Robotic repair control system and method

Abstract

A grinding setting selection system for a robotic grinding system is presented. The system includes an abrasive rotational speed acquirer that acquires a current rotational speed of a grinder in the robotic grinding system. The system also includes an end effector load acquirer that receives a current end effector load of an end effector in the robotic grinding system. The system also includes a material removal predictor that predicts a material removal rate based on the acquired rotational speed and end effector load. The system also includes a setting adjuster that provides setting adjustments for the robotic grinding system based on the predicted removal rate. The setting adjustments change mechanical settings of the robotic grinding system. The system also includes a setting communicator that communicates the setting adjustments to the robotic grinding system.

Description

[Background technology]

[0001] Surface repair and other abrasive operations are areas of abrasive operations that remain largely automated. Traditionally, human-operated abrasive devices provide more consistent control. Human operation is time-consuming, inconsistent, and labor-intensive. While robotic systems are known, techniques for better control of the automated abrasive process are desirable. Summary of the Invention

[0002] A grinding setting selection system for a robotic grinding system is presented. The system includes an abrasive rotational speed acquirer that acquires a current rotational speed of a grinder in the robotic grinding system. The system also includes an end effector load acquirer that receives a current end effector load of an end effector in the robotic grinding system. The system also includes a material removal predictor that predicts a material removal rate based on the acquired rotational speed and end effector load. The system also includes a setting adjuster that provides setting adjustments for the robotic grinding system based on the predicted removal rate. The setting adjustments change mechanical settings of the robotic grinding system. The system also includes a setting communicator that communicates the setting adjustments to the robotic grinding system. [Brief explanation of the drawings]

[0003] The drawings, which are not necessarily drawn to scale, and in which like numerals may refer to like elements in different views, illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document.

[0004] [Figure 1] 1 illustrates a robotic repair cell in which embodiments herein may be useful.

[0005] [Figure 2A] FIG. 1 is a schematic diagram of removal rates for human and robotic grinding operations over time. [Figure 2B]FIG. 1 is a schematic diagram of removal rates for human and robotic grinding operations over time.

[0006] [Figure 3A] 1 illustrates components of a robotic grinding system, according to embodiments herein. [Figure 3B] 1 illustrates components of a robotic grinding system, according to embodiments herein.

[0007] [Figure 4] 1 illustrates parameters of interest for determining settings for a grinding operation system, according to embodiments herein.

[0008] [Figure 5] 1 illustrates a method for adjusting grinding operation parameters according to an embodiment herein.

[0009] [Figure 6] 1 illustrates a grinding setting selection system according to an embodiment herein.

[0010] [Figure 7] 1 is a grinding setting selection system architecture.

[0011] [Figure 8] 1 illustrates an example of a mobile device that can be used in the embodiments shown in the previous figures. [Figure 9] 1 illustrates an example of a mobile device that can be used in the embodiments shown in the previous figures.

[0012] [Figure 10] FIG. 1 is a block diagram of a computing environment that can be used in the embodiments shown in the preceding figures.

[0013] [Figure 11] 1 is a chart of removal rates, which is described in more detail in the Examples. [Figure 12]1 is a chart of removal rates, which is described in more detail in the Examples. DETAILED DESCRIPTION OF THE INVENTION

[0014] Figure 1 is a schematic diagram of a robotic grinding system in which embodiments of the present invention are useful. The system 100 includes a robot unit 110 having a robot arm 120 coupled to an abrasive grinding element 130. The robotic grinding system 100 of Figure 1 is shown within a robot cell.

[0015] The robotic unit 100 may include at least one force control unit that may be aligned with an end effector, which is described in more detail in Figures 3A-3B. As shown herein, the end effector may also be coupled to a single tool, although other embodiments may include an end effector coupled to two or more tools, as further described in commonly owned U.S. Provisional Patent Application No. 62 / 940,950, filed November 27, 2019. Other suitable arrangements are also expressly contemplated.

[0016] The current state of the art in many grinding operations is for a human operator to apply an abrasive article to the work surface during the grinding operation, with or without the aid of a power tool. Skilled personnel performing such operations utilize extensive training and their senses to monitor the progress of the repair and make changes accordingly. Such advanced techniques are difficult to incorporate in a robotic solution.

