Workpiece cleaning method and cleaning system

Abstract

The present application relates to a kind of workpiece cleaning method and cleaning system, the workpiece to be cleaned is placed on conveying belt, conveying belt sends workpiece into workpiece identification module;Workpiece identification module identifies workpiece;Control module is according to the identification result received, in database query or calculate the cleaning parameter suitable for this workpiece, and send the setting result to cleaning parameter setting module;Cleaning parameter setting module is according to the setting result received, controls cleaning liquid circulation module;Spray head is cleaned to workpiece, and cleaning liquid is recycled in cleaning process;Cleanliness detection module detects the pollution degree on the surface of workpiece, and sends the detection result to control module;Control module is according to the detection result received, judges whether it needs to continue cleaning.The present application can realize the intelligent identification and cleaning of different types, size, shape, surface cleanliness workpiece, improves cleaning effect and resource utilization.

Description

TECHNICAL FIELD

[0001] The present application relates to a workpiece cleaning method and system, in particular to a workpiece cleaning method and system capable of automatically adjusting cleaning parameters and cleaning liquid treatment mode according to different types, sizes, shapes and surface cleanliness of workpieces. BACKGROUND

[0002] Workpiece cleaning is an important link in industrial production, which can remove impurities such as oil, dust and rust on the surface of workpieces, and improve the quality and performance of workpieces. At present, the commonly used workpiece cleaning methods are spray cleaning and immersion cleaning. Spray cleaning is to spray cleaning liquid to the surface of workpieces at a certain pressure and temperature by using a spray head, so as to achieve the purpose of cleaning. Immersion cleaning is to immerse workpieces in cleaning liquid containing cleaning agent, and use the chemical and mechanical effects of cleaning liquid to dissolve or fall off the contaminants on the surface of workpieces. The traditional workpiece cleaning method has the following problems: it cannot automatically adjust cleaning parameters (such as temperature, pressure, time, etc.) according to different types, sizes, shapes and surface cleanliness of workpieces, resulting in poor cleaning effect or waste of resources; it cannot automatically adjust cleaning liquid treatment mode according to different types, sizes, shapes and surface cleanliness of workpieces, resulting in unstable performance of cleaning liquid or unsuitability for workpieces; it cannot detect and feedback the contamination degree of workpiece surface, resulting in over-cleaning or insufficient cleaning. Therefore, it is necessary to provide a workpiece cleaning method and system capable of automatically adjusting cleaning parameters and cleaning liquid treatment mode according to different types, sizes, shapes and surface cleanliness of workpieces, so as to solve the above problems. SUMMARY

[0003] The technical problem solved by the method is that the traditional workpiece cleaning method cannot automatically adjust cleaning parameters according to different types, sizes, shapes and surface cleanliness of workpieces, resulting in poor cleaning effect or waste of resources.

[0004] A workpiece cleaning method, comprising the following steps:

[0005] Step 1: placing the workpiece to be cleaned on a conveyor belt, and conveying the workpiece into a workpiece recognition module by the conveyor belt;

[0006] Step 2: scanning the workpiece by the workpiece recognition module, identifying the type, size, shape and surface cleanliness characteristics of the workpiece, and sending the identification result to a control module;

[0007] Step 3: starting a parameter calculation module according to the received identification result, querying or calculating the cleaning parameters of temperature, pressure and time suitable for the workpiece from a database, and sending the setting result to a cleaning parameter setting module;

[0008] Step 4: The cleaning parameter setting module sends an instruction to the cleaning liquid calling module according to the received setting result, the cleaning liquid calling module extracts cleaning liquid from the cleaning liquid storage tank, and delivers the treated cleaning liquid to the spray head;

[0009] Step 5: The spray head cleans the workpiece, and the cleaning waste liquid enters the collection tank;

[0010] Step 6: The cleaning liquid collection module starts to work, filters and heats the cleaning liquid in the collection tank, and delivers the treated cleaning liquid to the cleaning liquid storage tank. The cleaning liquid is recycled during the cleaning process;

[0011] Step 7: The cleanliness detection module detects the degree of pollution on the surface of the workpiece and sends the detection result to the control module;

[0012] Step 8: The control module determines whether to continue cleaning according to the received detection result. If yes, steps 1 to 7 are repeated. If no, the cleaning process is ended;

[0013] Step 9: The workpiece meeting the requirements after cleaning is taken out from the conveying belt for subsequent processing or use.

