Part machining difficulty analysis system and tool based on artificial intelligence

Abstract

The invention discloses a part machining difficulty analysis system and tool based on artificial intelligence. The system comprises a drawing input module, an entity scanning module, a material machinability analysis module, a process constraint evaluation module, a feature extraction and quantification module, an intelligent difficulty scoring module, a simulation verification module and a process optimization module. By deeply applying the artificial intelligence technology and comprehensively considering multiple factors such as the geometrical shape, the material characteristics and the machine tool capacity of the part, accurate evaluation of the machining difficulty is achieved, the unified analysis standard and process are established, subjective influences of human factors are reduced, the analysis standardization degree is improved, and the machining difficulty is improved. And by optimizing cutting parameters, a tool path, a process chain and the like, the machining efficiency and quality are improved, the production cost is reduced, and by generating a risk heat map and conducting simulation verification, difficult points and risk areas in the machining process are found in advance, targeted prevention measures are formulated, and the machining risk is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of part machining, in particular to a part machining difficulty analysis system and tool based on artificial intelligence. BACKGROUND

[0002] Part machining is a process of cutting and forming materials such as metals and plastics through mechanical equipment to manufacture parts or products that meet design requirements. It is the core link of modern manufacturing and is widely used in the fields of automobiles, aerospace, electronics, medical equipment, etc.

[0003] The existing part machining difficulty analysis has the following defects: first, the traditional analysis method relies heavily on manual experience and simple rule base, lacks deep application of artificial intelligence technology, and leads to strong subjectivity and low standardization in the analysis process, making it difficult to adapt to the evaluation needs of new materials and complex structures, and unable to continuously optimize through machine learning of historical processing data; second, most existing systems can only process CAD models or drawing data, and cannot directly analyze physical parts; third, it is difficult to realize full-dimensional digital modeling of parts in three-dimensional space, and cannot meet the dual needs of high-precision modeling and automatic rapid measurement. SUMMARY

[0004] The purpose of the present application is to provide a part machining difficulty analysis system and tool based on artificial intelligence to solve the problems raised in the background.

[0005] To achieve the above purpose, the present application provides the following technical solution: a part machining difficulty analysis system based on artificial intelligence, comprising a drawing input module, a feature extraction and quantification module connected to the drawing input module, an entity scanning module and a feature extraction and quantification module connected to the feature extraction and quantification module, a material machinability analysis module and a process constraint evaluation module connected to the feature extraction and quantification module, and an intelligent difficulty scoring module connected to the material machinability analysis module and the process constraint evaluation module.

[0006] As a further technical solution of the present application, the drawing input module comprises a model analysis module, a drawing recognition module, a material database module and a historical data cleaning module, and the feature extraction and quantification module comprises a geometric complexity calculation module, a tolerance chain analysis module, a thin-walled feature detection module, a deep hole and micro-hole recognition module and an acute and sharp corner detection module.

[0007] As a further technical scheme of the present application, the material processability analysis module includes a material hardness mapping module, a chip morphology prediction module, a thermal conductivity influence module, and a stickiness tendency evaluation module, the process constraint evaluation module includes a machine tool capability matching module, a tool library matching module, a fixture accessibility module, and a coolant strategy module, and the intelligent difficulty scoring module includes a multi-dimensional weight distribution module, a dynamic scoring adjustment module, and a risk heat map generation module.

[0008] As a further technical scheme of the present application, the intelligent difficulty scoring module is data-connected with a simulation verification module, and the simulation verification module includes a cutting force prediction module, a thermal deformation simulation module, and a surface integrity prediction module.

[0009] As a further technical scheme of the present application, the simulation verification module is data-connected with a process optimization module, and the process optimization module includes a cutting parameter optimization module, a tool path planning module, a process chain reorganization module, and an alternative process recommendation module.

[0010] An artificial intelligence-based part machining difficulty analysis tool includes an entity scanning module, the entity scanning module includes a support, a fixed rod is fixedly connected to the support, a fixed table is fixedly connected to the fixed rod, a third motor is fixedly connected to the lower surface of the fixed table, an output shaft is fixedly connected to the output end of the third motor, a rotating platform is fixedly connected to the output shaft, the rotating platform is rotatably connected to the fixed table, a rotating shaft is sleeved on the fixed rod, a fixed block is fixedly connected to the rotating shaft, a fixed ring is fixedly connected to the fixed block, a rotating ring is rotatably connected to the fixed ring, a scanning laser and a camera are fixedly connected to the rotating ring.

