Part cleaning method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of precision machining, in particular to a part cleaning method and device, computer equipment and a storage medium, and the method comprises the steps: collecting part information and part images of a to-be-cleaned part, carrying out the feature extraction of the part images, obtaining surface image features, carrying out the cleanliness evaluation of the surface image features, and obtaining initial cleanliness parameters; a cleaning time correction index corresponding to the initial cleanliness parameter is matched from the database, N cleaning operations are determined according to the part information, the cleaning time corresponding to each cleaning operation is calculated according to the cleaning time correction index and the part information, and the part to be cleaned is cleaned according to the cleaning time corresponding to each cleaning operation. And cleaning is completed. The cleaning time of the to-be-cleaned part is calculated according to the part information of the to-be-cleaned part and the cleaning time correction index, and the cleaning time is automatically and accurately configured for different parts, so that self-adaptive cleaning with controllable cleaning time is realized, and the cleaning efficiency of the parts is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of precision machining, and particularly to a method and device for cleaning parts, a computer device, and a storage medium. Background Art

[0002] Part cleaning refers to the process of removing contaminants such as dirt, grease, chips, and residues on the surfaces of various parts during industrial production and maintenance, ensuring that the surfaces of the parts are clean and not affected by contaminants when in use.

[0003] Currently, the cleaning of parts using a cleaning machine usually includes multiple cleaning steps, and the operator needs to manually set the time parameters for each step. In some specific applications, the size and shape of the parts may limit the use of high-pressure spraying. To ensure the cleaning effect and integrity of the parts, appropriate cleaning time and cleaning methods need to be adopted during the cleaning process.

[0004] Therefore, how to automatically and accurately configure the cleaning time for different parts to achieve adaptive cleaning with controllable cleaning time has become an urgent problem to be solved. Summary of the Invention

[0005] Based on this, the present invention provides a method and device for cleaning parts, a computer device, and a storage medium to solve the problem of how to automatically and accurately configure the cleaning time for different parts to achieve adaptive cleaning with controllable cleaning time.

[0006] In a first aspect, an embodiment of the present invention provides a method for cleaning parts, including: Collecting part information and part images of the part to be cleaned, extracting features from the part images to obtain surface image features; Evaluating the cleanliness of the surface image features to obtain an initial cleanliness parameter, and matching a cleaning time correction index corresponding to the initial cleanliness parameter from a database; Determining N cleaning operations according to the part information, and calculating the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero; Performing cleaning on the part to be cleaned according to the cleaning time corresponding to each cleaning operation until the cleaning is completed.

[0007] In a second aspect, an embodiment of the present invention provides a device for cleaning parts, including: An image feature acquisition module, configured to collect part information and part images of the part to be cleaned, extract features from the part images to obtain surface image features; A correction index matching module is used to evaluate the cleanliness of the surface image features to obtain initial cleanliness parameters, and match a cleaning time correction index corresponding to the initial cleanliness parameters from a database; A calculation module is used to determine N cleaning operations according to the part information, and calculate the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero; A cleaning module is used to perform cleaning on the part to be cleaned according to the cleaning time corresponding to each cleaning operation until the cleaning is completed.

[0008] In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the part cleaning method described in the first aspect above is implemented.

[0009] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the part cleaning method described in the first aspect above is implemented.

[0010] The beneficial effects of the present invention compared with the prior art are as follows: By collecting the part information and part image of the part to be cleaned, extracting the features of the part image to obtain surface image features, evaluating the cleanliness of the surface image features to obtain initial cleanliness parameters, matching a cleaning time correction index corresponding to the initial cleanliness parameters from a database, determining N cleaning operations according to the part information, calculating the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero, and performing cleaning on the part to be cleaned according to the cleaning time corresponding to each cleaning operation until the cleaning is completed. Calculate the cleaning time of the part to be cleaned through the part information of the part to be cleaned and the cleaning time correction index, and automatically configure the cleaning time accurately for different parts to achieve adaptive cleaning with controllable cleaning time and improve the cleaning efficiency of the parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic diagram of the application environment of a part cleaning method provided in Embodiment 1 of the present invention; Figure 2It is a schematic flowchart of a part cleaning method provided in the second embodiment of the present invention; Figure 3 It is a schematic flowchart of a part cleaning method provided in the third embodiment of the present invention; Figure 4 It is a schematic flowchart of a part cleaning method provided in the fourth embodiment of the present invention; Figure 5 It is a schematic flowchart of a part cleaning method provided in the fifth embodiment of the present invention; Figure 6 It is a schematic flowchart of a part cleaning method provided in the sixth embodiment of the present invention; Figure 7 It is a schematic flowchart of a part cleaning method provided in the seventh embodiment of the present invention; Figure 8 It is a schematic structural diagram of a part cleaning device provided in the eighth embodiment of the present invention; Figure 9 It is a schematic structural diagram of a computer device provided in the ninth embodiment of the present invention. Detailed implementation manners

