An integrated wafer transfer robot

Abstract

The present invention relates to the field of semiconductor technology, and in particular to an integrated wafer transfer robot, which is composed of a robot body, a data acquisition module, and a fault diagnosis module. The present application provides a data acquisition module, utilizes a visual sensor to detect key operating nodes of the robot body, and collects parameter data of multiple motors built into the robot body. Combined with the fault diagnosis module, the application comprehensively determines whether the operating status of the robot body is normal, thereby enabling fault diagnosis of the robot body and further improving the accuracy and reliability of fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor technology, and in particular to an integrated wafer transfer robot. Background Art

[0002] Wafers are silicon chips used to make silicon semiconductor circuits and are one of the most important building blocks in semiconductor technology. Robots are required to transfer wafers or wafer cassettes during wafer handling, placement, and storage.

[0003] Traditional robotic arms can only transport wafers or cassettes individually, not both simultaneously. This results in low wafer and cassette transport efficiency within the confined space of wafer storage and transport equipment, hindering efficient production processes. Furthermore, robotic arms must maintain high stability and reliability in their high-precision, high-efficiency working environments. However, due to long-term operation, various faults such as mechanical component wear and motor failure may occur. Traditional fault diagnosis methods often rely on manual inspection and maintenance, which is inefficient and difficult to detect potential problems in a timely manner. While existing fault diagnosis methods utilize visual sensors and motor parameter monitoring, they still have some technical drawbacks in practical applications. For example, visual sensor detection results are easily affected by changes in ambient light, resulting in a high rate of false positives. Furthermore, while motor parameter monitoring can provide relatively accurate data, in complex working environments, single motor parameter monitoring may not fully reflect the operating status of the robotic arm, easily missing potential faults and resulting in low accuracy and reliability of fault diagnosis.

[0004] To this end, the present invention proposes an integrated wafer transfer robot suitable for use inside a wafer storage and transportation device. Summary of the Invention

[0005] Based on this, it is necessary to provide an integrated wafer transfer robot to address the above technical issues and solve the problems raised in the above background technology.

[0006] To achieve the above-mentioned objectives, the present invention provides the following technical solutions: an integrated wafer transfer robot, applied to a wafer storage and transportation device, comprising: a robot body, for synchronously transferring wafer boxes and wafers; a data acquisition module, for real-time acquisition of operating status images of key operating nodes of the robot body, and real-time acquisition of motor parameter data built into the robot body; the motor parameter data includes motor temperature data, motor torque data and motor travel data; a fault diagnosis module, for processing and analyzing the operating status image using an image processing algorithm, generating a mechanical component recognition result, and combining with a convolutional neural network model to obtain a mechanical component abnormality recognition result; a sliding average filtering algorithm is used to process the motor parameter data to generate a motor parameter abnormality result; based on the mechanical component abnormality recognition result and the motor parameter abnormality result, a comprehensive fault report is generated to determine whether the operating status of the robot body is normal, and when the operating status of the robot body is abnormal, an alarm system is triggered, and a comprehensive fault report is pushed through a human-machine interface or a mobile terminal to ensure timely response and processing.

[0007] Optionally, the robot body includes: a mounting portion for integratedly mounting a wafer clamping portion, a wafer box clamping portion and an electrical control module, wherein the wafer clamping portion and the wafer box clamping portion are respectively arranged on both sides of the mounting portion; a wafer clamping portion, wherein the wafer clamping portion includes an adsorption type wafer clamping end portion and a wafer clamping control structure, wherein the wafer clamping control structure is arranged on the inner side of the mounting portion, and the adsorption type wafer clamping end portion is fixedly mounted on a side of the mounting portion away from the wafer box clamping portion, and the wafer clamping control structure is connected to the adsorption type wafer clamping end portion through an air pipe, which is used to control the adsorption type wafer clamping end portion to adsorb, clamp or release the wafer, and the wafer clamping control structure is used to control the gas flow rate to adjust The strength of the adsorption force of the adsorption-type wafer clamping end on the wafer; the wafer box clamping part, the wafer box clamping part includes a wafer box clamping end for compatibly clamping multi-size wafer boxes and a wafer box clamping control structure, the wafer box clamping control structure is fixedly installed on one side of the mounting part, the wafer box clamping end passes through the wafer box clamping control structure and is slidably connected with the wafer box clamping control structure, so as to realize the wafer box clamping control structure driving the wafer box clamping end to move toward or away from each other; the electrical control module, the electrical control module is electrically connected to the wafer clamping part and the wafer box clamping part respectively, for realizing unified control of the wafer clamping part and the wafer box clamping part, and synchronous transportation of the wafer and the wafer box.

[0008] Optionally, the mounting portion includes a base shell and a joint shaft arranged on one side of the base shell. The base shell is a hollow shell structure, which is used to integrate the wafer clamping control structure inside the base shell and reduce the space occupancy rate of the wafer clamping control structure. The joint shaft is arranged on the robotic arm of the wafer handling robot, and is driven by the robotic arm of the wafer handling robot to drive the integrated wafer transfer robot to perform horizontal rotational movement.

[0009] Optionally, the adsorption-type wafer clamping end includes a wafer clamping claw housing fixedly mounted on one side of the base plate shell and a ceramic chuck fixedly mounted on the side of the wafer clamping claw housing away from the base plate shell, the interior of the wafer clamping claw housing is provided with a first air duct connected to the air pipe, the interior of the ceramic chuck is provided with a second air duct connected to the first air duct, the upper end of the ceramic chuck is provided with a plurality of vacuum adsorption ports connected to the second air duct, and the vacuum adsorption ports are evenly distributed on the upper end surface of the ceramic chuck; the wafer clamping control structure includes a solenoid valve bracket fixedly mounted on the inside of the base plate shell, a solenoid valve fixedly mounted on the solenoid valve bracket and connected to the air pipe, and a speed regulating valve mounted on the air pipe.