[0011] As a further technical scheme of the present application, a horizontal plate is fixedly connected to the support, a first motor is fixedly connected to the horizontal plate, a first pulley is fixedly connected to the output end of the first motor, a first synchronous belt is sleeved on the first pulley, a gear is fixedly connected to the rotating shaft, and the first synchronous belt is sleeved on the gear.

[0012] As a further technical scheme of the present application, a fixed plate is fixedly connected to the fixed ring, a second motor is fixedly connected to one side of the outer wall of the fixed plate, a second pulley is fixedly connected to the output end of the second motor, a second synchronous belt is sleeved on the second pulley, the second synchronous belt is sleeved on the rotating ring, a tension pulley is rotatably connected to the fixed ring, and the second synchronous belt is sleeved on the tension pulley.

[0013] As a further technical scheme of the present application, a protective shell is fixedly connected to the lower surface of the fixed table, and a heat dissipation hole is formed in the outer wall of the protective shell.

[0014] As a further technical scheme of the present application, a support leg is fixedly connected to the support.

[0015] Compared with the prior art, the beneficial effects of the present application are: the present application realizes accurate evaluation of machining difficulty by deeply applying artificial intelligence technology, comprehensively considering multiple factors such as the geometric shape of the part, material properties, machine tool capacity, etc., establishes a unified analysis standard and process, reduces the subjective influence of human factors, improves the standardization degree of analysis, and through optimization of cutting parameters, tool path and process chain, etc., improves machining efficiency and quality, reduces production cost, and through generation of risk heat map and simulation verification, discovers difficult points and risk areas in the machining process in advance, formulates targeted preventive measures to reduce machining risk, and the present application is designed with an entity scanning module to scan the entity part and generate a three-dimensional model for machining difficulty analysis, and through a composite rotating structure, the entity part is scanned in all directions in three-dimensional space through laser scanning and visual camera, improving the accuracy and reliability of entity scanning, and having the advantages of high precision and fast measurement. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a system block diagram of the present application;

[0017] Figure 2 is a module architecture diagram of the feature extraction and quantification module;

[0018] Figure 3 is a module architecture diagram of the intelligent difficulty scoring module;

[0019] Figure 4 is a module architecture diagram of the simulation verification module;

[0020] Figure 5 is a perspective structural schematic diagram of the entity scanning module of the present application;

[0021] Figure 6 is a front view structural schematic diagram of the entity scanning module of the present application;

[0022] Figure 7 is a top view structural schematic diagram of the entity scanning module of the present application;

[0023] Figure 8 is a perspective cut structural schematic diagram of the fixed table of the present application;

[0024] Figure 9 is Figure 5 is an enlarged structural schematic diagram of area A;

[0025] Figure 10 is a system flowchart of the present application.