[0013] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0014] As Figure 1 shown, it is a schematic application environment diagram of a part cleaning method provided in the first embodiment of the present invention. Among them, the client and the server are connected for communication. The user can provide conditions, requirements, operation instructions, etc. for part cleaning to the server through operating the client. The server is used to execute the part cleaning method of the present invention according to the relevant content sent by the client. Among them, the client includes but is not limited to various computer devices such as personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The computer device corresponding to the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0015] As Figure 2 shown, it is a schematic flowchart of a part cleaning method provided in the second embodiment of the present invention. Among them, the part cleaning method is applied to the Figure 1 server therein. The part cleaning method may include the following steps: Step S201, collect part information and part images of the parts to be cleaned, extract features from the part images, and obtain surface image features.

[0016] Among them, the information of the parts to be cleaned includes the material, size, shape, and use of the parts. Among the materials of the parts, different materials have different reactions to the cleaning agent, and appropriate cleaning methods need to be selected. The size of the parts, that is, the length, width, height, etc. of the parts, these data have an important impact on determining the selection of cleaning equipment and the setting of cleaning parameters. In the shape of the parts, complex part shapes may require more meticulous cleaning operations (such as the treatment of dead corners and gaps, etc.). In the use of the parts, according to the use of the parts, the cleanliness requirements are determined. For example, the parts of precision instruments have higher cleanliness requirements.

[0017] Take multi-angle photos of the surface of the parts to be cleaned in the cleaning machine to ensure that all surfaces of the parts are covered. Denoise, enhance, and standardize the collected images to improve the accuracy of subsequent analysis. Use image recognition algorithms (such as convolutional neural networks) to extract the features of the part surface images, including dirt, oil stains, scratches, etc.

[0018] Step S202, evaluate the cleanliness of the surface image features to obtain the initial cleanliness parameters, and match the cleaning time correction index corresponding to the initial cleanliness parameters from the database.

[0019] Among them, the goal of cleanliness evaluation is to quantitatively describe the dirt condition on the part surface, so as to determine the appropriate cleaning time and cleaning method subsequently. The initial evaluation result is represented by the initial cleanliness parameters. The cleanliness evaluation methods include but are not limited to convolutional neural networks, support vector machines, clustering algorithms, and regression models. Take the surface image features extracted in step S201 as the input and pass them into the evaluation system. Preprocess the input features, such as normalization, dimensionality reduction, etc., to ensure that they are suitable for the evaluation model. Use the processing methods of the part surface image features in the above methods to perform systematic calculations on the extracted image features to obtain the initial cleanliness parameters.

[0020] Among them, convolutional neural networks can refer to training a convolutional neural network to identify and distinguish the dirt types on the part surface, which can automatically extract high-level features and improve the accuracy and robustness of recognition. Support vector machines can refer to classifying the dirt types, training and predicting based on feature vectors. Clustering algorithms can refer to using clustering algorithms such as K-means to cluster the dirt areas on the part surface and analyze the characteristics of each type of dirt. Regression models can refer to training a regression model to predict the dirt coverage rate and dirt thickness based on the extracted features.

[0021] The content of the initial cleanliness parameters can refer to dirt coverage rate, dirt type, dirt distribution, dirt thickness, defect information, etc.

[0022] Among them, the dirt coverage rate, that is, the proportion of the area of the part surface covered by dirt, is usually expressed as a percentage. The dirt type, that is, the identified types of dirt, such as oil stains, dust, rust, etc. The dirt distribution can refer to the distribution of dirt on the part surface. For example, whether it is evenly distributed, locally concentrated, etc. The dirt thickness can refer to the dirt thickness estimated through color and texture analysis, usually expressed in millimeters or micrometers. The defect information can refer to the specific positions and degrees of defects such as scratches and pits on the part surface.

[0023] The structure of the database includes but is not limited to a cleanliness parameter table and a cleaning time correction index table. The cleanliness parameter table refers to a table containing the definitions and standard values of various cleanliness parameters. The cleaning time correction index table refers to a table containing the cleaning time correction indexes corresponding to different cleanliness parameters. The correction index can be a specific correction coefficient or time increment.

