Surface attachment control method, device, equipment, storage medium and program

Abstract

The invention relates to the technical field of cleaning and paint removal, in particular to a surface attachment control method and device, equipment, a storage medium and a program.The method comprises the steps that a pre-constructed surface attachment control model is obtained, and current surface image data and current equipment control data, sent by an intelligent controller, of a target workpiece are received; wherein the current equipment control data is used for determining current equipment process parameters required for cleaning the surface attachments of the target workpiece; processing the current surface image data and the current equipment control data by using a surface attachment control model to obtain target equipment control data; wherein the target equipment control data is used for determining target equipment process parameters required for cleaning the surface attachments of the target workpiece; and sending the target equipment control data to the intelligent controller, so that the intelligent controller automatically controls the surface attachments by using the target equipment control data.

Description

Technical Field

[0001] The present disclosure relates to the technical field of cleaning and paint removal, and in particular to a method, device, equipment, storage medium and program for controlling surface attachments. Background Art

[0002] During operation, stains, old paint layers and other impurities will appear on the surface of the train bogie. These attachments will affect the surface condition of the train bogie, so it needs to be cleaned to restore its surface cleanliness, smoothness and original coating adhesion, in preparation for subsequent surface treatment or repainting.

[0003] However, in the related art, the control of the train bogie surface relies on manual operation, which is not conducive to reducing production costs, and the surface control efficiency is not high. Summary of the invention

[0004] The present invention provides a method, device, equipment, storage medium and program for controlling surface attachments, so as to reduce the dependence on manual operation, reduce production costs and improve surface control efficiency.

[0005] In a first aspect, the present disclosure provides a method for controlling surface attachments, which is applied to a host computer server and includes:

[0006] Acquire a pre-built surface attachment control model, and receive current surface image data and current equipment control data of the target workpiece sent by the intelligent controller;

[0007] Processing the current surface image data and the current device control data using the surface attachment control model to obtain target device control data;

[0008] The target device control data is sent to the intelligent controller, so that the intelligent controller automatically controls the surface attachment of the target workpiece by using the target device control data.

[0009] In some embodiments, the current surface image data includes two-dimensional surface image data and three-dimensional surface image data, and the current device control data is a set of device control data determined by the intelligent controller from multiple sets of preset device control data based on the current surface image data.

[0010] In some embodiments, the surface attachment control model includes a data input module, an image analysis module, a data integration module, a feature extraction module and a data output module; the process of using the surface attachment control model to process the current surface image data and the current device control data to obtain the target device control data includes:

[0011] Inputting the current surface image data into the image analysis module through the data input module, and extracting surface image features from the current surface image data using the image analysis module;

[0012] Inputting the current device control data into the data integration module through the data input module, and integrating the surface image features and the current device control data using the data integration module to obtain current surface integration data;

[0013] Utilizing the feature extraction module, extracting surface control feature data from the current surface integrated data;

[0014] The surface control feature data is fused using the data output module to obtain target device control data.

[0015] In some embodiments, the surface image feature includes but is not limited to at least one of the type, hardness and thickness of the surface attachment; the extracting the surface image feature from the current surface image data includes:

[0016] Cleaning the current surface image data to obtain cleaned surface image data;

[0017] Feature extraction is performed on the cleaned surface image data to obtain at least one of the type, hardness and thickness of the surface attachments.

[0018] In some embodiments, the method further comprises:

[0019] Receiving feedback device control data sent by the intelligent controller for the target device control data;

[0020] The surface deposit control model is updated using the target device control data and the feedback device control data.

[0021] In some embodiments, the target device control data includes target cleaning device control parameters and / or target laser device control parameters; wherein the target cleaning device control parameters include but are not limited to at least one or more of the target type of cleaning agent, target size, target injection speed and target injection angle, and the target laser device control parameters include but are not limited to at least one or more of the target laser power, target scanning speed and target focal position.

[0022] In a second aspect, the present disclosure provides a control device for surface attachments, which is applied to a host computer server, comprising:

[0023] An acquisition module, used for acquiring a pre-built surface attachment control model;

[0024] A communication module, used for receiving current surface image data of a target workpiece and current device control data sent by the intelligent controller;

[0025] A processing module, used for processing the current surface image data and the current device control data using the surface attachment control model to obtain target device control data;

[0026] The communication module is further used to send the target device control data to the intelligent controller, so that the intelligent controller automatically controls the surface attachment of the target workpiece by using the target device control data.