[0014] In a preferred embodiment, when it is determined in step 7 that the workpiece needs to continue to be returned to the cleaning process, the cleaning counting module starts to work; when the cleaning counting module meets the following conditions J>J max , wherein J represents the number of times, J max represents the maximum number of times allowed for cleaning; the workpiece enters the manual intervention cleaning channel.

[0015] In a preferred embodiment, the workpiece recognition module comprises an image acquisition device, an image processing module, and a communication module; the image acquisition device is used to take pictures of the workpiece and obtain image data of the workpiece; the image processing module is used to pre-process, extract features, and classify the image data to obtain type, size, shape, and surface cleanliness feature data of the workpiece; and the communication module is used to send the feature data to the control module.

[0016] The image processing module adopts a convolutional neural network (CNN) to pre-process, extract features, and classify the image data, and adopts a support vector machine (SVM) to optimize and verify the output of the convolutional neural network (CNN).

[0017] In a preferred embodiment, the image processing module adopts a convolutional neural network (CNN) algorithm to pre-process, extract features, and classify the image data.

[0018] The type, size, shape and surface cleanliness of the workpiece are characterized by a mathematical model represented by the following image processing formula:

[0019] f(x) = max(0, x)

[0020] Wherein, f(x) represents an activation function; x represents an input signal;

[0021] y = W * x + b

[0022] Wherein, y represents an output signal; w represents a weight matrix; x represents an input signal; b represents a bias vector.

[0023]

[0024] Wherein, L represents a loss function; N represents the number of samples; K represents the number of categories; t nk represents the true value of the nth sample belonging to the kth category; y nk represents the predicted value of the nth sample belonging to the kth category.

[0025] In a preferred embodiment, the support vector machine (SVM) is used to optimize and verify the output of the convolutional neural network (CNN), and the support vector machine (SVM) is expressed by the following formula:

[0026]

[0027] Wherein, w represents a weight vector; b represents a bias scalar; C represents a penalty parameter; ξ i represents a relaxation variable. y = w T x + b

[0028] Wherein, y represents an output signal; w represents a weight vector; x represents an input signal; b represents a bias scalar.

[0029] y = sign(w T x + b)

[0030] Wherein, sign(x) represents a sign function, which returns 1 when x>0, -1 when x<0, and 0 when x=0.

[0031] In a preferred embodiment, the parameter calculation module is used to query or calculate the cleaning parameters suitable for the workpiece in the database according to the output of the workpiece recognition module, and an algorithm for calculating the temperature, pressure and time suitable for the workpiece is calculated according to the type, size, shape and surface cleanliness of the workpiece; The following formula is used to express:

[0032]

[0033] wherein, y represents an output variable; f(x1, x2, …, x n ) represents a fuzzy inference function; x1, x2, …, x n represent input variables; m represents the number of rules; w i represents the weight of the ith rule; y i represents the output of the ith rule.

[0034] In the preferred embodiment, the cleaning parameter setting module comprises a database module and a communication module; the database module is used to store the cleaning parameters corresponding to workpieces of different types, sizes, shapes and surface cleanliness, so that workpieces with the same cleaning parameters do not need to be repeatedly calculated; the database module is used to cache the cleaning parameters of workpieces being cleaned; and the communication module is used to send the cleaning parameters to the control module for controlling the workpieces being cleaned.

[0035] A workpiece cleaning system comprises a hardware part, a workpiece recognition module, a controller, a parameter calculation module, a cleaning parameter setting module, a cleaning liquid retrieval module, a cleaning liquid collection module and a cleanliness detection module; the hardware part comprises a conveying belt, a spray head arranged above the conveying belt, a collection tank arranged below the conveying belt, a liquid storage tank for preventing cleaning liquid, and a manual intervention cleaning channel arranged at the end of the conveying belt for transferring workpieces exceeding the maximum number of cleaning times;

[0036] The control module is used to receive the inputs of various modules, control the actions of various modules and realize the coordinated operation of the entire system;

[0037] The workpiece recognition module comprises an image acquisition device, an image processing module and a communication module; the image acquisition device and the control module realize bidirectional communication, are used to recognize the type, size, shape and surface cleanliness characteristics of a workpiece and send the recognition result to the control module;