[0024] According to the value of the initial cleanliness parameter, search for the preset threshold range in the database, match the corresponding cleaning time correction index, and match the corresponding cleaning time correction index according to the combined conditions of the initial cleanliness parameters. For example, for a part with a dirt coverage rate of 10% - 20% and a dirt type of oil stain, the corresponding cleaning time correction index is 1.2 times the standard time.

[0025] Step S203, determine N cleaning operations according to the part information, and calculate the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero.

[0026] Among them, the selection of cleaning operations depends on the part information and the initial cleanliness parameters. Common cleaning operations include high-pressure water washing, ultrasonic cleaning, chemical cleaning, mechanical brushing, dry ice cleaning, steam cleaning, etc. The factors determining the cleaning operations include but are not limited to part material, dirt type, dirt distribution, part shape and size, and cleanliness requirements.

[0027] The standard cleaning time of each determined cleaning operation can be obtained from the database. According to the cleaning time correction index matched in step S202, adjust the actual cleaning time of each cleaning operation. If multiple cleaning operations are used in combination, it is necessary to comprehensively consider the times of each cleaning operation to ensure that the total cleaning time is reasonable and effective.

[0028] Step S204, perform cleaning on the part to be cleaned according to the cleaning time corresponding to each cleaning operation until the cleaning is completed.

[0029] Among them, according to the actual cleaning time calculated in step S203, set the running time of the cleaning equipment. For example, the high-pressure water washing equipment is set to 5.5 minutes, the chemical cleaning equipment is set to 12 minutes, and the ultrasonic cleaning equipment is set to 18 minutes.

[0030] The sensor and monitoring system can monitor the progress and effect of each cleaning operation in real time to ensure the accurate execution of the cleaning time. If the monitoring system detects that the cleaning effect is not ideal, it can automatically adjust the cleaning time. For example, if there is still a lot of dirt after high-pressure water washing, the system can increase the time of high-pressure water washing.

[0031] In the embodiment of the present application, by collecting the part information and part image of the part to be cleaned, extracting the features of the part image to obtain the surface image features, evaluating the cleanliness of the surface image features to obtain the initial cleanliness parameters, matching the cleaning time correction index corresponding to the initial cleanliness parameters from the database, determining N cleaning operations according to the part information, calculating the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero, and performing cleaning on the part to be cleaned according to the cleaning time corresponding to each cleaning operation until the cleaning is completed. By calculating the cleaning time of the part to be cleaned based on the part information and the cleaning time correction index, the cleaning time of different parts can be accurately configured automatically to achieve adaptive cleaning with controllable cleaning time and improve the cleaning efficiency of the parts.

[0032] As Figure 3 shown, it is a schematic flowchart of a part cleaning method provided in Embodiment 3 of the present invention. After collecting the part information and part image of the part to be cleaned in step S201, the part cleaning method may further include the following steps: Step S301, detecting whether the part information includes the target cleaning position.

[0033] Step S302, if it is detected that the part information does not include the target cleaning position, then perform feature extraction on the part image to obtain the surface image features.

[0034] Among them, the target cleaning position refers to the area on the part surface that needs special attention and cleaning, and these areas have a greater impact on the performance of the part. Preprocess the collected part image, such as denoising, contrast enhancement, image segmentation, etc., to more clearly identify the target cleaning position, and use target detection algorithms to identify the target cleaning position in the image. These algorithms can be trained to identify specific types of dirt or areas, and judge whether there are areas that need special cleaning in the image according to the preset rule library. For example, if the dirt coverage rate exceeds a certain threshold, or the dirt type is oil stain, the system can automatically mark these areas as the target cleaning position.

[0035] Taking the part image collected in step S201 as input, the image is processed such as denoising and contrast enhancement to improve the image quality. A target detection algorithm is used to identify the target cleaning position in the image. If the target detection algorithm identifies the target cleaning position, it is further confirmed using a rule base, and the judgment result is output to determine whether the target cleaning position is included. If the target cleaning position is not included, the overall image of the part to be cleaned is extracted, and feature extraction is performed based on the overall image to obtain the overall surface image features. The specific extraction process of the part image can refer to the content of step S201 above and will not be elaborated here. Based on the extracted target position surface image features and overall surface image features, the cleaning of the target position of the part to be cleaned and the overall part to be cleaned is further performed.

[0036] In this embodiment, based on the part image, it is judged whether there is a target cleaning position on the part to be cleaned, and surface image features of the target position and the overall position of the part to be cleaned are extracted according to the judgment result, thereby providing basic information for the cleaning of the target position of the part to be cleaned.

