Metal workpiece detecting and cleaning control method and system based on image processing

Abstract

The invention discloses a metal workpiece detecting and cleaning control method and system based on image processing, and relates to the technical field of metal workpiece cleaning. Constructing a three-dimensional geometric model based on the image data and identifying a dirty area; calculating an optimal moving path of the cleaning nozzle according to the smudginess distribution; sending an instruction to a cleaning nozzle according to the optimal moving path; and comparing and analyzing the images acquired in real time with the images before cleaning and in the cleaning process. The optimal moving path is planned for the cleaning nozzle, so that the cleaning nozzle can accurately cover a dirty area, and cleaning omission or excessive cleaning is avoided, so that the cleaning precision is remarkably improved, the cleaning quality of the metal workpiece is ensured, unnecessary moving and idle stroke of the cleaning nozzle are reduced, the cleaning work is more efficient, and the cleaning efficiency is improved. And repeated cleaning caused by improper cleaning is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of metal workpiece cleaning, in particular to a metal workpiece detection and cleaning control method and system based on image processing. Background Art

[0002] In today's manufacturing industry, metal workpieces are widely used in many fields such as automobile manufacturing, mechanical processing, and electronic equipment production. The surface cleanliness of metal workpieces plays a key role in their performance, life, and product quality. In automobile engine manufacturing, if impurities remain on the surface of metal parts, it may cause abnormal engine operation, reduce fuel efficiency, and even cause safety problems. The cleaning of metal workpieces mainly relies on traditional methods. Manual cleaning is not only inefficient and costly, but also difficult to ensure the consistency and accuracy of cleaning. For some large metal components, manual cleaning takes a long time and is difficult to clean comprehensively. Although chemical cleaning can effectively remove dirt, it will produce a large amount of waste liquid that pollutes the environment, and may corrode the metal surface and affect the performance of the workpiece. With the advancement of industrial intelligence, traditional cleaning methods can no longer meet the needs of production. On the one hand, traditional methods cannot obtain the distribution and degree of dirt on the surface of metal workpieces in real time and accurately, making it difficult to achieve targeted cleaning, resulting in waste of cleaning resources and poor cleaning effects. On the other hand, the cleaning process lacks real-time monitoring and feedback mechanisms, and the cleaning strategy cannot be adjusted in time according to actual conditions, resulting in unstable cleaning quality. There are still many problems with existing cleaning technologies based on image processing. For example, the construction of three-dimensional geometric models is not accurate enough, resulting in deviations in the judgment of the surface shape and dirt location of the workpiece; the accuracy of the dirt recognition algorithm needs to be improved, and misjudgment or omission is prone to occur; the cleaning path planning is not scientific enough, and the cleaning efficiency and effect cannot be fully considered. These shortcomings limit the development and application of metal workpiece cleaning technology based on image processing, and new methods and systems are urgently needed to break through.

[0003] However, the common solutions currently available have many shortcomings, including: the existing technology only plans the cleaning path based on simple geometric shapes or fixed patterns, without considering the complex structure and dirt distribution on the workpiece surface, resulting in incomplete cleaning or excessive cleaning of certain areas; when cleaning complex molds, the grooves, corners and other special parts of the mold cannot be accurately covered and cleaned, affecting the cleaning quality; due to unreasonable path planning, the cleaning equipment may make a lot of invalid movements, resulting in a waste of cleaning fluid, energy and other resources; when cleaning large metal plates, the cleaning nozzle frequently passes back and forth through the cleaned area, consuming too much cleaning fluid and electricity. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing metal workpiece detection and cleaning control method and system based on image processing, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a metal workpiece inspection and cleaning control method and system based on image processing, which is suitable for solving the problem that the prior art only plans the cleaning path based on simple geometric shapes or fixed patterns, without considering the complex structure and dirt distribution on the workpiece surface, resulting in incomplete cleaning or excessive cleaning of certain areas. Due to unreasonable path planning, the cleaning equipment may perform a lot of invalid movements, resulting in waste of resources such as cleaning fluid and energy.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In the first aspect, an embodiment of the present invention provides a metal workpiece detection and cleaning control method based on image processing, which includes using a sensor to collect and preprocess image data of the metal workpiece surface; constructing a three-dimensional geometric model based on the image data and identifying dirty areas; calculating the optimal movement path of the cleaning nozzle according to the dirt distribution; sending instructions to the cleaning nozzle according to the optimal movement path; and comparing and analyzing the real-time acquired images with the images before and during cleaning.

