0014] The above method preferably comprises the following steps of:

[0015] According to the parameter extreme value corresponding to the first value range and the initial parameter value of the second parameter, a target quality parameter is obtained by using the quality model.

[0016] In the case where the target quality parameter satisfies the task quality condition, the initial parameter value of the second parameter is added to the second value range of the second parameter.

[0017] The initial parameter value of the second parameter is adjusted, and the following steps are executed until all parameter values of the second parameter are processed by the quality model: according to the parameter extreme value corresponding to the first value range and the initial parameter value of the second parameter, a target quality parameter is obtained by using the quality model.

[0018] The above method preferably comprises the following steps of adjusting the initial parameter value of the second parameter:

[0019] According to the relationship between the target quality parameter and the parameter threshold in the task quality condition, the initial parameter value of the second parameter is increased or the initial parameter value of the second parameter is decreased.

[0020] The above method preferably comprises the following steps of obtaining the second value range of at least one second parameter according to the first value range:

[0021] According to the parameter extreme value corresponding to the first value range, all parameter values of the second parameter are traversed by using the quality model to obtain a second value range of the second parameter, and the parameter value in the second value range and the parameter extreme value corresponding to the first value range make the target quality parameter output by the quality model satisfy the task quality condition.

[0022] The quality model is used to output a predicted quality parameter for the first parameter and the second parameter, and the predicted quality parameter represents the quality of the coating task.

[0023] The method preferably uses a quality model to traverse parameter values in the first value range and all parameter values of the second parameter to obtain a second value range of the second parameter, including:

[0024] For each first initial value in the first value range, the quality model is used to obtain a target quality parameter according to the first initial value and a second initial value of the second parameter;

[0025] If the target quality parameter meets the task quality condition, the second initial value is added to the second value range of the second parameter;

[0026] The second initial value of the second parameter is adjusted, and the method of using the quality model to obtain the target quality parameter according to the first initial value and the second initial value of the second parameter is executed until all parameter values of the second parameter are processed by the quality model.

[0027] The method preferably uses a quality model trained by a training sample; the training sample contains input parameters and output parameters, the input parameters include sample values of the first parameter and sample values of the second parameter, and the output parameters include quality label values.

[0028] The input parameters are obtained by collecting historical data of the coating device, and the input parameters include Boolean variable type parameters and dummy variable type parameters.

[0029] Before the quality model is trained using the input parameters and the output parameters, the method further includes:

[0030] The dummy variable type parameters in the input parameters are converted into Boolean variable type parameters.

[0031] The target quality parameter can represent the adhesion degree of the coating material, and the target quality parameter meets the task quality condition, including:

[0032] The parameter value of the target quality parameter is greater than or equal to a preset adhesion threshold.

[0033] A coating operation control device, including:

[0034] A first obtaining unit is configured to obtain a first value range of at least one first parameter; wherein the first value range can make a coating task performed by a coating device according to the first value range meet at least one optimization condition, and the first parameter includes a coating operation parameter associated with the task optimization condition;

[0035] a second obtaining unit configured to obtain a second value range of at least one second parameter according to the first value range, wherein the first value range and the second value range can enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition;

[0036] a device control unit configured to control the coating device to perform the coating task according to the first value range and the second value range.

[0037] As can be seen from the above technical solution, in the coating operation control method and device disclosed in the present application, first, a first value range of at least one first parameter is obtained, the first value range can enable the coating task performed by the coating device according to the first value range to satisfy at least one optimization condition, the first parameter includes a coating operation parameter associated with the task optimization condition, then, a second value range of at least one second parameter is obtained according to the first value range, the first value range and the second value range can enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition; based on this, the coating device is controlled to perform the coating task according to the first value range and the second value range. As can be seen, in the present application, the value range of the coating operation parameter satisfying the optimization condition is used to screen the value range of the second parameter satisfying the optimization condition and the quality condition, so that the coating task performed by the coating device can satisfy both the optimization condition and the quality condition, thereby avoiding the case that the adhesion of the coating is low, and thus improving the coating quality of the coating task. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0039] Figure 1 a flowchart of a coating operation control method provided by Embodiment One of the present application;

[0040] Figure 2 and Figure 3 are partial flowcharts of a coating operation control method provided by Embodiment One of the present application, respectively;

[0041] Figure 4 is a structural schematic diagram of a coating operation control device provided by Embodiment Two of the present application;

[0042] Figure 5 Another structural schematic diagram of a coating operation control device provided for Embodiment Two of the present application;

[0043] Figure 6 A structural schematic diagram of an electronic device provided for Embodiment Three of the present application;

[0044] Figure 7 An example flowchart for obtaining a parameter value range in a paint spraying operation scenario applicable to the present application. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0046] REFERENCE Figure 1 An implementation flowchart of a coating operation control method provided for Embodiment One of the present application is shown, which can be applicable to an electronic device capable of data processing, such as a computer or a server, etc. The technical solution in the present embodiment is mainly used to improve the coating quality of a coating task and avoid the case of low paint adhesion.