[0037] As Figure 4 shown, it is a flowchart of a part cleaning method provided by Embodiment 4 of the present invention. Based on the above Embodiment 3, the feature extraction of the part image in step S201 to obtain the surface image features may include the following steps: Step S401, if the part information includes the target cleaning position, then according to the target cleaning position, the part image is extracted to obtain the target position image, and feature extraction is performed on the target position image to obtain the target surface image features.

[0038] Step S402, after obtaining the part after cleaning at the target position, collect the part image of the part after cleaning at the target position, and return to perform feature extraction on the part image to obtain the surface image features.

[0039] Step S403, perform feature extraction on the part image of the part after cleaning at the target position to obtain the surface image features.

[0040] Among them, according to the detection result of step S301, if the detection result is that the target cleaning position is included, then the target position image of the part to be cleaned is extracted, and image feature extraction is performed based on the target position image to obtain the features of the target position image of the part. And according to the features of the target position image, the steps of steps S202 to S204 are performed. After the cleaning is completed, the part image features are extracted again based on the part after cleaning, so as to extract the complete image features of the part containing the target position. The extraction process of the part image can refer to the content in step S201 above and will not be elaborated here.

[0041] As Figure 5As shown in the figure, it is a schematic flowchart of a part cleaning method provided in the fifth embodiment of the present invention. After the cleaning in step S204 is completed, the part cleaning method may further include the following steps: Step S501: Evaluate the cleanliness of the cleaned part to obtain a cleanliness evaluation result, and determine whether the cleanliness evaluation result meets the preset standard cleanliness.

[0042] Step S502: If the cleanliness evaluation result does not meet the preset standard cleanliness, return to execute the acquisition of the part information and part image of the part to be cleaned until the cleanliness evaluation result meets the preset standard cleanliness.

[0043] Among them, the preset standard cleanliness characteristics may include that the dirt coverage rate is lower than a certain threshold, the color histogram meets the expectation, the texture characteristics are uniform, etc. If the evaluation result of the part to be cleaned after passing the cleanliness evaluation does not meet the preset cleanliness, return to execute the acquisition of the part information and part image of the part to be cleaned, extract the characteristics of the part image to obtain the surface image characteristics, and match the cleaning time, cleaning time correction index, cleaning operation steps, and execute the cleaning process until the cleanliness evaluation result meets the preset standard cleanliness, so as to realize the full-automatic cyclic cleaning of the part.

[0044] In this embodiment, the cleanliness of the cleaned part is evaluated by the preset standard cleanliness. If it does not meet the standard cleanliness, it is cleaned again, so as to further judge the cleaning degree of the part and improve the accuracy of part cleaning.

[0045] As Figure 6 shown in the figure, it is a schematic flowchart of a part cleaning method provided in the sixth embodiment of the present invention. The part cleaning method may further include the following steps: Step S601: Record the initial cleanliness parameters when the cleanliness evaluation result does not meet the preset standard cleanliness, and count the total cleaning time of each cleaning operation until the cleanliness evaluation result meets the preset standard cleanliness.

[0046] Among them, the initial cleanliness parameters of the part whose cleanliness evaluation result does not meet the preset standard cleanliness are obtained in step S501. The total cleaning time includes, after each cleaning operation is completed, accumulating the cleaning time and counting the total cleaning time of each operation.

[0047] Step S602: Calculate an updated correction index according to the total cleaning time.

[0048] Step S603: Update the preset regression model according to the initial cleanliness parameters and the updated correction index to obtain an updated regression model. The preset regression model is used to construct a database, and the updated regression model is used to update the mapping relationship between the cleanliness parameters and the correction index in the database.

[0049] Among them, the updated correction index is calculated by combining the total cleaning time obtained in step S601 with the part information. The selection of the regression model includes, but is not limited to, linear regression, support vector regression, random forest regression, and neural network regression. The initial cleanliness parameter of the currently to-be-cleaned part is input into the regression model. The regression model updates the parameters of the regression model according to the input initial cleanliness parameter and with reference to the updated correction index.

[0050] Among them, by comparing the input initial cleanliness parameter with the updated correction index, it is judged whether the initial cleanliness parameter is reasonable. Linear or non-linear adjustment methods can be used to adjust specific parameter values according to the specific evaluation results. For example, if the dirt coverage rate is too high, the parameter value can be appropriately reduced. The adjusted cleanliness parameter and the corresponding cleaning time correction index are used to retrain the preset regression model, and the retrained model is tested using the test set to evaluate the performance of the model. If the cleaning time correction index meets the updated correction index, an updated regression model is obtained. If the cleaning time correction index still does not meet the standard, continue to loop through steps S601 to S603 until the model performance is satisfactory.