[0009] As a preferred solution of the metal workpiece detection and cleaning control method based on image processing described in the present invention, wherein: the sensor is a 3D scanning device and a high-resolution industrial camera; the image data includes spatial information data, visual feature data, image statistical data, feature description data and dirt feature data.

[0010] As a preferred solution of the metal workpiece detection and cleaning control method based on image processing described in the present invention, the specific steps of constructing a three-dimensional geometric model are as follows: collect metal workpiece surface image data according to the sensor and preprocess it; construct a three-dimensional geometric model based on a recurrent neural network and extract features of the image data; identify dirty areas according to the extracted features; calculate the optimal moving path of the cleaning nozzle according to the dirt distribution; and send the optimal moving path to the cleaning nozzle.

[0011] As a preferred solution of the metal workpiece detection and cleaning control method based on image processing of the present invention, the specific formula for calculating the optimal moving path is as follows:

[0012]

[0013] Among them, C is a comprehensive evaluation index; L j is the Euclidean distance from the current position of the nozzle to the center of the jth dirty area; λ is the weight coefficient; E i is the cleaning efficiency of the nozzle on the i-th dirty area; n is the number of dirty areas.

[0014] As a preferred solution of the metal workpiece detection and cleaning control method based on image processing of the present invention, the specific formula of the Euclidean distance of the nozzle moving from the current position to the center of the j-th dirty area is as follows:

[0015]

[0016] Among them, L j is the Euclidean distance from the current position of the nozzle to the center of the jth dirty area; (x, y, z) is the current position coordinate of the nozzle in three-dimensional space; (x j ,y j ,z j ) is the coordinate of the center of the jth dirty area in three-dimensional space.

[0017] As a preferred solution of the metal workpiece detection and cleaning control method based on image processing described in the present invention, the specific steps of comparing and analyzing the real-time acquired image with the images before cleaning and during cleaning are as follows: comparing the real-time image with the reference image before cleaning and the previous cleaning process image; calculating the corresponding difference value according to the set comparison and analysis index; comparing the calculated difference value with the set threshold value; making corresponding decisions based on the comparison and analysis results and judgment conclusions; in the entire cleaning process monitoring and feedback adjustment, recording in detail all collected data, comparison and analysis results, decision content and execution of adjustment measures.

[0018] As a preferred solution of the metal workpiece detection and cleaning control method based on image processing of the present invention, the specific formula for calculating the corresponding difference value according to the set comparative analysis index is as follows:

[0019]

[0020] Where D is the difference between the real-time image and the reference image before cleaning; N is the total number of pixels in the image; I t (k) is the value of the kth pixel in the real-time image; 0 (k) is the value of the kth pixel in the reference image before cleaning;

[0021] The specific situation of comparing the difference value with the threshold value is as follows:

[0022] When the difference between the real-time image and the pre-cleaning reference image is less than the threshold, it means that the difference between the real-time image and the pre-cleaning reference image and the previous cleaning process image is within an acceptable range, indicating that the current cleaning process is progressing smoothly, the cleaning effect is in line with expectations, there are no obvious abnormalities, the working state of the cleaning equipment is stable, and there is no need to adjust the cleaning process parameters or equipment;

[0023] When the difference between the real-time image and the reference image before cleaning is equal to the threshold, it means that the difference between the real-time image and the reference image has just reached the set boundary, and more information needs to be combined for comprehensive evaluation;

[0024] When the difference value between the real-time image and the reference image before cleaning is greater than a threshold, it means that the difference between the real-time image and the reference image and the previous cleaning process image exceeds an acceptable range, reflecting that a deviation or abnormality has occurred in the cleaning process.