[0027] In a third aspect, the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above aspects.

[0028] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0029] In a fifth aspect, the present disclosure provides a computer program product, including a computer program / instructions, which implements the steps of the method described in the above aspects when the computer program is executed by a processor.

[0030] The present disclosure provides a method, device, equipment, storage medium and program for controlling surface attachments. The method obtains a pre-built surface attachment control model and receives current surface image data and current device control data of a target workpiece sent by an intelligent controller; processes the current surface image data and the current device control data using the surface attachment control model to obtain target device control data; and sends the target device control data to the intelligent controller so that the intelligent controller automatically controls the surface attachments of the target workpiece using the target device control data. This method can reduce dependence on manual operation, reduce production costs and improve surface control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0032] Figure 1 A topological architecture of a workpiece surface intelligent control system provided in an embodiment of the present disclosure;

[0033] Figure 2 A schematic flow chart of a method for controlling surface attachments provided in an embodiment of the present disclosure;

[0034] Figure 3A schematic diagram of a learning process of a surface attachment control model provided in an embodiment of the present disclosure;

[0035] Figure 4 A display interface of the laser device during paint removal provided by an embodiment of the present disclosure;

[0036] Figure 5 A schematic diagram of the structure of a control device for surface attachments provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device 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 units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0039] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] In order to completely remove stains, old paint layers and other impurities on the surface of train bogies to restore their surface cleanliness, smoothness and original coating adhesion, and prepare for subsequent surface treatment or repainting. Generally, the maintenance plan for train bogies can include dry ice cleaning and laser paint removal. The following describes the dry ice cleaning and laser paint removal plans respectively.

[0041] 1. Dry ice cleaning solution

[0042] (1) Composition of dry ice cleaning equipment

[0043] Dry ice cleaning equipment mainly consists of dry ice particle preparation system, injection system, dry ice control system and dry ice recovery system.

[0044] Dry ice particle preparation system: responsible for converting solid dry ice into dry ice particles of appropriate size to meet different cleaning requirements. Here, the specific size range of the dry ice particles can be determined according to the actual application scenario, and the embodiments of the present disclosure do not specifically limit this.

[0045] Spraying system: includes a nozzle and a spraying pipe, which sprays dry ice particles onto the surface of the workpiece at high speed to clean the surface of the workpiece.

[0046] Dry ice control system: collects sensor data and adjusts dry ice cleaning equipment control parameters through an intelligent controller (Programmable Logic Controller, PLC controller). Here, the dry ice cleaning equipment control parameters may include but are not limited to at least one or more of the size of dry ice particles, spray speed and spray angle.

[0047] Dry ice recovery system: collects dry ice particles and dust generated during the workpiece surface cleaning process for recycling.

[0048] (2) Process flow

[0049] a. Place the workpiece to be cleaned in the cleaning area and ensure that the workpiece is stable and easy to operate.

[0050] b. Set appropriate dry ice cleaning equipment control parameters through the control system, including the size of dry ice particles, spray speed and spray angle.

[0051] c. Start the dry ice cleaning equipment, and spray the dry ice particles prepared by the dry ice particle preparation system onto the surface of the workpiece at high speed through the spray system to clean the surface of the workpiece. The dry ice particles sublimate quickly when they come into contact with the surface of the workpiece, generating impact force to peel off the dirt and paint on the surface.

[0052] d. During the cleaning process, the recovery system continuously collects dry ice particles and dust to keep the cleaning area clean.

[0053] e. Observe the cleaning effect manually and adjust the control parameters of the dry ice cleaning equipment as needed. When the surface of the workpiece is clean, turn off the dry ice cleaning equipment.

[0054] It should be noted that during the dry ice cleaning operation, workers need to wear protective glasses and gloves to prevent injury caused by splashing dry ice particles. At the same time, the cleaning area needs to be well ventilated to avoid accumulation of dry ice particles and dust.

[0055] 2. Laser paint removal solution

[0056] (1) Composition of laser paint removal equipment

[0057] Laser paint removal equipment mainly includes laser generator, optical system, working platform and laser control system.

[0058] Laser generator: produces high-energy laser beam.

[0059] Optical system: guides and focuses the laser beam onto the workpiece surface.

[0060] Working platform: used to place the workpiece to be depainted, and the position and angle can be adjusted.

