Self-adaptive coating method and platform for electric sanitation tricycle

Abstract

The invention discloses a self-adaptive coating method and platform for an electric three-wheeled sanitation truck, and relates to the technical field of coating, and the method comprises the steps: dividing a to-be-coated electric three-wheeled sanitation truck into a plurality of coating areas, and extracting the related information of each area; the material, the surface state and the predicted coating environment data of each area are collected, and a coating scene matrix is formed; performing multi-layer coating parameter decision by combining the expected coating result of each area and the scene matrix, and establishing a coating decision space; the decision space is optimized based on the coating prediction evaluation channel, a coating candidate decision space is generated, and an optimization result is maximized through fitness calculation; the optimization result is applied to the whole coating strategy, and accurate coating of the electric sanitation tricycle is achieved. The technical problems that an existing electric sanitation tricycle is low in coating control precision and poor in coating adaptability are solved, and the technical effect of improving the coating precision and adaptability is achieved.

Description

Technical Field

[0001] The present application relates to the field of coating technology, and in particular to an adaptive coating method and platform for an electric three-wheeled sanitation vehicle. Background Art

[0002] Electric three-wheeled sanitation vehicles are widely used in public service fields such as urban cleaning. Their exterior coating not only needs to meet the requirements of beauty and durability, but also needs to have anti-fouling and anti-corrosion properties. However, traditional coating technology has problems such as uneven coating effect, low coating accuracy and poor control adaptability. In particular, it is difficult to make intelligent adjustments according to the characteristics of different regions and materials during the coating process, resulting in unstable coating quality and a large waste of resources and time. Although the existing automated control methods have improved the coating efficiency to a certain extent, they still cannot achieve precise control of multi-layer coating, and it is difficult to meet the high-precision and high-adaptability requirements of the electric three-wheeled sanitation vehicle coating process. Therefore, how to improve the coating control accuracy and adaptability, reduce resource waste, and improve the coating effect has become a key issue that needs to be urgently solved in current coating technology.

[0003] In the current relevant technologies, there are technical problems such as low painting control accuracy and poor painting adaptability of electric three-wheeled sanitation vehicles. Summary of the invention

[0004] The present application solves the technical problems of low painting control accuracy and poor painting adaptability of existing electric three-wheeled sanitation vehicles by providing an adaptive painting method and platform for electric three-wheeled sanitation vehicles.

[0005] The present application provides an adaptive painting method for an electric three-wheeled sanitation vehicle, comprising: The electric three-wheeled sanitation vehicles to be painted are divided into E electric vehicle painting areas, and the e-th electric vehicle painting area is extracted according to the E electric vehicle painting areas, wherein e and E are both positive integers, 1≤e≤E; the material shape, surface state and predicted painting environment information of the e-th electric vehicle painting area are collected to obtain the e-th area painting scene matrix; the expected painting result of the e-th area corresponding to the e-th electric vehicle painting area is obtained, and the multi-layer painting parameter collaborative decision is made for the e-th electric vehicle painting area in combination with the e-th area painting scene matrix, and a painting collaborative decision is established. The same decision-making first space; based on the painting scene matrix of the e-th area and the expected painting result of the e-th area, the painting evaluation constraint optimization is performed on the first painting collaborative decision space according to the painting prediction evaluation channel to generate a painting candidate decision space; according to the painting fitness calculation channel, the painting candidate decision space is optimized for maximizing the painting fitness to obtain the painting optimization result of the e-th area; the painting optimization result of the e-th area is added to the electric vehicle painting optimization strategy, and the electric three-wheeled sanitation vehicle to be painted is painted according to the electric vehicle painting optimization strategy.

[0006] This application also provides an adaptive painting platform for electric three-wheeled sanitation vehicles, including: A painting area acquisition module, the painting area acquisition module is used to divide the electric three-wheeled sanitation vehicle to be painted, obtain E electric vehicle painting areas, and extract the e-th electric vehicle painting area based on the E electric vehicle painting areas, wherein e and E are both positive integers, 1≤e≤E; a painting scene matrix acquisition module, the painting scene matrix acquisition module is used to collect the material shape, surface state and predicted painting environment information of the e-th electric vehicle painting area, and obtain the e-th area painting scene matrix; a painting result acquisition module, the painting result acquisition module is used to obtain the e-th area expected painting result corresponding to the e-th electric vehicle painting area, and perform multi-layer painting parameter collaborative decision-making on the e-th electric vehicle painting area in combination with the e-th area painting scene matrix, and establish a painting collaborative decision-making system. Decision first space; painting evaluation constraint optimization module, the painting evaluation constraint optimization module is used to perform painting evaluation constraint optimization on the painting collaborative decision first space based on the painting scene matrix of the e-th area and the expected painting result of the e-th area according to the painting prediction evaluation channel, and generate a painting candidate decision space; painting optimization result acquisition module, the painting optimization result acquisition module is used to perform painting fitness maximization optimization on the painting candidate decision space according to the painting fitness calculation channel, and obtain the painting optimization result of the e-th area; sanitation vehicle painting module, the sanitation vehicle painting module is used to add the painting optimization result of the e-th area to the electric vehicle painting optimization strategy, and paint the electric three-wheeled sanitation vehicle to be painted according to the electric vehicle painting optimization strategy.

[0007] The adaptive painting method and platform for electric three-wheeled sanitation vehicles proposed in this application first divide the electric three-wheeled sanitation vehicle to be painted into multiple painting areas, and extract the relevant information of each area; collect the material, surface state and predicted painting environment data of each area to form a painting scene matrix; combine the expected painting results of each area and the scene matrix to make multi-layer painting parameter decisions and establish a painting decision space; optimize the decision space based on the painting prediction evaluation channel to generate a painting candidate decision space, and maximize the optimization result through fitness calculation; apply the optimization result to the entire painting strategy to achieve precise painting for electric three-wheeled sanitation vehicles, achieving the technical effect of improving painting accuracy and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in this application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic flow chart of an adaptive painting method for an electric three-wheeled sanitation vehicle provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the structure of the adaptive painting platform of the electric three-wheeled sanitation vehicle provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: painting area acquisition module 10 , painting scene matrix acquisition module 20 , painting result acquisition module 30 , painting evaluation constraint optimization module 40 , painting optimization result acquisition module 50 , sanitation vehicle painting module 60 . DETAILED DESCRIPTION

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0013] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0014] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0015] The present application embodiment provides an adaptive coating method for an electric three-wheeled sanitation vehicle, such as Figure 1 As shown, the method includes: Step S100, divide the electric three-wheeled sanitation vehicle to be painted, obtain E electric vehicle painting areas, and extract the e-th electric vehicle painting area based on the E electric vehicle painting areas, where e and E are both positive integers, 1≤e≤E. Specifically, first analyze the overall structure of the electric three-wheeled sanitation vehicle, and preliminarily divide the body, compartment, front, rear, door, window frame, wheel hub, vehicle chassis and other parts as potential painting areas. Based on the painting characteristics, each part is refined, the side and top of the body are separated due to different flatness and functions; the inside and outside of the compartment are each a zone due to different requirements; the front face, bumper and other complex structures of the front are subdivided according to the situation; the taillights, bumper, and signboard areas of the rear are also divided into zones; the doors and window frames are divided separately due to frequent friction; the wheel hub is an independent zone due to the special driving environment; the chassis is a zone as a whole due to the harsh environment. The above areas are then numbered in sequence from 1 to E. When an operation is required on a specific area, the e-th electric vehicle painting area (1≤e≤E) is extracted according to the numbering rules so as to collect and analyze information based on its characteristics, achieve high-quality and personalized painting of the vehicle, and improve protection, aesthetics, durability and reliability.