[0025] In the second aspect, in order to further solve the above-mentioned technical problems, the embodiment of the present invention provides a metal workpiece detection and cleaning control system based on image processing, which includes: a data acquisition module, used to collect and pre-process the surface image data of the metal workpiece; a model building module, used to build a three-dimensional geometric model and identify dirty areas; a path generation module, used to calculate the optimal movement path of the cleaning nozzle; an instruction sending module, used to send the optimal movement path to the cleaning nozzle; an image comparison module, used to compare and analyze the real-time acquired image with the images before and during cleaning.

[0026] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the metal workpiece detection and cleaning control method based on image processing as described in the first aspect of the present invention is implemented.

[0027] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the metal workpiece detection and cleaning control method based on image processing as described in the first aspect of the present invention is implemented.

[0028] The beneficial effects of the present invention are as follows: the present invention accurately identifies dirty areas by constructing a three-dimensional geometric model, plans the optimal moving path for the cleaning nozzle, and enables the cleaning nozzle to accurately cover the dirty areas, avoiding cleaning omissions or excessive cleaning, thereby significantly improving the cleaning accuracy and ensuring the cleaning quality of metal workpieces. The optimal moving path is calculated based on the dirt distribution, reducing unnecessary movement and idle strokes of the cleaning nozzle, making the cleaning work more efficient. At the same time, real-time image comparison and analysis can promptly discover problems in the cleaning process and make adjustments, avoiding repeated cleaning due to improper cleaning, and further improving the cleaning efficiency. The entire cleaning process is automatically controlled based on image processing and analysis, reducing manual intervention, reducing errors and uncertainties caused by manual operations, realizing the intelligence of the cleaning process, and improving the stability and reliability of the cleaning process. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0030] Figure 1 This is a flow chart for implementing the present invention in Example 1.

[0031] Figure 2 This is a dynamic adjustment diagram of the optimal cleaning path in Example 1. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0034] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0035] Example 1

[0036] Reference Figure 1 and Figure 2, which is the first embodiment of the present invention, provides a metal workpiece detection and cleaning control method based on image processing, comprising the following steps:

[0037] S1: Use sensors to collect metal workpiece surface image data and perform preprocessing.

[0038] Preferably, Figure 1 The figure shows the implementation process of the present invention. First, the sensor is used to collect and preprocess the surface image data of the metal workpiece. A three-dimensional geometric model is constructed based on the image data and the dirty area is identified. Then, the optimal moving path of the cleaning nozzle is calculated according to the dirt distribution. Subsequently, instructions are sent to the cleaning nozzle according to the optimal moving path. Finally, the real-time image is compared and analyzed with the images before and during cleaning.

[0039] Furthermore, the sensors are 3D scanning equipment and high-resolution industrial cameras.

[0040] Furthermore, the image data includes spatial information data, visual feature data, image statistical data, feature description data, and dirt feature data.

[0041] Specifically, preprocessing ensures the quality and consistency of data by performing real-time preprocessing of image data on data nodes, including data cleaning, noise reduction, and standardization.

[0042] S2: Build a 3D geometric model based on the image data and identify dirty areas.

[0043] Preferably, the specific steps of constructing the three-dimensional geometric model are as follows: collecting surface image data of the metal workpiece according to the sensor and performing preprocessing.

[0044] Construct a three-dimensional geometric model based on a recurrent neural network and perform feature extraction on image data.

[0045] Identify dirty areas based on the extracted features.

[0046] The optimal movement path of the cleaning nozzle is calculated based on the dirt distribution.

[0047] Send the optimal moving path to the cleaning nozzle.

[0048] Preferably, the three-dimensional model can fully present the surface morphology of the metal workpiece, accurately locate the position, shape and size of the dirty area, and accurately identify the hidden dirt on the workpiece with complex structure. By analyzing the dirty area, it can also quantify the degree of dirtiness and provide a quantitative basis for the cleaning strategy.