[0061] Laser control system: The PLC controller is used to collect sensor data and adjust the control parameters of the laser paint removal equipment. Here, the control parameters of the laser paint removal equipment may include but are not limited to at least one or more of laser power, scanning speed and focus position.

[0062] (2) Process flow

[0063] a. Place the workpiece to be depainted on the work platform and adjust the position and angle to suit the laser scanning.

[0064] b. Set appropriate laser paint removal equipment control parameters through the control system, including laser power, scanning speed and focus position.

[0065] c. Start the laser paint removal equipment and irradiate the laser beam to the surface of the workpiece. The laser beam instantly generates high temperature, causing the paint layer to burn and fall off quickly.

[0066] d. Observe the paint removal effect manually to ensure that the laser beam accurately irradiates the target area and avoids damage to the surrounding area. Adjust the control parameters of the laser paint removal equipment as needed to obtain the best paint removal effect.

[0067] e. When the paint layer on the workpiece surface is completely peeled off, turn off the laser paint removal equipment.

[0068] It should be noted that during the laser paint removal process, workers need to wear protective glasses and protective clothing to prevent damage caused by laser radiation and splashes. At the same time, workers must also ensure that the work platform is stable and the workpiece is firmly fixed to prevent the workpiece from moving or shaking during the laser scanning process.

[0069] In actual applications, due to the different conditions of dirt and paint on the surface of train bogies, traditional fixed parameter operation methods often fail to achieve the best results; and, as can be seen from the above description, both dry ice cleaning solutions and laser paint removal solutions rely on manual experience, requiring manual observation of the state of attachments such as stains, old paint layers and other impurities on the workpiece surface, and adjusting corresponding equipment control parameters (such as dry ice cleaning equipment control parameters or laser paint removal equipment control parameters) as needed. Therefore, intelligent control of the workpiece surface cannot be achieved.

[0070] Based on this, an embodiment of the present disclosure provides a method for controlling surface attachments, which is applied to a host computer server. The host computer server is used to analyze the real-time surface monitoring data of the workpiece through an intelligent controller and in combination with a machine learning model to determine the equipment control data of the workpiece, so as to use the equipment control data to realize automatic control of the surface attachments of the workpiece, thereby reducing dependence on manual operation, reducing production costs, and improving the control efficiency of the surface attachments of the workpiece.

[0071] In order to implement the above-mentioned method for controlling surface attachments, an embodiment of the present disclosure provides a workpiece surface intelligent control system for controlling attachments on the workpiece surface. Figure 1 The topological architecture of a workpiece surface intelligent control system provided by the embodiment of the present disclosure. Figure 1 As shown, the workpiece surface intelligent control system can generally include a high-precision three-dimensional camera, an image processing and analysis module, a machine learning model library, an intelligent controller (i.e., a PLC controller), and dry ice cleaning equipment and laser paint removal equipment. A three-dimensional camera is introduced into the workpiece surface intelligent control system. For example, a three-dimensional camera can be installed in the dry ice cleaning area and the laser paint removal area, and the three-dimensional camera can be used to capture high-definition video image data of the surface of the train bogie to monitor the dirt distribution and paint removal of the workpiece surface in real time.

[0072] Then, the PLC controller can send the high-definition video image data captured by the three-dimensional camera and the current equipment control data to the host computer server. Here, the equipment control data can be the equipment process parameters for cleaning the attachments on the surface of the workpiece, which can include dry ice cleaning equipment control parameters and laser paint removal equipment control parameters. Among them, the dry ice cleaning equipment control parameters can include but are not limited to at least one or more of the size of the dry ice particles, the spray speed and the spray angle, and the laser paint removal equipment control parameters can include but are not limited to at least one or more of the laser power, the scanning speed and the focus position.

[0073] The host server can process the high-definition video image data through the image processing and analysis module, and combine it with the machine learning model library and use the machine learning algorithm to model the collected sensor data (such as high-definition video image data and two-dimensional image data) and equipment control data, learn how to evaluate the degree of dirt and oil stains based on the high-definition video image data of the three-dimensional camera, and create a surface attachment control model.

[0074] The host server can automatically adjust the control parameters of the dry ice cleaning equipment and the laser paint removal equipment based on the analysis results of the surface attachment control model. Based on this, the host server can intelligently adjust and optimize the control parameters of the dry ice cleaning equipment and the laser paint removal equipment to achieve more efficient and uniform cleaning and paint removal effects.