[0026] In the figure: 1, drawing input module; 11, model analysis module; 12, drawing recognition module; 13, material database module; 14, historical data cleaning module; 2, entity scanning module; 21, support; 22, support foot; 23, cross plate; 24, fixed rod; 25, rotating shaft; 26, fixed block; 27, fixed ring; 28, first motor; 29, first pulley; 210, first synchronous belt; 211, gear; 212, fixed plate; 213, second motor; 214, second pulley; 215, second synchronous belt; 216, tension pulley; 217, rotating ring; 218, scanning laser; 219, camera; 220, fixed table; 221, protective shell; 222, third motor; 223, heat dissipation hole; 224, output shaft; 225, rotating platform; 3, material machinability analysis module; 31, material hardness mapping module; 32, chip form prediction module; 33, thermal conductivity influence module; 34, stick tendency evaluation module; 4, process constraint evaluation module; 41, machine tool capability matching module; 42, tool library matching module; 43, fixture accessibility module; 44, coolant strategy module; 5, feature extraction and quantification module; 51, geometric complexity calculation module; 52, tolerance chain analysis module; 53, thin-walled feature detection module; 54, deep hole and micro hole identification module; 55, acute and sharp corner detection module; 6, intelligent difficulty scoring module; 61, multi-dimensional weight allocation module; 62, dynamic score adjustment module; 63, risk heat map generation module; 7, simulation verification module; 71, cutting force prediction module; 72, thermal deformation simulation module; 73, surface integrity prediction module; 8, process optimization module; 81, cutting parameter optimization module; 82, tool path planning module; 83, process chain reorganization module; 84, alternative process recommendation module. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0028] Please refer to the drawings in the embodiments of the present application Figure 1 - the drawings in the embodiments of the present application Figure 4The application provides an embodiment: a part machining difficulty analysis system based on artificial intelligence, which comprises a drawing input module 1, a feature extraction and quantification module 5 connected with the drawing input module 1, an entity scanning module 2 and a feature extraction and quantification module 5 connected with the feature extraction and quantification module 5, a material machinability analysis module 3 and a process constraint evaluation module 4 connected with the feature extraction and quantification module 5, and an intelligent difficulty scoring module 6 connected with the material machinability analysis module 3 and the process constraint evaluation module 4; the drawing input module 1 comprises a model analysis module 11, a drawing recognition module 12, a material database module 13 and a historical data cleaning module 14, the feature extraction and quantification module 5 comprises a geometric complexity calculation module 51, a tolerance chain analysis module 52, a thin-wall feature detection module 53, a deep hole and micro hole identification module 54 and an acute angle and sharp corner detection module 55, the geometric complexity calculation module 51 analyzes the geometric features of the part, and preliminarily evaluates the complexity grade thereof, the tolerance chain analysis module 52 analyzes the size chain and tolerance of the part, and evaluates the influence on machining precision, the thin-wall feature detection module 53 detects the thin-wall features in the part, and evaluates the machining difficulty and deformation risk, the deep hole and micro hole identification module 54 identifies the deep hole and micro hole in the part, and evaluates the machining difficulty and tool selection, and the acute angle and sharp corner detection module 55 detects the acute angle and sharp corner in the part, and evaluates the machining difficulty and surface quality; the material machinability analysis module 3 comprises a material hardness mapping module 31, a chip morphology prediction module 32, a thermal conductivity influence module 33 and a tool sticking tendency evaluation module 34, the process constraint evaluation module 4 comprises a machine tool capability matching module 41, a tool library matching module 42, a fixture accessibility module 43 and a cooling liquid strategy module 44, the intelligent difficulty scoring module 6 comprises a multi-dimensional weight distribution module 61, a dynamic scoring adjustment module 62 and a risk heat map generation module 63, the multi-dimensional weight distribution module 61 adjusts the scoring weight according to the importance of different dimensions, and ensures the rationality of the score, the dynamic scoring adjustment module 62 adjusts the weight of each evaluation factor according to the actual situation, so that the score is more in line with the actual demand, and the risk heat map generation module 63 generates a risk heat map of part machining, and intuitively displays the difficulty and risk area in the machining process; the intelligent difficulty scoring module 6 is connected with a simulation verification module 7, the simulation verification module 7 comprises a cutting force prediction module 71, a thermal deformation simulation module 72 and a surface integrity prediction module 73, the cutting force prediction module 71 predicts the cutting force generated in the cutting process, optimizes the cutting parameters and tool selection, the thermal deformation simulation module 72 simulates the thermal deformation in the machining process, and evaluates the influence on machining precision, and the surface integrity prediction module 73 predicts the surface quality of the part after machining, and ensures that the design requirements are met.The simulation verification module 7 is connected with a process optimization module 8, which includes a cutting parameter optimization module 81, a tool path planning module 82, a process chain reorganization module 83 and a substitute process recommendation module 84. The cutting parameter optimization module 81 optimizes parameters such as cutting speed, feed rate and cutting depth, improves machining efficiency and quality, the tool path planning module 82 plans reasonable tool path, reduces machining time and tool wear, the process chain reorganization module 83 reorganizes the process chain according to the machining difficulty and efficiency requirement, optimizes the machining process, and the substitute process recommendation module 84 is used to recommend a substitute process scheme when a certain process is difficult to implement, to ensure the smooth progress of machining.