[0051] In this embodiment, the initial cleanliness parameter is input into the preset regression model, and the initial cleanliness parameter is adjusted according to the cleanliness evaluation result and then input into the regression model again for training until the cleaning time correction index of the to-be-cleaned part meets the cleanliness evaluation result, and an updated regression model is obtained. Thereby, the accuracy of the cleaning time correction index is ensured.

[0052] As Figure 7 shown, it is a flowchart of a part cleaning method provided by Embodiment 7 of the present invention. After calculating the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and part information in step S203, the part cleaning method may further include the following steps: Step S701: According to the part information of the to-be-cleaned part, judge whether the to-be-cleaned part is an easily bendable part.

[0053] Step S702: If the to-be-cleaned part is not an easily bendable part, determine the ultrasonic cleaning operation, spraying operation, blowing operation, and drying operation, and calculate the cleaning times corresponding to the ultrasonic cleaning operation, spraying operation, blowing operation, and drying operation respectively according to the part information and the cleaning time correction index.

[0054] Step S703: If the to-be-cleaned part is an easily bendable part, determine the ultrasonic cleaning operation, blowing operation, and drying operation, and calculate the cleaning times corresponding to the ultrasonic cleaning operation, blowing operation, and drying operation respectively according to the part information and the cleaning time correction index.

[0055] Among them, detailed information of the parts to be cleaned is obtained from the parts database, and the dimensional information of the parts is detected using an automatic detection device (such as a 3D scanner). Parts made of certain materials are prone to deformation or bending during the cleaning process. For example, thin metal sheets, flexible materials, etc. Larger sizes (length, width, height) of the parts will increase the risk of bending, and complex shapes or thin-walled structures will also increase the risk of bending.

[0056] The judgment of easy bending can be carried out by checking whether the length, width and height of the part exceed the preset dimensional threshold, and checking whether the part shape belongs to an easily bendable shape. If all the judgment conditions meet one of them, the part is easily bendable.

[0057] Among them, the cleaning time corresponding to the spraying operation includes the cleaning time corresponding to the rotary spraying operation and the cleaning time corresponding to the up-and-down spraying operation. The cleaning time corresponding to the blowing operation includes the cleaning time corresponding to the rotary blowing operation and the cleaning time corresponding to the horizontal blowing operation.

[0058] Optionally, the cleaning time correction indicators in step S202 include a cleaning time correction coefficient and a cleaning time correction constant.

[0059] The cleaning time corresponding to the ultrasonic cleaning operation is: Using the cleaning time correction coefficient, perform correction calculations on the length of the corresponding part to be cleaned, the width of the corresponding part to be cleaned, and the height of the corresponding part to be cleaned extracted from the part information to obtain the initial ultrasonic cleaning time. Add the initial ultrasonic cleaning time to the cleaning time correction constant, and the added result is the cleaning time corresponding to the ultrasonic cleaning operation.

[0060] The cleaning time corresponding to the spraying operation is: Using the cleaning time correction coefficient, perform correction calculations on the length of the corresponding part to be cleaned, the width of the corresponding part to be cleaned, and the height of the corresponding part to be cleaned extracted from the part information to obtain the initial spraying cleaning time. Add the initial spraying cleaning time to the cleaning time correction constant, and the added result is the cleaning time corresponding to the spraying operation; The cleaning time corresponding to the blowing operation is: Using the cleaning time correction coefficient, perform correction calculations on the length of the corresponding part to be cleaned, the width of the corresponding part to be cleaned, and the height of the corresponding part to be cleaned extracted from the part information to obtain the initial blowing cleaning time. Add the initial blowing cleaning time to the cleaning time correction constant, and the added result is the cleaning time corresponding to the blowing operation; The cleaning time corresponding to the drying operation is: Using the cleaning time correction coefficient, perform correction calculations on the length of the corresponding part to be cleaned, the width of the corresponding part to be cleaned, and the height of the corresponding part to be cleaned extracted from the part information to obtain the initial drying cleaning time. Add the initial drying cleaning time to the cleaning time correction constant, and the added result is the cleaning time corresponding to the drying operation; Perform cleaning on the part to be cleaned according to the cleaning time corresponding to the ultrasonic cleaning operation, the cleaning time corresponding to the spraying operation, the cleaning time corresponding to the air blowing operation, and the cleaning time corresponding to the drying operation until the cleaning is completed.