[0047] Specifically, the method in the present embodiment can include the following steps:

[0048] Step 101: Obtain a first value range of at least one first parameter, which can enable a coating task performed by a coating device according to the first value range to satisfy at least one optimization condition.

[0049] The first parameter includes a coating operation parameter associated with a task optimization condition. Taking a paint spraying operation performed by a spray gun as an example, the coating operation parameter can include any one or any multiple of the following: baking temperature, baking duration, pre-opening bucket swing duration, post-opening bucket stirring duration, post-mixing stirring duration, paint mixing ratio, spray gun speed, and spray gun pressure.

[0050] Specifically, the optimization condition is a condition corresponding to an optimization item, and the optimization item can be any one or any multiple of the following: energy saving, high efficiency, and cost saving. For example, the optimization condition can include any one or any multiple of the following:

[0051] The energy consumption of the coating operation is less than or equal to an energy consumption threshold value;

[0052] The coating time of the coating operation is less than or equal to an efficiency threshold value, i.e., the coating efficiency is higher than the coating efficiency realized by other parameters;

[0053] The cost value of the coating operation is less than or equal to a cost threshold, and the cost value can include cost values caused by labor consumption and equipment wear and tear.

[0054] It should be noted that in the embodiment, the parameter value in the first value range also causes the coating task to meet at least one task quality inspection condition.

[0055] The task quality inspection condition is a condition corresponding to a quality inspection item, and the quality inspection item can be any one or any multiple of gloss, film thickness, hardness, and wear resistance. For example, the task quality inspection condition can include any one or any multiple of the following:

[0056] The gloss is greater than or equal to a preset gloss threshold;

[0057] The film thickness is in a preset thickness range;

[0058] The wear resistance value is greater than or equal to a preset wear resistance threshold.

[0059] Specifically, in the embodiment, the first value range of at least one first parameter can be obtained in the following manner:

[0060] First, according to the above coating operation parameters, historical data is collected, the historical data includes coating operation parameters and corresponding quality inspection results, and an optimization item is set;

[0061] Then, the relationship between the coating operation parameters and the quality inspection results is analyzed. Specifically, the coating operation parameters and the quality inspection results can be subjected to a Cartesian product operation, and then each group of independent variables (coating operation data) and dependent variables (quality inspection results) of the result of the Cartesian product operation is subjected to a degree of association analysis, that is, the coating operation parameters that affect each quality inspection result are analyzed.

[0062] After that, data modeling is performed on the quality inspection results and the set of coating operation parameters that affect the quality inspection results, that is, a mathematical model is used to establish a calculation relationship between the quality inspection results and the coating operation.

[0063] Finally, an optimization objective function about the above optimization item is created in combination with the above mathematical model, based on which, with the quality inspection results as the premise and the optimization item as the target, the range and the extreme value in the range of each variable (i.e., the coating operation parameter) in the optimization objective function are solved, that is, the first value range of the first parameter and the parameter extreme value in the first value range, and the parameter extreme value causes the optimization objective to be optimal.

[0064] Step 102: According to the first value range, a second value range of at least one second parameter is obtained, and the first value range and the second value range can cause the coating task to meet the task optimization condition and at least one task quality condition.

[0065] The second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition. For example, the second parameter can have parameters such as whether the substrate is clean, whether the substrate is smooth, paint placement time, spray gun route, spray gun nozzle distance, etc. The first parameter and the second parameter form a parameter combination that simultaneously affects the task quality inspection and the task quality. Based on this, in this embodiment, the second value range of each second parameter is obtained based on the obtained first value range, so that the task optimization condition and the task quality condition are simultaneously satisfied.

[0066] It should be noted that the first value range and the second value range can make the coating task satisfy the task optimization condition and at least one task quality condition, that is, any parameter value in the first value range of each first parameter has a parameter value in the second value range of each second parameter to form a parameter combination, and the parameter combination can make the coating task satisfy the task optimization condition and the task quality condition. Or, any parameter value in the second value range of each second parameter has a parameter value in the first value range of each first parameter to form a parameter combination, and the parameter combination can make the coating task satisfy the task optimization condition and the task quality condition.

[0067] The task quality condition includes that a quality parameter representing the quality of the coating task is in a preset quality range. For example, the adhesion value representing the adhesion degree of the coating task is greater than or equal to the adhesion threshold value. Taking a paint spraying task as an example, the task quality condition can be that the adhesion value of the paint is high, that is, greater than or equal to the adhesion threshold value.

[0068] Step 103: controlling the coating device to perform the coating task according to the first value range and the second value range.

[0069] Specifically, in this embodiment, a parameter value can be selected in the first value range of each first parameter and a parameter value can be selected in the second value range of each second parameter to form a parameter combination, and then the coating device is controlled to perform the coating task according to each parameter value in the parameter combination.

