A metal scrap intelligent cleaning method and device

Abstract

The present invention belongs to the technical field of smart factories, and provides a method and device for intelligent cleaning of metal chips. The method comprises: shooting high-definition image data of the movable guide rail wall of a CNC lathe, analyzing and processing the high-definition image data to obtain first attribute data of the metal chips on the movable guide rail wall; evaluating the difficulty of cleaning the metal chips on the movable guide rail wall based on the first attribute data, obtaining a cleaning difficulty evaluation index, and obtaining a target adsorption force according to the matching of the cleaning difficulty evaluation index; obtaining an adsorption working parameter according to the target adsorption force, and controlling the adsorption cleaning device to execute the adsorption working parameter to realize automatic cleaning of the metal chips on the movable guide rail wall. The present invention can control the adsorption cleaning device to automatically clean the metal chips adhered to the movable guide rail wall, thereby improving the cleaning efficiency of the metal chips and avoiding the safety risks of manual cleaning methods.

Description

Technical Field

[0001] The present invention relates to the technical field of smart factories, and in particular to a method and equipment for intelligently cleaning metal chips. Background Art

[0002] CNC lathes can achieve high-precision and high-efficiency processing. When CNC lathes process brittle light metal materials, the cut metal chips will adhere to the movable guide rail wall inside the lathe, which needs to be cleaned to ensure the processing efficiency, processing accuracy and sanitation and safety of the working environment of the CNC lathe.

[0003] The current method of cleaning the metal chips adhered to the movable guide rail wall of the CNC lathe is mainly manual cleaning, that is, after the CNC lathe completes the processing of the metal parts, the relevant personnel hold the adsorption equipment to adsorb the metal chips adhered to the movable guide rail wall of the CNC lathe. However, the manual cleaning method has certain safety risks, and the cleaning efficiency is not high. Therefore, how to further improve the cleaning efficiency of the metal chips adhered to the movable guide rail wall of the CNC lathe is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a method and equipment for intelligent cleaning of metal chips.

[0005] The present invention provides a method for intelligently cleaning metal chips, comprising the following steps:

[0006] Taking high-definition image data of a movable guide rail wall of a CNC lathe, and analyzing and processing the high-definition image data to obtain first attribute data of metal chips on the movable guide rail wall; wherein the first attribute data includes the size and weight of the metal chips;

[0007] Based on the first attribute data, the cleaning difficulty of the metal chips on the movable guide rail wall is evaluated to obtain a cleaning difficulty evaluation index, and the target adsorption strength is obtained according to the matching of the cleaning difficulty evaluation index;

[0008] Adsorption working parameters are calculated based on the target adsorption strength, and the adsorption cleaning equipment is controlled to execute the adsorption working parameters to achieve automatic cleaning of metal chips on the movable guide rail wall.

[0009] In some embodiments, the capturing of high-definition image data of the movable guide rail wall of the CNC lathe includes:

[0010] Controlling a high-definition camera arranged on the adsorption cleaning device to capture high-definition video data of the CNC lathe, and judging the working state of the CNC lathe according to the high-definition video data; wherein the working state includes a rough processing state, a fine processing state, and a shutdown state;

[0011] If the working state meets the cleaning condition, the high-definition camera is controlled to capture high-definition image data of the movable guide rail wall of the CNC lathe; wherein the cleaning condition refers to the working state being the finishing state or the shutdown state.

[0012] In some embodiments, judging the working state of the CNC lathe according to the high-definition video data includes:

[0013] Extracting the feed speed, cutting speed, tool type, and surface roughness of the processed metal part of the CNC lathe according to the high-definition video data;

[0014] If the feed speed and the cutting speed are zero, it is determined that the working state of the CNC lathe is the shutdown state;

[0015] If the feed speed and the cutting speed are not zero, the working state of the CNC lathe is determined to be the rough machining state or the fine machining state according to the feed speed, the cutting speed, the tool type and the surface roughness.