[0038] The parameter calculation module and the control module realize bidirectional communication, query or calculate the cleaning parameters of temperature, pressure and time suitable for the workpiece from the database and send the setting result to the cleaning parameter setting module;

[0039] The cleaning parameter setting module and the control module realize bidirectional communication, are used to query or calculate the cleaning parameters of temperature, pressure and time suitable for the workpiece from the database according to the output of the workpiece recognition module and send the setting result to the control module;

[0040] The cleaning liquid circulation module and the control module realize bidirectional communication, are used to filter, heat and pressurize the cleaning liquid and deliver the processed cleaning liquid to the liquid storage tank;

[0041] The cleanliness detection module and the control module realize bidirectional communication, and are used for detecting the pollution degree of the surface of the cleaned workpiece, and sending the detection result to the control module.

[0042] The present application has the following advantages:

[0043] The artificial intelligence technology and high mathematical formula expression are adopted, the image processing and fuzzy logic technology are used, the workpiece feature recognition and the cleaning parameter setting are realized, the genetic algorithm technology is used, the cleaning liquid circulation module optimization control is realized, the cleanliness detection technology is used, and the cleaning effect feedback regulation is realized.

[0044] The fuzzy inference of the cleaning parameter can be realized, the most suitable cleaning parameter can be dynamically set according to the actual situation of the workpiece, and the cleaning effect and resource utilization rate are improved.

[0045] The cleaning liquid circulation module optimization control can be realized, the cleaning liquid is filtered, heated, pressurized and treated according to different cleaning parameters, so that the best cleaning effect is achieved, and the service life of the cleaning liquid is prolonged.

[0046] The system can realize intelligent recognition and individual cleaning of different types, sizes and shapes of workpieces, improve the cleaning efficiency and quality, and save cleaning liquid and energy. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 The flowchart of the method of the present application.

[0048] Figure 2 The principle diagram of the system of the present application. DETAILED DESCRIPTION

[0049] As shown in Figure 1 A workpiece cleaning method, comprising the following steps:

[0050] Step 1: Put the workpiece to be cleaned on the conveying belt, and the conveying belt sends the workpiece into the workpiece recognition module;

[0051] Step 2: The workpiece recognition module scans the workpiece, identifies the type, size, shape and surface cleanliness feature of the workpiece, and sends the identification result to the control module;

[0052] Step 3: The control module starts the parameter calculation module according to the received identification result, queries or calculates the cleaning parameters of temperature, pressure and time suitable for the workpiece from the database, and sends the setting result to the cleaning parameter setting module;

[0053] Step 4: The cleaning parameter setting module sends an instruction to the cleaning liquid calling module according to the received setting result, the cleaning liquid calling module extracts cleaning liquid from the cleaning liquid storage tank, and delivers the treated cleaning liquid to the spray head;

[0054] Step 5: The spray head cleans the workpiece, and the cleaning waste liquid enters the collection tank;

[0055] Step 6: The cleaning liquid collection module starts to start, filters and heats the cleaning liquid in the collection tank, and delivers the treated cleaning liquid to the cleaning liquid storage tank. The cleaning liquid is recycled during the cleaning process;

[0056] Step 7: The cleanliness detection module detects the degree of pollution on the surface of the workpiece and sends the detection result to the control module;

[0057] Step 8: The control module judges whether it is necessary to continue cleaning according to the received detection result, if yes, repeats steps 1 to 7, if not, ends the cleaning process;

[0058] Step 9: The workpiece meeting the requirements after cleaning is taken out from the conveying belt for subsequent processing or use.

[0059] In order to prevent a workpiece from entering a cleaning dead loop, the cleaning counting module starts to work when it is judged in step 7 that the workpiece needs to continue to return to cleaning; when the cleaning counting module meets the following conditions J>J max , wherein J represents the number of counts, J max represents the maximum number of cleaning allowed; the workpiece enters the manual intervention cleaning channel.

[0060] The workpiece recognition module comprises an image acquisition device, an image processing module and a communication module; the image acquisition device is used for photographing the workpiece to obtain image data of the workpiece; the image processing module is used for pre-processing, feature extraction and classification operation on the image data to obtain type, size, shape and surface cleanliness feature data of the workpiece; and the communication module is used for sending the feature data to the control module.