[0016] Step S200, collect the material shape, surface state and predicted painting environment information of the e-th electric vehicle painting area to obtain the painting scene matrix of the e-th area. Specifically, for the e-th electric vehicle painting area, first use a metal detector, material analyzer, etc. to determine whether its material is metal (such as steel, aluminum alloy) or non-metal such as plastic, and then use a three-dimensional measuring instrument to accurately measure the shape, including flatness, radius of curvature, edge profile size, etc., because the material and shape affect the paint selection and painting process. Use an optical microscope, electron microscope and roughness measuring instrument to check the surface state, check for oil stains, dust, rust, old paint residue, scratches, pits, etc., measure the roughness, oil stains and dust affect adhesion, rust needs to be removed, old paint residue needs to evaluate compatibility, and large roughness requires pretreatment or selection of a suitable primer. At the same time, we cooperate with the meteorological department to obtain weather forecast data for future coating construction and coating drying and curing period, such as temperature, humidity, light intensity, precipitation probability, and understand the surrounding geographical environment, such as whether it is close to pollution sources and ventilation conditions. Temperature and humidity affect drying and curing, light and precipitation affect coatings, and pollution sources and ventilation affect quality and health. Finally, the above information is quantified and organized into the e-region coating scenario matrix to provide a data basis for subsequent coating decisions, coating selection and process optimization.

[0017] Step S300, obtain the expected painting result of the e-th area corresponding to the e-th electric vehicle painting area, combine the e-th area painting scene matrix to make a multi-layer painting parameter collaborative decision for the e-th electric vehicle painting area, and establish a first painting collaborative decision space. Specifically, according to the overall design specifications and use requirements of the electric three-wheeled sanitation vehicle, clarify the expected painting result of the e-th area, covering the coating color distribution, thickness, glossiness, uniformity and special performance. Then, the multi-layer coating parameter collaborative decision is made in combination with the coating scenario matrix of the e-th area. For the primer layer, the appropriate type (such as epoxy or zinc yellow primer for metal) is selected according to the material, the construction viscosity is determined according to the surface state, and the drying and curing parameters are adjusted according to the environmental conditions to form the primer layer decision domain; the middle layer is to fill the surface and enhance the performance. According to the expected thickness and flatness, polyester and other intermediate paints are selected. The spraying thickness and number of layers are determined according to the primer condition. The process parameters are optimized in combination with the environment to obtain the middle layer decision domain; the topcoat layer determines the appearance and some performance. According to the color, glossiness, and weather resistance, acrylic polyurethane or fluorocarbon topcoat is selected. According to the surface and middle layer conditions, the construction viscosity and spray gun parameters are determined, and the drying and curing time is adjusted according to the environment to form the topcoat layer decision domain. Finally, the parameters of each layer of the decision domain are comprehensively combined to form the first space of coating collaborative decision-making, which provides a basis for selecting the optimal coating solution to improve the quality, performance, life, appearance and recognition of vehicle coating.

[0018] In a possible implementation, the expected painting result of the e-th area corresponding to the e-th electric vehicle painting area is obtained, and the multi-layer painting parameter collaborative decision is made for the e-th electric vehicle painting area in combination with the e-th area painting scene matrix, and the first painting collaborative decision space is established. Step S300 further includes step S310, based on the e-th area painting scene matrix, the surface state inspection of the e-th electric vehicle painting area is carried out to obtain the surface state inspection result of the e-th area. Specifically, according to the information about the surface state in the e-th area painting scene matrix, a comprehensive and detailed inspection is carried out using detection tools and techniques. An optical microscope or an electron microscope is used to observe the microscopic flatness of the surface, whether there are fine scratches, pits, and peeling of the old paint layer, etc.; a roughness measuring instrument is used to accurately measure the surface roughness value to evaluate the smoothness of the surface; and a chemical analysis method is used to detect whether the surface is contaminated with oil, rust, and other impurities that may affect the painting quality. The detection data is compared with the pre-set surface state qualification standard, and a comprehensive judgment is made to obtain the surface state inspection result of the e-th area. For example, if the surface roughness is within the specified range, there are no obvious scratches or pits, and the content of impurities such as oil and rust is lower than the allowable value, the surface condition inspection result may be judged as passed; conversely, if there are more surface defects or impurities exceed the standard, the inspection result will be failed.

[0019] Step S320, when the surface state inspection result of the e-th area is passed, the electric vehicle painting record block is activated. Specifically, once it is determined that the surface state inspection result of the e-th area is passed, it means that the area has the basic conditions for normal painting operations. The electric vehicle painting record block stored in the database is activated through a control system or software program. The record block contains previous successful painting case data for similar vehicles and the same or similar painting areas, covering the types of paint used for the primer layer, intermediate layer and topcoat layer, coating process parameters (such as spraying pressure, spray gun angle, paint viscosity, drying time, etc.) and actual effect evaluation after painting (such as coating adhesion, durability, appearance quality, etc.) and other rich information, providing valuable reference basis and experience for subsequent painting parameter decisions, which helps to improve the accuracy and efficiency of this painting parameter decision and avoid starting from scratch.

[0020] Step S330, based on the electric vehicle painting record block, the primer layer painting parameter decision is made for the e-th electric vehicle painting area according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, and the primer layer painting decision domain is obtained. Specifically, based on the activated electric vehicle painting record block, combined with the performance requirements of the primer layer in the expected painting result of the e-th area (such as good adhesion, anti-corrosion ability, compatibility with subsequent coatings, etc.) and the material information in the painting scene matrix of the e-th area (such as metal materials may require different types of primers to prevent rust, while plastic materials require primers with good adhesion and flexibility), the past primer layer painting case data that matches the current situation is screened out. Further analyze the primer type and construction parameters (such as the spray thickness, curing conditions, construction temperature range, etc. of the primer) in the case, and make appropriate adjustments and optimizations according to the actual situation. For example, if the metal material of the painting area this time is slightly different from that in previous cases, it may be necessary to adjust the primer formula or construction process parameters to ensure that the primer can better adhere to the surface and provide sufficient protective performance. Through the process of analysis, screening and adjustment, a series of feasible combinations of primer layer coating parameters are determined. The set of combinations is the primer layer coating decision domain, which provides a range for the subsequent selection of the best primer layer coating scheme.

[0021] Step S340, based on the electric vehicle painting record block, according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, the intermediate layer painting parameter decision is made for the e-th electric vehicle painting area, and the intermediate layer painting decision domain is obtained. Specifically, according to the electric vehicle painting record block, referring to the functional requirements of the expected painting result of the e-th area for the intermediate layer (such as filling small surface defects, enhancing the overall strength of the coating, providing a good adhesion basis for the topcoat layer, etc.) and the surface state information in the painting scene matrix of the e-th area (such as a thicker intermediate layer may be needed to fill the surface if the surface roughness is large, or there are some tiny pores on the surface that need to be filled by the intermediate layer), data with reference value is selected from past intermediate layer painting cases. Analyze the type of intermediate paint (such as polyester intermediate paint, epoxy intermediate paint, etc., different types of intermediate paints have differences in filling performance, hardness, and bonding strength with upper and lower coatings), spraying process parameters (such as the number of layers of intermediate paint, the spraying thickness of each layer, the drying time interval, etc.) and the compatibility requirements with the primer layer and the topcoat layer, and comprehensively evaluate and adjust the parameters. For example, if the desired coating thickness is thicker and the surface flatness requirement is higher, it may be necessary to increase the number of intermediate layers and appropriately increase the spray thickness of each layer, while ensuring that the intermediate layer is firmly bonded to the primer and topcoat without interlayer peeling. After such an analysis and optimization process, the intermediate layer coating parameter combination suitable for the e-th area is determined to form an intermediate layer coating decision domain, which provides an optional parameter range for the intermediate layer for building a complete coating solution.

[0022] Step S350, based on the electric vehicle painting record block, the topcoat layer painting parameter decision is made for the e-th electric vehicle painting area according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, and the topcoat layer painting decision domain is obtained. Specifically, according to the data in the electric vehicle painting record block, combined with the expected painting result of the e-th area, the appearance and performance requirements of the topcoat layer (such as color accuracy, glossiness, weather resistance, wear resistance, etc.) and the environmental information in the e-th area painting scene matrix (such as the light intensity of the vehicle use environment, the temperature range, whether it is exposed to harsh climatic conditions, etc.), the topcoat layer painting case that matches the current demand is screened out. The type of topcoat in the case (such as acrylic polyurethane topcoat, fluorocarbon topcoat, etc., different topcoats have their own advantages and disadvantages in terms of color vividness, gloss retention, weather resistance, etc.), construction parameters (such as spray viscosity of topcoat, atomization effect of spray gun, drying and curing conditions, whether it is necessary to add light stabilizer or other additives, etc.) and performance in actual use are analyzed. For example, if the vehicle is often used in areas with strong sunlight and high ultraviolet radiation, it is necessary to select a fluorocarbon topcoat with excellent weather resistance and UV resistance, and appropriately adjust the drying and curing time of the topcoat and add additives such as ultraviolet absorbers to ensure that the topcoat does not fade in color and maintains good gloss during long-term use, while also having sufficient wear resistance and scratch resistance. Through the decision-making process, the feasible combination of topcoat coating parameters is determined to form the topcoat coating decision domain, which provides a variety of options for the final determination of the topcoat coating scheme.