[0075] Based on the intelligent control system of the workpiece surface, a method for controlling surface attachments provided by an embodiment of the present disclosure is specifically described below.

[0076] Embodiment 1

[0077] Figure 2 The following is a flow chart of a method for controlling surface attachments provided by an embodiment of the present disclosure. Figure 2 As shown, a method for controlling surface attachments comprises:

[0078] S201, acquiring a pre-built surface attachment control model, and receiving current surface image data and current device control data of a target workpiece sent by an intelligent controller;

[0079] S202, using the surface attachment control model to control the current surface image data and the current device

[0080] Process the control data of the target device to obtain the control data of the target device;

[0081] S203, sending the target device control data to the intelligent controller, so that the intelligent controller automatically controls the surface attachments using the target device control data.

[0082] Specifically, the target workpiece may be a train bogie, or other workpieces with a control requirement for surface attachments, which is not specifically limited in the present embodiment. In the method of the present embodiment, the target workpiece is a train bogie as an example for explanation.

[0083] The above-mentioned surface attachments may be stains, old paint layers and other impurities located on the surface of the target workpiece. These surface attachments may affect the surface cleanliness, smoothness and original coating adhesion of the target workpiece. Therefore, it is necessary to control the surface attachments of the target workpiece to ensure that the surface state of the target workpiece meets actual needs.

[0084] The embodiment of the present disclosure may perform model training in advance to obtain a surface attachment control model. The network architecture of the surface attachment control model may include but is not limited to one of a deep learning algorithm, a support vector machine, and a decision tree, which is not specifically limited in the embodiment of the present disclosure.

[0085] The surface attachment control model can be used to predict the target device control data based on the current surface image data and the current device control data. Here, the current device control data can be used to determine the current device process parameters required for cleaning the surface attachments of the target workpiece; the target device control data can be used to determine the target device process parameters required for cleaning the surface attachments of the target workpiece. Therefore, by comparing the current device process parameters with the target device process parameters, it can be determined whether the current device process parameters meet the needs for optimization to achieve the target device process parameters, that is, the target device control data can be used to evaluate whether the current device control data needs to be optimized, thereby ensuring that the surface state of the target workpiece meets the actual needs.

[0086] After determining the target device control data, the host computer server returns the target device control data to the intelligent controller, so that the intelligent controller controls the surface attachments of the target workpiece according to the target device control data, thereby realizing intelligent automatic control of the surface attachments of the workpiece, reducing dependence on manual operation, reducing production costs, and improving surface control efficiency.

[0087] At the same time, the host server uses machine learning intelligent algorithms to determine the target device control data, which can reduce the number of times surface attachments are cleaned, avoid repeated cleaning, improve work efficiency and reduce energy consumption.

[0088] According to the technical solution of the embodiment of the present disclosure, by acquiring a pre-built surface attachment control model and receiving the current surface image data and current device control data of the target workpiece sent by the intelligent controller; using the surface attachment control model to process the current surface image data and the current device control data to obtain target device control data; sending the target device control data to the intelligent controller so that the intelligent controller uses the target device control data to automatically control the surface attachments of the target workpiece, it is possible to reduce dependence on manual operation, reduce production costs, and improve surface control efficiency.

[0089] Embodiment 2

[0090] Based on the above embodiment, the current surface image data includes two-dimensional surface image data and three-dimensional surface image data, and the current device control data is a set of device control data determined by the intelligent controller from multiple sets of preset device control data based on the current surface image data.

[0091] Specifically, the embodiment of the present disclosure can capture a two-dimensional image and a three-dimensional image of the surface of the target workpiece respectively, so as to more accurately obtain the surface information of the target workpiece. Therefore, in the method of the embodiment of the present disclosure, the current surface image data can include two-dimensional surface image data and three-dimensional surface image data.

[0092] The two-dimensional surface image data can be collected by a two-dimensional camera, and the three-dimensional surface image data can be collected by a three-dimensional camera. The image collection areas of the two-dimensional camera and the three-dimensional camera at least cover the surface of the target workpiece. Figure 1 As shown, in the embodiment of the present disclosure, a two-dimensional camera and a three-dimensional camera can be installed in the dry ice cleaning area and the laser paint removal area, and the three-dimensional camera can be used to capture the three-dimensional high-definition video image data of the surface of the train bogie, and the dirt distribution and paint removal of the workpiece surface can be monitored in real time. The two-dimensional surface image data collected by the two-dimensional camera can be used to assist the three-dimensional high-definition video image data to more accurately determine and obtain the surface information of the train bogie.