[0049] S3: Calculate the optimal moving path of the cleaning nozzle according to the dirt distribution.

[0050] Preferably, the specific formula for calculating the optimal moving path is as follows:

[0051]

[0052] Among them, C is a comprehensive evaluation index; L j is the Euclidean distance from the current position of the nozzle to the center of the jth dirty area; λ is the weight coefficient; E i is the cleaning efficiency of the nozzle on the i-th dirty area; n is the number of dirty areas.

[0053] Specifically, the specific formula for the Euclidean distance of the nozzle moving from the current position to the center of the jth dirty area is as follows:

[0054]

[0055] Among them, L j is the Euclidean distance from the current position of the nozzle to the center of the jth dirty area; (x, y, z) is the current position coordinate of the nozzle in three-dimensional space; (x j ,y j ,z j ) is the coordinate of the center of the jth dirty area in three-dimensional space.

[0056] Optimally, the nozzle is prevented from making ineffective movements, the cleaning time and energy consumption are reduced, the cleaning efficiency is improved, the nozzle is allowed to accurately cover the dirty area, the cleaning is ensured to be uniform, the cleaning dead corners and excessive cleaning are avoided, and the cleaning quality is improved.

[0057] S4: Send instructions to the cleaning nozzle according to the optimal moving path.

[0058] Preferably, the theoretical optimal path is converted into actual control instructions to ensure that the nozzle is cleaned according to the predetermined path, to ensure the accuracy and repeatability of cleaning, to achieve seamless connection between path planning and cleaning execution, and to improve system coordination.

[0059] S5: Compare and analyze the images acquired in real time with the images before and during cleaning.

[0060] Specifically, the specific steps for comparing and analyzing the real-time acquired image with the images before and during cleaning are as follows:

[0061] Compare the live image with a baseline image before cleaning and with images from previous cleaning sessions.

[0062] According to the set comparative analysis indicators, calculate the corresponding difference value.

[0063] The calculated difference value is compared with the set threshold value.

[0064] Make corresponding decisions based on the comparative analysis results and judgment conclusions.

[0065] During the entire cleaning process monitoring and feedback adjustment, all collected data, comparative analysis results, decision content and implementation of adjustment measures are recorded in detail.

[0066] Furthermore, according to the set comparative analysis index, the specific formula for calculating the corresponding difference value is as follows:

[0067]

[0068] Where D is the difference between the real-time image and the reference image before cleaning; N is the total number of pixels in the image; I t (k) is the value of the kth pixel in the real-time image; 0 (k) is the value of the kth pixel in the reference image before cleaning.

[0069] Furthermore, the specific situation of comparing the difference value with the threshold value is as follows:

[0070] When the difference value between the real-time image and the reference image before cleaning is less than the threshold, it means that the difference between the real-time image and the reference image before cleaning and the previous cleaning process image is within an acceptable range, indicating that the current cleaning process is progressing smoothly, the cleaning effect is as expected, there are no obvious abnormalities, the working state of the cleaning equipment is stable, and there is no need to adjust the cleaning process parameters or equipment.

[0071] When the difference value between the real-time image and the reference image before cleaning is equal to the threshold, it means that the difference between the real-time image and the reference image just reaches the set boundary, and more information needs to be combined for comprehensive evaluation.

[0072] When the difference value between the real-time image and the reference image before cleaning is greater than a threshold, it means that the difference between the real-time image and the reference image and the previous cleaning process image exceeds an acceptable range, reflecting that a deviation or abnormality has occurred in the cleaning process.

[0073] Furthermore, the determination of the threshold requires multiple steps. First, experts preliminarily set the threshold range based on industry experience and similar project data, combined with workpiece characteristics and cleaning standards. Then, single-factor and orthogonal experiments are carried out, cleaning parameters are changed and image differences are analyzed. The preliminary threshold is determined through statistical analysis. Next, the image data annotated with cleaning effects is used to build a classification model through support vector machine, which is tested and optimized on the validation set to determine the final threshold. In actual applications, regular evaluation and fine-tuning will be performed based on production changes to ensure accurate cleaning control.