[0023] Step S360, based on the electric vehicle painting record block, multi-layer painting parameter combinations are performed according to the primer layer painting decision domain, the intermediate layer painting decision domain and the topcoat layer painting decision domain to generate the first painting collaborative decision space. Specifically, a primer layer painting parameter combination is selected from the primer layer painting decision domain, and then an intermediate layer and topcoat layer painting parameter combination is selected from the intermediate layer painting decision domain and the topcoat layer painting decision domain respectively, and the three parameters are combined together to form a complete painting collaborative decision. Since each decision domain contains a variety of feasible parameter combinations, a large number of different painting collaborative decisions can be obtained by comprehensively cross-combining the three decision domains. The collection of all painting collaborative decisions is the first painting collaborative decision space. For example, if there are 5 feasible combinations of primer parameters in the primer layer painting decision domain, 4 for the intermediate layer, and 6 for the topcoat layer, then a total of 5×4×6=120 different collaborative painting decisions can be generated. The decisions cover different paint types, construction processes, and parameter settings, providing a wide range of possibilities for subsequent screening of the optimal painting scheme through evaluation constraint optimization and fitness maximization optimization, so that the most suitable multi-layer painting parameter combination can be found while meeting the actual situation of the e-th area and the expected painting effect.

[0024] In a possible implementation, the surface state of the e-th electric vehicle painting area is inspected based on the e-th area painting scene matrix to obtain the surface state inspection result of the e-th area, and step S310 further includes step S311, performing surface state feature recognition according to the e-th area painting scene matrix to obtain surface state feature data of the e-th area. Specifically, information related to the surface state is extracted from the e-th area painting scene matrix, and the information includes surface microtexture data obtained by optical detection equipment, surface roughness values ​​obtained by roughness measuring instruments, surface oil and impurity components and contents determined by chemical analysis, and surface scratches, pits, and old paint layer integrity recorded by visual inspection. Image recognition technology and data analysis algorithms are used to process these multi-source data, converting micro-textures into quantifiable texture feature parameters, such as texture directionality, periodicity, roughness, etc.; statistical analysis is performed on the roughness values ​​to determine their distribution range and mean; oil and impurity components are classified and identified, and their coverage area ratio on the surface is quantified; scratches and pits are measured in size and counted, so as to obtain comprehensive and detailed surface state characteristic data of the e-th area.

[0025] Step S312, evaluate the surface state of the e-th electric vehicle coating area according to the surface state characteristic data of the e-th area, and obtain the surface state coefficient of the e-th area. Specifically, based on the pre-established surface state evaluation model, the obtained surface state characteristic data of the e-th area is substituted into it for calculation. The evaluation model comprehensively analyzes the influence of factors such as surface flatness, roughness, oil and impurity content, scratches and pits on the coating quality, and assigns a corresponding weight coefficient to each factor. For example, poor surface flatness may lead to uneven distribution of paint, affecting the aesthetics and protective performance of the coating, so it is given a higher weight in the evaluation model; excessive oil and impurity content may seriously affect the adhesion of the coating, and is also given a larger weight. By performing weighted summation calculation on the quantified values ​​of each factor and the corresponding weight, a numerical value that can comprehensively reflect the quality of the surface state of the e-th area is obtained, that is, the surface state coefficient of the e-th area. The range of this coefficient can be set according to actual conditions, for example, between 0 and 1. The closer the value is to 1, the better the surface condition is, and the more conducive it is to painting operations; the closer the value is to 0, the worse the surface condition is, and more pretreatment or repair work is required.

[0026] Step S313, determine whether the surface state coefficient of the e-th region is greater than or equal to the surface state threshold. Specifically, compare the calculated surface state coefficient of the e-th region with the preset surface state threshold. The threshold is determined according to the coating process requirements and quality standards, and represents a minimum surface state requirement that can ensure the coating quality. For example, if the surface state coefficient is greater than or equal to 0.8 (assuming the threshold is 0.8), it is considered that the surface state of the area basically meets the coating conditions, and the next step of the coating parameter decision process can be entered; if the surface state coefficient is less than 0.8, the surface needs to be further processed or repaired to improve the surface state so that it reaches acceptable coating conditions.

[0027] Step S314, if the surface state coefficient of the e-th region is greater than or equal to the surface state threshold, the surface state inspection result of the e-th region is passed. Specifically, when the surface state coefficient of the e-th region satisfies the condition of being greater than or equal to the surface state threshold, it means that the surface state of the region has reached the standard for normal painting operations in terms of flatness, cleanliness, roughness, etc., and will not have obvious adverse effects on the adhesion of the paint, the uniformity of the coating, and the appearance quality. Therefore, the surface state inspection result of the e-th region is judged to be passed, and the subsequent painting process can be activated at this time, such as making decisions on the painting parameters of each layer based on the electric vehicle painting record block to determine the most suitable painting scheme for the area.

[0028] Step S315, if the surface state coefficient of the e-th region is less than the surface state threshold, the surface state inspection result of the e-th region is not passed, and the surface state warning instruction of the e-th region is generated. Specifically, once it is found that the surface state coefficient of the e-th region is lower than the surface state threshold, it indicates that there are some problems on the surface of the region, which may lead to a decline in coating quality, such as insufficient coating adhesion, bubbles, sagging and other defects. At this time, the surface state inspection result of the e-th region is marked as not passed, and the surface state warning instruction of the e-th region is immediately generated. The warning instruction mainly includes relevant measures for pre-treatment of the surface. For example, if the surface oil and impurity content is too high, the warning instruction will require the use of a specific cleaning agent for thorough cleaning to remove oil and impurities and ensure surface cleanliness; if the surface roughness exceeds the allowable range, it may indicate the use of grinding, polishing and other processes to reduce the roughness and improve the surface flatness; for the case where there are many scratches and pits, the instruction will recommend filling and repair operations to restore the surface to an acceptable state. Through pretreatment measures, the aim is to improve the surface condition coefficient so that it reaches or exceeds the surface condition threshold, thereby providing good basic conditions for subsequent painting operations, ensuring that the painting quality and effect meet the expected requirements, avoiding painting failures or quality problems caused by poor surface conditions, and improving the overall quality and reliability of electric three-wheeled sanitation vehicle painting, extending the vehicle's service life and appearance retention time.

[0029] In a possible implementation, based on the electric vehicle painting record block, the primer layer painting parameter decision is made for the e-th electric vehicle painting area according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, and the primer layer painting decision domain is obtained. Step S330 further includes step S331. When determining the primer layer painting scheme, the key requirements in the expected painting result of the e-th area are first clarified, such as anti-corrosion duration, adhesion level, compatibility with subsequent coatings, etc. Analyze the various parameters in the painting scene matrix of the e-th area, including material type, surface state characteristics and painting environment conditions (such as temperature, humidity, light intensity, etc.). Combine the expected painting results with the painting scene matrix information, input them into the painting record database as retrieval conditions, and accurately screen out the primer layer painting scheme set that meets the conditions. For example, a scheme with anti-rust performance in a high humidity environment and a painting area made of aluminum alloy will be retrieved and summarized as a scheme set, making full use of past successful experiences, improving decision-making efficiency, and avoiding repeated experiments.