[0093] The disclosed embodiment can also pre-store multiple sets of preset device control data in the intelligent controller, which correspond to different cleaning solutions for surface attachments. Therefore, after acquiring the current surface image data, the intelligent controller can select a set of device control data from the multiple sets of preset device control data as the cleaning solution for surface attachments corresponding to the current surface image data, which can provide a reference for the host computer server and improve the efficiency of determining the target device control data.

[0094] It should be noted that in the method of the embodiment of the present disclosure, the current surface image data and the current device control data are transmitted through the standard interface between the host server and the intelligent controller, and the current surface image data is acquired by the intelligent controller using the data transmission link of the sensor.

[0095] Embodiment 3

[0096] On the basis of the above-mentioned embodiment, the surface attachment control model includes a data input module, an image analysis module, a data integration module, a feature extraction module and a data output module; the surface attachment control model is used to process the current surface image data and the current device control data to obtain the target device control data, including:

[0097] Inputting the current surface image data into the image analysis module through the data input module, and extracting the surface image features from the current surface image data using the image analysis module;

[0098] Inputting the current device control data into the data integration module through the data input module, and integrating the surface image features and the current device control data using the data integration module to obtain the current surface integration data;

[0099] Utilizing a feature extraction module, surface control feature data is extracted from current surface integration data;

[0100] The data output module is used to fuse the surface control feature data to obtain the target device control data.

[0101] Specifically, Figure 3 Schematic diagram of the learning process of a surface attachment control model provided by the embodiment of the present disclosure. Figure 3 As shown, the host server can use machine learning algorithms to model the collected sensor data and equipment control data, learn how to evaluate the degree of dirt and oil stains based on the high-definition video image data of the 3D camera, and integrate the sensor data collected by the PLC controller into the database of the host server. The machine learning algorithm can extract features from the sensor data and equipment control data, design process models, and verify the process models until the cleaning and paint removal effect requirements are met, the model learning is successfully created, and the surface attachment control model is obtained.

[0102] The surface attachment control model may include a data input module, an image analysis module, a data integration module, a feature extraction module and a data output module. After obtaining the surface attachment control model, the embodiment of the present disclosure may use the surface attachment control model to process the current surface image data and the current device control data to obtain the target device control data.

[0103] The specific process is as follows: input the current surface image data into the image analysis module through the data input module, and use the image analysis module to extract surface image features from the current surface image data; input the current device control data into the data integration module through the data input module, and use the data integration module to integrate the surface image features and the current device control data to obtain the current surface integrated data; use the feature extraction module to extract surface control feature data from the current surface integrated data; use the data output module to fuse the surface control feature data to obtain the target device control data.

[0104] The disclosed embodiments can construct a surface attachment control model through a machine learning intelligent algorithm, and predict the target device control data corresponding to the current surface image data and the current device control data through the surface attachment control model, so that the intelligent controller can accurately control the surface attachment of the target workpiece, reduce the number of times the surface attachment is cleaned, avoid repeated cleaning and paint removal, improve work efficiency, and reduce the energy consumption of cleaning equipment.

[0105] Embodiment 4

[0106] On the basis of the above embodiment, the surface image feature includes but is not limited to at least one of the type, hardness and thickness of the surface attachment; extracting the surface image feature from the current surface image data includes:

[0107] Cleaning the current surface image data to obtain cleaned surface image data;

[0108] Feature extraction is performed on the surface image data after cleaning to obtain at least one of the type, hardness and thickness of the surface attachments.

[0109] Specifically, the surface image features include but are not limited to at least one of the type, hardness and thickness of the surface attachments. These surface image features can be used to determine in real time the distribution and removal status of the surface attachments of the target workpiece, such as the distribution of dirt and the removal status of paint, to improve monitoring efficiency.

[0110] When extracting surface image features from current surface image data, the disclosed embodiment can first clean the current surface image data to obtain cleaned surface image data. At this time, the cleaned surface image data can reduce interference in subsequent feature extraction, accurately extract surface features, and thus improve the recognition accuracy of the surface information of the target workpiece.