[0029] Please refer to the attached Figure 5 - attached Figure 10The application provides an embodiment: an artificial intelligence part machining difficulty analysis tool, which comprises an entity scanning module 2, the entity scanning module 2 comprises a support 21, a fixed rod 24 is fixedly connected to the support 21, a fixed table 220 is fixedly connected to the fixed rod 24, a third motor 222 is fixedly connected to the lower surface of the fixed table 220, an output shaft 224 is fixedly connected to the output end of the third motor 222, a rotating platform 225 is fixedly connected to the output shaft 224, and the rotating platform 225 is rotatably connected to the fixed table 220, a rotating shaft 25 is sleeved on the fixed rod 24, a fixed block 26 is fixedly connected to the rotating shaft 25, a fixed ring 27 is fixedly connected to the fixed block 26, a rotating ring 217 is rotatably connected to the fixed ring 27, a scanning laser 218 and a camera 219 are fixedly connected to the rotating ring 217; a horizontal plate 23 is fixedly connected to the support 21, a first motor 28 is fixedly connected to the horizontal plate 23, a first pulley 29 is fixedly connected to the output end of the first motor 28, a first synchronous belt 210 is sleeved on the first pulley 29, a gear 211 is fixedly connected to the rotating shaft 25, and the first synchronous belt 210 is sleeved on the gear 211, the first motor 28 drives the first pulley 29 to rotate, the first pulley 29 drives the first synchronous belt 210, the first synchronous belt 210 drives the gear 211 to rotate, and then drives the rotating shaft 25 to rotate, the rotating shaft 25 is connected to the fixed ring 27 through the fixed block 26 and drives the fixed ring 27 to rotate, and the rotating ring 217 on the fixed ring 27 rotates around the rotating shaft 25 as the center; a fixed plate 212 is fixedly connected to the fixed ring 27, a second motor 213 is fixedly connected to the outer wall on one side of the fixed plate 212, a second pulley 214 is fixedly connected to the output end of the second motor 213, a second synchronous belt 215 is sleeved on the second pulley 214, and the second synchronous belt 215 is sleeved on the rotating ring 217, a tension pulley 216 is rotatably connected to the fixed ring 27, and the second synchronous belt 215 is sleeved on the tension pulley 216, the second motor 213 drives the second pulley 214 to rotate, the second pulley 214 drives the second synchronous belt 215 to rotate, the second synchronous belt 215 drives the rotating ring 217 to rotate through the tension pulley 216, and the scanning laser 218 and the camera 219 on the rotating ring 217 are used for collecting scanning data of an entity part; a protective shell 221 is fixedly connected to the lower surface of the fixed table 220, and a plurality of heat dissipation holes 223 are formed in the outer wall of the protective shell 221, the protective shell 221 is used for protecting the third motor 222, and the heat dissipation holes 223 are used for heat dissipation; a support leg 22 is fixedly connected to the support 21, and the support 21 and the support leg 22 are used for supporting and fixing a scanning structure.