[0070] Taking a paint spraying task as an example, in this embodiment, after the first value range of each paint spraying operation parameter and the second value range of each adhesion influence parameter are screened out, a parameter value is selected in each first value range and second value range to form a parameter combination, and the paint spraying device is controlled to perform the paint spraying task according to the parameter combination. The paint spraying task meets the task optimization condition and the task quality condition on the premise of meeting the task quality inspection condition, that is, on the premise of ensuring the gloss, film thickness, hardness and wear resistance of the paint spraying, the optimization target of energy saving, efficiency improvement and cost saving is realized, and the paint spraying adhesion is improved.

[0071] It can be seen from the technical solution that the method for controlling coating operation provided by the embodiment one of the application first obtains a first value range of at least one first parameter, the first value range can enable the coating task performed by the coating device according to the first value range to meet at least one optimization condition, the first parameter includes a coating operation parameter associated with the task optimization condition, then, according to the first value range, a second value range of at least one second parameter is obtained, the first value range and the second value range can enable the coating task to meet the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition; based on this, the coating device is controlled to perform the coating task according to the first value range and the second value range. It can be seen that in the embodiment, the value range of the second parameter meeting the optimization condition and the quality condition is screened according to the value range of the coating operation parameter meeting the optimization condition, so that the coating task performed by the coating device can meet the optimization condition and the quality condition, avoiding the case that the adhesion of the coating is low, thereby improving the adhesion of the coating.

[0072] In an implementation manner, the first value range of each first parameter corresponds to a parameter extreme value, and the parameter extreme value can enable the coating task to meet the optimization extreme value in the task optimization condition. For example, taking a paint spraying task as an example, in the first value range of each paint spraying operation parameter, there is a parameter extreme value enabling the energy consumption to reach the lowest, the cost to be the lowest and the efficiency to be the highest.

[0073] Based on the above implementation, when the second value range of at least one second parameter is obtained according to the first value range in step 102, the following manner can be used to implement:

[0074] Using a quality model, all parameter values of the second parameter are traversed according to the parameter extreme value corresponding to the first value range, so as to obtain the second value range of the second parameter.

[0075] Among them, the parameter value in the second value range and the parameter extreme value corresponding to the first value range enable the target quality parameter output by the quality model to meet the task quality condition. The quality model is used to output a predicted quality parameter with respect to the first parameter and the second parameter, and the predicted quality parameter represents the quality of the coating task.

[0076] Specifically, the quality model can be a mathematical model constructed in advance with the first parameter and the second parameter as independent variables and with the quality parameter as dependent variable, such as a multiple cloud regression equation. In the embodiment, the parameter extreme value corresponding to the first value range and the parameter value in the second value range are input into the quality model, and the quality model can output the target quality parameter meeting the task quality condition.

[0077] Specifically, the target quality parameter satisfies the task quality condition, which can be that the target quality parameter is greater than or equal to a parameter threshold in the task quality condition.

[0078] For example, the target quality parameter is a parameter capable of representing the degree of adhesion of the coating material, and the target quality parameter satisfies the task quality condition, specifically, the parameter value of the target quality parameter is greater than or equal to a preset adhesion threshold.

[0079] Specifically, in step 102, when the quality model is utilized to traverse all parameter values of the second parameter according to the parameter extreme value corresponding to the first value range, the second value range of the second parameter can be obtained by the following manner, as shown in the following formula (1): Figure 2

[0080] Step 201: Utilizing the quality model, obtaining the target quality parameter according to the parameter extreme value corresponding to the first value range and the initial parameter value of the second parameter.

[0081] For example, the parameter extreme value corresponding to the first value range of each first parameter and the initial parameter value of the second parameter are input into the quality model, and the target quality parameter output by the quality model is obtained.

[0082] Step 202: judging whether the target quality parameter satisfies the task instruction condition, in the case that the target quality parameter satisfies the task quality condition, executing step 203, and in the case that the target quality parameter does not satisfy the task quality condition, executing step 204.

[0083] Step 203: adding the initial parameter value of the second parameter to the second value range of the second parameter, and executing step 204.

[0084] Step 204: adjusting the initial parameter value of the second parameter, and returning to execute step 201 to utilize the quality model to obtain the target quality parameter according to the parameter extreme value corresponding to the first value range and the adjusted initial parameter value of the second parameter, until all parameter values of the second parameter are processed by the quality model, and the current process is ended, that is, the traversal of all parameter values of the second parameter is ended.

[0085] Specifically, in step 204, when the initial parameter value of the second parameter is adjusted, the following manner can be used to achieve it:

[0086] According to the relationship between the target quality parameter and the parameter threshold in the task quality condition, the initial parameter value of the second parameter is increased, or the initial parameter value of the second parameter is decreased, or the second parameter is switched from the current initial parameter value to other initial parameter value.