[0061] The image processing module adopts a convolutional neural network (CNN) for pre-processing, feature extraction and classification of the image data, and adopts a support vector machine (SVM) for optimization and verification of the output of the convolutional neural network (CNN).

[0062] In the preferred embodiment, the image processing module uses a convolutional neural network (CNN) algorithm for pre-processing, feature extraction, and classification of image data.

[0063] A mathematical model representing the type, size, shape, and surface cleanliness of the workpiece is obtained using the following image processing formula:

[0064] f(x) = max(0, x)

[0065] where f(x) represents the activation function; x represents the input signal;

[0066] y = W * x + b

[0067] where y represents the output signal; w represents the weight matrix; x represents the input signal; b represents the bias vector.

[0068]

[0069] where L represents the loss function; N represents the number of samples; K represents the number of classes; t nk represents the true value of the nth sample belonging to the kth class; y nk represents the predicted value of the nth sample belonging to the kth class.

[0070] The above uses image acquisition and image processing technologies to obtain image data of the workpiece through photography and scanning technologies; pre-processing and feature extraction technologies are used to process the image data and obtain feature data of the workpiece; classification technologies are used to analyze the feature data and obtain information such as the type, size, and shape of the workpiece. Convolutional neural networks and support vector machines are used to implement feature extraction and classification of image data through activation functions and weight matrices; loss functions and optimization algorithms are used to optimize and verify the output of CNN.

[0071] The support vector machine (SVM) is used to optimize and verify the output of the convolutional neural network (CNN), and the support vector machine (SVM) is expressed using the following formula:

[0072]

[0073] where w represents the weight vector; b represents the bias scalar; C represents the penalty parameter; ξ i represents the slack variable.

[0074] y = w T x + b

[0075] where y represents the output signal; w represents the weight vector; x represents the input signal; b represents the bias scalar.

[0076] y = sign(w T x + b)

[0077] Wherein, sign(x) represents a sign function, returns 1 when x>0, returns-1 when x<0, and returns 0 when x=0.

[0078] The above technology adopts weight vector and bias scalar and other technologies to realize linear mapping of the output of the CNN; through penalty parameter and relaxation variable and other technologies, the constraint and adjustment of the output of the CNN are realized; through the sign function and other technologies, the classification and judgment of the output of the CNN are realized.

[0079] In the preferred embodiment, the parameter calculation module is used to query or calculate the cleaning parameters suitable for the workpiece in the database according to the output of the workpiece recognition module, to calculate the temperature, pressure and time algorithm suitable for the workpiece through the type, size, shape and surface cleanliness of the workpiece; the following formula is used to express:

[0080]

[0081] Wherein, y represents the output variable; f(x1,x2,…,x n ) represents a fuzzy reasoning function; x1,x2,…,x n represent input variables; m represents the number of rules; w i represents the weight of the ith rule; y i represents the output of the ith rule.

[0082] The principle of the above formula is that different input independent variables x1,x2,…,x n represent type, size, shape and surface cleanliness, etc., because each workpiece is different in each case, represented by a numerical value, so that a different output variable y is finally obtained, and the cleaning parameter setting is determined according to the output variable y.

[0083] The cleaning parameter setting module includes a database module and a communication module; the database module is used to store the cleaning parameters corresponding to workpieces of different types, sizes, shapes and surface cleanliness, so that workpieces with the same cleaning parameters do not need to be calculated repeatedly; the database module is used to cache the cleaning parameters of the workpieces being cleaned; the communication module is used to send the cleaning parameters to the control module for controlling the workpieces being cleaned.

[0084] As Figure 2As shown, a workpiece cleaning system includes a hardware part, a workpiece recognition module, a controller, a parameter calculation module, a cleaning parameter setting module, a cleaning liquid retrieval module, a cleaning liquid collection module, and a cleanliness detection module. The hardware part includes a conveyor belt, a spray head arranged above the conveyor belt, a collection tank arranged below the conveyor belt, a liquid storage tank for preventing cleaning liquid, and a manual intervention cleaning channel arranged at the end of the conveyor belt for transferring workpieces exceeding the maximum number of cleaning times.

[0085] A control module is configured to receive inputs from each module, control the actions of each module, and realize coordinated operation of the entire system.

[0086] The workpiece recognition module includes an image acquisition device, an image processing module, and a communication module. The image acquisition device and the control module realize bidirectional communication, and are configured to identify the type, size, shape, and surface cleanliness characteristics of the workpiece, and send the identification result to the control module.