[0030] Based on the above, the advantages of the present application are that when the part machining difficulty analysis is carried out using the present application, firstly, the part drawing is imported through the drawing input module 1, specifically, the model analysis module 11 is responsible for analyzing the input model or drawing data, extracting the basic information of the part such as geometry, size, etc., the drawing recognition module 12 automatically recognizes the annotations, symbols and text information in the drawing, ensures the accuracy and integrity of the data, the material database module 13 provides the physical, chemical and mechanical property data of the material used by the part, provides the basis for subsequent analysis, the historical data cleaning module 14 cleans and arranges the historical machining data, removes abnormal data, improves the data quality, or scans the entity part through the entity scanning module 2 to obtain the three-dimensional model of the entity part, specifically, the entity part is placed on the rotating platform 225, the first motor 28 on the horizontal plate 23 is started to drive the first pulley 29 to rotate, the first pulley 29 drives the first synchronous belt 210 to rotate, the first synchronous belt 210 drives the gear 211 to rotate, and then drives the rotating shaft 25 to rotate, the rotating shaft 25 is connected with the fixed ring 27 through the fixed block 26 and drives it to rotate, realizes the rotation of the rotating ring 217 on it with the rotating shaft 25 as the center, at the same time, the second motor 213 on the fixed plate 212 drives the second pulley 214 to rotate, the second pulley 214 drives the second synchronous belt 215 to rotate, the second synchronous belt 215 drives the rotating ring 217 to rotate through the tensioning wheel 216, and the scanning laser 218 and the camera 219 on it are used to collect scanning data of the entity part, the scanning laser 218 adopts a line laser mode, realizes the rapid deflection scanning of the laser beam through a precision galvanometer system, the camera 219 is equipped with a global shutter CMOS sensor, the synchronous trigger acquisition frequency is strictly time-synchronous with the laser scanning, and three-dimensional model establishment is realized in combination with data, at the same time, the third motor 222 on the fixed table 220 drives the rotating platform 225 to rotate through the output shaft 224, realizes the full-range scanning model generation of the entity part on it in three-dimensional space, wherein the support 21 and the support leg 22 are used to support and fix the scanning structure, the fixed rod 24 is used to fix the fixed table 220, the protection shell 221 is used to protect the third motor 222, the heat dissipation hole 223 is used for heat dissipation, the drawing data of the part is analyzed by the geometric complexity calculation module 51 in the feature extraction and quantization module 5, the geometric features of the part are analyzed, the complexity level is preliminarily evaluated, the tolerance chain analysis module 52 analyzes the size chain and tolerance of the part, evaluates the influence on the machining precision, the thin-wall feature detection module 53 detects the thin-wall feature in the part, evaluates the machining difficulty and deformation risk, the deep hole and micro-hole recognition module 54 recognizes the deep hole and micro-hole in the part, evaluates the machining difficulty and tool selection, the acute angle and sharp corner detection module 55 detects the acute angle and sharp corner in the part, evaluates the machining difficulty and surface quality, then the material machinability analysis module 3 is used to analyze the material machinability of the part, specifically, the material hardness mapping module 31 analyzes the hardness distribution of the material, evaluates the influence on the machining process,The chip morphology prediction module 32 predicts the morphology of the chip in the cutting process, optimizes the cutting parameters, the thermal conductivity influence module 33 evaluates the influence of the thermal conductivity of the material on the machining temperature, prevents thermal damage, the tool sticking tendency evaluation module 34 analyzes whether the material is easy to adhere to the tool, which affects the machining efficiency and tool life, the process constraint evaluation module 4 evaluates the process constraints in the machining process according to the material properties, ensures the feasibility of machining, specifically, the machine tool capability matching module 41 matches the appropriate machining machine tool model according to the material machining properties and machining requirements of the part, the tool library matching module 42 matches the most suitable tool type and specification according to the machining requirements of the part, the fixture accessibility module 43 evaluates whether the fixture can reach each machining position of the part, ensures the stability of machining, the coolant strategy module 44 formulates appropriate coolant use strategy, reduces machining temperature and reduces tool wear, after the above analysis, the intelligent difficulty scoring module 6 considers the geometric complexity of the part, the material machinability, the machine tool capability and other factors to give the machining difficulty score of the part, the multi-dimensional weight distribution module 61 adjusts the scoring weight according to the importance of different dimensions to ensure the rationality of the score, the dynamic score adjustment module 62 adjusts the weight of each evaluation factor according to the actual situation, so that the score is more in line with the actual demand, the risk heat map generation module 63 generates a risk heat map of the part machining, which intuitively displays the difficulties and risk areas in the machining process, and then the cutting force prediction module 71 in the simulation verification module 7 predicts the cutting force generated in the cutting process, optimizes the cutting parameters and tool selection, the thermal deformation simulation module 72 simulates the thermal deformation in the machining process, evaluates its influence on machining accuracy, the surface integrity prediction module 73 predicts the surface quality of the part after machining to ensure that the design requirements are met, the cutting parameter optimization module 81 in the process optimization module 8 optimizes the cutting speed, feed rate and cutting depth and other parameters to improve the machining efficiency and quality, the tool path planning module 82 plans a reasonable tool path to reduce the machining time and tool wear, the process chain reorganization module 83 reorganizes the process chain according to the machining difficulty and efficiency requirements to optimize the machining process, and the alternative process recommendation module 84 is used when a certain process is difficult to implement to recommend an alternative process scheme to ensure the smooth progress of machining.

[0031] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended to encompass all changes falling within the meaning and scope of the equivalent elements of the claims. Any reference signs in the claims should not be considered as limiting the claims involved.