[0061] Among them, the calculation formula for the cleaning time corresponding to the ultrasonic cleaning operation is as follows: T_ us = Base time + 0.5×(L + W + H)* + ; The calculation formula for the cleaning time corresponding to the rotary spraying operation is as follows: ; The calculation formula for the cleaning time corresponding to the up-and-down spraying operation is as follows: ; The calculation formula for the cleaning time corresponding to the rotary air blowing operation is as follows: ; The calculation formula for the cleaning time corresponding to the horizontal air blowing operation is as follows: ; The calculation formula for the cleaning time corresponding to the drying operation is as follows: ; In the formula, T_us is the cleaning time corresponding to the ultrasonic cleaning operation, T_r 喷 is the cleaning time corresponding to the rotary spraying operation, T_u 喷 is the cleaning time corresponding to the up-and-down spraying operation, T_r 吹 is the cleaning time corresponding to the rotary air blowing operation, T_h 吹 is the cleaning time corresponding to the horizontal air blowing operation, T_ 烘 is the cleaning time corresponding to the drying operation, L is the length of the part to be cleaned, W is the width of the part to be cleaned, H is the height of the part to be cleaned, is the cleaning time correction coefficient, is the cleaning time correction constant.

[0062] In this embodiment, by determining whether the part to be cleaned meets the condition of being easily bent, and according to the judgment result, the cleaning time corresponding to the ultrasonic cleaning operation, the cleaning time corresponding to the spraying operation, the cleaning time corresponding to the blowing operation, and the drying operation for the non-easily bent parts are calculated, so as to accurately obtain the cleaning time of the part to be cleaned.

[0063] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0064] As Figure 8 shown, it is a schematic diagram of a part cleaning device provided by Embodiment 9 of the present invention. This part cleaning device corresponds one-to-one with the part cleaning method in the above embodiment. The part cleaning device includes an image feature acquisition module 81, a correction index matching module 82, a calculation module 83, and a cleaning module 84. The detailed description of each functional module is as follows: The image feature acquisition module 81 is used to collect the part information and part image of the part to be cleaned, extract features from the part image, and obtain the surface image features. The correction index matching module 82 is used to evaluate the cleanliness of the surface image features to obtain the initial cleanliness parameters, and match the cleaning time correction index corresponding to the initial cleanliness parameters from the database. The calculation module 83 is used to determine N cleaning operations according to the part information, and calculate the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero. The cleaning module 84 is used to perform cleaning on the part to be cleaned according to the cleaning time corresponding to each cleaning operation until the cleaning is completed.

[0065] Optionally, the part cleaning device further includes: The target position judgment module is used to detect whether the part information includes the target cleaning position after collecting the part information and part image of the part to be cleaned. The overall image feature extraction module is used to perform feature extraction on the part image to obtain the surface image features if it is detected that the part information does not include the target cleaning position.

[0066] Optionally, the part cleaning device further includes: The target image feature extraction module is used to extract the part image according to the target cleaning position after detecting whether the part information includes the target cleaning position, obtain the target position image, and extract features from the target position image to obtain the target surface image features. A loop execution module, which is used to obtain the parts after cleaning at the target position after cleaning is completed, collect the part images of the parts after cleaning at the target position, and return to execute feature extraction on the part images to obtain surface image features; A target part overall feature extraction module, which is used to perform feature extraction on the part images of the parts after cleaning at the target position to obtain surface image features.

[0067] Optionally, the part cleaning device further includes: A cleanliness judgment module, which is used to evaluate the cleanliness of the parts after cleaning after cleaning is completed, obtain a cleanliness evaluation result, and judge whether the cleanliness evaluation result meets a preset standard cleanliness; A return execution judgment module, which is used to return to execute the collection of part information and part images of the parts to be cleaned if the cleanliness evaluation result does not meet the preset standard cleanliness until the cleanliness evaluation result meets the preset standard cleanliness.

[0068] Optionally, the part cleaning device further includes: An information collection module, which is used to record the initial cleanliness parameters when the cleanliness evaluation result does not meet the preset standard cleanliness, and count the total cleaning time of each cleaning operation until the cleanliness evaluation result meets the preset standard cleanliness; A correction index calculation module, which is used to calculate an updated correction index according to the total cleaning time; A regression model update module, which is used to update a preset regression model according to the initial cleanliness parameters and the updated correction index to obtain an updated regression model. The preset regression model is used to construct a database, and the updated regression model is used to update the mapping relationship between the cleanliness parameters and the correction index in the database.

[0069] Optionally, the above calculation module 83 includes: A bending judgment unit, which is used to judge whether the part to be cleaned is an easily bendable part according to the part information of the part to be cleaned; A non-easily bendable part time determination unit, which is used to determine ultrasonic cleaning operation, spraying operation, blowing operation and drying operation if the part to be cleaned is not an easily bendable part, and calculate the cleaning times corresponding to the ultrasonic cleaning operation, spraying operation, blowing operation and drying operation respectively according to the part information and the cleaning time correction index; An easily bendable part time determination unit, which is used to determine ultrasonic cleaning operation, blowing operation and drying operation if the part to be cleaned is an easily bendable part, and calculate the cleaning times corresponding to the ultrasonic cleaning operation, blowing operation and drying operation respectively according to the part information and the cleaning time correction index.