[0030] Step S332, according to the retrieved primer layer coating scheme set, the coating parameter trigger feature recognition is performed to establish the primer layer coating trigger domain. Specifically, the retrieved primer layer coating scheme set is subjected to data analysis and feature extraction, and the coating parameters in each scheme are analyzed, such as primer type, construction viscosity, spray thickness, drying time, curing conditions, and spray gun pressure and angle. Through data mining and statistical analysis methods, the parameter change law and key trigger factors are identified. For example, for areas with steel materials and large surface roughness, high-viscosity, thick-coating epoxy primers are usually selected, with higher spray gun pressure and longer drying time; while for smooth plastic surfaces, low-viscosity, quick-drying primers are used, and lower spray gun pressure and specific spray angles are used. By identifying and summarizing key factors, the primer layer coating trigger domain is established, the reasonable selection range of coating parameters under different conditions is clarified, and a guiding framework is provided for subsequent coating decisions. This method improves the accuracy and efficiency of decision-making, optimizes coating quality and adaptability, reduces coating costs, reduces resource waste, ensures the protection needs of vehicles in different environments, and extends service life.

[0031] Step S333, according to the primer layer coating trigger domain, the primer layer coating decision is made for the e-th electric vehicle coating area, and the primer layer coating decision domain is obtained. Specifically, based on the established primer layer coating trigger domain, the primer layer coating parameters are carefully decided in combination with the actual situation and expected coating results of the e-th electric vehicle coating area. First, according to the material and surface state of the coating area, the suitable primer type and construction viscosity are determined from the trigger domain. For example, for pretreated metal surfaces, a medium viscosity epoxy primer with good adhesion and anti-rust performance is selected; for metal surfaces that are not fully treated and have oil and rust on the surface, a high viscosity primer is selected and pretreated with an appropriate rust remover. According to the predicted coating environment information (such as temperature, humidity, light, etc.), the trigger domain further determines the drying time, curing conditions, and pressure and angle of the primer. For example, in a high temperature and low humidity environment, the primer drying time can be shortened, but it is necessary to avoid drying too fast to cause surface defects; in a low temperature and high humidity environment, it may be necessary to extend the drying time and adjust the spray gun settings. Through the decision-making process, a series of feasible primer coating parameter combinations are determined to form a primer coating decision domain, which provides a basis for subsequent intermediate and topcoat coating decisions. Through multi-layer coating parameter combination and optimization, high-quality and efficient coating operations are achieved, improving the coating quality, durability and aesthetics of electric three-wheeled sanitation vehicles, while ensuring the stability and repeatability of the coating process, reducing maintenance costs and resource waste, and providing guarantees for long-term stable operation.

[0032] Step S400, based on the painting scene matrix of the e-th area and the expected painting result of the e-th area, the painting evaluation constraint optimization is performed on the first space of the painting collaborative decision according to the painting prediction and evaluation channel to generate a painting candidate decision space. Specifically, a painting prediction and evaluation channel is constructed and prepared, and a prediction model including painting durability, defect degree, and energy efficiency is integrated, and training and initialization are performed based on the material, environment and other information in the painting scene matrix of the e-th area, as well as the expected painting results and the coating parameters of each scheme in the first space of the painting collaborative decision. The schemes are taken out one by one from the first space of the painting collaborative decision, and the evaluation channel is input in combination with the relevant information. Each prediction model calculates its durability, defect degree, and energy efficiency respectively, and obtains a preliminary painting prediction and evaluation result, which is presented as a quantitative indicator. The painting evaluation constraints are set according to the actual needs and quality standards of the electric three-wheeled sanitation vehicle, such as the durability years, defect probability and quantity, energy consumption upper limit and energy efficiency cost ratio and other indicator thresholds under a specific environment. The evaluation results of each scheme are compared with the constraints one by one. The schemes that meet all constraints are selected as candidate schemes, and the reasons and data of those that do not meet the constraints are recorded for subsequent improvement. Finally, all schemes that meet the constraints are summarized to generate a painting candidate decision space. The schemes in the space will provide a basis for further screening and determination of the optimal painting scheme, ensuring that the selected scheme is balanced in all aspects and meets the actual use requirements, improving the quality and benefits of the painting of electric three-wheeled sanitation vehicles, extending the service life and appearance retention of the vehicles, and taking into account the energy utilization efficiency and cost control of the painting process, so that the vehicles have better performance and economic benefits in long-term operation.

[0033] In a possible implementation, based on the painting scene matrix of the e-th area and the expected painting result of the e-th area, the first space of the painting collaborative decision is optimized according to the painting prediction evaluation channel to generate a painting candidate decision space, and step S400 further includes step S410, performing a painting expectation check on the first space of the painting collaborative decision according to the expected painting result of the e-th area to generate a second space of the painting collaborative decision. Specifically, the various indicators and requirements in the expected painting result of the e-th area are analyzed, including specific parameters and performance targets such as expected coating color distribution, thickness uniformity, gloss, corrosion resistance, and wear resistance. For each painting collaborative decision in the first space of the painting collaborative decision (each decision contains a detailed combination of painting parameters for the primer layer, the intermediate layer, and the topcoat layer), the coating performance indicators that can actually be achieved after the decision is adopted for painting are predicted through simulation software or a calculation method based on a mathematical model. These prediction results are compared and verified with the expected coating results of the e-th area one by one, for example, whether the deviation between the predicted coating thickness and the expected thickness is within the allowable range, whether the predicted glossiness meets the expected glossiness range, and whether various performance indicators (such as corrosion resistance, wear resistance, etc.) meet or exceed the expected minimum standards. Only the coating collaborative decisions that match the expected coating results in various indicators can be screened out, and these screened decision sets constitute the second space of coating collaborative decision-making. This step ensures that the subsequent coating schemes considered are optimized in the direction of meeting actual expectations, avoiding wasting time and resources on schemes that do not meet expectations, improving the efficiency and accuracy of optimization, and laying the foundation for ultimately finding the best coating scheme.

[0034] Step S420, extracting the first painting collaborative decision according to the second painting collaborative decision space. Specifically, in the generated second painting collaborative decision space, one of the painting collaborative decisions is selected in a certain order (such as random order or based on a certain priority order, such as analyzing the coating uniformity first, or sorting according to the success rate of previous similar cases, etc.), and it is defined as the first painting collaborative decision. The decision will be the object of subsequent evaluation and verification. Through the analysis and testing of the decision, the feasibility and advantages and disadvantages of the decision in the actual painting scenario will be further understood. At the same time, it also provides a benchmark reference for subsequent comparison and optimization, so as to compare with other decisions, and gradually screen out the optimal painting scheme to meet the painting needs of electric three-wheeled sanitation vehicles in different aspects, such as appearance quality, protective performance, durability and cost-effectiveness.

[0035] Step S430, input the e-th region painting scene matrix and the first painting collaborative decision into the painting prediction and evaluation channel to obtain the first painting prediction and evaluation result, wherein the painting prediction and evaluation channel includes a painting durability prediction model, a painting defect prediction model and a painting energy efficiency prediction model. Specifically, the detailed information in the e-th region painting scene matrix, including data such as material type, surface state, predicted painting environment (temperature, humidity, light, etc.), is combined with the painting parameters of the primer layer, intermediate layer and topcoat layer in the selected first painting collaborative decision (such as paint type, spray thickness, drying time, construction process, etc.), and passed to the painting prediction and evaluation channel as input parameters. The coating durability prediction model in the coating prediction evaluation channel will predict the service life and corrosion resistance of the coating under the coating scheme based on the chemical composition of the coating, coating thickness and environmental factors, using the existing material aging data and environmental corrosion model, and derive the predicted coating durability; the coating defect prediction model will estimate the probability and severity of defects such as sag, bubbles, orange peel, pinholes, etc. that may appear during the coating process and in the early stage of the coating based on the surface state, construction process parameters and rheological properties of the coating, combined with the defect statistics data that appeared in previous similar coating cases, and obtain the predicted coating defect degree; the coating energy efficiency prediction model will comprehensively analyze the coating spraying energy consumption, the energy consumption during the drying and curing process, and the efficiency of the construction equipment, calculate the energy consumption of the coating scheme in the entire coating process, and combine it with the coating cost, construction labor cost, etc. to derive the predicted value of the coating energy efficiency. Through the calculation and analysis of the model, we finally obtain the comprehensive predictive evaluation results of the first coating collaborative decision-making in the current coating scenario, including key indicators such as predicted coating durability, predicted coating energy efficiency, predicted coating defect degree, etc., to provide quantitative data support for subsequent judgments and decisions.