[0010] Optionally, the wafer box clamping control structure includes a back plate fixedly mounted on one side of the base plate shell, a motor fixedly mounted inside the back plate, a transmission block fixedly mounted on the output shaft end of the motor, a transmission structure rotatably connected to the transmission block and used to drive the wafer box clamping end to move toward or away from each other, a first guide body fixedly mounted inside the back plate and used to guide the wafer box clamping end, and a second guide body fixedly mounted inside the back plate and used to guide the transmission block. The motor and the second guide body are both arranged on the vertical center line inside the back plate, the transmission block is slidably connected to the second guide body, and the wafer box clamping end is slidably connected to the first guide body.

[0011] Optionally, the wafer box clamping end includes a pair of clamping claw brackets, a pair of clamping blocks A, a pair of clamping blocks B, a pair of support blocks A, a pair of support blocks B and a wafer baffle, the wafer baffle is fixedly mounted on the side of the back plate facing the wafer box to be clamped, and a pair of the clamping claw brackets are symmetrically distributed on both sides of the back plate, the end of the clamping claw bracket close to the back plate passes through the back plate and is slidably connected to the back plate, the end of the clamping claw bracket passing through the inside of the back plate is fixedly connected to the transmission structure, the end of the clamping claw bracket passing through the inside of the back plate is sleeved on the outside of the first guide body and is slidably connected to the first guide body, the clamping block A and the clamping block B are fixedly mounted on the clamping claw bracket located on the outside of the back plate from the outside to the inside in sequence, the support block A and the support block B are both fixedly mounted on the clamping claw bracket, and the support block A and the support block B are respectively arranged at the lower ends of the clamping block A and the clamping block B.

[0012] Optionally, the transmission structure includes a pair of connecting rod transmission parts, which are symmetrically distributed on both sides of the motor. The connecting rod transmission parts include a main connecting rod and a rotating connecting rod. One end of the main connecting rod is rotatably connected to the transmission block, and the other end is rotatably connected to the middle part of the rotating connecting rod. The end of the rotating connecting rod is fixedly connected to one side end of the clamping bracket passing through the inside of the back plate.

[0013] Optionally, the wafer box clamping control structure also includes an in-place detection structure for determining whether wafer boxes of different sizes to be transferred are successfully clamped. The in-place detection structure is arranged inside the backplate. The in-place detection structure includes a motor retraction position in-place sensor, a first motor extension position in-place sensor and a second motor extension position in-place sensor. The motor retraction position in-place sensor is arranged at the starting working position of the transmission block, and the first motor extension position in-place sensor and the second motor extension position in-place sensor are arranged in sequence from top to bottom on the motion trajectory of the transmission block.

[0014] Optionally, the data acquisition module includes a visual sensor installed at a key operating node of the manipulator body, and a temperature sensor, a torque sensor and a displacement sensor installed on the motor.

[0015] Optionally, the fault diagnosis module includes: an image data processing and analysis submodule, which is used to pre-process the collected operating status image using an ambient light compensation algorithm to generate an operating status pre-processed image; use the SIFT algorithm to perform feature retrieval and description on the operating status pre-processed image to generate a feature descriptor; use the watershed algorithm to perform image segmentation on the operating status pre-processed image to obtain a marked image and a separated mechanical component result; in the mechanical component result, the feature descriptor is used for matching processing to generate a mechanical component recognition result, and the mechanical component recognition result is input into the trained convolutional neural network model to output a mechanical component abnormality recognition result; a motor data processing and analysis submodule, which is used to process the motor parameter data using a sliding average filtering algorithm to generate a motor parameter abnormality result; a report generation and alarm submodule, which is used to generate a comprehensive fault report based on the mechanical component abnormality recognition result and the motor parameter abnormality result, so as to determine whether the operating status of the manipulator body is normal, and when the operating status of the manipulator body is abnormal, trigger the alarm system and push the comprehensive fault report through the human-machine interface or mobile terminal to ensure timely response and processing.

[0016] The present invention provides an integrated wafer transfer robot with the following beneficial effects.

[0017] 1. By integrating the wafer clamping part and the wafer box clamping part, not only can the unified control of the two be achieved, but also the synchronous transportation of wafers and wafer boxes can be achieved. When the integrated wafer transfer robot needs to synchronously transport the wafer box and wafers, it can successively clamp the wafer box and wafers, and then execute the synchronous transportation instruction. Compared with the two robots in the prior art that perform the wafer box and wafer clamping and transportation operations respectively, it can reduce the round-trip operation steps and effectively improve work efficiency. At the same time, the wafer clamping part and the wafer box clamping part adopt an integrated structure design, which can This effectively reduces the space occupancy rate. For two separate wafer box clamps and wafer clamps, it is easy for the wafer box clamps and wafer clamps to collide in a limited space, requiring additional motion planning and other work. The integrated wafer transfer robot provided in this application can significantly reduce the size and complexity of the equipment, and can operate more flexibly in wafer storage and transportation devices with limited space, and after clamping the wafer or wafer box, it can be placed in the required position to improve the transfer efficiency of the wafer and wafer box, thereby ensuring the efficiency of the production process.

[0018] 2. By setting up an adsorption-type wafer clamping end and a wafer clamping control structure, the wafer can be adsorbed, clamped or released, and the strength of the adsorption force of the adsorption-type wafer clamping end on the wafer can be adjusted by controlling the gas flow rate, thereby avoiding the wafer from falling off or being damaged due to the adsorption force being too weak or too strong.

[0019] 3. By setting the wafer box clamping end, the wafer box clamping control structure and the in-place detection structure, it is possible not only to clamp or release the wafer box and achieve compatible clamping of wafer boxes of different sizes, but also to detect whether wafer boxes of different sizes are clamped successfully, thereby improving the accuracy of clamping detection of wafer boxes of corresponding sizes and further improving the transmission efficiency of the production process.

[0020] 4. By setting up a data acquisition module, using visual sensors to detect the key operating nodes of the robot body, and collecting multiple motor parameter data built into the robot body, combined with the fault diagnosis module, a comprehensive judgment is made on whether the operating status of the robot body is normal, so as to realize the fault diagnosis of the robot body and further improve the accuracy and reliability of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0022] Figure 2 This is a front view of the integrated wafer transfer robot of the present invention.