[0016] In some embodiments, the step of evaluating the difficulty of cleaning the metal chips on the movable guide rail wall based on the first attribute data to obtain a cleaning difficulty evaluation index includes:

[0017] Obtaining a corresponding first cleaning difficulty assessment index according to matching of the first attribute data and the first comparison table;

[0018] Acquire second attribute data of the oily substance on the movable guide rail wall of the CNC lathe from the high-definition image data, the second attribute data including the type of the oily substance and the thickness of the oily substance, predict the viscosity grade of the mixture of metal chips and the oily substance based on the first attribute data and the second attribute data, and obtain the difficulty adjustment coefficient based on the viscosity grade matching;

[0019] A second cleaning difficulty assessment index is calculated using the difficulty adjustment coefficient and the first cleaning difficulty assessment index, and the second cleaning difficulty assessment index is used as the cleaning difficulty assessment index.

[0020] In some embodiments, the viscosity grade of the mixture of metal chips and oily substances is predicted based on the first attribute data and the second attribute data, and the difficulty adjustment coefficient is obtained based on the viscosity grade matching, including:

[0021] Inputting the first attribute data and the second attribute data into a viscosity grade prediction model, the viscosity grade prediction model outputting the viscosity grade of the mixture of metal chips and oily substances;

[0022] The difficulty adjustment coefficient is obtained by matching the viscosity grade with the second comparison table.

[0023] In some embodiments, the viscosity grade prediction model is built based on Transformer and distributed training is performed based on a consortium chain.

[0024] The present invention also provides a metal chip intelligent cleaning device, the device comprising a controller and a storage unit, the controller calls a computer program from the storage unit, and executes the computer program to implement the following steps:

[0025] Taking high-definition image data of a movable guide rail wall of a CNC lathe, and analyzing and processing the high-definition image data to obtain first attribute data of metal chips on the movable guide rail wall; wherein the first attribute data includes the size and weight of the metal chips;

[0026] Based on the first attribute data, the cleaning difficulty of the metal chips on the movable guide rail wall is evaluated to obtain a cleaning difficulty evaluation index, and the target adsorption strength is obtained according to the matching of the cleaning difficulty evaluation index;

[0027] Adsorption working parameters are calculated based on the target adsorption strength, and the adsorption cleaning equipment is controlled to execute the adsorption working parameters to achieve automatic cleaning of metal chips on the movable guide rail wall.

[0028] The beneficial effects of the present invention are:

[0029] 1) The present invention can control the adsorption cleaning device to automatically clean the metal chips adhered to the wall of the movable guide rail, thereby improving the cleaning efficiency of the metal chips and avoiding the safety risks of manual cleaning;

[0030] 2) The above scheme of the present invention can identify the difficulty of cleaning metal chips on the movable guide rail wall based on image recognition technology and cleaning difficulty assessment technology, and then dynamically determine the optimal adsorption working parameters, and then control the adsorption cleaning equipment to automatically clean the metal chips on the movable guide rail wall. The adsorption cleaning equipment can dynamically adjust its own adsorption strength without the need to perform cleaning operations with the maximum adsorption strength, which is beneficial to reducing power consumption and noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present invention.

[0032] Figure 1 It is a schematic flow chart of a metal scrap intelligent cleaning method disclosed in an embodiment of the present invention;

[0033] Figure 2 It is a structural schematic diagram of the viscosity grade prediction model disclosed in an embodiment of the present invention;

[0034] Figure 3It is a structural schematic diagram of a metal chip intelligent cleaning device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following is a description of the exemplary embodiments disclosed in the present invention in conjunction with the accompanying drawings, including various details of the embodiments disclosed in the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0036] The current method of cleaning the metal chips adhered to the movable guide rail wall of the CNC lathe is mainly manual cleaning, that is, after the CNC lathe completes the processing of the metal parts, the relevant personnel hold the adsorption equipment to adsorb the metal chips adhered to the movable guide rail wall of the CNC lathe. However, the manual cleaning method has certain safety risks, and the cleaning efficiency is not high. Therefore, how to further improve the cleaning efficiency of the metal chips adhered to the movable guide rail wall of the CNC lathe is a technical problem that needs to be solved urgently.