[0070] Optionally, the above correction index matching module 82 further includes: An ultrasonic cleaning time unit, which is used to use a cleaning time correction coefficient to perform correction calculations on the length of the part to be cleaned, the width of the part to be cleaned, and the height of the part to be cleaned extracted from the part information, obtain the initial ultrasonic cleaning time, add the initial ultrasonic cleaning time to the cleaning time correction constant, and the obtained addition result is the cleaning time corresponding to the ultrasonic cleaning operation; A spray cleaning time unit, which is used to use a cleaning time correction coefficient to perform correction calculations on the length of the part to be cleaned, the width of the part to be cleaned, and the height of the part to be cleaned extracted from the part information, obtain the initial spray cleaning time, add the initial spray cleaning time to the cleaning time correction constant, and the obtained addition result is the cleaning time corresponding to the spray operation; A blowing cleaning time unit, which is used to use a cleaning time correction coefficient to perform correction calculations on the length of the part to be cleaned, the width of the part to be cleaned, and the height of the part to be cleaned extracted from the part information, obtain the initial blowing cleaning time, add the initial blowing cleaning time to the cleaning time correction constant, and the obtained addition result is the cleaning time corresponding to the blowing operation; A drying cleaning time unit, which is used to use a cleaning time correction coefficient to perform correction calculations on the length of the part to be cleaned, the width of the part to be cleaned, and the height of the part to be cleaned extracted from the part information, obtain the initial drying cleaning time, add the initial drying cleaning time to the cleaning time correction constant, and the obtained addition result is the cleaning time corresponding to the drying operation; A cleaning execution unit, which is used to perform cleaning on the part to be cleaned according to the cleaning time corresponding to the ultrasonic cleaning operation, the cleaning time corresponding to the spray operation, the cleaning time corresponding to the blowing operation, and the cleaning time corresponding to the drying operation until the cleaning is completed.

[0071] As Figure 9 shown, it is a schematic structural diagram of a computer device provided in Embodiment 9 of the present invention. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a part cleaning method.

[0072] In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the part cleaning method in the above embodiment. For example Figures 2 to 7 As shown, to avoid repetition, it will not be elaborated here. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in this embodiment of the part cleaning device. For example Figure 8 the functions of the image feature acquisition module 81, the correction index matching module 82, the calculation module 83, and the cleaning module 84 shown. To avoid repetition, it will not be elaborated here.

[0073] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements the part cleaning method in the above embodiment, as Figures 2 to 7 shown. To avoid repetition, it will not be elaborated here. Alternatively, when the computer program is executed by the processor, it implements the functions of each module / unit in this embodiment of the above part cleaning device. For example Figure 8 the functions of the image feature acquisition module 81, the correction index matching module 82, the calculation module 83, and the cleaning module 84 shown. To avoid repetition, it will not be elaborated here. The computer-readable storage medium can be non-volatile or volatile.

[0074] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0076] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A parts cleaning method, characterized in that: include: Collecting part information and part images of the parts to be cleaned, performing feature extraction on the part images, and obtaining surface image features; Performing cleanliness evaluation on the surface image features to obtain initial cleanliness parameters, and matching cleaning time correction indicators corresponding to the initial cleanliness parameters from a database; Determine N cleaning operations according to the part information, and calculate the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero; According to the cleaning time corresponding to each cleaning operation, the parts to be cleaned are cleaned until the cleaning is completed.

2. The parts cleaning method according to claim 1, characterized in that: After collecting the part information and part image of the part to be cleaned, the method further includes: detecting whether the part information includes a target cleaning position; If it is detected that the target cleaning position is not included in the part information, the feature extraction of the part image is performed to obtain the surface image feature.

3. The parts cleaning method according to claim 2, characterized in that: After detecting whether the part information includes a target cleaning position, extracting features from the part image to obtain surface image features includes: If the part information includes a target cleaning position, the part image is extracted according to the target cleaning position to obtain a target position image, and features are extracted from the target position image to obtain target surface image features; After cleaning is complete, it also includes: Obtaining a cleaned part at a target position, collecting a part image of the cleaned part at the target position, and returning to perform feature extraction on the part image to obtain surface image features; The step of extracting features from the part image to obtain surface image features includes: Feature extraction is performed on the part image of the cleaned part at the target position to obtain surface image features.