[0023] Figure 3 This is a top view of the integrated wafer transfer robot of the present invention.

[0024] Figure 4 It is a structural schematic diagram of the transmission structure of the present invention.

[0025] Figure 5 It is a structural schematic diagram of the wafer box clamping end of the present invention.

[0026] Figure 6 It is a partial enlarged view of the in-place detection structure of the present invention.

[0027] Figure 7 Schematic diagram of the installation position of the vacuum detection sensor of the present invention.

[0028] Figure 8 This is a structural block diagram of the fault diagnosis module of the present invention.

[0029] Figure numerals: ceramic chuck 1, base plate housing 2, back plate 3, wafer clamp housing 4, joint shaft 5, clamp bracket 6, clamping block A7, clamping block B8, support block A9, support block B10, transmission block 11, solenoid valve 12, main connecting rod 13, rotating connecting rod 14, solenoid valve bracket 15, wafer baffle 16, motor 17, motor retraction position sensor 18, first motor extension position sensor 19, vacuum detection sensor 20, speed control valve 21, electrical control module 22, vacuum adsorption port 23, air pipe 24, first guide body 25, second guide body 26, robotic arm 27, main structure 28, second motor extension position sensor 29. DETAILED DESCRIPTION

[0030] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limitations on the present application. In addition, the following embodiments and features in the embodiments may be combined with each other unless there is a conflict. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0031] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0032] Reference Attachment Figure 1-6, an integrated wafer transfer robot, which is used for wafer storage and transportation devices, and consists of a robot body, a data acquisition module and a fault diagnosis module.

[0033] In some optional implementations of the present application, the robot body is composed of a mounting part, a wafer clamping part, a wafer box clamping part and an electrical control module.

[0034] In some optional implementations of this application, please refer to the attached Figure 1-4 The wafer clamping part and the wafer box clamping part are respectively arranged on both sides of the mounting part, and the electrical control module 22 is electrically connected to the wafer clamping part and the wafer box clamping part respectively, for realizing unified control of the wafer clamping part and the wafer box clamping part, and synchronous transportation of the wafer and the wafer box. In addition, it should be noted that the electrical control module 22 (i.e., the controller) can be integrated and installed inside the mounting part (i.e., the base plate shell 2) so as to centrally control the wafer clamping part and the wafer box clamping part.

[0035] In some optional implementations of the present application, during the unified control process of the wafer clamping part and the wafer box clamping part by the electrical control module 22, when the integrated wafer transfer robot needs to synchronously transfer the wafer box and the wafer, the wafer box clamping part is controlled in turn to clamp the wafer box or the wafer clamping part to clamp the wafer, and then the synchronous transfer instruction is executed to reduce the round-trip operation steps.

[0036] It should be noted that, in the unified control process of the electrical control module 22 over the wafer clamping part and the wafer box clamping part, the electrical control module 22 will limit the execution of clamping in a single direction, that is, when clamping the wafer box, the wafer will not be clamped, and when clamping the wafer, the wafer box will not be clamped. After executing the clamping operation in a single direction, the clamping operation in the other direction will be executed to realize the synchronous transportation of the wafer box and the wafer.

[0037] In some optional implementations of the present application, in order to avoid the problem of mutual interference between the wafer clamping part and the wafer box clamping part in a limited space, the clamping directions of the wafer clamping part and the wafer box clamping part of the present application are arranged back to back.

[0038] In some optional implementations of this application, please refer to the attached Figure 1-2The mounting portion includes a base shell 2 and a joint shaft 5 arranged on one side of the base shell 2. The base shell 2 is a hollow shell structure. Specifically, the base shell 2 is a rectangular structure, and the wafer clamping control structure and the electrical control module 22 can be integrated and installed inside it, so as to reduce the space occupancy rate of the wafer clamping control structure and the electrical control module 22. The joint shaft 5 is arranged on the robotic arm 27 of the wafer handling robot, and is driven by the robotic arm 27 of the wafer handling robot to drive the integrated wafer transfer robot to perform horizontal rotational movement. In addition, it should be noted that the integrated wafer transfer robot involved in this application can be integrated and installed on the robotic arm 27 of the wafer handling robot through the joint shaft 5, so as to realize the handling process of wafer boxes and wafers.

[0039] In some optional implementations of the present application, the wafer clamping portion includes an adsorption-type wafer clamping end and a wafer clamping control structure, wherein the wafer clamping control structure is arranged on the inner side of the mounting portion, and the adsorption-type wafer clamping end is fixedly mounted on the side of the mounting portion away from the wafer box clamping portion, and the wafer clamping control structure is connected to the adsorption-type wafer clamping end through an air pipe 24, which is used to control the adsorption-type wafer clamping end to adsorb, clamp or release the wafer, and the wafer clamping control structure is used to control the gas flow rate to adjust the strength of the adsorption force of the adsorption-type wafer clamping end on the wafer.

[0040] In some optional implementations of this application, please refer to the attached Figure 1-3 The adsorption-type wafer clamping end includes a wafer clamping claw shell 4 fixedly mounted on one side of the base plate shell 2 and a ceramic chuck 1 fixedly mounted on the side of the wafer clamping claw shell 4 away from the base plate shell 2, the interior of the wafer clamping claw shell 4 is provided with a first air channel connected to the air pipe 24, the interior of the ceramic chuck 1 is provided with a second air channel connected to the first air channel, the upper end of the ceramic chuck 1 is provided with a plurality of vacuum adsorption ports 23 connected to the second air channel, the vacuum adsorption ports 23 are evenly distributed on the upper end surface of the ceramic chuck 1, and the first air channel connected to the air pipe 24, the second air channel connected to the first air channel and the vacuum adsorption ports 23 connected to the second air channel are provided so as to realize the adsorption and clamping of the wafer. At the same time, in order to generate a uniform adsorption force on the upper end surface of the ceramic chuck 1, the multiple vacuum adsorption ports 23 in this application need to be evenly distributed on the upper end surface of the ceramic chuck 1, and the number of vacuum adsorption ports 23 can be flexibly set according to actual production needs, which is no longer limited here. Figure 3 As shown, the number of the vacuum adsorption ports 23 is set to 3.