[0087] ​For example, the initial parameter value of the second parameter can be increased when the parameter value of the target quality parameter is less than the parameter threshold in the task quality condition; for another example, the initial parameter value of the second parameter can be decreased when the parameter value of the target quality parameter is greater than the parameter threshold in the task quality condition; for another example, the initial parameter value of the second parameter can be switched from 0 to 1 or from 1 to 0 when the parameter value of the target quality parameter is less than the parameter threshold in the task quality condition.

[0088] For example, in the case that the parameter value of the target quality parameter representing the adhesion degree of the coating task is less than the adhesion threshold in the task quality condition, the paint standing time is increased; in the case that the parameter value of the target quality parameter is less than the adhesion threshold, the nozzle distance is decreased; in the case that the parameter value of the target quality parameter is less than the adhesion threshold, the parameter value of whether the substrate is clean is switched from 0 (representing that the substrate is not clean) to 1 (representing that the substrate is clean), and the like.

[0089] In an implementation manner, in the step 102, the second value range of the at least one second parameter is obtained according to the first value range, which can be implemented in the following manner:

[0090] The parameter value in the second value range and the parameter value in the first value range are such that the target quality parameter output by the quality model satisfies the task quality condition. The quality model is used to output a predicted quality parameter for the first parameter and the second parameter, and the predicted quality parameter represents the quality of the coating task.

[0091] The parameter value in the second value range and the parameter value in the first value range are such that the target quality parameter output by the quality model satisfies the task quality condition. The quality model is used to output a predicted quality parameter for the first parameter and the second parameter, and the predicted quality parameter represents the quality of the coating task.

[0092] Specifically, the quality model can be a mathematical model constructed in advance with the first parameter and the second parameter as independent variables and the quality parameter as dependent variable, such as a multiple cloud regression equation. In this embodiment, the parameter value in the first value range and the parameter value in the second value range are input into the quality model, and the quality model can output the target quality parameter satisfying the task quality condition.

[0093] Specifically, the target quality parameter satisfying the task quality condition can be that the target quality parameter is greater than or equal to the parameter threshold in the task quality condition.

[0094] For example, the target quality parameter is a parameter capable of representing the adhesion degree of the coating material, and the target quality parameter satisfies the task quality condition, specifically, the parameter value of the target quality parameter is greater than or equal to a preset adhesion threshold.

[0095] Specifically, in step 102, when the quality model is used to traverse the parameter values in the first value range and all parameter values of the second parameter to obtain the second value range of the second parameter, each first initial value in the first value range of each first parameter can be traversed to obtain the second value range of the second parameter. Specifically, the traversal can be achieved by the following method, as shown in the following formula: Figure 3

[0096] Step 301: selecting a parameter value in the first value range as a first initial value;

[0097] Step 302: using the quality model to obtain a target quality parameter according to the first initial value and a second initial value of the second parameter.

[0098] In the embodiment, the first initial value and the second initial value are used to distinguish the parameter values of the first parameter and the parameter values of the second parameter in sequence.

[0099] Step 303: determining whether the target quality parameter meets a task quality condition, and executing step 304 when the target quality parameter meets the task quality condition, and executing step 305 when the target quality parameter does not meet the task quality condition.

[0100] Step 304: adding the second initial value to the second value range of the second parameter, and executing step 305;

[0101] Step 305: adjusting the second initial value of the second parameter, returning to execute step 302 to use the quality model to obtain a target quality parameter according to the first initial value and the adjusted second initial value of the second parameter, until all parameter values of the second parameter are processed by the quality model, that is, the traversal of all parameter values of the second parameter is completed for the currently selected first initial value, at this time, step 306 is executed.

[0102] Step 306: selecting a next parameter value in the first value range as a first initial value, returning to execute step 302 to use the quality model to re-traverse all parameter values of the second parameter according to the re-selected first initial value, until all parameter values in the first value range are selected, ending the current process, that is, the traversal of all parameter values of the second parameter is completed for all parameter values in the first value range, at this time, the second value range is obtained.

[0103] Based on this, each parameter value in the first value range of each first parameter has a parameter combination composed of parameter values in the second value range of the second parameter, so that the coating task meets the task quality condition, the task optimization condition and the task quality condition.​

[0104] Based on the above implementation, the quality model in the embodiment is trained by a training sample; the training sample contains input parameters and output parameters, the input parameters include sample values of the first parameter and sample values of the second parameter, and the output parameters include quality label values.

[0105] Based on this, the training of the quality model by multiple sets of input parameters and output parameters optimizes the model parameters in the quality model, so that the quality model can output the target quality parameter according to the parameter values of the first parameter and the second parameter.

[0106] For example, the quality model can be a mathematical model based on machine learning, such as a multiple regression equation. In the embodiment, the input parameters in the training sample are input into the quality model, the predicted quality parameter output by the quality model is compared with the quality label value in the output parameter, and the model parameters in the quality model are adjusted according to the comparison result, so that the predicted quality parameter output by the quality model meets the model convergence condition.