[0017] Human grinding operations are gradually being replaced by robotic systems, such as those shown in Figures 1 and 3A. This reduces labor costs but results in inconsistent removal rates after repeated operations. As shown in Figure 2A, human operators may have variable removal rates over time, but they can keep the removal rate within a consistent range by dynamically changing grinding conditions based on the state of the disc and workpiece material, which can be inferred from the grinding system's vision or response. In contrast, as shown in Figure 2B, robotic units experience a predictable decline in removal rate over time. This is because, in traditional methods, the system continues grinding under the same settings (e.g., the same arm angle, translational speed, rotational speed, and pressure) for each operation, regardless of disc wear. In contrast, human operators can make dynamic adjustments based on visible abrasive wear, tactile feedback, or the grinding behavior during operation.

[0018] It would be desirable to have a robotic system that can better detect and respond to changes in conditions during a grinding operation. While many existing systems can vary input parameters (rotational or lateral speed, arm angle, pressure), it would be desirable to have a system that can adjust these inputs based on real-time known or predicted grinding conditions. For example, it would be desirable to have a system that can adjust operating parameters based on the detected wear rate or amount of abrasive article, the color of the abrasive article, the sight and sound of sparks during the grinding operation, etc. Many of these parameters are particularly difficult to measure in situ.

[0019] 3A and 3B illustrate components of a robotic grinding system according to embodiments herein. Similar components are similarly numbered in FIGS. 3A and 3B. The robotic grinding unit may be stationary in some embodiments and mobile in other embodiments. While the description is limited herein to the range and capabilities of movement of arm component 310, it is expressly contemplated that the robotic grinding unit 300 may have multiple movable arm components extending from a base (not shown in FIG. 3A ) to a force control unit. The base of the robotic grinding unit 300 may also have multiple degrees of freedom so that each of its articulated components may move.

[0020] The robot arm 310 may be movable laterally, for example, toward or away from the base of the robotic grinding unit 300. The end effector 320 may be coupled to the robot arm 310 directly or via a force control unit that may control, for example, rotational movement. The end effector 320 may apply a pressing force via the grinder 330 to bring the abrasive 340 into contact with the workpiece 350. The grinder 330 may be rotated to position the abrasive 340 at an angle relative to the workpiece 350, as shown in FIG. 3B . The abrasive 340 may be selected from any suitable abrasive article, including a bonded abrasive article, a nonwoven abrasive article, or a coated abrasive article.

[0021] The system 300 may include one or more sensors 370. The sensors 370 may be capable of detecting, among other parameters, information related to the real-time material removal rate of the abrasive 340 from the workpiece 350. The sensors 370 may send feedback 380 to one or more components of the grinding system 300 based on, for example, the detectable information 360 about the current grinding operation, thereby adjusting grinding system parameters to maintain a desired removal rate. The workpiece may be any suitable material, such as metal, wood, or other material.

[0022] Detectable information 360 may include the abrasive spark color or grinding sound produced by the current abrasive operation, as shown in Figure 3 A. Additionally, the reaction force exhibited by the abrasive material in response to the force applied to the grinder 330 by the end effector may be detectable.

[0023] Ideally, the real-time removal rate is used as the basis for algorithmic adjustments to the current grinding system parameters. Several different options exist for measuring the removal rate in situ. For example, the weight of the workpiece can be measured after each grinding pass. Additionally, when the force is removed from the abrasive article, its weight can also be detected by the force control unit. However, the weight difference is small, and a high-resolution measurement system would be required to detect the exact weight difference. It may also be necessary to remove debris from the grinding operation to accurately measure the wear rate.

[0024] Another option for measuring wear rate is to use a laser profiler that detects differences in the shape of the abrasive article or the workpiece itself. For example, differences in weld height between removal runs can be detected. However, such systems are expensive, difficult to implement, and still require stopping the grinding operation to remove debris in order to make accurate measurements.

[0025] Described herein is a predictive model that can be used to predict the real-time removal rate of an abrasive article and, based on the detected real-time removal rate, adjust grinding system parameters of the grinding system to maintain a consistent removal rate over the use of the abrasive article. Examples described in more detail below demonstrate how the predictive model can be adapted to feedback from a series of actual grinding results.