[0037] In response to the above technical issues, such as Figure 1 As shown, the embodiment of the present invention discloses a metal scrap intelligent cleaning method, comprising the following steps:

[0038] Taking high-definition image data of a movable guide rail wall of a CNC lathe, and analyzing and processing the high-definition image data to obtain first attribute data of metal chips on the movable guide rail wall; wherein the first attribute data includes the size and weight of the metal chips;

[0039] Based on the first attribute data, the cleaning difficulty of the metal chips on the movable guide rail wall is evaluated to obtain a cleaning difficulty evaluation index, and the target adsorption strength is obtained according to the matching of the cleaning difficulty evaluation index;

[0040] Adsorption working parameters are calculated based on the target adsorption strength, and the adsorption cleaning equipment is controlled to execute the adsorption working parameters to achieve automatic cleaning of metal chips on the movable guide rail wall.

[0041] In order to improve the cleaning efficiency of metal chips adhered to the movable guide rail wall of the CNC lathe, the present invention designs the above-mentioned automatic cleaning scheme. Specifically, an adsorption cleaning device is configured for the CNC lathe, and a high-definition camera is arranged on the adsorption cleaning device. The high-definition camera shoots the movable guide rail wall corresponding to each CNC lathe, and analyzes and processes the high-definition image data obtained by shooting to obtain the first attribute data of the metal chips adhered to the movable guide rail wall, including the size of the metal chips and the weight of the metal chips. Then, based on the obtained first attribute data, the cleaning difficulty of the metal chips adhered to the movable guide rail wall is evaluated to obtain a cleaning difficulty evaluation index. The higher the cleaning difficulty evaluation index, the more difficult it is for the metal chips to be cleaned to be adsorbed by the adsorption cleaning device, and a greater adsorption force is required, otherwise a smaller adsorption force is required. Therefore, the target adsorption force can be matched according to the cleaning difficulty evaluation index, and then the target adsorption force is converted into an adsorption working parameter (such as motor speed) for the adsorption cleaning device to perform. Therefore, when controlling the adsorption working parameters of the adsorption cleaning equipment, the metal chips adhered to the wall of the movable guide rail can be automatically adsorbed and cleaned with the target adsorption force, thereby ensuring efficient and complete cleaning of the metal chips.

[0042] On the one hand, the above scheme of the present invention can control the adsorption cleaning device to automatically clean the metal chips adhered to the wall of the movable guide rail, thereby improving the cleaning efficiency of the metal chips and avoiding the safety risks of manual cleaning methods. On the other hand, the above scheme of the present invention can identify the difficulty of cleaning the metal chips adhered to the wall of the movable guide rail based on image recognition technology and cleaning difficulty assessment technology, and then dynamically determine the optimal adsorption working parameters, and then control the adsorption cleaning device to automatically clean the metal chips adhered to the wall of the movable guide rail. The adsorption cleaning device can dynamically adjust its own adsorption strength without having to perform cleaning operations at the maximum adsorption strength, which is beneficial to reducing power consumption and noise.

[0043] In some embodiments, the capturing of high-definition image data of the movable guide rail wall of the CNC lathe includes:

[0044] Controlling a high-definition camera arranged on the adsorption cleaning device to capture high-definition video data of the CNC lathe, and judging the working state of the CNC lathe according to the high-definition video data; wherein the working state includes a rough processing state, a fine processing state, and a shutdown state;

[0045] If the working state meets the cleaning condition, the high-definition camera is controlled to capture high-definition image data of the movable guide rail wall of the CNC lathe; wherein the cleaning condition refers to the working state being the finishing state or the shutdown state.