[0036] Step S440, determining whether the first coating prediction evaluation result satisfies coating evaluation constraints, wherein the coating evaluation constraints include coating durability constraints, coating energy efficiency constraints, and coating defect constraints. Specifically, clear coating evaluation constraints are set in advance based on the actual use requirements and coating quality standards of the electric three-wheeled sanitation vehicle. Coating evaluation constraints include coating durability constraints, such as requiring the coating to maintain effective protective performance for at least [X] years under specific use environments (such as urban road cleaning operations, often exposed to the sun, rain, dust pollution and possible chemical corrosion environments), that is, the predicted coating durability must reach or exceed the corresponding annual limit value; coating energy efficiency constraints, which stipulate that the energy consumption during the coating process shall not exceed [X] kilowatt-hours per square meter, and the coating energy efficiency cost ratio (that is, the coating performance improvement benefit brought by unit energy consumption) must meet certain economic rationality indicators to ensure that the predicted coating energy efficiency is within an acceptable range; coating defect constraints, which set the probability of serious coating defects (such as large-scale coating peeling, serious bubbles leading to coating failure, etc.) in the initial stage after coating construction (such as within one month) shall not exceed [X]%, and the number of general defects (such as slight orange peel phenomenon, a small number of pinholes, etc.) shall not exceed [X] per square meter, to ensure that the predicted coating defect degree is at a controllable low level. The predicted coating durability, predicted coating energy efficiency, and predicted coating defect degree in the first coating prediction evaluation results are compared and judged one by one with these pre-set coating evaluation constraints. If each indicator meets the corresponding constraints, it means that the first coating collaborative decision preliminarily meets the requirements and can enter the next screening process; if any of the indicators does not meet the constraints, the decision is judged as not meeting the requirements and will be eliminated. The plan will no longer be analyzed to avoid continuing to invest resources and time in unfeasible plans, improve the efficiency and accuracy of optimization, and ensure that the final coating plan can meet actual needs and quality standards in all key aspects, thereby ensuring the coating quality and long-term performance of the electric three-wheeled sanitation vehicle.

[0037] Step S450, if the first painting prediction and evaluation result satisfies the painting evaluation constraint, the first painting collaborative decision is added to the painting candidate decision space. Specifically, when the first painting prediction and evaluation result successfully passes the test of the painting evaluation constraint, it means that the painting collaborative decision has high feasibility and potential superiority in the current e-th area painting scenario, and can meet the basic requirements and quality standards of electric three-wheeled sanitation vehicles in terms of painting durability, painting energy efficiency and painting defect degree. Therefore, this first painting collaborative decision is formally included in the painting candidate decision space, and is further optimized and screened as one of the potential optimal painting solutions. As more and more painting collaborative decisions that meet the painting evaluation constraints are added to the candidate decision space, the space will gradually gather a series of competitive painting schemes, providing abundant choices for selecting the most suitable painting scheme for the e-th area through more sophisticated optimization algorithms and comparative analysis. The final painting scheme can achieve the best balance in comprehensive performance, ensuring good painting quality and long-term durability, while taking into account energy utilization efficiency and low defect risk. At the same time, it can meet the various functional requirements and appearance requirements of the electric three-wheeled sanitation vehicle in actual use, and improve the overall quality and value of the vehicle.

[0038] Step S460, according to the coating prediction evaluation channel and the coating evaluation constraint, the second space of the coating collaborative decision is continued to be constrained and optimized to generate the coating candidate decision space. Specifically, after the first coating collaborative decision (if the constraint condition is met) is added to the coating candidate decision space, similar operations are continued for other coating collaborative decisions in the second space of the coating collaborative decision. According to the previous steps, each coating collaborative decision is extracted in turn, and input into the coating prediction evaluation channel together with the coating scene matrix of the e-th area, and the corresponding coating prediction evaluation result is obtained, and compared and judged with the coating evaluation constraint. If the constraint condition is met, it is added to the coating candidate decision space; if not, the decision is eliminated. By repeating this process continuously, all the schemes in the second space of the coating collaborative decision are comprehensively screened and optimized, and the schemes that do not meet the requirements are gradually eliminated, and the high-quality schemes that meet the coating evaluation constraints are retained and accumulated, and the coating candidate decision space is continuously enriched and improved. In this process, with the evaluation and screening of more schemes, the schemes in the coating candidate decision space will continue to evolve and optimize, and gradually approach the optimal solution. By analyzing and comparing various schemes, we can further understand the influence of different parameter combinations on the painting effect, and provide valuable reference for possible subsequent parameter adjustments and scheme improvements, so that the schemes in the final generated painting candidate decision space can not only meet the current basic requirements, but also have certain optimizability and adaptability, and can be flexibly adjusted and improved according to changes in actual conditions and further needs, ensuring that the painting scheme of the electric three-wheeled sanitation vehicle always remains at a high level, providing a solid guarantee for the long-term stable operation and good performance of the vehicle.

[0039] In a possible implementation, the first space of the painting collaborative decision is subjected to a painting expectation check according to the expected painting result of the e-th area, and the second space of the painting collaborative decision is generated. Step S410 further includes step S411, modeling is performed based on the painting scene matrix of the e-th area, and the painting scene model of the e-th area is obtained. Specifically, the data in the painting scene matrix of the e-th area are analyzed, including the material information of the area (such as the material type, hardness, roughness and other parameters of metal, the material characteristics and flexibility of plastic, etc.), surface state data (such as the flatness of the surface, whether there are scratches, pits, oil stains, rust, etc., and their distribution and severity), and predicted painting environment information (such as the range and trend of changes in temperature, humidity, light intensity, ventilation conditions, etc. during the painting process and subsequent use). Using modeling software (such as computer-aided design software, finite element analysis software, etc.), a three-dimensional model that can accurately simulate the actual situation of the e-th area is constructed according to the data, that is, the painting scene model of the e-th area. During the modeling process, the physical properties of the material are accurately set so that it can reflect the interaction between the paint and the material during the painting process; the various characteristics of the surface state are presented in the form of geometric shapes and surface properties so that their influence on the adhesion and distribution of the paint can be considered in the subsequent simulation of painting; environmental factors are incorporated into the boundary conditions and physical field settings of the model to simulate the influence of the actual environment on the drying, curing and coating performance of the paint.

[0040] Step S412, based on the painting scene model of the e-th area, simulate the painting according to each painting collaborative decision in the first space of the painting collaborative decision, and obtain multiple simulated painting results. Specifically, for each painting collaborative decision in the first space of the painting collaborative decision, which includes a specific combination of painting parameters for the primer layer, the intermediate layer and the topcoat layer (such as the type of primer, spraying thickness, drying time, construction process parameters, corresponding parameters of the intermediate paint and the topcoat, etc.), the parameter settings are applied to the painting simulation module in the simulation software. On the basis of the painting scene model of the e-th area, the spraying process of the paint is simulated, considering the rheological properties of the paint (such as viscosity, fluidity, etc.), the parameters of the spray gun (such as pressure, angle, nozzle type, etc.) and the influence of the painting environment on the atomization and deposition of the paint, and calculating the adhesion amount, distribution, and drying and curing process of the paint on the surface of the model. By simulating multiple painting processes and different parameter combinations, multiple simulation painting results are obtained. Each result describes the key indicators of the coating on the painting scene model of the e-th area, such as thickness distribution, color uniformity, surface flatness, adhesion to the substrate, and possible defects (such as sagging, bubbles, orange peel, etc.) under a specific painting collaborative decision. It provides rich data information for subsequent evaluation and comparison, helps analyze the advantages and disadvantages and feasibility of different painting schemes, and thus selects the painting scheme that best suits the actual situation of the e-th area.

[0041] Step S413, determine whether the multiple simulated coating results meet the expected coating results of the e-th area, and obtain multiple expected coating verification results. Specifically, each simulated coating result is compared and analyzed in detail with the expected coating result of the e-th area. The expected coating result of the e-th area clarifies the various performance indicators and appearance requirements of the coating, such as the expected coating thickness range, color accuracy and consistency, gloss requirements, corrosion resistance and wear resistance indicators, surface flatness and smoothness, etc. For each simulated coating result, check one by one whether its coating thickness is within the expected range, whether the color is consistent with expectations and uniform, whether the gloss meets the requirements, and evaluate its corrosion resistance and wear resistance through simulated corrosion and wear tests. Whether it meets the set standards, as well as whether the surface flatness and smoothness meet expectations. Based on the comparison results, a coating expectation verification result is generated for each simulated coating result, marking whether it meets the expected coating result of the e-th area. If a certain simulation painting result is consistent with or better than the expected painting result in all indicators, then the expected painting verification result is "satisfied"; if any indicator does not meet the expected requirements, then the expected painting verification result is "unsatisfied". Through the judgment process, it is possible to quickly and accurately identify which painting collaborative decisions are likely to meet actual needs in the simulation environment, providing a clear direction and basis for subsequent screening and optimization, avoiding trying those solutions that obviously do not meet the requirements in actual painting, saving time and cost, and improving the efficiency and quality of determining painting solutions.