[0026] One basis for understanding material removal and the systems and methods described herein is the well-known Preston equation for material removal (Equation 1 below), which expresses the instantaneous rate of material removal (cutting) as a product of pressure, relative velocity, and a constant (Preston's constant) that is defined in part by the complex interactions between the abrasive, the substrate, and any cutting fluid.

number

[0027] where k p is a constant that depends on the abrasive / surface interaction, p is the pressure at any given point on the surface, and v rel is the relative velocity between the abrasive and the surface at that point. The term dh / dt is the rate at which material is removed. If the abrasive and any cutting fluid are given and kept constant over the duration of the defect repair (i.e., k p , is fixed), from Equation 1, the domain specific inputs of instantaneous cut are the applied force (and resulting pressure) and the tool velocity (rotational speed, orbital speed, etc.). The total amount of cut is determined via the integral of instantaneous cut over time, appropriately distributed as a function of any macroscopic movement of the end effector by the robot. Embodiments herein use parameters that affect removal rate, which are the left hand side of Preston's law and can be measured in situ, to determine the Preston coefficient (k p ) to provide a method for predicting

[0028] In this regard, material removal across a surface can be expressed as the integral of the relative velocity between the abrasive and the substrate, and the pressure distribution across the polishing media (created by its interaction with the substrate), scaled by Preston's constant.

[0029] constant term k pchanges as the disk life erodes. Many different parameters can be measured during the grinding operation, many of which can be correlated to material removal rate. For example, the rotational or lateral speed of the robot arm, grinder motor power, load, reaction force, wear rate, and contact angle can all be measured by sensors in modern grinding systems. These variables are converted to values ​​that describe the condition of the abrasive article. A regression model is then used to predict the removal rate. The regression model uses a constant term k instead of estimating the Preston coefficient itself. p These terms are used to create an estimated distribution of possible values ​​of . Integrating these terms over time gives the total amount of cut at that point.

[0030] The systems and methods herein apply regression to kp using inputs of other measurable parameters such as motor power, reaction force, wear volume, contact angle, etc.

[0031] k p Various regression models may be used to predict σ, such as either linear or nonlinear regression models. Some possible models may include, but are not limited to, polynomial regression models, support vector regression models, Gaussian process regression models, ridge regression models, lasso regression models, elastic net regression models, nearest neighbor regression models, naive Bayes regression models, decision tree regression models, random forest regression models, and neural network regression models.

[0032] Such predictive models can be used to estimate the removal rate of the abrasive article, and parameters of the grinding system can be adjusted based on the estimate. For example, the removal rate can be increased by increasing the pressing force of the end effector 320. The angle of the grinder 330 relative to the workpiece can be increased to increase the grinding force. The load can be increased to increase the removal rate. The rotational speed can be increased to increase the removal rate. As the amount of wear increases, the removal rate decreases. Various parameters can be adjusted to reduce or address abrasive sparking.

[0033] 4 illustrates parameters of interest for determining settings for a grinding operation system, according to embodiments herein. Settings 470 for the grinding operation illustrate some, but not all, of the input settings that may be adjusted based on known parameters for the grinding system 410, parameters related to the workpiece surface 430, and known parameters for the abrasive article 450.

[0034] The grinding system parameters 410 include force limits 404 that can be applied by the end effector unit, the range of angular positions 406 that the grinder can assume, grinder motor power 408, and upper and lower functional limits for the velocity 420 of the robot arm, including lateral movement 424 and rotational movement 422. The grinding system may also have other parameters 412, such as sensor feedback parameters for sensors associated with the grinding system.

[0035] The workpiece surface may also have parameters 430 that may affect the settings 470 for the grinding operation. For example, the workpiece surface has a composition 434, a hardness 432, and other physical parameters 440. In addition, the workpiece surface has a current surface roughness 436 and a current weight loss 444 during the grinding operation.

[0036] The abrasive article may also have parameters 450 related to the grinding operation, including abrasive particle type 452, size 454, and shape 456 throughout the article. Other physical parameters 460 may be relevant. The abrasive article may have a current weight loss 464 from its original weight or pre-operation weight. The abrasive article may have a color 466 that may change during the abrading operation.

[0037] Additionally, an interaction response 480 may be observed due to the interaction between the abrasive article and the work surface during the grinding operation. For example, the work surface may exhibit sparks 438, which may have an associated color, quantity, or pattern, and may exhibit a current grinding sound 442. The abrasive article also exhibits a reaction force as a result of the interaction.