[0046] In this embodiment, the machining operation of the CNC lathe is divided into rough machining and fine machining. There will be more and larger metal chips during rough machining, while the metal chips splashed during fine machining are less and of small size. The metal chips splashed during rough machining may have a certain impact on the adsorption cleaning equipment (when the adsorption cleaning equipment is arranged inside the shielding door of the CNC lathe, the splashed large-sized metal chips will damage the high-precision sensor of the adsorption cleaning equipment), and it is not economical to clean at the stage when a large number of large-sized metal chips are splashing. Therefore, the present invention is preferably set to clean the metal chips adhering to the movable guide rail wall during the fine machining and shutdown stages.

[0047] On the basis of the above cleaning opportunity, the present invention is arranged to first control the high-definition camera arranged on the adsorption cleaning device to shoot the high-definition video data of the CNC lathe, and judge the working state of the CNC lathe according to the high-definition video data, and the working state includes three states of rough machining, fine machining and shutdown. When judging the working state of the CNC lathe, the above scheme of the present invention can be executed to trigger the control of the high-definition camera to shoot the high-definition image data of the active guide rail wall of the CNC lathe, so as to determine the corresponding adsorption working parameters for the adsorption cleaning device.

[0048] In some embodiments, judging the working state of the CNC lathe according to the high-definition video data includes:

[0049] Extracting the feed speed, cutting speed, tool type, and surface roughness of the processed metal part of the CNC lathe according to the high-definition video data;

[0050] If the feed speed and the cutting speed are zero, it is determined that the working state of the CNC lathe is the shutdown state;

[0051] If the feed speed and the cutting speed are not zero, the working state of the CNC lathe is determined to be the rough machining state or the fine machining state according to the feed speed, the cutting speed, the tool type and the surface roughness.

[0052] In this embodiment, the state of the working parts of the CNC lathe is different when performing rough machining and fine machining operations. The feed speed, cutting speed, tool type, and surface roughness of the processed metal parts can be extracted from the high-definition video data. The relationship between the above factors and the machining state is as follows:

[0053] Feed Rate: During rough machining, a higher feed rate is usually used to quickly remove material, because the purpose of rough machining is to quickly approach the final shape of the part, and the surface roughness requirement is not high. During fine machining, the feed rate will be reduced to ensure the roughness and dimensional accuracy of the machined surface and achieve a more refined machining effect.

[0054] Cutting Speed: Roughing may use a lower cutting speed because the goal is to remove material quickly rather than pursue surface roughness. When finishing, the cutting speed may be increased to obtain better surface roughness and processing accuracy.

[0055] Tool Type: Roughing tools are usually designed to be very strong and durable, with coarse pitch and large flute capacity to handle the heavy cutting loads. Finishing tools require smaller flutes and finer pitches, allowing them to remove material more slowly and with greater accuracy.

[0056] Surface finish: Roughing results in a relatively rough surface, often with visible tool marks. Finishing uses gentle cuts to leave a smooth, flawless surface.

[0057] Therefore, by comprehensively analyzing the feed speed, cutting speed, tool type, and surface roughness of the processed metal parts of the CNC lathe, it is possible to determine whether the CNC lathe is in a rough machining state or a fine machining state. Of course, the comprehensive analysis here can be achieved through a pre-built working state classification model, preferably using a large model, such as a BERT large model, a GPT large model, etc. In addition, when the feed speed and cutting speed of the CNC lathe are both zero, the CNC lathe is determined to be in a shutdown state.

[0058] Among them, in order to more accurately obtain the feed speed, cutting speed, tool type and surface roughness of the processed metal parts, the adsorption cleaning equipment can be set inside the shielding door of the CNC lathe, so that high-definition video data of the CNC lathe can be captured at a closer distance.