[0041] In some optional implementations of this application, please refer to the attached Figure 3The wafer clamping control structure includes a solenoid valve bracket 15 fixedly mounted on the inside of the base shell 2, a solenoid valve 12 fixedly mounted on the solenoid valve bracket 15 and connected to the air pipe 24, and a speed regulating valve 21 mounted on the air pipe 24. By integrating the solenoid valve bracket 15, the solenoid valve 12, the air pipe 24 and the speed regulating valve 21 inside the base shell 2, not only can the space occupancy rate be effectively reduced, but also the solenoid valve bracket 15, the solenoid valve 12, the air pipe 24 and the speed regulating valve 21 can be avoided from being exposed to the external environment, thereby protecting the wafer clamping control structure. The function of protecting and storing the wafer is to slow down the aging speed of the electromagnetic valve 12, the air pipe 24 and the speed regulating valve 21. In addition, when the electromagnetic valve 12 controls the ceramic chuck 1 to adsorb and clamp the wafer, the gas flow rate is regulated by the speed regulating valve 21 to adjust the strength of the ceramic chuck 1's adsorption force on the wafer. By controlling the speed regulating valve 21, the gas flow rate flowing through the air pipe 24 can be effectively controlled, thereby effectively controlling the adsorption force of the vacuum adsorption port 23, thereby avoiding damage or falling off of the wafer due to excessive or insufficient adsorption force of the vacuum adsorption port 23. Figure 7 In order to monitor the size of the adsorption force in real time, a vacuum detection sensor 20 can also be installed on the side of the main structure 28 of the wafer handling robot. The input end of the vacuum detection sensor 20 is connected to the air pipe 24 and is arranged at the front end of the gas flow through the speed control valve 21, so as to monitor the pressure changes of the gas in the air pipe 24 before it flows through the speed control valve 21 in real time.

[0042] In some optional implementations of the present application, the working principle of the wafer clamping part includes: through the set solenoid valve 12, when the ceramic chuck 1 is needed to clamp the wafer, the solenoid valve 12 starts to operate, and the air pipe 24 connected to it starts to suck air, forming a negative pressure at the vacuum adsorption port 23 on the ceramic chuck 1, thereby realizing vacuum adsorption of the wafer, and through the set speed control valve 21, the gas flow rate can be controlled, thereby controlling the strength of the ceramic chuck 1's adsorption force on the wafer. At the same time, through the set vacuum detection sensor 20, the pressure changes of the gas in the air pipe 24 before flowing through the speed control valve 21 can be monitored in real time, so as to monitor the size of the adsorption force in real time.

[0043] In some optional implementations of this application, please refer to the attached Figure 1-5The wafer box clamping part includes a wafer box clamping end portion for clamping compatible wafer boxes of multiple sizes and a wafer box clamping control structure. The wafer box clamping control structure is fixedly installed on one side of the mounting part. The wafer box clamping end portion passes through the wafer box clamping control structure and is slidably connected to the wafer box clamping control structure. The wafer box clamping control structure is internally provided with an in-place detection structure for judging whether wafer boxes of different sizes to be transferred are successfully clamped. The wafer box clamping control structure drives the wafer box clamping end portion to move toward or away from each other. In the process of the structure driving the wafer box clamping ends to move toward each other, the in-place detection structure detects whether the wafer box clamping ends have successfully clamped the wafer box to be transferred according to the size of the wafer box to be transferred, and is used for the wafer box clamping ends to successfully clamp wafer boxes to be transferred of different sizes, and in the process of the wafer box clamping control structure driving the wafer box clamping ends to move backwards, the in-place detection structure detects whether the wafer box clamping ends have successfully released the wafer box to be transferred according to the size of the wafer box to be transferred, and is used for the wafer box clamping ends to successfully release the wafer box to be transferred.

[0044] In some optional implementations of this application, please refer to the attached Figure 1-4 The wafer box clamping control structure includes a back plate 3 fixedly mounted on one side of the base shell 2, a motor 17 fixedly mounted inside the back plate 3, a transmission block 11 fixedly mounted on the output shaft end of the motor 17, a transmission structure rotatably connected to the transmission block 11 and used to drive the wafer box clamping end to move toward or away from each other, a first guide body 25 fixedly mounted inside the back plate 3 and used to guide the wafer box clamping end, and a second guide body 26 fixedly mounted inside the back plate 3 and used to guide the transmission block 11. The back plate 3 is a hollow shell structure, and its structure and function are similar to those of the base shell 2, which will not be repeated here. The motor 17 and the second guide body 26 are both arranged on the vertical center line inside the back plate 3. It should be noted that in order to improve the connecting rods distributed on both sides of the motor 17, The force balance of the transmission part and the wafer box clamping end, the motor 17 and the second guide body 26 involved in this application are both arranged on the center line of the vertical direction of the back plate 3, the transmission block 11 is slidingly connected to the second guide body 26, and the wafer box clamping end is slidingly connected to the first guide body 25. Driven by the motor 17, the transmission block 11 is vertically lifted and lowered along the second guide body 26, and drives the transmission structure to perform reciprocating translational motion inside the back plate 3, so as to drive the wafer box clamping end to move toward or away from each other, and during the movement of the wafer box clamping end, the wafer box clamping end and the first guide body 25 are slidingly matched to improve the stability of the matching between the wafer box clamping end and the wafer box clamping control structure, and reduce the space occupancy rate of the wafer box clamping end and the wafer box clamping control structure.