[0074] This embodiment also provides a metal workpiece detection and cleaning control system based on image processing, including: a data acquisition module, used to collect and pre-process metal workpiece surface image data; a model building module, used to build a three-dimensional geometric model and identify dirty areas; a path generation module, used to calculate the optimal movement path of the cleaning nozzle; an instruction sending module, used to send the optimal movement path to the cleaning nozzle; an image comparison module, used to compare and analyze the real-time acquired image with the images before and during cleaning.

[0075] This embodiment also provides a computer device, which is suitable for the case of a metal workpiece detection and cleaning control method based on image processing, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the metal workpiece detection and cleaning control method based on image processing proposed in the above embodiment.

[0076] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0077] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the metal workpiece detection and cleaning control method based on image processing as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0078] In summary, the present invention accurately identifies dirty areas by constructing a three-dimensional geometric model, plans the optimal moving path for the cleaning nozzle, and enables the cleaning nozzle to accurately cover the dirty areas, avoiding cleaning omissions or excessive cleaning, thereby significantly improving the cleaning accuracy and ensuring the cleaning quality of metal workpieces. The optimal moving path is calculated based on the dirt distribution, which reduces unnecessary movement and idle strokes of the cleaning nozzle, making the cleaning work more efficient. At the same time, real-time image comparison and analysis can promptly discover problems in the cleaning process and make adjustments, avoiding repeated cleaning due to improper cleaning, and further improving the cleaning efficiency. The entire cleaning process is automatically controlled based on image processing and analysis, which reduces manual intervention, reduces errors and uncertainties caused by manual operations, realizes the intelligence of the cleaning process, and improves the stability and reliability of the cleaning process.

[0079] Example 2

[0080] Referring to Tables 1 to 3, the second embodiment of the present invention is shown. This embodiment is different from the first embodiment in that, in order to verify its beneficial effects, operating data and related instructions of the present invention in an actual environment are provided.

[0081] Table 1 shows the image data recorded in this example, including the dirty area and the image quality score after preprocessing, which provides a data basis for subsequent cleaning path analysis.

[0082] Table 1 Image data record table

[0083]

[0084] Table 2 is a comparison table of cleaning paths of the cleaning nozzles when cleaning metal workpieces in the prior art and the present invention.

[0085] Table 2 Comparison of cleaning paths

[0086] Part Number Cleaning method Nozzle moving distance (m) Cleaning time (min) Amount of cleaning fluid (L) 1 Prior Art 4.5 18 4.5 1 Our invention 3 10 2.5 2 Prior Art 5 20 5 2 Our invention 3.5 12 3

[0087] Table 3 is a comparative table of cleaning effect evaluation after cleaning metal workpieces by the prior art and the present invention.

[0088] Table 3 Cleaning effect evaluation table

[0089]

[0090] As can be seen from the above table, the present invention enables the cleaning nozzle to accurately cover the dirty area, avoids cleaning omissions or excessive cleaning, ensures the cleaning quality of metal workpieces, calculates the optimal movement path based on the dirt distribution, reduces unnecessary movement and idle stroke of the cleaning nozzle, and makes the cleaning work more efficient.

[0091] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A metal workpiece detection and cleaning control method based on image processing, characterized in that: include: Use sensors to collect and pre-process image data of metal workpiece surfaces; constructing a three-dimensional geometric model based on the image data and identifying dirty areas; Calculate the optimal movement path of the cleaning nozzle according to the dirt distribution; Sending instructions to the cleaning nozzle according to the optimal moving path; The images acquired in real time were compared and analyzed with the images before and during cleaning.

2. The metal workpiece detection and cleaning control method based on image processing as claimed in claim 1, characterized in that: The sensors are 3D scanning equipment and high-resolution industrial cameras; The image data includes spatial information data, visual feature data, image statistical data, feature description data and dirt feature data.