[0059] In some embodiments, the step of evaluating the difficulty of cleaning the metal chips on the movable guide rail wall based on the first attribute data to obtain a cleaning difficulty evaluation index includes:

[0060] Obtaining a corresponding first cleaning difficulty assessment index according to matching of the first attribute data and the first comparison table;

[0061] Acquire second attribute data of the oily substance on the movable guide rail wall of the CNC lathe from the high-definition image data, the second attribute data including the type of the oily substance and the thickness of the oily substance, predict the viscosity grade of the mixture of metal chips and the oily substance based on the first attribute data and the second attribute data, and obtain the difficulty adjustment coefficient based on the viscosity grade matching;

[0062] A second cleaning difficulty assessment index is calculated using the difficulty adjustment coefficient and the first cleaning difficulty assessment index, and the second cleaning difficulty assessment index is used as the cleaning difficulty assessment index.

[0063] In this embodiment, the cleaning difficulty of metal chips is mainly affected by two factors, namely, the first attribute data of the metal chips themselves and the second attribute data of the oily substance. Specifically, a first comparison table of metal chip size and metal chip weight and the first cleaning difficulty evaluation index is pre-established, as shown in Table 1:

[0064] Table 1 The first comparison table

[0065] Metal Chip Size Metal shavings weight First cleaning difficulty assessment indicator 1-5mm <0.2g A1 5mm-10mm >0.2g A2(A2>A1)

[0066] As the size of the metal chips gradually increases and the weight of the metal chips gradually increases, the difficulty of adsorbing and cleaning the metal chips also increases, and the first cleaning difficulty evaluation index also increases accordingly. It should be noted that the above-mentioned metal chip size and metal chip weight refer to the average size and weight of all metal chips adhered to the wall of the movable guide rail, and the metal chip weight is estimated based on the metal chip size and metal chip density (based on the type of metal parts being processed).

[0067] Therefore, after extracting the size and weight of the metal chips on the movable guide rail wall, the corresponding first cleaning difficulty evaluation index can be obtained by querying the above table. However, the above comparison table is only for illustration and is not intended to limit the corresponding relationship of the present invention to only the above first comparison table example.

[0068] At the same time, there may be oily substances on the wall of the movable guide rail (mainly cutting fluid splashed due to high-pressure injection or rapid movement of metal parts). The mixture of oily substances and metal chips will have a certain viscosity, which makes it more difficult to clean the metal chips. In this regard, the present invention is configured to obtain the second attribute data of the oily substance on the wall of the movable guide rail from the high-definition image data, including the type of oily substance and the thickness of the oily substance. Based on the first attribute data and the second attribute data, the viscosity grade of the mixture can be predicted, and the difficulty adjustment coefficient can be obtained based on the viscosity grade matching. Finally, the difficulty adjustment coefficient (greater than 1) is multiplied by the first cleaning difficulty assessment index obtained above to obtain the second cleaning difficulty assessment index, and the second cleaning difficulty assessment index is ultimately the final cleaning difficulty assessment index.

[0069] Among them, the type of oily substance refers to the type of cutting fluid. Different types of cutting fluids have different viscosities. The type of cutting fluid can be determined by analyzing the type of metal parts being processed on the CNC lathe and the processing method, including emulsion, cutting oil, extreme pressure / high concentration emulsion, oiliness agent + extreme pressure agent composite cutting fluid, etc. The thickness of the oily substance refers to the thickness of the oil film on the wall of the movable guide rail. The method for determining the thickness of the oil film is as follows:

[0070] Based on the high-definition image data, the area where the oily substance is located on the movable guide rail wall is identified, and the metal chips falling into the area where the oily substance is located are tracked to obtain the average wall-falling rebound height of the metal chips;

[0071] The oil film thickness is calculated based on the average wall rebound height and the standard average wall rebound height; wherein the standard average wall rebound height is the average wall rebound height of metal chips that have not fallen into the area where the oily substance is located.