Claims

1. A part machining difficulty analysis system based on artificial intelligence, comprising a drawing input module (1), characterized in that: The drawing input module (1) is connected to a feature extraction and quantization module (5). The feature extraction and quantization module (5) is connected to an entity scanning module (2) and a feature extraction and quantization module (5). The feature extraction and quantization module (5) is connected to a material processability analysis module (3) and a process constraint evaluation module (4). The material processability analysis module (3) and the process constraint evaluation module (4) are connected to an intelligent difficulty scoring module (6).

2. The part machining difficulty analysis system based on artificial intelligence according to claim 1, characterized in that: The drawing input module (1) includes a model parsing module (11), a drawing recognition module (12), a material database module (13), and a historical data cleaning module (14). The feature extraction and quantification module (5) includes a geometric complexity calculation module (51), a tolerance chain analysis module (52), a thin-wall feature detection module (53), a deep hole / microhole recognition module (54), and an acute angle / sharp corner detection module (55).

3. The part machining difficulty analysis system based on artificial intelligence according to claim 1, characterized in that: The material machinability analysis module (3) includes a material hardness mapping module (31), a chip morphology prediction module (32), a thermal conductivity influence module (33), and a tool sticking tendency assessment module (34). The process constraint assessment module (4) includes a machine tool capability matching module (41), a tool library matching module (42), a fixture accessibility module (43), and a coolant strategy module (44). The intelligent difficulty scoring module (6) includes a multi-dimensional weight allocation module (61), a dynamic scoring adjustment module (62), and a risk heat map generation module (63).

4. The part machining difficulty analysis system based on artificial intelligence according to claim 3, characterized in that: The intelligent difficulty scoring module (6) is connected to a simulation verification module (7), which includes a cutting force prediction module (71), a thermal deformation simulation module (72), and a surface integrity prediction module (73).

5. The part machining difficulty analysis system based on artificial intelligence according to claim 4, characterized in that: The simulation verification module (7) is connected to a process optimization module (8), which includes a cutting parameter optimization module (81), a tool path planning module (82), a process chain reorganization module (83), and an alternative process recommendation module (84).

6. A part machining difficulty analysis tool based on artificial intelligence, comprising a solid scanning module (2), characterized in that: The entity scanning module (2) includes a bracket (21), a fixed rod (24) is fixedly connected to the bracket (21), a fixed platform (220) is fixedly connected to the fixed rod (24), a third motor (222) is fixedly connected to the lower surface of the fixed platform (220), an output shaft (224) is fixedly connected to the output end of the third motor (222), a rotating platform (225) is fixedly connected to the output shaft (224), and the rotating platform (225) is rotatably connected to the fixed platform (220). A rotating shaft (25) is sleeved on the fixed rod (24), a fixed block (26) is fixedly connected to the rotating shaft (25), a fixed ring (27) is fixedly connected to the fixed block (26), a rotating ring (217) is rotatably connected to the fixed ring (27), and a scanning laser (218) and a camera (219) are fixedly connected to the rotating ring (217).

7. The part machining difficulty analysis tool based on artificial intelligence according to claim 6, characterized in that: A horizontal plate (23) is fixedly connected to the bracket (21), a first motor (28) is fixedly connected to the horizontal plate (23), a first pulley (29) is fixedly connected to the output end of the first motor (28), a first synchronous belt (210) is sleeved on the first pulley (29), a gear (211) is fixedly connected to the rotating shaft (25), and the first synchronous belt (210) is sleeved on the gear (211).

8. The part machining difficulty analysis tool based on artificial intelligence according to claim 6, characterized in that: A fixing plate (212) is fixedly connected to the fixing ring (27). A second motor (213) is fixedly connected to one side of the outer wall of the fixing plate (212). A second pulley (214) is fixedly connected to the output end of the second motor (213). A second synchronous belt (215) is sleeved on the second pulley (214) and the second synchronous belt (215) is sleeved on the rotating ring (217). A tensioning wheel (216) is rotatably connected to the fixing ring (27) and the second synchronous belt (215) is sleeved on the tensioning wheel (216).

9. The part machining difficulty analysis tool based on artificial intelligence according to claim 6, characterized in that: A protective shell (221) is fixedly connected to the lower surface of the fixed platform (220), and heat dissipation holes (223) are provided on the outer wall of the protective shell (221).

10. The part machining difficulty analysis tool based on artificial intelligence according to claim 7, characterized in that: The bracket (21) is fixedly connected to a support leg (22).

Images