3. The metal workpiece detection and cleaning control method based on image processing as claimed in claim 2, characterized in that: The specific steps to construct a 3D geometric model are as follows: Collect and pre-process the surface image data of metal workpieces according to sensors; Construct 3D geometric models based on recurrent neural networks and extract features from image data; Identify dirty areas based on the extracted features; Calculating an optimal moving path for the cleaning nozzle according to the dirt distribution; The optimal moving path is sent to the cleaning nozzle.

4. The metal workpiece detection and cleaning control method based on image processing as claimed in claim 3, characterized in that: The specific formula for calculating the optimal moving path is as follows: Among them, C is a comprehensive evaluation index; L j is the Euclidean distance from the current position of the nozzle to the center of the jth dirty area; λ is the weight coefficient; E i is the cleaning efficiency of the nozzle on the i-th dirty area; n is the number of dirty areas.

5. The metal workpiece detection and cleaning control method based on image processing as claimed in claim 4, characterized in that: The specific formula for the Euclidean distance of the nozzle moving from the current position to the center of the jth dirty area is as follows: Among them, L j is the Euclidean distance from the current position of the nozzle to the center of the jth dirty area; (x, y, z) is the current position coordinate of the nozzle in three-dimensional space; (x j ,y j ,z j ) is the coordinate of the center of the jth dirty area in three-dimensional space.

6. The metal workpiece detection and cleaning control method based on image processing as claimed in claim 1, characterized in that: The specific steps of comparing and analyzing the real-time acquired image with the images before and during cleaning are as follows: Comparing the real-time image with the baseline image before cleaning and the previous cleaning process image; Calculate the corresponding difference value according to the set comparative analysis index; Compare the calculated difference value with the set threshold; Make corresponding decisions based on comparative analysis results and judgment conclusions; During the entire cleaning process monitoring and feedback adjustment, all collected data, comparative analysis results, decision content and implementation of adjustment measures are recorded in detail.

7. The metal workpiece detection and cleaning control method based on image processing as claimed in claim 6, characterized in that: The specific formula for calculating the corresponding difference value according to the set comparative analysis index is as follows: Where D is the difference between the real-time image and the reference image before cleaning; N is the total number of pixels in the image; I t (k) is the value of the kth pixel in the real-time image; I0(k) is the value of the kth pixel in the reference image before cleaning; The specific situation of comparing the difference value with the threshold value is as follows: When the difference between the real-time image and the pre-cleaning reference image is less than the threshold, it means that the difference between the real-time image and the pre-cleaning reference image and the previous cleaning process image is within an acceptable range, indicating that the current cleaning process is progressing smoothly, the cleaning effect is in line with expectations, there are no obvious abnormalities, the working state of the cleaning equipment is stable, and there is no need to adjust the cleaning process parameters or equipment; When the difference between the real-time image and the reference image before cleaning is equal to the threshold, it means that the difference between the real-time image and the reference image has just reached the set boundary, and more information needs to be combined for comprehensive evaluation; When the difference value between the real-time image and the reference image before cleaning is greater than a threshold, it means that the difference between the real-time image and the reference image and the previous cleaning process image exceeds an acceptable range, reflecting that a deviation or abnormality has occurred in the cleaning process.

8. A metal workpiece detection and cleaning control system based on image processing, based on the metal workpiece detection and cleaning control method based on image processing according to any one of claims 1 to 7, characterized in that: include, Data acquisition module, used to collect metal workpiece surface image data and perform preprocessing; A model building module, used to build a 3D geometric model and identify dirty areas; A path generation module is used to calculate the optimal movement path of the cleaning nozzle; An instruction sending module, used for sending the optimal moving path to the cleaning nozzle; The image comparison module is used to compare and analyze the real-time acquired image with the images before and during cleaning.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the metal workpiece detection and cleaning control method based on image processing according to any one of claims 1 to 7 are implemented.

10. 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 metal workpiece detection and cleaning control method based on image processing according to any one of claims 1 to 7 are implemented.

Images