[0107] Specifically, the input parameters are obtained by collecting historical data of the coating equipment, and the input parameters include parameters of Boolean variable type and parameters of dummy variable type.

[0108] Before training the quality model using the input parameters and the output parameters, the parameters of dummy variable type in the input parameters can be converted into parameters of Boolean variable type in the embodiment.

[0109] For example, the input parameters include a parameter of whether the substrate is smooth, which is a parameter of dummy variable type. At this time, it is converted into a parameter of Boolean variable type. For example, the parameter of the smooth substrate is converted into 1, and the parameter of the non-smooth substrate is converted into 0, so as to facilitate model calculation.

[0110] Similarly, in the embodiment, the parameter values of dummy variable type can be converted into parameter values of Boolean variable type for the first parameter and the second parameter. The obtained parameter values in the first value range and the second value range are all parameter values of Boolean variable type.

[0111] Reference Figure 4 A structure schematic diagram of a coating operation control device provided by Embodiment Two of the application is provided, which can be configured in an electronic device capable of data processing, such as a computer or a server. The technical solution in the embodiment is mainly used to improve the coating quality of the coating task and avoid the case that the coating adhesion is low.

[0112] Specifically, the device in the embodiment can include the following units:

[0113] The first obtaining unit 401 is configured to obtain a first value range of at least one first parameter, wherein the first value range can enable a coating task performed by the coating device according to the first value range to satisfy at least one optimization condition, and the first parameter comprises a coating operation parameter associated with the task optimization condition;

[0114] The second obtaining unit 402 is configured to obtain a second value range of at least one second parameter according to the first value range, wherein the first value range and the second value range can enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition;

[0115] The device control unit 403 is configured to control the coating device to perform the coating task according to the first value range and the second value range.

[0116] As can be seen from the above technical solution, the control device for coating operation provided in Embodiment Two of the present application first obtains a first value range of at least one first parameter, the first value range can enable a coating task performed by the coating device according to the first value range to satisfy at least one optimization condition, the first parameter comprises a coating operation parameter associated with the task optimization condition, then, according to the first value range, a second value range of at least one second parameter is obtained, the first value range and the second value range can enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition; based on this, the coating device is controlled to perform the coating task according to the first value range and the second value range. As can be seen, in the present embodiment, the value range of the second parameter which satisfies both the optimization condition and the quality condition is screened according to the value range of the coating operation parameter which satisfies the optimization condition, and thus the coating task performed by the coating device can satisfy both the optimization condition and the quality condition, avoiding the situation that the adhesion of the coating is low, thereby improving the adhesion of the coating.

[0117] In an implementation manner, the first value range corresponds to a parameter extreme value, and the parameter extreme value can enable the coating task to satisfy an optimization extreme value in the task optimization condition;

[0118] The second obtaining unit 402 is specifically configured to: traverse all parameter values of the second parameter according to the parameter extreme value corresponding to the first value range by using a quality model, to obtain a second value range of the second parameter, wherein the parameter values in the second value range and the parameter extreme value corresponding to the first value range make the target quality parameter output by the quality model satisfy the task quality condition; and the quality model is used to output a predicted quality parameter for the first parameter and the second parameter, and the predicted quality parameter represents the quality of the coating task.

[0119] Specifically, the second obtaining unit 402 is configured to: obtain a target quality parameter according to the parameter extreme value corresponding to the first value range and an initial parameter value of the second parameter by using a quality model; in a case where the target quality parameter satisfies the task quality condition, add the initial parameter value of the second parameter to a second value range of the second parameter; adjust the initial parameter value of the second parameter, and return to execute the operation of obtaining the target quality parameter according to the parameter extreme value corresponding to the first value range and the initial parameter value of the second parameter by using the quality model, until all parameter values of the second parameter are processed by the quality model.

[0120] Preferably, the second obtaining unit 402 is specifically configured to: according to a relationship between the target quality parameter and a parameter threshold in the task quality condition, increase the initial parameter value of the second parameter, or decrease the initial parameter value of the second parameter, when adjusting the initial parameter value of the second parameter.

[0121] In an implementation manner, the second obtaining unit 402 is specifically configured to: traverse the parameter values in the first value range and all parameter values of the second parameter by using a quality model, to obtain a second value range of the second parameter, wherein the parameter values in the second value range and the parameter values in the first value range make the target quality parameter output by the quality model satisfy the task quality condition; and the quality model is used to output a predicted quality parameter for the first parameter and the second parameter, and the predicted quality parameter represents the quality of the coating task.

[0122] Specifically, the second obtaining unit 402 is configured to: for each first initial value in the first value range, obtain a target quality parameter according to the first initial value and a second initial value of the second parameter by using a quality model; in a case where the target quality parameter satisfies the task quality condition, add the second initial value to a second value range of the second parameter; adjust the second initial value of the second parameter, and return to execute the operation of obtaining the target quality parameter according to the first initial value and the second initial value of the second parameter by using the quality model, until all parameter values of the second parameter are processed by the quality model.