[0038] Grinding operation settings 470 are initially set for each grinding operation. Some settings can be adjusted in situ during the grinding operation. Some settings can be adjusted between operations. In some embodiments, each setting can be adjusted based on feedback regarding workpiece surface parameters 430 and abrasive parameters 450 received during the grinding operation. For example, the current pressing end effector force 484 can be increased or decreased, and the grinding angle 486 can be increased or decreased to change the angle of contact of the abrasive article with the workpiece surface. The robot arm speed 472 can be adjusted, as can both the rotational speed 474 and the lateral speed 476. Other parameters 478 can also be adjusted.

[0039] FIG. 5 illustrates a method for adjusting grinding operation parameters according to embodiments herein. The method illustrated in FIG. 5 may be implemented, for example, as an API that runs automatically in the background without requiring any interaction from an operator. However, in another embodiment, one or more steps of the method illustrated in FIG. 5 are at least partially displayed to an operator of the robotic grinding system. The operator, in some embodiments, may only be able to see the changes made or may only see that the current grinding operation parameter values ​​have been changed. In other embodiments, the operator can override the changes being made. In other embodiments, the operator must approve the suggested changes before the proposed changes are implemented.

[0040] At block 510, current grinding operation parameters are received. The current parameters may include setup parameters 512 for the grinding system, workpiece characteristics 514 of the current workpiece, and other information 516. For example, sensor feedback may be received regarding the current color or sound of the abrasive article, the current spark color or intensity from the workpiece, or other mechanical information such as feedback regarding the reaction force of the abrasive article. The setup parameters may include the lateral or rotational speed of the robot arm, the end effector load, or other information regarding the current grinding operation.

[0041] At block 520, grinding effectiveness is determined. Detecting current grinding effectiveness can include calculating a predicted material removal rate 522 based on the acquired grinding operation information. For example, as described above, the material removal rate can be predicted using a modified Preston's Law calculation using the current rotational speed, wear amount, and end effector load. In some embodiments, the predicted material removal rate can be improved using the current grinder motor power. The material removal rate can be more accurately predicted by using the current reaction force of the abrasive article applied to the grinding system. Grinding effectiveness can also be determined based on the current or estimated surface roughness 524 of the workpiece. Determining grinding effectiveness can also take into account current characteristics of the abrasive 526, such as the color, sound, and whether sparks are occurring, and, if so, the characteristics of the sparks. For example, the abrasive may change color based on the amount of useful life remaining. The sound or color of the sparks may also indicate burning or other undesirable abrasive activity. Other characteristics 528 can also be considered when determining current grinding effectiveness.

[0042] At block 530, the current grinding effectiveness is compared to a baseline to determine whether the grinding effectiveness can be improved. For example, as shown at block 532, the current grinding effectiveness may be compared to other grinding operations performed by the same or similar grinding system under similar setup parameters. If the current effectiveness is lower than the baseline grinding effectiveness, changes may be needed to increase grinding efficiency. Similarly, as shown at block 534, it may be compared to similar grinding operations on similar workpieces. Other parameters may also be considered, as shown at block 536.

[0043] In some embodiments, a comparison step as shown in block 530 is not required, and parameters are adjusted directly based on the grinding effectiveness determined using Preston's Law as described above, as indicated by arrow 550. For example, if the calculated removal rate is lower than desired, one or more parameters may be adjusted by adjusting the velocity or the contact force (p) applied by the end effector to reduce k. p Either the estimated distribution of or the rate over time can be increased.

[0044] At block 540, grinding parameters are adjusted. For example, the grinding angle 542 may be increased or decreased based on the comparison of grinding efficiency. The grinder rotational speed or lateral speed 544 may be adjusted. The end effector pressure force 546 may be increased or decreased. Other parameters 548 may also be adjusted.

[0045] 5 may be repeated periodically by the robotic grinding system, as indicated by arrow 560. For example, the method may be repeated at least once, or at least twice, or even more frequently during each grinding operation. In another embodiment, the method may be repeated periodically, for example, once every hour, once every minute, or once every second.

[0046] FIG. 6 illustrates a grinding setting selection system according to embodiments herein. While FIG. 6 illustrates one exemplary setup of a grinding setting selection system, other setups are expressly contemplated. For example, grinding setting selection system 610 may be part of grinding system 680, may be located on a remote device, and may be accessed via a wireless network or a cloud-based network. As described below with respect to FIG. 9, the grinding setting selection system may be accessible via a graphical user interface on a computing device.

[0047] The robotic grinding system 680 includes multiple components, each having one or more settings 682. The system also includes at least one abrasive article having multiple abrasive parameters 684. The system also includes a workpiece manipulated by the grinding system, the workpiece having multiple workpiece parameters 686. The system 680 may also include other components 688.