[0072] The camera captures multiple high-definition image data, identifies and tracks the metal chips that splash and fall onto the wall of the movable guide rail, obtains the wall rebound height of these metal chips after falling on the oily substance on the wall of the movable guide rail, and calculates the average wall rebound height of multiple metal chips, that is, the average wall rebound height. At the same time, the average wall rebound height of the metal chips that have not fallen into the area where the oily substance is located is also obtained, which is used as the standard average wall rebound height. Then calculate the difference between the standard average wall rebound height and the average wall rebound height, and the oil film thickness can be inferred based on the difference. The thicker the oil film, the greater the rebound resistance of the metal chips, the smaller the average wall rebound height of the metal chips, and the greater the difference between it and the standard average wall rebound height; and the thinner the oil film, the smaller the rebound resistance of the metal chips, the greater the average wall rebound height of the metal chips, and the smaller the difference between it and the standard average wall rebound height. Through statistical analysis, the difference between the average wall-falling rebound height of metal chips splashing into various types of oily substances with different first attribute data and the standard average wall-falling rebound height can be obtained, and then the corresponding relationship between the average wall-falling rebound height and the set oil film thickness of this type of oily substance can be established, and then the above-mentioned oil film thickness can be inferred based on the corresponding relationship.

[0073] In some embodiments, the viscosity grade of the mixture of metal chips and oily substances is predicted based on the first attribute data and the second attribute data, and the difficulty adjustment coefficient is obtained based on the viscosity grade matching, including:

[0074] Inputting the first attribute data and the second attribute data into a viscosity grade prediction model, the viscosity grade prediction model outputting the viscosity grade of the mixture of metal chips and oily substances;

[0075] The difficulty adjustment coefficient is obtained by matching the viscosity grade with the second comparison table.

[0076] In this embodiment, the first attribute data and the second attribute data are used to characterize the measured characteristics of metal chips and oily substances, respectively. By using the pre-built viscosity grade prediction model to comprehensively analyze the first attribute data and the second attribute data, the predicted viscosity grade of the mixture of metal chips and oily substances can be obtained. At the same time, similar to the above, a second comparison table is pre-established, and the second comparison table contains a comparison relationship between multiple sets of viscosity grades and difficulty adjustment coefficients. Based on the predicted viscosity grade, the second comparison table is queried to obtain the corresponding difficulty adjustment coefficient. The second comparison table will not be described in detail here.

[0077] In some embodiments, the viscosity grade prediction model is built based on Transformer and distributed training is performed based on a consortium chain.

[0078] In this embodiment, the viscosity grade prediction model of the present invention preferably uses the Transformer algorithm as a construction basis. Figure 2 As shown in the figure, the viscosity grade prediction model mainly includes input layer, encoder, decoder, position encoding, multi-head attention mechanism and output layer.

[0079] like Figure 3 As shown, an embodiment of the present invention discloses an intelligent metal chip cleaning device, the device comprising a controller and a storage unit, the controller calls a computer program from the storage unit, and executes the computer program to implement the following steps:

[0080] Taking high-definition image data of a movable guide rail wall of a CNC lathe, and analyzing and processing the high-definition image data to obtain first attribute data of metal chips on the movable guide rail wall; wherein the first attribute data includes the size and weight of the metal chips;

[0081] Based on the first attribute data, the cleaning difficulty of the metal chips on the movable guide rail wall is evaluated to obtain a cleaning difficulty evaluation index, and the target adsorption strength is obtained according to the matching of the cleaning difficulty evaluation index;

[0082] Adsorption working parameters are calculated based on the target adsorption strength, and the adsorption cleaning equipment is controlled to execute the adsorption working parameters to achieve automatic cleaning of metal chips on the movable guide rail wall.

[0083] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] The program code for implementing the method disclosed in the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0085] In the context disclosed by the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0087] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0088] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0089] The above specific implementations do not constitute a limitation on the scope of protection disclosed by the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle disclosed by the present invention shall be included in the scope of protection disclosed by the present invention.