[0045] In some optional implementations of this application, please refer to the attached Figure 1-4 The wafer box clamping end includes a pair of clamping claw brackets 6, a pair of clamping blocks A7, a pair of clamping blocks B8, a pair of support blocks A9 and a pair of support blocks B10. The pair of clamping claw brackets 6 are symmetrically distributed on both sides of the back plate 3. The clamping claw bracket 6 is a "concave" structure, and the two "convex" ends of the "concave" structure respectively penetrate the back plate 3 and are slidably connected to the back plate 3. At the same time, the two "convex" ends are fixedly connected to the two ends of the rotating connecting rod 14 respectively. The clamping claw bracket 6 with this "concave" structure, compared with the clamping claw bracket 6 with a rectangular structure or the clamping claw bracket 6 with one end (similar to a convex structure), can not only improve the stability of the overall structure of the wafer box clamping end in reciprocating translation motion, but also reduce weight and save material costs; at the same time, the "convex" end of the clamping claw bracket 6 is sleeved on the outside of the first guide body 25 and is slidably connected to the first guide body 25. In order to further improve the clamping claw bracket 6 In order to ensure the stability of movement, the number of the first guide bodies 25 can be set to 2, that is, the two ends of the clamping bracket 6 are respectively slidably matched with the first guide bodies 25. With the transmission action of the transmission structure and the guiding action of the first guide body 25, the clamping bracket 6 performs reciprocating translational motion along the horizontal direction of the back plate 3. The clamping block A7 and the clamping block B8 are fixedly installed on the clamping bracket 6 located outside the back plate 3 from the outside to the inside in sequence. The support block A9 and the support block B10 are both fixedly installed on the clamping bracket 6, and the support block A9 and the support block B10 are respectively arranged at the lower ends of the clamping block A7 and the clamping block B8. When the transmission structure performs reciprocating translational motion inside the back plate 3, the clamping block A7 and the clamping block B8 are respectively used to clamp the wafer box to be transferred of the corresponding size, and under the coordinated action of the corresponding support block A9 and the support block B10, they are used to prevent the wafer box to be transferred of the corresponding size from falling off during the clamping process.

[0046] It should be noted that the wafer box clamping end involved in the present application can clamp wafer boxes of two sizes, that is, two clamping blocks A7 and two support blocks A9 are used to clamp wafer boxes of one size (such as an 8-inch wafer box), and two clamping blocks B8 and two support blocks B10 are used to clamp wafer boxes of another size (such as a 6-inch wafer box). If it is necessary to clamp wafer boxes of more sizes (such as a 12-inch wafer box), clamping blocks and support blocks of wafer boxes of corresponding sizes can be arranged on the clamping claw bracket 6 and on the outside of the support block A9 according to actual production needs, and no further limitation is given here.

[0047] In some optional implementations of this application, please refer to the attached Figure 4The transmission structure includes a pair of connecting rod transmission parts, which are symmetrically distributed on both sides of the motor 17. The connecting rod transmission part includes a main connecting rod 13 and a rotating connecting rod 14, wherein one end of the main connecting rod 13 is rotatably connected to the transmission block 11, and the other end is rotatably connected to the middle part of the rotating connecting rod 14, and the two ends of the rotating connecting rod 14 are respectively fixedly connected to the two ends of the clamping claw bracket 6, so as to stably drive the clamping end of the wafer box to perform reciprocating translation motion.

[0048] In some optional implementations of this application, please refer to the attached Figure 5 The wafer box clamping end also includes a wafer baffle 16, which is fixedly mounted on the side of the back plate 3 facing the wafer box to be clamped. The wafer baffle 16 is used to protect the wafers in the wafer box.

[0049] In some optional implementations of this application, please refer to the attached Figure 6 The in-position detection structure is arranged inside the back plate 3, and the in-position detection structure includes a motor retraction position in-position sensor 18, a first motor extension position in-position sensor 19 and a second motor extension position in-position sensor 29, wherein the two motor extension position in-position sensors involved in this application cooperate with the clamping block A7 and the clamping block B8 respectively, and the motor retraction position in-position sensor 18 is arranged at the starting working position of the transmission block 11. The starting working position of the transmission block 11 indicates that the clamping end of the wafer box is in the maximum open state. The first motor extension position in-position sensor 19 and the second motor extension position in-position sensor 29 are arranged on the motion trajectory of the transmission block 11 from top to bottom, and the wafer box to be transferred of the corresponding size is clamped with the clamping block A7 or the clamping block B8. The first motor extension position in-position sensor 19 and the second motor extension position in-position sensor 29 are respectively used to determine whether the wafer box to be transferred of the corresponding size is clamped successfully. For example, when the clamping block A7 and the supporting block A9 are used to clamp the wafer box to be transferred of the corresponding size, the motor 17 drives the transmission block 11 to move upward along the second guide body 26. If the clamping block A7 and the supporting block A9 correctly clamp the wafer box to be transferred of the corresponding size, the transmission block 11 can be sensed by the first motor extension position sensor 19, and the clamping is judged to be successful. If the clamping block A7 and the supporting block A9 do not correctly clamp the wafer box to be transferred of the corresponding size, the upward movement position of the transmission block 11 at this time may exceed the clamping position or fail to reach the clamping position, resulting in the first motor extension position sensor 19 not sensing the transmission block 11, and the clamping is judged to be failed; then, after completing the wafer box transfer process, the wafer box to be transferred of the corresponding size can be released along with the clamping block A7 or the clamping block B8, and the motor retraction position sensor 18 is used to judge whether the wafer box to be transferred of the corresponding size is successfully released.

[0050] In some optional implementations of the present application, the data acquisition module includes a visual sensor (not shown) installed at the key operating nodes of the manipulator body, and a temperature sensor, a torque sensor and a displacement sensor (not shown) installed on the motor, wherein the visual sensor is used to collect the operating status images of the key operating nodes of the manipulator body in real time, the temperature sensor is used to collect the motor temperature data in real time, the torque sensor is used to collect the motor torque data in real time, and the displacement sensor is used to collect the motor travel data in real time.

[0051] It should be noted that the key operating nodes include the machine parts that constitute the main body of the robot, such as the installation part, the wafer clamping part, the wafer box clamping part, etc. By identifying the operating status of the mechanical parts of the key operating nodes, it is used to identify and classify abnormal conditions of the mechanical parts contained in the machine parts, such as wear, looseness, deformation, etc.