[0111] Embodiment 5

[0112] Based on the above embodiment, the method may further include:

[0113] Receiving feedback device control data for target device control data sent by the intelligent controller;

[0114] The surface deposit control model is updated using the target device control data and the feedback device control data.

[0115] Specifically, after the host computer service sends the target device control data to the intelligent controller, the intelligent controller can use the target device control data to automatically control the surface attachment. At this time, the intelligent controller can also send feedback device control data for the target device control data to the host computer server.

[0116] After receiving the feedback device control data, the host server can further optimize the surface deposition control model. For example, the surface deposition control model can be updated using the target device control data and the feedback device control data. In this way, the adjustment effect can be monitored, and the model can be trained multiple times according to the actual situation of the target workpiece surface to improve the running-in degree between the surface deposition control model and the equipment operation; at the same time, the process parameters can be automatically adjusted to enhance the adaptability of the process to different dirt and paint conditions, and at the same time, the adaptability of the surface deposition control model can also be improved.

[0117] Embodiment 6

[0118] Based on the above embodiments, the target device control data includes target cleaning device control parameters and / or target laser device control parameters; wherein the target cleaning device control parameters include but are not limited to at least one or more of the target type of cleaning agent, target size, target injection speed and target injection angle, and the target laser device control parameters include but are not limited to at least one or more of the target laser power, target scanning speed and target focal position.

[0119] Specifically, the target device control data may include target cleaning device control parameters, and the target cleaning device control parameters include but are not limited to at least one or more of the target type, target size, target injection speed, and target injection angle of the cleaning agent. Here, the cleaning agent may be dry ice or other cleaning agents with cleaning properties, and the exemplary embodiment of the present disclosure does not specifically limit this. Based on this, the embodiment of the present disclosure can clean the surface attachments of the target workpiece by dry ice cleaning equipment.

[0120] The target device control data may also include target laser device control parameters, which include but are not limited to at least one or more of target laser power, target scanning speed, and target focal position. Based on this, the embodiment of the present disclosure can perform paint removal operation on the surface of the target workpiece by laser paint removal equipment. Figure 4 The display interface of the laser device provided in the embodiment of the present disclosure during the paint removal process. Figure 4 As shown, the target laser device control parameters can be displayed in the display interface.

[0121] Embodiment 7

[0122] Based on the above embodiments, this embodiment provides an application example.

[0123] The present embodiment provides a method for controlling surface attachments, which can optimize the maintenance scheme of the train bogie mentioned above, including a dry ice cleaning scheme and a laser paint removal scheme, so as to realize automatic quantitative analysis of cleaning dirt and removing paint oil stains, and combine the sensor data and equipment control data collected by the PLC controller to optimize the process parameters through machine learning modeling to realize digital intelligent production.

[0124] In this embodiment, the attachments on the workpiece surface can be controlled by the workpiece surface intelligent control system. The topological architecture of the workpiece surface intelligent control system is as follows: Figure 2 As shown, the workpiece surface intelligent control system can generally include a high-precision 3D camera, an image processing and analysis module, a machine learning model library, an intelligent control system, and dry ice cleaning equipment and laser paint removal equipment. By introducing a 3D camera into the workpiece surface intelligent control system, for example, a 3D camera can be installed in the dry ice cleaning area and the laser paint removal area, and the 3D camera can be used to capture high-definition video image data of the surface of the train bogie, and monitor the dirt distribution and paint removal of the workpiece surface in real time.

[0125] The workpiece surface intelligent control system can send the high-definition video image data captured by the three-dimensional camera to the data computing platform in the host computer server through a dedicated data transmission line. At the same time, the sensor data (three-dimensional high-definition video image data captured by the three-dimensional camera and two-dimensional image data captured by the two-dimensional camera) and the device control data collected by the PLC controller can be uploaded to the host computer server through a standard interface. Here, the device control data corresponds to the sensor data, which can be a set of device control data among multiple sets of preset device control data.

[0126] like Figure 3 As shown, the host server can use machine learning algorithms to model the collected sensor data and equipment control data, learn how to evaluate the degree of dirt and oil stains based on the high-definition video image data of the 3D camera, and integrate the sensor data collected by the PLC controller into the database of the host server. The machine learning algorithm can extract features from the sensor data and equipment control data, design process models, and verify the process models until the cleaning and paint removal effect requirements are met, the model learning is successfully created, and the surface attachment control model is obtained.