[0087] The parameter calculation module realizes bidirectional communication with the control module, queries or calculates the cleaning parameters (temperature, pressure, and time) suitable for the workpiece from a database, and sends the setting result to the cleaning parameter setting module.

[0088] The cleaning parameter setting module realizes bidirectional communication with the control module, queries or calculates the cleaning parameters (temperature, pressure, and time) suitable for the workpiece from a database according to the output of the workpiece recognition module, and sends the setting result to the control module.

[0089] The cleaning liquid circulation module realizes bidirectional communication with the control module, filters, heats, and pressurizes the cleaning liquid, and delivers the processed cleaning liquid to the liquid storage tank.

[0090] The cleanliness detection module realizes bidirectional communication with the control module, detects the contamination level of the surface of the cleaned workpiece, and sends the detection result to the control module.

[0091] In this embodiment, the specific workpiece type, size, shape, contamination level, cleanliness, and other data are shown in Table 1:

[0092] Workpiece No. Workpiece Type Workpiece Size (mm) Workpiece Shape Degree of Contamination Cleanliness 1 Steel Plate 100*200 Rectangle High Low 2 Aluminum Tube 50*500 Cylinder Medium Medium 3 Copper Ingot 80*80 Cube Low High

[0093] In this embodiment, the specific cleaning parameters (such as temperature, pressure, and time) are shown in Table 2:

[0094]

[0095]

[0096] In this embodiment, the specific cleaning effect is shown in Table 3:

[0097] Workpiece No. Cleanliness Test Result 1 Pass 2 Pass 3 Pass

[0098] In this embodiment, the specific cleaning liquid is water.

[0099] The above embodiments are only used for illustrating the technical solutions of the present application, but not for limiting the present application. Any modification, equivalent replacement, and improvement, etc. made to the present application within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0100] It should be noted that, in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or device. The principles and implementation modes of the technical solutions of the present application are described by applying specific examples. The above example is only used to help understand the method of the present application and its core idea. The above description is only the preferred embodiments of the present application. It should be pointed out that, due to the limited nature of the language expression, there are objectively infinite specific structures. For ordinary skilled persons in the technical field, without departing from the principles of the present application, a number of improvements, refinements, or changes can be made, or the above technical features can be combined in an appropriate manner. These improvements, refinements, changes, or combinations, or the direct application of the concepts and technical solutions of the present application to other occasions without improvement, shall be considered as the protection scope of the present application.

Claims

1. A method for cleaning a workpiece, characterized in that, Includes the following steps: Step 1: Place the workpiece to be cleaned onto the conveyor belt, and the conveyor belt will send the workpiece into the workpiece recognition module; Step 2: The workpiece recognition module scans the workpiece, identifies its type, size, shape, and surface cleanliness characteristics, and sends the recognition results to the control module. Step 3: Based on the received identification results, the control module activates the parameter calculation module to query or calculate the appropriate cleaning parameters for the workpiece, including temperature, pressure, and time, from the database; and sends the settings to the cleaning parameter setting module. Step 4: Based on the received setting results, the cleaning parameter setting module sends a command to the cleaning fluid retrieval module. The cleaning fluid retrieval module then draws cleaning fluid from the cleaning fluid storage tank and delivers the cleaning fluid to the spray head. Step 5: The spray head cleans the workpiece, and the cleaning waste liquid enters the collection tank; Step 6: The cleaning fluid collection module starts up, filters and heats the cleaning fluid in the collection tank, and then transports the treated cleaning fluid to the cleaning fluid storage tank. The cleaning fluid is recycled during the cleaning process. Step 7: The cleanliness detection module detects the degree of contamination on the workpiece surface and sends the detection results to the control module; Step 8: The control module determines whether cleaning needs to continue based on the received detection results. If yes, steps 1 to 7 are repeated; otherwise, the cleaning process ends. Step 9: Remove the cleaned and qualified workpieces from the conveyor belt for further processing or use; In step 7, if it is determined that the workpiece needs to be returned for cleaning, the cleaning counting module will start working; the cleaning counting module will start working when the following condition is met: J Where J represents the number of counts, This represents the maximum number of times the cleaning is allowed. The workpiece enters the manual cleaning channel; the workpiece identification module includes an image acquisition device, an image processing module, and a communication module. The image acquisition device is used to photograph the workpiece and acquire its image data; the image processing module is used to preprocess the image data, extract features, and classify it to obtain the workpiece's type, size, shape, and surface cleanliness characteristics. The communication module is used to send feature data to the control module; The image processing module employs a convolutional neural network (CNN) for preprocessing, feature extraction, and classification of image data; and a support vector machine (SVM) for optimizing and validating the output of the CNN.