[0042] Step S414, according to the multiple expected painting verification results, select the first space of the painting collaborative decision to obtain the second space of the painting collaborative decision. Specifically, based on the multiple expected painting verification results, the first space of the painting collaborative decision is screened and optimized. For the simulation painting results whose expected painting verification results are "satisfied", find out the corresponding painting collaborative decisions, and add these decisions to the second space of the painting collaborative decision. The selected painting collaborative decisions represent the combination of solutions that can better meet the expected painting results of the e-th area under the simulation environment. They have high feasibility and potential superiority, and are worthy of further in-depth research and optimization. As for the painting collaborative decisions corresponding to the simulation painting results whose expected painting verification results are "unsatisfied", they will be eliminated from the analysis scope, and no subsequent analysis and attempts will be carried out. Through the selection process, the second space for painting collaborative decision-making will gather a group of painting schemes that have been preliminarily screened and are more likely to meet actual needs, providing a narrowed but higher-quality decision-making space for selecting the final painting scheme that is most suitable for the e-th area from these schemes through more sophisticated evaluation and optimization algorithms. This makes the entire painting scheme determination process more efficient and accurate, while also ensuring that the final selected painting scheme can achieve the expected painting effect in actual applications, thereby improving the painting quality and overall performance of the electric three-wheeled sanitation vehicle.

[0043] Step S500, according to the painting fitness calculation channel, the painting candidate decision space is optimized for maximizing the painting fitness, and the painting optimization result of the e-th region is obtained. Specifically, a painting fitness calculation channel is constructed, and the predetermined weights of the painting durability, painting energy efficiency and painting defect degree in the calculation function are set according to the actual needs of the electric three-wheeled sanitation vehicle (such as durability 0.4, energy efficiency 0.3, defect degree 0.3), and the quantification and normalization methods of each factor are determined, such as converting the painting durability, painting energy efficiency and painting defect degree into values ​​between 0 and 1 respectively through experiments or data analysis. Then, the candidate decisions containing the detailed parameter combinations of primer, intermediate layer and topcoat are taken out one by one from the painting candidate decision space, and the channel is combined with the weights and quantization values, and the function is used to calculate the weights. Calculate the coating fitness value. Finally, compare the fitness values ​​of all candidate decisions and find the decision corresponding to the maximum value. Its parameter combination is the optimal result of the coating in the e-th area.

[0044] In a possible implementation, the coating fitness maximization optimization is performed on the coating candidate decision space according to the coating fitness calculation channel to obtain the coating optimization result of the e-th region, and step S500 further includes step S510, the coating fitness calculation channel includes a coating fitness calculation function, and the coating fitness calculation function is: ; Among them, SCF represents the coating fitness, NXW represents the predetermined weight of coating durability, K(SNX) represents the normalized predicted coating durability, NEW represents the predetermined weight of coating energy efficiency, K(SNE) represents the normalized predicted coating energy efficiency, NDW represents the predetermined weight of coating defects, and K(SND) represents the normalized predicted coating defects. Specifically, the function in the coating fitness calculation channel is , where the meaning of each parameter is clear. SCF stands for coating adaptability, which is a comprehensive quantitative indicator for evaluating the pros and cons of coating schemes. The larger the value, the better. NXW is the predetermined weight of coating durability. Based on the complex outdoor working environment of electric three-wheeled sanitation vehicles, its value is set according to the durability expectation, such as 0.4 and above, to highlight the importance of durability. K(SNX) is the normalized predicted coating durability. The coating durability is estimated through laboratory simulation, actual case statistics or theoretical calculation and normalized to the range of 0~1. For example, the actual 5 years and the ideal 8 years are 0.625. NEW is the predetermined weight of coating energy efficiency. If you pay attention to coating energy efficiency and cost, it can be set to about 0.3. K(SNE) is the normalized predicted coating energy efficiency, which is obtained by normalizing the energy efficiency ratio after comprehensive spraying, drying and curing energy consumption and coating performance. NDW is the predetermined weight of coating defect degree, which is generally set to about 0.3, reflecting the importance of coating defects. K(SND) is the normalized predicted coating defect degree. It is based on factors such as coating construction parameters, coating settings, and regional surface conditions, combined with historical defect data or models to estimate defects and quantify normalization. In actual application, for each solution in the coating candidate decision space, according to its parameters and the coating scenario matrix information of the e-th region, K(SNX), K(SNE), and K(SND) are calculated respectively, and substituted into the function to calculate SCF, so as to compare the advantages and disadvantages of each solution, find the solution that maximizes SCF, and achieve coating solution optimization.

[0045] Step S600, add the optimization results of the painting of the e-th area to the optimization strategy of the painting of the electric vehicle, and paint the electric three-wheeled sanitation vehicle to be painted according to the optimization strategy of the painting of the electric vehicle. Specifically, the optimization results of the painting of the e-th area are parsed and sorted, which cover the optimal painting parameters of the primer, the intermediate layer and the topcoat, such as the paint type, spraying thickness, construction process of the primer, the corresponding parameters of the intermediate layer and the topcoat, etc., and these parameters are added to the optimization strategy of the painting of the electric vehicle according to the predetermined format rules to ensure the coordination and compatibility of the parameters of each area. Then, according to the strategy, high-quality and environmentally friendly paints are purchased, and painting tools such as spray guns and drying equipment are prepared and debugged. At the same time, the painting site is cleaned and sorted, and environmental factors such as dust, temperature and humidity are controlled. Then, the electric three-wheeled sanitation vehicle is painted according to the strategy. First, the primer layer parameters of the e-th area are evenly sprayed, and adjusted according to environmental changes to ensure the quality of the primer; then, the intermediate layer parameters are sprayed to fill the primer defects; finally, the topcoat layer parameters are operated to ensure that the color, gloss and performance meet the standards. During painting, the coatings in each area are strictly inspected and defects are corrected in a timely manner to ensure that the vehicle painting quality meets strategic expectations, thereby improving the vehicle's quality, life, appearance and sanitation operation efficiency.

[0046] In the above, refer to Figure 1 The adaptive painting method of the electric three-wheeled sanitation vehicle according to the embodiment of the present invention is described in detail. Figure 2An adaptive painting platform for an electric three-wheeled sanitation vehicle according to an embodiment of the present invention is described.

[0047] The adaptive painting platform of the electric three-wheeled sanitation vehicle according to the embodiment of the present invention is used to solve the technical problems of low painting control accuracy and poor painting adaptability of the existing electric three-wheeled sanitation vehicles, and achieves the technical effect of improving painting accuracy and adaptability. The adaptive painting platform of the electric three-wheeled sanitation vehicle includes: a painting area acquisition module 10, a painting scene matrix acquisition module 20, a painting result acquisition module 30, a painting evaluation constraint optimization module 40, a painting optimization result acquisition module 50, and a sanitation vehicle painting module 60.

[0048] The painting area acquisition module 10 is used to divide the electric three-wheeled sanitation vehicle to be painted, obtain E electric vehicle painting areas, and extract the e-th electric vehicle painting area based on the E electric vehicle painting areas, wherein e and E are both positive integers, 1≤e≤E.

[0049] The painting scene matrix acquisition module 20 is used to collect the material shape, surface state and predicted painting environment information of the e-th electric vehicle painting area to obtain the e-th area painting scene matrix.

[0050] The painting result acquisition module 30 is used to obtain the expected painting result of the e-th area corresponding to the e-th electric vehicle painting area, and perform multi-layer painting parameter collaborative decision-making on the e-th electric vehicle painting area in combination with the e-th area painting scene matrix to establish a first painting collaborative decision-making space.