[0127] At this time, the host computer server can automatically adjust the control parameters of the dry ice cleaning equipment and the laser paint removal equipment based on the analysis results of the surface attachment control model; wherein the control parameters of the dry ice cleaning equipment may include but not limited to at least one or more of the size of the dry ice particles, the spray speed and the spray angle, and the control parameters of the laser paint removal equipment may include but not limited to at least one or more of the laser power, the scanning speed and the focus position. Based on this, the host computer server can intelligently adjust and optimize the control parameters of the dry ice cleaning equipment and the laser paint removal equipment to achieve more efficient and uniform cleaning and paint removal effects.

[0128] In the above process, the host computer server can clean and process the data according to the real-time monitoring data of the 3D camera; and model, train and experiment the 3D camera data according to the big data modeling analysis. The goal is to output the predicted values ​​of process parameters such as cleaning pressure and laser gear position as the analysis results of the surface attachment control model based on the oil pollution and paint thickness measured by the 3D camera. Then, the analysis results are fed back to the PLC controller in real time, and the PLC controller adjusts the process parameters and performs real-time feedback adjustment at the same time. In addition, the host computer server can also monitor the adjustment effect, and train the model multiple times according to the cleaning and paint removal effect and data mechanism to improve the running-in degree of the surface attachment control model and the equipment operation.

[0129] In this embodiment, the host computer server can establish a new closed-loop control system with the original control system of the PLC controller, and the machine learning model and optimization algorithm (i.e., the surface attachment control model) run in the host computer server as the auxiliary intelligent brain of the PLC controller. In this way, the host computer server in the closed-loop control system can automatically adjust the process parameters (including the control parameters of the dry ice cleaning equipment and the control parameters of the laser paint removal equipment) according to the real-time sensor data and image data, and pass them to the PLC controller to realize intelligent control, while not affecting the manual operation function of the original control system, reducing the cost of transformation.

[0130] The above-mentioned machine learning models and optimization algorithms may include deep learning algorithms, support vector machines, decision trees, etc., which are used to evaluate and optimize process parameters based on surface information.

[0131] Based on this, the technical solution of this embodiment can bring the following beneficial effects:

[0132] 1. Improve process efficiency: Through intelligent control, the dependence on manual operation is reduced, and the efficiency of dry ice cleaning and laser paint removal processes is improved.

[0133] 2. Ensure process quality: Through intelligent video analysis and machine learning modeling, indicators are quantified instead of manual experience observation values. While improving the monitoring level, it can also ensure that the quality of cleaning and paint removal is stable and achieves the best effect.

[0134] 3. Reduce costs: Production costs can be reduced by reducing manual operations and improving process efficiency.

[0135] 4. Improve adaptability: Automatically adjust process parameters according to the actual conditions of the train bogie surface, enhancing the adaptability of the process to different dirt and paint conditions.

[0136] The above mainly introduces the scheme provided by the embodiment of the present disclosure. It is understandable that in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment disclosed in this article, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0137] The disclosed embodiment can divide the electronic device into functional units according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the disclosed embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0138] In the case of dividing each functional module according to each function, an embodiment of the present disclosure provides a control device for a surface attachment, which is applied to a host computer server. The control device for the surface attachment may be a host computer server or a chip applied to the host computer server. Figure 5 This is a schematic diagram of the structure of a control device for surface attachments provided by an embodiment of the present disclosure. Figure 5 As shown, the device 500 includes:

[0139] An acquisition module 501 is used to acquire a pre-built surface attachment control model;

[0140] The communication module 502 is used to receive the current surface image data and current device control data of the target workpiece sent by the intelligent controller;

[0141] A processing module 503 is used to process the current surface image data and the current device control data using the surface attachment control model to obtain target device control data;

[0142] The communication module 502 is further configured to send the target device control data to the intelligent controller, so that the intelligent controller automatically controls the surface attachments of the target workpiece using the target device control data.

[0143] In some embodiments, the current surface image data includes two-dimensional surface image data and three-dimensional surface image data, and the current device control data is a set of device control data determined by the intelligent controller from multiple sets of preset device control data based on the current surface image data.