[0048] The grinding setting selection system 610 can also obtain information from a database 670, which may be stored locally, for example, as part of the grinding system 680 or as part of a computing unit including the grinding setting selection system 610. The database 670 may also, in another embodiment, be located remotely from either the grinding system 680 or the grinding setting selection system 610, accessible using a wireless network or a cloud network. The database 670 may include grinding performance data 672, which may include performance information such as cut rates, wear rates, and material composition of multiple abrasives. The database 670 may also include workpiece data 674, which may include information about the workpiece, such as composition, hardness, thickness, 3D structure, or other related information. The database 670 may also include grinding system data 676, for example, historical or predicted grinding efficiency, predicted or predicted material removal rate, or other information related to a given operation. The database 670 may also include other data 678.

[0049] The grinding setting selection system 610 includes a wear amount acquirer 612 that acquires the wear state of the abrasive article. The grinding setting selection system 610 may also include a surface roughness acquirer that acquires information regarding the current roughness of the workpiece surface. The grinding setting selection system 610 may also include an abrasive color acquirer 618 that acquires information regarding the current color of the abrasive article, which may indicate the amount of wear on the abrasive article or the current temperature of the grinding information. Similarly, a sound acquirer 622 may acquire and analyze the sound of the grinding operation for abnormalities, and a grinding spark acquirer 624 may acquire information regarding whether sparks are occurring during the grinding operation, how many sparks are occurring, and what color sparks are occurring. The grinding setting selection system 610 may also include a grinder motor power acquirer 626 that acquires the current grinder motor power of the grinder motor. The grinding setting selection system 610 may also include a reaction force acquirer 628 that acquires the current reaction force from the abrasive article on the grinding system. The grinding setting selection system 610 may also include a pressure obtainer 629 that obtains the pressure of the end effector acting on the abrasive article. Other information regarding the grinding operation may also be obtained by other obtainers 632.

[0050] 6 may obtain information about the current grinding operation from a sensor 689, such as an optical sensor, force sensor, or other sensor, associated with grinding system 680. The sensor may be part of grinding system 680, part of a cell associated with grinding system 680, or located in another suitable location.

[0051] Based on the obtained information, the material removal predictor 614 may predict the current material removal rate of the grinding system 680. Additionally, the current abrasive condition estimator 620 may estimate the current condition of the abrasive article, including the wear level and temperature of the abrasive article.

[0052] Based on the predicted material removal rate and the abrasive conditions, the setting selector 640 may change the settings of the grinding system 680. For example, the grinder angle may be adjusted by a grinder angle setter 642. The grinder speed may be adjusted by a rotational speed setter 644 or a lateral speed setter 646. The end effector load may be adjusted by an end effector load setter 648. The end effector pressure may also be adjusted by a pressure setter 652. Other settings may be adjusted by an other setting setter 654. The settings may be adjusted to increase the efficiency of the grinding system 680, for example, to increase the predicted material removal rate or to reduce the risk of burning the workpiece.

[0053] The new settings are communicated from the grinding setting selection system 610 to the grinding system by the new setting communicator 660, which can automatically implement the settings within the grinding system 680.

[0054] FIG. 7 is a block diagram of a grinding setting selection system in a cloud-based architecture. Remote server architecture 700 illustrates one embodiment of an implementation of grinding setting selection system 710. As an example, remote server architecture 700 can provide computing, software, data access, and storage services that do not require end-user knowledge of the physical location or configuration of the systems delivering the services. In various embodiments, the remote server can deliver services over a wide area network, such as the Internet, using an appropriate protocol. For example, the remote server can deliver applications over the wide area network, which can be accessed through a web browser or any other computing component. The software or components shown or described in FIGS. 1-6 and corresponding data can be stored on a server at a remote location. Computing resources in a remote server environment can be aggregated at a remote data center location, or they can be distributed. The remote server infrastructure can deliver services through shared data centers, which appear as a single point of access to users. Thus, the components and functionality described herein can be provided from a remote server at a remote location using a remote server architecture. Alternatively, they may be provided by a traditional server, installed directly on the client device, or provided in other ways.