[0052] In some optional implementations of the present application, the fault diagnosis module is used to process and analyze the operating status image using an image processing algorithm to generate a mechanical component identification result, and combine it with a convolutional neural network model to obtain a mechanical component abnormality identification result; a sliding average filtering algorithm is used to process the motor parameter data to generate a motor parameter abnormality result; based on the mechanical component abnormality identification result and the motor parameter abnormality result, a comprehensive fault report is generated to determine whether the operating status of the manipulator body is normal, and when the operating status of the manipulator body is abnormal, an alarm system is triggered, and a comprehensive fault report is pushed through the human-machine interface or mobile terminal to ensure timely response and processing.

[0053] In some optional implementations of this application, please refer to the attached Figure 8 ,The fault diagnosis module is composed of the image data processing and ,analysis submodule, the motor data processing and analysis submodule, and the ,report generation and alarm submodule.

[0054] In some optional implementations of the present application, the image data processing and analysis submodule is used to pre-process the collected operating status image using an ambient light compensation algorithm to generate an operating status pre-processed image; use the SIFT algorithm to perform feature retrieval and description on the operating status pre-processed image to generate a feature descriptor; use the watershed algorithm to perform image segmentation on the operating status pre-processed image to obtain a marked image and separated mechanical component results; among the mechanical component results, use the feature descriptor for matching processing to generate a mechanical component recognition result; and input the mechanical component recognition result into the trained convolutional neural network model to output a mechanical component abnormality recognition result.

[0055] In some optional implementations of the present application, an ambient light compensation algorithm is used to preprocess the collected operating status image to generate a preprocessed operating status image, including: dividing the collected operating status image into multiple small blocks, for example, small blocks of 8×8 pixels; calculating the local illumination model parameters for each small block, including local average brightness and local contrast, wherein the calculation formula for the local average brightness is: , the calculation formula of local contrast is: , where N represents the number of pixels in the small block, represents the local average brightness, represents the local contrast, Represents the running status image; the pixel value of each small block is adjusted to make its brightness and contrast conform to the global illumination model. The calculation formula for parameter adjustment is: , where It represents the parameter adjustment result of the pixel value of each small block. α and β represent the adjustment parameters of the local average brightness and local contrast, respectively. They can be adjusted according to actual needs. All small blocks are integrated into one image to generate the running status preprocessing image. The above improvement scheme can better adapt to the changes in illumination and avoid the collected running status image being too bright or too dark, thereby improving the accuracy and reliability of image preprocessing.

[0056] In some optional implementations of the present application, the SIFT algorithm is used to perform feature retrieval and description on the running state preprocessing image to generate a feature descriptor, including: image preprocessing: converting the running state preprocessing image into a grayscale image and performing noise removal, such as using Gaussian filtering or median filtering; constructing a scale space: constructing a Gaussian pyramid and smoothing the grayscale image using Gaussian functions of different scales. The formula is: , where represents the scale space, represents the Gaussian kernel function, σ represents the scale parameter of the Gaussian pyramid, Represents a grayscale image; extreme point detection: detect extreme points in the constructed Gaussian pyramid. These points are local extreme values ​​in scale space and spatial position. The values ​​of each pixel and its adjacent points are compared through a preset neighborhood window (for example, 3×3×3) to determine the extreme points. The formula is: , where Represents the pixel value of the local extreme point, Represents the pixel value of the adjacent point, k represents the offset of the scale parameter between each pixel and its adjacent points; Accurate positioning of extreme points: Taylor expansion is used to accurately locate the extreme points and improve the boundary response. The formula is: , where x represents the initial position of the extreme point, H is the Hessian matrix, and D(x) represents the gradient vector of the extreme point. Indicates the corrected position of the extreme point; Feature point direction assignment: assign a main direction to each feature point to improve the rotation invariance of the feature point. The formula is: , where represents the directional cumulative histogram, represents the directional gradient, represents the gradient direction, r and Both represent directional gradient parameters, r and The value of is 1, θ represents the main direction of the statistical histogram, and δ represents the scale parameter of the gradient direction; Generate feature descriptors: Use the target dimension vector to describe each feature point. For example, a 128-dimensional vector is usually used to describe each extreme point. The formula is: , where Represents an element in a feature descriptor, Indicates a preset small tile, for example, an 8x8 small tile.

[0057] In some optional implementations of the present application, a captured 256x256 pixel image is taken as an example. The image is a high-resolution photo of a machine part, which contains multiple different mechanical parts. Key feature points need to be extracted from it, and the different parts in the image need to be separated for subsequent part identification and analysis, which specifically includes the following steps.

[0058] 1. Image preprocessing: Convert the image to a grayscale image and remove noise. A Gaussian filter can be used to remove noise. For example, the noise should be evenly distributed on the image and should be reduced to 10% of the average value of the image pixels.

[0059] 2. Scale space construction: The image is smoothed by Gaussian filtering to construct a Gaussian pyramid. For example, the scale parameter σ of the Gaussian pyramid is 1.6, and the Gaussian kernel function is as follows: , where x and y represent spatial position parameters, σ represents the scale parameter of the Gaussian pyramid, and the image is smoothed at multiple scales to obtain the scale space .

[0060] 3. Extreme point detection: Detect each pixel of the image in the Gaussian pyramid and perform extreme point detection in the scale space. For example, when the scale parameter σ of the Gaussian pyramid is 2, the pixel value at (100, 150) in the image is 128, and the values ​​of the adjacent pixels are 120, 130, and 118 respectively. According to the following formula: , where k=1.6. The calculation results are as follows: D(100, 150, 2)=128-125=3. Since the current pixel value is a local extreme point, it is marked as an extreme point candidate.

[0061] 4. Accurately locate the extreme point: Use Taylor expansion to accurately locate the extreme point. For example, at the extreme point x=(125, 125) near the center of the image, according to the following formula: , where , D(x)=5, the calculation results are as follows: .