[0144] In some embodiments, the surface attachment control model includes a data input module, an image analysis module, a data integration module, a feature extraction module, and a data output module;

[0145] The processing module 503 is also used to input the current surface image data into the image analysis module through the data input module, and use the image analysis module to extract surface image features from the current surface image data; input the current device control data into the data integration module through the data input module, and use the data integration module to integrate the surface image features and the current device control data to obtain current surface integrated data; use the feature extraction module to extract surface control feature data from the current surface integrated data; use the data output module to fuse the surface control feature data to obtain target device control data.

[0146] In some embodiments, the surface image feature includes but is not limited to at least one of the type, hardness and thickness of the surface attachment;

[0147] The processing module 503 is further used to clean the current surface image data to obtain cleaned surface image data; perform feature extraction on the cleaned surface image data to obtain at least one of the type, hardness and thickness of the surface attachments.

[0148] In some embodiments, the communication module 501 is further used to receive feedback device control data sent by the intelligent controller for the target device control data;

[0149] The processing module 503 is further configured to update the surface attachment control model using the target device control data and the feedback device control data.

[0150] In some embodiments, the target device control data includes target cleaning device control parameters and / or target laser device control parameters; wherein the target cleaning device control parameters include but are not limited to at least one or more of the target type of cleaning agent, target size, target injection speed and target injection angle, and the target laser device control parameters include but are not limited to at least one or more of the target laser power, target scanning speed and target focal position.

[0151] On the basis of the above embodiments, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above embodiments.

[0152] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0153] In some implementations of this embodiment, a computer program product is provided, including a computer program / instructions, and when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0154] The processor may include, but is not limited to, one or more processors or microprocessors, etc. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the methods in the above embodiments.

[0155] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the computer-readable storage medium may include but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0156] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0157] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0158] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0159] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0160] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0161] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0162] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A method for controlling surface attachments, characterized in that: Applied to host server, including: Acquire a pre-built surface attachment control model, and receive current surface image data and current equipment control data of the target workpiece sent by the intelligent controller; Processing the current surface image data and the current device control data using the surface attachment control model to obtain target device control data; The target device control data is sent to the intelligent controller, so that the intelligent controller automatically controls the surface attachment of the target workpiece by using the target device control data.

2. The method according to claim 1, characterized in that The current surface image data includes two-dimensional surface image data and three-dimensional surface image data, and the current device control data is a set of device control data determined by the intelligent controller from multiple sets of preset device control data based on the current surface image data.

3. The method according to claim 1, characterized in that The surface attachment control model includes a data input module, an image analysis module, a data integration module, a feature extraction module and a data output module; the current surface image data and the current device control data are processed by the surface attachment control model to obtain the target device control data, including: Inputting the current surface image data into the image analysis module through the data input module, and extracting surface image features from the current surface image data using the image analysis module; Inputting the current device control data into the data integration module through the data input module, and integrating the surface image features and the current device control data using the data integration module to obtain current surface integration data; Utilizing the feature extraction module, extracting surface control feature data from the current surface integrated data; The surface control feature data is fused using the data output module to obtain target device control data.

4. The method according to claim 3, characterized in that The surface image feature includes but is not limited to at least one of the type, hardness and thickness of the surface attachment; the extracting the surface image feature from the current surface image data includes: Cleaning the current surface image data to obtain cleaned surface image data; Feature extraction is performed on the cleaned surface image data to obtain at least one of the type, hardness and thickness of the surface attachments.

5. The method according to claim 1, characterized in that The method further comprises: Receiving feedback device control data sent by the intelligent controller for the target device control data; The surface deposit control model is updated using the target device control data and the feedback device control data.

6. The method according to any one of claims 1 to 5, characterized in that: The target device control data includes target cleaning device control parameters and / or target laser device control parameters; wherein the target cleaning device control parameters include but are not limited to at least one or more of the target type of cleaning agent, target size, target injection speed and target injection angle, and the target laser device control parameters include but are not limited to at least one or more of the target laser power, target scanning speed and target focal position.

7. A control device for surface attachments, characterized in that: Applied to host server, including: An acquisition module, used for acquiring a pre-built surface attachment control model; A communication module, used for receiving current surface image data of a target workpiece and current device control data sent by the intelligent controller; A processing module, used for processing the current surface image data and the current device control data using the surface attachment control model to obtain target device control data; The communication module is further used to send the target device control data to the intelligent controller, so that the intelligent controller automatically controls the surface attachment of the target workpiece by using the target device control data.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images