Claims

1. A metal shavings intelligent cleaning method, characterized in that: The steps include: Taking high-definition image data of a movable guide rail wall of a CNC lathe, and analyzing and processing the high-definition image data to obtain first attribute data of metal chips on the movable guide rail wall; wherein the first attribute data includes the size and weight of the metal chips; Based on the first attribute data, the cleaning difficulty of the metal chips on the movable guide rail wall is evaluated to obtain a cleaning difficulty evaluation index, and the target adsorption strength is obtained according to the matching of the cleaning difficulty evaluation index; The adsorption working parameters are calculated according to the target adsorption strength, and the adsorption cleaning device is controlled to execute the adsorption working parameters to realize automatic cleaning of metal chips on the movable guide rail wall; The high-definition image data of the movable guide rail wall of the CNC lathe is captured, including: Controlling a high-definition camera arranged on the adsorption cleaning device to capture high-definition video data of the CNC lathe, and judging the working state of the CNC lathe according to the high-definition video data; wherein the working state includes a rough processing state, a fine processing state, and a shutdown state; If the working state meets the cleaning condition, the high-definition camera is controlled to capture high-definition image data of the movable guide rail wall of the CNC lathe; wherein the cleaning condition refers to the working state being the finishing state or the shutdown state; The determining the working state of the CNC lathe according to the high-definition video data comprises: Extracting the feed speed, cutting speed, tool type, and surface roughness of the processed metal part of the CNC lathe according to the high-definition video data; If the feed speed and the cutting speed are zero, it is determined that the working state of the CNC lathe is the shutdown state; If the feed speed and the cutting speed are not zero, determining the working state of the CNC lathe as the rough machining state or the fine machining state according to the feed speed, the cutting speed, the tool type and the surface roughness; The step of evaluating the difficulty of cleaning the metal chips on the movable guide rail wall based on the first attribute data to obtain a cleaning difficulty evaluation index includes: Obtaining a corresponding first cleaning difficulty assessment index according to matching of the first attribute data and the first comparison table; Acquire second attribute data of the oily substance on the movable guide rail wall of the CNC lathe from the high-definition image data, the second attribute data including the type of the oily substance and the thickness of the oily substance, predict the viscosity grade of the mixture of metal chips and the oily substance based on the first attribute data and the second attribute data, and obtain the difficulty adjustment coefficient based on the viscosity grade matching; A second cleaning difficulty assessment index is calculated using the difficulty adjustment coefficient and the first cleaning difficulty assessment index, and the second cleaning difficulty assessment index is used as the cleaning difficulty assessment index.

2. The intelligent metal chip cleaning method according to claim 1, characterized in that: The predicting of the viscosity grade of the mixture of metal chips and oily substances based on the first attribute data and the second attribute data, and the difficulty adjustment coefficient based on the matching of the viscosity grades, include: Inputting the first attribute data and the second attribute data into a viscosity grade prediction model, the viscosity grade prediction model outputting the viscosity grade of the mixture of metal chips and oily substances; The difficulty adjustment coefficient is obtained by matching the viscosity grade with the second comparison table.

3. The intelligent metal chip cleaning method according to claim 2, characterized in that: The viscosity grade prediction model is built based on Transformer and is distributedly trained based on the alliance chain.

4. A device based on the metal chips intelligent cleaning method according to any one of claims 1 to 3, the device comprising a controller and a storage unit, characterized in that: The controller retrieves a computer program from the storage unit and executes the computer program to implement the following steps: Taking high-definition image data of a movable guide rail wall of a CNC lathe, and analyzing and processing the high-definition image data to obtain first attribute data of metal chips on the movable guide rail wall; wherein the first attribute data includes the size and weight of the metal chips; Based on the first attribute data, the cleaning difficulty of the metal chips on the movable guide rail wall is evaluated to obtain a cleaning difficulty evaluation index, and the target adsorption strength is obtained according to the matching of the cleaning difficulty evaluation index; Adsorption working parameters are calculated based on the target adsorption strength, and the adsorption cleaning equipment is controlled to execute the adsorption working parameters to achieve automatic cleaning of metal chips on the movable guide rail wall.

Images