[0123] In an implementation manner, the apparatus in the embodiment can further include units as shown in the following: Figure 5

[0124] The model training unit 404 is configured to train the quality model by using training samples, wherein the training samples include input parameters and output parameters, the input parameters include sample values of the first parameters and sample values of the second parameters, and the output parameters include quality label values.

[0125] Preferably, the input parameters are obtained by collecting historical data of the coating device, and the input parameters include parameters of Boolean variable type and parameters of dummy variable type; before the quality model is trained by using the input parameters and the output parameters, the model training unit 404 is further configured to convert the parameters of dummy variable type in the input parameters into parameters of Boolean variable type.

[0126] In an implementation manner, the target quality parameter can represent the adhesion degree of the coating material, and the target quality parameter satisfies the task quality condition, including that a parameter value of the target quality parameter is greater than or equal to a preset adhesion threshold.

[0127] It should be noted that the specific implementation of each unit in the embodiment can refer to the corresponding content in the foregoing, which will not be described in detail here.

[0128] Reference Figure 6 is a structural schematic diagram of an electronic device provided by the embodiment three, and the electronic device can be an electronic device capable of data processing, such as a computer or a server. The technical solution in the embodiment is mainly used for improving the coating quality of the coating task and avoiding the case that the adhesion degree of the coating is low.

[0129] Specifically, the electronic device in the embodiment can include the following structure:

[0130] The memory 601 is configured to store computer programs and data generated by running of the computer programs.

[0131] ​The processor 602 is configured to execute a computer program to obtain a first value range of at least one first parameter, wherein the first value range can enable a coating task performed by the coating device according to the first value range to satisfy at least one optimization condition, and the first parameter comprises a coating operation parameter associated with the task optimization condition; obtain a second value range of at least one second parameter according to the first value range, wherein the first value range and the second value range can enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition; and control the coating device to perform the coating task according to the first value range and the second value range.

[0132] From the above technical solution, it can be seen that the electronic device provided by the embodiment three of the present application first obtains a first value range of at least one first parameter, the first value range can enable a coating task performed by the coating device according to the first value range to satisfy at least one optimization condition, the first parameter comprises a coating operation parameter associated with the task optimization condition, then, according to the first value range, a second value range of at least one second parameter is obtained, the first value range and the second value range can enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter is a coating operation parameter associated with the task quality condition, and the second parameter is a coating operation parameter not associated with the task optimization condition; based on this, the coating device is controlled to perform the coating task according to the first value range and the second value range. It can be seen that in the embodiment, the value range of the second parameter which satisfies the optimization condition and the quality condition is screened according to the value range of the coating operation parameter which satisfies the optimization condition, and thus the coating task performed by the coating device can satisfy the optimization condition and the quality condition, avoiding the situation that the adhesion of the coating is low, thereby improving the adhesion of the coating.

[0133] Taking a paint spraying operation for a notebook as an example, the technical solution of the present application is illustrated as follows:

[0134] In the process of painting the notebook shell, various parameters of the painting process are set according to the standard requirements (for example, the setting of factors such as paint swing, stirring time, room temperature, spray gun pressure, angle, baking time, baking temperature, etc.), and for different scenarios, if the painting operation is carried out according to fixed parameters, it may be contrary to a certain target (for example, efficiency, cost saving, energy saving). If this problem is solved, the parameters of the painting operation are usually adjusted through historical data, combined with a certain target, through a regression model or linear programming to balance the target and the painting operation parameters. For example: in the summer of 2022, due to the hot weather, the power consumption across the country has risen sharply, and during this period, the painting process operation parameters are adjusted, such as adjusting the paint mixing ratio, increasing the mixing time of mixed paint (main agent, curing agent, thinner) to reduce the pre-opening swing and single paint stirring time after opening the barrel, in order to achieve the goal of energy saving.

[0135] But in the implementation process, it will be found that this way will have some problems, while achieving the optimization target, some quality problems still exist. While meeting the optimization target, it is found that the adhesion of the final painting does not meet the standard, because the adhesion is not only affected by the painting operation process parameters, but also the film thickness and the spray gun route of the operation process, air humidity, temperature and other external factors have a great influence on the adhesion. Research shows that usually manufacturers basically improve the painting operation process, replace the curing agent, and even replace the substrate, and then detect it through destructive testing after painting is completed. Modification of the painting operation process may cause other quality problems, and replacement of the substrate will have a negative impact on the overall quality of the product and the composition of the supply chain.