[0062] 5. Feature point direction assignment: Assign directions to extreme points using gradient direction statistics. For example, the gradient direction distribution at pixel point (100, 150) is shown in Table 1 below. Calculate the direction cumulative histogram using the following formula: , where r and The value of is 1, and the main direction of the statistical histogram is 90°.

[0063] Table 1 Gradient direction distribution at pixel (100, 150)

[0064]

[0065] 6. Generate feature descriptors: Generate descriptors for the extreme point (100, 150). For example, the descriptor calculation uses a 16x16 neighborhood block. In the descriptor calculation, the direction statistics of each small block (such as 4x4) are shown in Table 2 below. The feature descriptor is calculated according to the following formula: , after calculation, a 128-dimensional descriptor vector is generated.

[0066] Table 2 Direction statistics for each small tile (e.g. 4x4)

[0067]

[0068] In some optional implementations of the present application, a watershed algorithm is used to segment the running state preprocessed image to obtain a marked image and a separated mechanical component result. In the mechanical component result, a feature descriptor is used for matching processing to generate a mechanical component recognition result, including: calculating a gradient image based on the grayscale image after noise removal: using the Sobel algorithm to calculate the image gradient. The formula of the Sobel algorithm is: , where and Represents the gradient in horizontal and vertical directions, Represents the gradient amplitude; Marking image: To mark the image, you can use distance transformation or manual marking to mark the background or foreground area; Watershed transformation: Use the watershed transformation algorithm to separate the different mechanical parts in the image. The formula is: , where represents the gradient image, represents a labeled image, Represents the label image after watershed transformation; feature point matching and integration: In the label image after watershed transformation, feature descriptors are used for matching (such as nearest neighbor matching or FLANN matching algorithm) to generate feature point matching results, and the feature point matching results are combined with the segmented mechanical parts to generate mechanical part recognition results.

[0069] In some optional implementations of the present application, the mechanical component recognition result is input into the trained convolutional neural network model, and the mechanical component abnormality recognition result is output, including: constructing and training a convolutional neural network model, which is used to identify and classify abnormal conditions of each mechanical component contained in the machine parts, such as wear, looseness, deformation, etc.; inputting the mechanical component recognition result into the trained convolutional neural network model, and outputting the mechanical component abnormality recognition result.

[0070] In some optional implementations of the present application, the motor data processing and analysis submodule is used to process the motor parameter data using a sliding average filtering algorithm to generate a motor parameter abnormality result.

[0071] In some optional implementations of the present application, the formula of the sliding average filtering algorithm is: , where Represents motor parameter data, specifically motor temperature data or motor torque data or motor travel data, m represents the sliding window size, which can be 10. It represents the average value of the current motor parameters, specifically the average value of the motor temperature data or the motor torque data or the motor travel data. After the motor parameter data is processed by the sliding average filter algorithm, the average value of the current motor parameters is generated and compared with the preset motor parameter threshold to determine whether the deviation of each motor parameter exceeds the allowable range. If exceeded, it is marked as abnormal and a motor parameter abnormality result is generated, such as excessive temperature, excessive torque, abnormal travel, etc.

[0072] In some optional implementations of the present application, the report generation and alarm submodule is used to generate a comprehensive fault report based on the abnormal identification results of mechanical parts and the abnormal results of motor parameters, so as to determine whether the operating status of the robot body is normal. The comprehensive fault report may include the fault type, location, degree and recommended maintenance measures. The recommended maintenance measures may be pre-stored in a constructed database. In the process of generating the comprehensive fault report, the corresponding recommended maintenance measures in the database can be called based on the fault type, location and degree; when the operating status of the robot body is abnormal, the alarm system can be triggered, and the comprehensive fault report can be pushed through the human-machine interface or mobile terminal to ensure timely response and processing.

[0073] The above content is a further detailed description of the present invention in conjunction with specific embodiments, and the specific implementation of the present invention cannot be considered to be limited to these descriptions. For those skilled in the art of the present invention, without departing from the concept of the present invention, several simple deductions or substitutions can be made, which should be considered to fall within the scope of protection of the present invention.

Claims

1. An integrated wafer transfer robot, used in wafer storage and transportation devices, characterized in that: include: The main body of the robot is used to synchronously transport wafer boxes and wafers; A data acquisition module is used to collect real-time operating status images of key operating nodes of the manipulator body and real-time motor parameter data built into the manipulator body; the motor parameter data includes motor temperature data, motor torque data, and motor travel data; The fault diagnosis module is used to process and analyze the operating status image using an image processing algorithm to generate mechanical component recognition results, and combined with the convolutional neural network model to obtain mechanical component abnormality recognition results; The sliding average filter algorithm is used to process the motor parameter data to generate motor parameter abnormality results; Based on the abnormal identification results of mechanical parts and motor parameters, a comprehensive fault report is generated to determine whether the operation status of the robot body is normal. When the operation status of the robot body is abnormal, the alarm system is triggered and the comprehensive fault report is pushed through the human-machine interface or mobile terminal to ensure timely response and processing; A wafer box clamping portion, the wafer box clamping portion comprising a wafer box clamping end portion for compatibly clamping wafer boxes of multiple sizes and a wafer box clamping control structure; The wafer box clamping control structure includes a back plate fixedly mounted on one side of the base plate shell, a motor fixedly mounted inside the back plate, a transmission block fixedly mounted on the output shaft end of the motor, a transmission structure rotatably connected to the transmission block and used to drive the wafer box clamping end to move toward or away from each other, a first guide body fixedly mounted inside the back plate and used to guide the wafer box clamping end, and a second guide body fixedly mounted inside the back plate and used to guide the transmission block. The motor and the second guide body are both arranged on the vertical center line inside the back plate, the transmission block is slidably connected to the second guide body, and the wafer box clamping end is slidably connected to the first guide body. The wafer box clamping control structure also includes an in-place detection structure for judging whether the wafer boxes of different sizes to be transferred are successfully clamped. The in-place detection structure is arranged inside the backplate. The in-place detection structure includes a motor retraction position in-place sensor, a first motor extension position in-place sensor and a second motor extension position in-place sensor. The motor retraction position in-place sensor is arranged at the starting working position of the transmission block, and the first motor extension position in-place sensor and the second motor extension position in-place sensor are arranged in sequence from top to bottom on the motion trajectory of the transmission block.