2. The workpiece cleaning method according to claim 1, characterized in that, The image processing module employs a convolutional neural network (CNN) algorithm for preprocessing, feature extraction, and classification of image data. A mathematical model characterizing the type, size, shape, and surface cleanliness of the workpiece is obtained using the following image processing formula: in, Indicates the activation function; Indicates the input signal; in, Indicates the output signal; Represents the weight matrix; Indicates the input signal; Represents the bias vector; in, Represents the loss function; Indicates the number of samples; Indicates the number of categories; Indicates the first The sample belongs to the first The true values ​​of each category; Indicates the first The sample belongs to the first Predicted values ​​for each category.

3. The workpiece cleaning method according to claim 1, characterized in that, The Support Vector Machine (SVM) described above is used to optimize and validate the output of a Convolutional Neural Network (CNN). The Support Vector Machine (SVM) is expressed by the following formula: in, Represents the weight vector; Indicates a bias scalar; Indicates the penalty parameter; Represents slack variables; in, Indicates the output signal; Represents the weight vector; Indicates the input signal; Indicates a bias scalar; in, Represents a sign function, when When, return 1. When, return -1. If the value is 0, it returns 0.

4. The workpiece cleaning method according to claim 1, characterized in that, In step 3, the parameter calculation module is used to query or calculate the cleaning parameters suitable for the workpiece in the database based on the output of the workpiece identification module. It is used to calculate the appropriate temperature, pressure and time for the workpiece based on the type, size, shape and surface cleanliness of the workpiece. Expressed using the following formula: in, Indicates the output variable; Represents a fuzzy inference function; Indicates input variables; Indicates the number of rules; Indicates the first The weight of each rule; Indicates the first Output of the rules.

5. The workpiece cleaning method according to claim 1, characterized in that, The cleaning parameter setting module includes a database module and a communication module. The database module is used to store cleaning parameters corresponding to workpieces of different types, sizes, shapes, and surface cleanliness, so that workpieces with the same cleaning parameters do not need to be recalculated. The database module is used to cache the cleaning parameters that are being cleaned. The communication module is used to send cleaning parameters to the control module, which is used to control the workpiece being cleaned.

6. A workpiece cleaning system using the workpiece cleaning method according to any one of claims 1-5, characterized in that, It includes a hardware component, a workpiece identification module, a control module, a parameter calculation module, a cleaning parameter setting module, a cleaning fluid dispensing module, a cleaning fluid collection module, and a cleanliness detection module. The hardware component includes a conveyor belt, a spray head set above the conveyor belt, a collection tank set below the conveyor belt, a storage tank for storing cleaning fluid, and a manual intervention cleaning channel set at the end of the conveyor belt for transferring workpieces that have exceeded the maximum number of cleaning cycles. The control module receives input from each module, controls the actions of each module, and enables the coordinated operation of the entire system. The workpiece recognition module includes an image acquisition device, an image processing module, and a communication module. The image acquisition device and the control module communicate bidirectionally to identify the type, size, shape, and surface cleanliness characteristics of the workpiece, and send the recognition results to the control module. The parameter calculation module and the control module communicate bidirectionally. The module queries or calculates the appropriate cleaning parameters for the workpiece, such as temperature, pressure, and time, from the database and sends the settings to the cleaning parameter setting module. The cleaning parameter setting module and the control module communicate bidirectionally. Based on the output of the workpiece identification module, the module queries or calculates the appropriate cleaning parameters for the workpiece from the database: temperature, pressure, and time, and sends the setting results to the control module. The cleaning fluid circulation module and the control module communicate bidirectionally to filter, heat, and pressurize the cleaning fluid, and then deliver the treated cleaning fluid to the storage tank. The cleanliness detection module and the control module communicate bidirectionally to detect the degree of contamination on the surface of the cleaned workpiece and send the detection results to the control module.

Images