[0051] The painting evaluation constraint optimization module 40 is used to perform painting evaluation constraint optimization on the first painting collaborative decision space based on the painting scene matrix of the e-th area and the expected painting result of the e-th area according to the painting prediction evaluation channel to generate a painting candidate decision space.

[0052] The painting optimization result acquisition module 50 is used to optimize the painting candidate decision space by maximizing the painting fitness according to the painting fitness calculation channel, and obtain the painting optimization result of the e-th area.

[0053] The sanitation vehicle painting module 60 is used to add the painting optimization result of the e-th area to the electric vehicle painting optimization strategy, and paint the electric three-wheeled sanitation vehicle to be painted according to the electric vehicle painting optimization strategy.

[0054] Below, the specific configuration of the painting result acquisition module 30 will be described in detail. As described above, the expected painting result of the e-th area corresponding to the e-th electric vehicle painting area is obtained, and the multi-layer painting parameter collaborative decision is performed on the e-th electric vehicle painting area in combination with the e-th area painting scene matrix, and a first painting collaborative decision space is established. The painting result acquisition module 30 further includes: a surface state inspection unit, the surface state inspection unit is used to perform a surface state inspection on the e-th electric vehicle painting area based on the e-th area painting scene matrix to obtain the surface state inspection result of the e-th area; a painting record block activation unit, the painting record block activation unit is used to activate the electric vehicle painting record block when the surface state inspection result of the e-th area is passed; a primer layer painting parameter decision unit, the primer layer painting parameter decision unit is used to make a primer layer painting parameter decision on the e-th electric vehicle painting area based on the electric vehicle painting record block and according to the expected painting result of the e-th area and the e-th area painting scene matrix. , obtaining a primer layer painting decision domain; an intermediate layer painting decision domain acquisition unit, the intermediate layer painting decision domain acquisition unit is used to make an intermediate layer painting parameter decision for the e-th electric vehicle painting area based on the electric vehicle painting record block, according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, and obtain the intermediate layer painting decision domain; a topcoat layer painting decision domain acquisition unit, the topcoat layer painting decision domain acquisition unit is used to make a topcoat layer painting parameter decision for the e-th electric vehicle painting area based on the electric vehicle painting record block, according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, and obtain the topcoat layer painting decision domain; a multi-layer painting parameter combination unit, the multi-layer painting parameter combination unit is used to perform multi-layer painting parameter combination based on the electric vehicle painting record block, according to the primer layer painting decision domain, the intermediate layer painting decision domain and the topcoat layer painting decision domain, to generate the first painting collaborative decision space.

[0055] Among them, the surface state inspection of the e-th electric vehicle painting area is performed based on the e-th area painting scene matrix to obtain the surface state inspection result of the e-th area, and the surface state inspection unit further includes: a state feature recognition subunit, the state feature recognition subunit is used to perform surface state feature recognition according to the e-th area painting scene matrix to obtain the surface state feature data of the e-th area; a surface state evaluation subunit, the surface state evaluation subunit is used to perform surface state evaluation on the e-th electric vehicle painting area according to the surface state feature data of the e-th area to obtain the surface state coefficient of the e-th area; a state threshold judgment subunit, the state threshold judgment subunit is used to judge whether the surface state coefficient of the e-th area is greater than or equal to the surface state threshold; an inspection result judgment subunit, the inspection result judgment subunit is used to judge that if the surface state coefficient of the e-th area is greater than or equal to the surface state threshold, the surface state inspection result of the e-th area is passed; a state warning instruction generation subunit, the state warning instruction generation subunit is used to judge that if the surface state coefficient of the e-th area is less than the surface state threshold, the surface state inspection result of the e-th area is failed, and generate a surface state warning instruction for the e-th area.

[0056] Among them, based on the electric vehicle painting record block, according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, a primer layer painting parameter decision is made for the e-th electric vehicle painting area to obtain a primer layer painting decision domain, and the primer layer painting parameter decision unit further includes: a block retrieval subunit, the block retrieval subunit is used to use the expected painting result of the e-th area and the painting scene matrix of the e-th area as retrieval constraints, and the primer layer painting scheme as the retrieval target, to retrieve the electric vehicle painting record block to obtain a retrieved primer layer painting scheme set; a painting trigger domain construction subunit, the painting trigger domain construction subunit is used to perform painting parameter trigger feature recognition according to the retrieved primer layer painting scheme set, and establish a primer layer painting trigger domain; a primer layer painting decision subunit, the primer layer painting decision subunit is used to make a primer layer painting decision for the e-th electric vehicle painting area according to the primer layer painting trigger domain to obtain the primer layer painting decision domain.

[0057] The following will describe in detail the painting evaluation constraint optimization module 40, which is used to perform painting evaluation constraint optimization on the first painting collaborative decision space based on the painting scene matrix of the e-th area and the expected painting result of the e-th area according to the painting prediction evaluation channel to generate a painting candidate decision space. The painting evaluation constraint optimization module 40 further includes: a painting expectation verification unit, which is used to perform painting expectation verification on the first painting collaborative decision space according to the expected painting result of the e-th area to generate a painting collaborative decision second space; a painting collaborative decision extraction unit, which is used to extract the first painting collaborative decision according to the second painting collaborative decision space; and a painting prediction evaluation result acquisition unit, which is used to input the painting scene matrix of the e-th area and the first painting collaborative decision into the painting prediction evaluation channel to obtain A first coating prediction and evaluation result, wherein the coating prediction and evaluation channel includes a coating durability prediction model, a coating defect prediction model and a coating energy efficiency prediction model; a coating evaluation constraint judgment unit, wherein the coating evaluation constraint judgment unit is used to judge whether the first coating prediction and evaluation result satisfies the coating evaluation constraint, wherein the coating evaluation constraint includes a coating durability constraint, a coating energy efficiency constraint and a coating defect constraint; a candidate decision space adding unit, wherein the candidate decision space adding unit is used to add the first coating collaborative decision to the coating candidate decision space if the first coating prediction and evaluation result satisfies the coating evaluation constraint; a coating candidate decision space generating unit, wherein the coating candidate decision space generating unit is used to continue to perform constraint optimization on the second coating collaborative decision space according to the coating prediction and evaluation channel and the coating evaluation constraint to generate the coating candidate decision space.

[0058] Among them, the first painting collaborative decision-making space is subjected to painting expectation verification according to the expected painting result of the e-th area to generate a second painting collaborative decision-making space, and the painting expectation verification unit further includes: a painting scene matrix construction subunit, the painting scene matrix construction subunit is used to perform modeling based on the painting scene matrix of the e-th area to obtain the painting scene model of the e-th area; A simulation painting sub-unit, the simulation painting sub-unit is used to perform simulation painting based on the painting scene model of the e-th area and according to each painting collaborative decision in the first space of the painting collaborative decision, to obtain multiple simulation painting results; a painting expected verification result acquisition sub-unit, the painting expected verification result acquisition sub-unit is used to determine whether the multiple simulation painting results meet the expected painting results of the e-th area, to obtain multiple expected painting verification results; a painting collaborative decision second space acquisition sub-unit, the painting collaborative decision second space acquisition sub-unit is used to select the painting collaborative decision first space according to the multiple expected painting verification results, to obtain the painting collaborative decision second space.

[0059] The specific configuration of the coating optimization result acquisition module 50 will be described in detail below. As described above, the coating candidate decision space is optimized by maximizing the coating fitness according to the coating fitness calculation channel to obtain the coating optimization result of the e-th region. The coating optimization result acquisition module 50 further includes: a coating fitness calculation function unit, and the coating fitness calculation function unit is used for the coating fitness calculation channel to include a coating fitness calculation function, and the coating fitness calculation function is: ; Among them, SCF represents the coating adaptability, NXW represents the predetermined weight of coating durability, K(SNX) represents the normalized predicted coating durability, NEW represents the predetermined weight of coating energy efficiency, K(SNE) represents the normalized predicted coating energy efficiency, NDW represents the predetermined weight of coating defects, and K(SND) represents the normalized predicted coating defects.