[0136] Therefore, the technical solution of the present application is to calculate and adjust the parameters again after the general target optimization process, while achieving the normal optimization target, to ensure that the film adhesion meets the standard. Specifically, the technical solution of the present application mainly collects the entire painting process and the quality inspection result set, analyzes the relationship and range between the quality inspection dimension and the painting process technology related parameters. The painting parameters are associated with the optimization target. In actual operation, after setting the final optimization target (for example, the current energy saving target), the various parameters of the painting process can be automatically balanced to achieve the set optimization target while ensuring the painting quality, and finally the painting operation parameters are optimized according to the data analysis of the film adhesion to improve the film adhesion result. It can be seen that in the technical solution of the present application, the balance point of adhesion and other parameters is optimized through the improved algorithm to ensure that the optimization target and the quality detection are balanced and meet the standard.

[0137] The detailed implementation scheme for obtaining the parameter value range in the present application can refer to Figure 7 as shown, including the following process:

[0138] Step 1: Collect historical spray painting data sets, such as spray painting operation parameters and quality inspection test results, and list optimization targets.

[0139] Among them, the spray painting operation parameters include: baking temperature, baking time, pre-opening bucket swing time, post-opening bucket stirring time, post-mixing stirring time, paint mixing ratio, spray gun speed, spray gun pressure; The quality inspection test results include: gloss test results, film thickness, hardness, wear resistance test results. Correspondingly, the optimization targets include: energy saving, efficiency improvement, cost saving.

[0140] Step 2: Analyze the relationship between process data and quality test result data, for example, analyze the relationship between spray painting operation parameters and quality test result data.

[0141] The data column of the process (i.e. spray painting operation parameters) and the data column of the quality inspection test results are operated by Cartesian product, and then the degree of association analysis is performed on each group of independent variables (spray painting operation parameters) and dependent variables (quality inspection test results) of the Cartesian product result, thereby obtaining the factors that affect each quality inspection type, as shown in Table 1.

[0142] Table 1 Relationship between quality inspection types and influencing factors

[0143]

[0144]

[0145] Step 3: Make mathematical modeling on the set related to quality targets and process engineering, and establish a relationship model. For example, make data modeling on the set of quality inspection types and their related spray painting operation parameters to obtain the corresponding mathematical model, as shown in Table 2.

[0146] Table 2 Mathematical model

[0147]

[0148] Step 4: Find the extreme value of the optimization target function by synthesizing the modeling relationship.

[0149] According to the optimization target, create an optimization target function, find the range of each variable in the optimization target function, and find the extreme value.

[0150] Step 5: Optimize the final parameter extreme value to meet the adhesion requirement without affecting other quality indicators.

[0151] The operation steps are as follows:

[0152] Step 5.1: Collect historical data and adhesion results, such as collecting adhesion-affected condition data (i.e. the second parameter in the foregoing) and the result data of the final adhesion experiment. Based on this, the first parameter and the second parameter are collected as follows:

[0153] Film thickness, whether the substrate is clean, whether the substrate is smooth, paint placement time, spray gun route, speed, pressure, spray gun nozzle distance, etc.

[0154] Correspondingly, the adhesion test results can be detected by performing destructive operations on the substrate after spraying.

[0155] Step 5.2: Data processing obtains dataset 1. For example, dummy variables such as whether the substrate is clean, whether the substrate is smooth, and spray gun route are processed. For example, the whether clean column is expanded into clean and not clean, and then the corresponding column is filled with 1 and 0 (1: yes, 0: no); whether the substrate is smooth is also processed. The spray gun route is expanded into multiple columns, respectively, whether the vertical line overlaps, whether the horizontal line overlaps, and whether the vertical and horizontal lines alternate hash, and filled with 1 or 0. The transformed dataset 1 is obtained.

[0156] Step 5.3: Data permutation obtains transformed dataset 2. For example, the dataset 1 obtained in 5.2 is permuted with the corresponding data in the data obtained in 5.1 to obtain dataset 2.

[0157] Step 5.4: Obtain the innovation model. For example, the mathematical model of spraying is obtained according to the data in dataset 2, that is, the quality model in the foregoing.

[0158] Step 5.5: The actual parameters of the work and the extreme values are brought into the solution of the paint film adhesion. For example, the relevant extreme values obtained in step 4 are brought into the mathematical model of spraying obtained in step 5.4, and the adhesion result is calculated.

[0159] Step 5.6: The parameters and whether the adhesion meets the quality inspection requirements are comprehensively considered. If the adhesion result is greater than or equal to the adhesion threshold, it is ended, if it does not meet the requirements, step 5.7 is performed, that is, the values of other variables are adjusted within the extreme value range, so that the adhesion meets the quality inspection requirements.

[0160] It can be seen that after adopting the scheme of the present application, the following advantages are achieved:

[0161] Firstly, the present application can achieve the optimization targets of saving energy by 10%-15%, improving efficiency by 5%-10%, and reducing cost by 0.5%-1% under the premise of ensuring quality and without modifying the spraying operation process;

[0162] Secondly, the adjustment of the present application for different optimization targets will not cause the whole system to be affected by a single factor;

[0163] Thirdly, the present application balances the parameters after optimizing the parameters by using the method, so as to ensure that the final paint film adhesion meets the standards, which makes up for the shortcomings of the existing method.