4. The parts cleaning method according to claim 1, characterized in that: After the cleaning is completed, the method further comprises: Performing cleanliness evaluation on the cleaned parts to obtain cleanliness evaluation results, and determining whether the cleanliness evaluation results meet the preset standard cleanliness; If the cleanliness evaluation result does not meet the preset standard cleanliness, the process returns to the step of collecting part information and part images of the parts to be cleaned until the cleanliness evaluation result meets the preset standard cleanliness.

5. The parts cleaning method according to claim 4, characterized in that: Also includes: Recording the initial cleanliness parameters when the cleanliness assessment result does not meet the preset standard cleanliness, and counting the total cleaning time of each cleaning operation until the cleanliness assessment result meets the preset standard cleanliness; Calculating an updated correction index based on the total cleaning time; According to the initial cleanliness parameters and the updated correction index, the preset regression model is updated to obtain an updated regression model, the preset regression model is used to construct the database, and the updated regression model is used to update the mapping relationship between the cleanliness parameters and the correction index in the database.

6. The parts cleaning method according to claim 1, characterized in that: The cleaning time corresponding to each cleaning operation is calculated according to the cleaning time correction index and the part information, including: According to the part information of the part to be cleaned, determining whether the part to be cleaned is an easily bendable part; If the part to be cleaned is not an easily bendable part, then determine the ultrasonic cleaning operation, spraying operation, blowing operation and drying operation, and calculate the cleaning time corresponding to the ultrasonic cleaning operation, the spraying operation, the blowing operation and the drying operation respectively according to the part information and the cleaning time correction index; If the part to be cleaned is an easily bendable part, the ultrasonic cleaning operation, the blowing operation and the drying operation are determined, and the cleaning times corresponding to the ultrasonic cleaning operation, the blowing operation and the drying operation are calculated according to the part information and the cleaning time correction index.

7. The parts cleaning method according to claim 6, characterized in that: The cleaning time correction index includes a cleaning time correction coefficient and a cleaning time correction constant; The cleaning time corresponding to the ultrasonic cleaning operation is: Using the cleaning time correction coefficient, the length of the part to be cleaned, the width of the part to be cleaned and the height of the part to be cleaned extracted from the part information are corrected and calculated to obtain the ultrasonic initial cleaning time, and the ultrasonic initial cleaning time is added to the cleaning time correction constant to obtain the addition result, which is the cleaning time corresponding to the ultrasonic cleaning operation; The cleaning time corresponding to the spray operation is: Using the cleaning time correction coefficient, the length of the part to be cleaned, the width of the part to be cleaned and the height of the part to be cleaned extracted from the part information are corrected and calculated to obtain the initial spray cleaning time, and the initial spray cleaning time is added to the cleaning time correction constant to obtain the addition result, which is the cleaning time corresponding to the spray operation; The cleaning time corresponding to the blowing operation is: Using the cleaning time correction coefficient, a correction calculation is performed on the length of the part to be cleaned, the width of the part to be cleaned, and the height of the part to be cleaned extracted from the part information to obtain an initial air blowing cleaning time, and the initial air blowing cleaning time is added to the cleaning time correction constant to obtain the addition result, which is the cleaning time corresponding to the air blowing operation; The cleaning time corresponding to the drying operation is: Using the cleaning time correction coefficient, a correction calculation is performed on the length of the part to be cleaned, the width of the part to be cleaned, and the height of the part to be cleaned extracted from the part information to obtain an initial drying cleaning time, and the initial drying cleaning time is added to the cleaning time correction constant to obtain the addition result, which is the cleaning time corresponding to the drying operation; The parts to be cleaned are cleaned according to the cleaning time corresponding to the ultrasonic cleaning operation, the cleaning time corresponding to the spraying operation, the cleaning time corresponding to the blowing operation and the cleaning time corresponding to the drying operation until the cleaning is completed.

8. A parts cleaning device, characterized in that: include: An image feature acquisition module is used to collect part information and part images of the parts to be cleaned, perform feature extraction on the part images, and obtain surface image features; A correction index matching module is used to evaluate the cleanliness of the surface image features to obtain initial cleanliness parameters, and match the cleaning time correction index corresponding to the initial cleanliness parameters from a database; A calculation module, used to determine N cleaning operations according to the part information, and calculate the cleaning time corresponding to each cleaning operation according to the cleaning time correction index and the part information, where N is an integer greater than zero; The cleaning module is used to clean the parts to be cleaned according to the cleaning time corresponding to each cleaning operation until the cleaning is completed.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the parts cleaning method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the parts cleaning method according to any one of claims 1 to 7 is implemented.

Images