[0060] The adaptive painting platform for an electric three-wheeled sanitation vehicle provided in an embodiment of the present invention can execute the adaptive painting method for an electric three-wheeled sanitation vehicle provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0061] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0062] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The adaptive painting method of an electric three-wheeled sanitation vehicle is characterized in that: The method comprises: Divide the electric three-wheeled sanitation vehicles to be painted to obtain E electric vehicle painting areas, and extract the e-th electric vehicle painting area according to the E electric vehicle painting areas, where e and E are both positive integers, 1≤e≤E; Collecting the material shape, surface state and predicted painting environment information of the e-th electric vehicle painting area to obtain the e-th area painting scene matrix; Obtaining an expected painting result of an e-th area corresponding to the e-th electric vehicle painting area, performing a multi-layer painting parameter collaborative decision on the e-th electric vehicle painting area in combination with the e-th area painting scene matrix, and establishing a first painting collaborative decision space; Based on the painting scenario matrix of the e-th area and the expected painting result of the e-th area, performing painting evaluation constraint optimization on the first painting collaborative decision space according to the painting prediction evaluation channel to generate a painting candidate decision space; According to the coating fitness calculation channel, the coating candidate decision space is optimized by maximizing the coating fitness, and the coating optimization result of the e-th area is obtained; The painting optimization result of the e-th area is added to the electric vehicle painting optimization strategy, and the electric three-wheeled sanitation vehicle to be painted is painted according to the electric vehicle painting optimization strategy.

2. The method according to claim 1, characterized in that Obtaining the expected painting result of the e-th area corresponding to the e-th electric vehicle painting area, performing multi-layer painting parameter collaborative decision-making on the e-th electric vehicle painting area in combination with the e-th area painting scene matrix, and establishing a first painting collaborative decision-making space, including: Performing a surface condition inspection on the e-th electric vehicle painting area based on the e-th area painting scene matrix to obtain a surface condition inspection result of the e-th area; When the surface condition inspection result of the e-th area is passed, activating the electric vehicle painting record block; Based on the electric vehicle painting record block, making a primer layer painting parameter decision for the e-th electric vehicle painting area according to the expected painting result of the e-th area and the e-th area painting scene matrix, and obtaining a primer layer painting decision domain; Based on the electric vehicle painting record block, making an intermediate layer painting parameter decision for the e-th electric vehicle painting area according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, and obtaining an intermediate layer painting decision domain; Based on the electric vehicle painting record block, making a topcoat layer painting parameter decision for the e-th electric vehicle painting area according to the expected painting result of the e-th area and the e-th area painting scene matrix, and obtaining a topcoat layer painting decision domain; Based on the electric vehicle painting record block, multi-layer painting parameter combination is performed according to the primer layer painting decision domain, the intermediate layer painting decision domain and the topcoat layer painting decision domain to generate the first painting collaborative decision space.

3. The method according to claim 2, characterized in that Performing a surface condition inspection on the e-th electric vehicle painting area based on the e-th area painting scene matrix to obtain a surface condition inspection result of the e-th area includes: Performing surface state feature recognition according to the painting scene matrix of the e-th region to obtain surface state feature data of the e-th region; Performing a surface state evaluation on the e-th electric vehicle coating region according to the surface state characteristic data of the e-th region to obtain a surface state coefficient of the e-th region; Determining whether the surface state coefficient of the e-th region is greater than or equal to a surface state threshold; If the surface state coefficient of the e-th region is greater than or equal to the surface state threshold, the surface state inspection result of the e-th region is passed; If the surface state coefficient of the e-th region is less than the surface state threshold, the surface state inspection result of the e-th region is failed, and a surface state warning instruction of the e-th region is generated.

4. The method according to claim 2, characterized in that Based on the electric vehicle painting record block, a primer layer painting parameter decision is made for the e-th electric vehicle painting area according to the expected painting result of the e-th area and the painting scene matrix of the e-th area, and a primer layer painting decision domain is obtained, including: Taking the expected painting result of the e-th area and the painting scene matrix of the e-th area as retrieval constraints and the primer layer painting scheme as the retrieval target, the electric vehicle painting record block is retrieved to obtain a retrieved primer layer painting scheme set; Performing coating parameter trigger feature recognition according to the retrieved primer layer coating scheme set, and establishing a primer layer coating trigger domain; A primer layer painting decision is made for the e-th electric vehicle painting area according to the primer layer painting trigger domain to obtain the primer layer painting decision domain.

5. The method according to claim 1, characterized in that Based on the painting scene matrix of the e-th area and the expected painting result of the e-th area, the painting evaluation constraint optimization is performed on the first painting collaborative decision space according to the painting prediction evaluation channel to generate a painting candidate decision space, including: Performing a painting expectation check on the first painting collaborative decision-making space according to the expected painting result of the e-th area to generate a second painting collaborative decision-making space; Extracting a first painting collaborative decision according to the second painting collaborative decision space; Inputting the e-th region painting scenario matrix and the first painting collaborative decision into the painting prediction and evaluation channel to obtain a first painting prediction and evaluation result, wherein the painting prediction and evaluation channel includes a painting durability prediction model, a painting defect prediction model, and a painting energy efficiency prediction model; Determining whether the first coating prediction evaluation result satisfies coating evaluation constraints, wherein the coating evaluation constraints include coating durability constraints, coating energy efficiency constraints, and coating defect constraints; If the first coating prediction evaluation result satisfies the coating evaluation constraint, adding the first coating collaborative decision to the coating candidate decision space; The second painting collaborative decision space is continuously subjected to constraint optimization according to the painting prediction evaluation channel and the painting evaluation constraint to generate the painting candidate decision space.

6. The method according to claim 5, characterized in that The first painting collaborative decision-making space is subjected to painting expectation verification according to the expected painting result of the e-th area to generate a second painting collaborative decision-making space, including: Modeling is performed based on the painting scene matrix of the e-th area to obtain a painting scene model of the e-th area; Based on the e-th area painting scene model, simulated painting is performed according to each painting collaborative decision in the first painting collaborative decision space to obtain multiple simulated painting results; Determine whether the plurality of simulation painting results meet the expected painting result of the e-th region, and obtain a plurality of expected painting verification results; According to the multiple painting expectation verification results, the painting collaborative decision-making first space is selected to obtain the painting collaborative decision-making second space.

7. The method according to claim 1, characterized in that The coating fitness calculation channel includes a coating fitness calculation function, and the coating fitness calculation function is: ； Among them, SCF represents the coating adaptability, NXW represents the predetermined weight of coating durability, K(SNX) represents the normalized predicted coating durability, NEW represents the predetermined weight of coating energy efficiency, K(SNE) represents the normalized predicted coating energy efficiency, NDW represents the predetermined weight of coating defects, and K(SND) represents the normalized predicted coating defects.

8. The adaptive painting platform of the electric three-wheeled sanitation vehicle is characterized by: The platform is used to implement the adaptive painting method of the electric three-wheeled sanitation vehicle according to any one of claims 1 to 7, and the platform comprises: A painting area acquisition module, the painting area acquisition module is used to divide the electric three-wheeled sanitation vehicle to be painted, obtain E electric vehicle painting areas, and extract the e-th electric vehicle painting area according to the E electric vehicle painting areas, wherein e and E are both positive integers, 1≤e≤E; A painting scene matrix acquisition module, wherein the painting scene matrix acquisition module is used to collect the material shape, surface state and predicted painting environment information of the e-th electric vehicle painting area to obtain the e-th area painting scene matrix; A painting result acquisition module, the painting result acquisition module is used to obtain the expected painting result of the e-th area corresponding to the e-th electric vehicle painting area, and perform multi-layer painting parameter collaborative decision-making on the e-th electric vehicle painting area in combination with the e-th area painting scene matrix to establish a first painting collaborative decision-making space; A painting evaluation constraint optimization module, wherein the painting evaluation constraint optimization module is used to perform painting evaluation constraint optimization on the first painting collaborative decision space according to the painting prediction evaluation channel based on the painting scenario matrix of the e-th area and the expected painting result of the e-th area, and generate a painting candidate decision space; A painting optimization result acquisition module, wherein the painting optimization result acquisition module is used to optimize the painting candidate decision space by maximizing the painting fitness according to the painting fitness calculation channel, and obtain the painting optimization result of the e-th region; A sanitation vehicle painting module, which is used to add the painting optimization result of the e-th area to the electric vehicle painting optimization strategy, and paint the electric three-wheeled sanitation vehicle to be painted according to the electric vehicle painting optimization strategy.

Images