[0164] In addition, the application can predict the final quality of paint spraying in advance by the process conditions of the non-occurred paint spraying operation, save manpower, material resources and financial resources, and reduce destructive experiments.

[0165] Finally, the application avoids pollution to the environment in the process of destroying the materials for destructive experiments, and is consistent with the current sustainable development strategy.

[0166] The various embodiments described in the specification are progressive in nature, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be mutually referred to. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part.

[0167] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of the two. In order to clearly show the interchangeability of hardware and software, the components and steps of the examples have been described in the above description. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0168] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art.

[0169] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling a coating job, comprising: obtaining a first value range of at least one first parameter, wherein the first value range enables a coating task performed by a coating device according to the first value range to satisfy at least one task optimization condition, the first parameter comprising a coating job parameter associated with the task optimization condition; obtaining a second value range of at least one second parameter according to the first value range, wherein the first value range and the second value range enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter being a coating job parameter associated with the task quality condition and the second parameter being a coating job parameter not associated with the task optimization condition; controlling the coating device to perform the coating task according to the first value range and the second value range; the first value range corresponding to a parameter extreme value, the parameter extreme value enabling the coating task to satisfy an optimization extreme value in the task optimization condition; wherein the obtaining the second value range of at least one second parameter according to the first value range comprises: iterating through all parameter values of the second parameter according to the parameter extreme value corresponding to the first value range by using a quality model to obtain the second value range of the second parameter, the parameter value in the second value range and the parameter extreme value corresponding to the first value range enabling a target quality parameter output by the quality model to satisfy the task quality condition; wherein the quality model is configured to output a predicted quality parameter with respect to the first parameter and the second parameter, the predicted quality parameter representing a quality of the coating task. 2.The method of claim 1, wherein the iterating through all parameter values of the second parameter according to the parameter extreme value corresponding to the first value range by using a quality model to obtain the second value range of the second parameter comprises: obtaining a target quality parameter according to the parameter extreme value corresponding to the first value range and an initial parameter value of the second parameter by using the quality model; in a case where the target quality parameter satisfies the task quality condition, adding the initial parameter value of the second parameter to the second value range of the second parameter; adjusting the initial parameter value of the second parameter, and returning to perform the obtaining the target quality parameter according to the parameter extreme value corresponding to the first value range and the initial parameter value of the second parameter by using the quality model until all parameter values of the second parameter are processed by the quality model. 3.The method of claim 2, wherein the adjusting the initial parameter value of the second parameter comprises: according to a relationship between the target quality parameter and a parameter threshold value in the task quality condition, increasing the initial parameter value of the second parameter, or decreasing the initial parameter value of the second parameter.

4. The method of claim 1, wherein the quality model is trained by training samples, and the training samples include input parameters and output parameters, and the input parameters include: the sample value of the first parameter and the sample value of the second parameter, the output parameter comprising a quality label value. 5.The method of claim 4, wherein the input parameter is obtained by collecting historical data of the coating device, and the input parameter comprises a parameter of a Boolean variable type and a parameter of a dummy variable type. wherein Before training the quality model using the input parameters and the output parameters, the method further comprises: converting a parameter of a dummy variable type in the input parameters into a parameter of a Boolean variable type.

6. The method of claim 1, the target quality parameter being capable of characterizing a degree of adhesion of a coating material, the target quality parameter satisfying the task quality condition, comprising: a parameter value of the target quality parameter being greater than or equal to a preset adhesion threshold.

7. A control device of a coating operation, comprising: a first obtaining unit configured to obtain a first value range of at least one first parameter, wherein the first value range enables a coating task performed by a coating device according to the first value range to satisfy at least one optimization condition, the first parameter comprising a coating operation parameter associated with the task optimization condition; a second obtaining unit configured to obtain a second value range of at least one second parameter according to the first value range, wherein the first value range and the second value range enable the coating task to satisfy the task optimization condition and at least one task quality condition, the second parameter being a coating operation parameter associated with the task quality condition and being a coating operation parameter not associated with the task optimization condition; a device control unit configured to control the coating device to perform the coating task according to the first value range and the second value range; the first value range corresponding to a parameter extreme value, the parameter extreme value enabling the coating task to satisfy an optimization extreme value in the task optimization condition; wherein the second obtaining unit is specifically configured to traverse all parameter values of the second parameter according to the parameter extreme value corresponding to the first value range to obtain the second value range of the second parameter by using a quality model, the parameter value in the second value range and the parameter extreme value corresponding to the first value range enabling a target quality parameter output by the quality model to satisfy the task quality condition; wherein the quality model is used to output a predicted quality parameter for the first parameter and the second parameter, the predicted quality parameter characterizing a quality of the coating task.

Images