2. The integrated wafer transfer robot according to claim 1, characterized in that: The manipulator body comprises: A mounting portion, for integrally mounting a wafer clamping portion, a wafer box clamping portion, and an electrical control module, wherein the wafer clamping portion and the wafer box clamping portion are respectively disposed on two sides of the mounting portion; A wafer clamping portion, the wafer clamping portion comprising a suction-type wafer clamping end portion and a wafer clamping control structure, the wafer clamping control structure being disposed on the inner side of the mounting portion, the suction-type wafer clamping end portion being fixedly mounted on a side of the mounting portion away from the wafer cassette clamping portion, the wafer clamping control structure being connected to the suction-type wafer clamping end portion via an air pipe for controlling the suction-type wafer clamping end portion to suction, clamp, or release the wafer, and the wafer clamping control structure being used to control the gas flow rate to adjust the strength of the suction-type wafer clamping end portion's suction force on the wafer; The wafer box clamping control structure is fixedly mounted on one side of the mounting portion, and the wafer box clamping end portion passes through the wafer box clamping control structure and is slidably connected to the wafer box clamping control structure, so as to enable the wafer box clamping control structure to drive the wafer box clamping end portion to move toward or away from each other; An electrical control module is electrically connected to the wafer clamping part and the wafer box clamping part respectively, and is used to achieve unified control of the wafer clamping part and the wafer box clamping part, and synchronous transportation of the wafer and the wafer box.

3. The integrated wafer transfer robot according to claim 2, characterized in that: The mounting portion includes a base shell and a joint shaft arranged on one side of the base shell. The base shell is a hollow shell structure, which is used to integrate and install the wafer clamping control structure inside the base shell, and reduce the space occupancy rate of the wafer clamping control structure. The joint shaft is arranged on the robotic arm of the wafer handling robot, and is driven by the robotic arm of the wafer handling robot to drive the integrated wafer transfer robot to perform horizontal rotational movement.

4. The integrated wafer transfer robot according to claim 3, characterized in that: The adsorption-type wafer clamping end portion comprises a wafer clamping claw housing fixedly mounted on one side of the base plate housing and a ceramic chuck fixedly mounted on the side of the wafer clamping claw housing away from the base plate housing, a first air channel connected to the air pipe is provided inside the wafer clamping claw housing, a second air channel connected to the first air channel is provided inside the ceramic chuck, a plurality of vacuum adsorption ports connected to the second air channel are opened on the upper end of the ceramic chuck, and the vacuum adsorption ports are evenly distributed on the upper end surface of the ceramic chuck; The wafer clamping control structure includes a solenoid valve bracket fixedly installed inside the base plate shell, a solenoid valve fixedly installed on the solenoid valve bracket and connected to the air pipe, and a speed regulating valve installed on the air pipe.

5. The integrated wafer transfer robot according to claim 1, characterized in that: The wafer box clamping end includes a pair of clamping claw brackets, a pair of clamping blocks A, a pair of clamping blocks B, a pair of support blocks A, a pair of support blocks B and a wafer baffle, wherein the wafer baffle is fixedly mounted on the side of the back plate facing the wafer box to be clamped, and a pair of the clamping claw brackets are symmetrically distributed on both sides of the back plate, and the end of the clamping claw bracket close to the back plate passes through the back plate and is slidably connected to the back plate, and the end of the clamping claw bracket passing through the inside of the back plate is fixedly connected to the transmission structure, and the end of the clamping claw bracket passing through the inside of the back plate is sleeved on the outside of the first guide body and slidably connected to the first guide body, and the clamping block A and the clamping block B are fixedly mounted on the clamping claw bracket located on the outside of the back plate from the outside to the inside in sequence, and the support block A and the support block B are both fixedly mounted on the clamping claw bracket, and the support block A and the support block B are respectively arranged at the lower ends of the clamping block A and the clamping block B.

6. The integrated wafer transfer robot according to claim 5, characterized in that: The transmission structure includes a pair of connecting rod transmission parts, which are symmetrically distributed on both sides of the motor. The connecting rod transmission parts include a main connecting rod and a rotating connecting rod. One end of the main connecting rod is rotatably connected to the transmission block, and the other end is rotatably connected to the middle part of the rotating connecting rod. The end of the rotating connecting rod is fixedly connected to one side end of the clamping bracket passing through the inside of the back plate.

7. The integrated wafer transfer robot according to claim 1, characterized in that: The data acquisition module includes a visual sensor installed on the key operating nodes of the manipulator body, and a temperature sensor, a torque sensor and a displacement sensor installed on the motor.

8. The integrated wafer transfer robot according to claim 1, characterized in that: The fault diagnosis module includes: The image data processing and analysis submodule is used to pre-process the collected operating status image using an ambient light compensation algorithm to generate an operating status pre-processed image; use the SIFT algorithm to perform feature retrieval and description on the operating status pre-processed image to generate feature descriptors; use the watershed algorithm to segment the operating status pre-processed image to obtain a labeled image and separated mechanical component results; use the feature descriptors to perform matching processing on the mechanical component results to generate mechanical component recognition results; and input the mechanical component recognition results into the trained convolutional neural network model to output mechanical component abnormality recognition results; The motor data processing and analysis submodule is used to process the motor parameter data using a sliding average filter algorithm to generate motor parameter abnormality results; The report generation and alarm submodule is used to generate a comprehensive fault report based on the abnormal identification results of mechanical parts and motor parameters to determine whether the operating status of the robot body is normal. When the operating status of the robot body is abnormal, the alarm system is triggered and the comprehensive fault report is pushed through the human-machine interface or mobile terminal to ensure timely response and processing.

Images