[0055] In the example shown in FIG. 7 , some items are similar to those shown in the previous figures. FIG. 7 specifically illustrates that the grinding setting selection systems can be located at a remote server location 702. Thus, the computing device 720 accesses these systems via the remote server location 702. An operator 750 can also access a user interface 722 using the computing device 720. The embodiments described herein focus on systems and methods that automatically acquire data to estimate the current material removal rate and adjust the parameters of the current grinding operation based on that estimate, all in situ. However, it is expressly contemplated that the acquired data, adjustments, or other information can be presented on the user interface 722 for action or approval from the operator 750. For example, the operator 750 may be required to approve the proposed parameter adjustments before they are implemented on the grinding system. Alternatively, the operator may be able to make changes to the proposed parameter adjustments. Or, in some embodiments, the operator 750 may only be able to view the current parameters.

[0056] Figure 7 also illustrates another example of a remote server architecture. Figure 7 illustrates that it is also contemplated that some elements of the systems described herein may be located at a remote server location 702, while other elements may not. By way of example, storage 730, 740, or 760 or grinding system 770 may be located at a location separate from location 702 and accessed via a remote server at location 702. Regardless of where they are located, they may be accessed directly by computing device 720 over a network (either a wide area network or a local area network), hosted at a remote site by a service, provided as a service, or accessed via a connectivity service residing at a remote location. Data may also be stored virtually anywhere and intermittently accessed by or transferred to a party. For example, a physical carrier may be used instead of or in addition to an electromagnetic carrier.

[0057] It should also be noted that elements of the systems described herein, or portions thereof, can be located on a wide variety of different devices, some of which include servers, desktop computers, laptop computers, embedded computers, industrial controllers, tablet computers, or other mobile devices such as palmtop computers, mobile phones, smartphones, multimedia players, personal digital assistants, etc. Any suitable computing device having a display may be capable of functioning as computing device 1520 with user interface 1522.

[0058] Figure 8 is a simplified block diagram of an illustrative embodiment of a handheld or mobile computing device that may be used as a user or client handheld device 816 (e.g., such as computing device 720 of Figure 7) on which the present system (or portions thereof) may be deployed. For example, a mobile device may be deployed within an operator compartment of computing device 720 for use in generating, processing, or displaying data. Figure 9 is another embodiment of a handheld or mobile device.

[0059] 8 provides a schematic block diagram of components of a client device 816 capable of executing some of the components shown and described herein. The client device 816 interacts with, or executes and interacts with, some of the components. The device 816 is provided with a communication link 813 that enables the handheld device to communicate with other computing devices and, under some embodiments, provides a channel for automatically receiving information, such as by scanning. Examples of communication link 813 include those that enable communication via one or more communication protocols, such as wireless services used to provide cellular access to networks, as well as protocols that provide local wireless connectivity to networks.

[0060] In another embodiment, the application may be received on a removable Secure Digital (SD) card that is connected to interface 815. Interface 1615 and communication link 813 communicate with processor 817 (which may also embody a processor) along bus 819, which is also connected to memory 821 and input / output (I / O) components 823, as well as clock 825 and position information system 827.

[0061] I / O components 823, in one embodiment, are provided to facilitate input and output operations, and device 816 may include input components such as buttons, touch sensors, optical sensors, microphones, touch screens, proximity sensors, accelerometers, orientation sensors, etc., and output components such as display devices, speakers, and / or printer ports. Other I / O components 823 may be used as well.

[0062] Clock 825 illustratively includes a real-time clock component that outputs the time and date, and may also provide timing functions for processor 817.

[0063] Illustratively, location information system 827 includes components that output the current geographic location of device 816. This may include, for example, a global positioning system (GPS) receiver, a LORAN system, a dead-reckoning system, a cellular triangulation system, or other positioning systems. It may also include, for example, mapping or navigation software that generates desired maps, navigation routes, and other geographic features.

[0064] Memory 821 stores operating system 829, network settings 831, applications 833, application configuration settings 835, data storage 837, communication drivers 839, and communication configuration settings 841. Memory 821 may include all types of tangible, volatile, and non-volatile computer-readable memory devices. It may also include computer storage media (described below). Memory 821 stores computer-readable instructions that, when executed by processor 817, cause the processor to perform computer-implemented steps or functions in accordance with the instructions. Processor 817 may also be activated by other components to facilitate their functions.

[0065] FIG. 9 shows that the device may be a smartphone 971. The smartphone 971 has a touch-sensitive display 973 that displays icons or tiles or other user input mechanisms 975. The mechanisms 975 can be used by a user to run applications, make phone calls, perform data transfer operations, etc. Generally, smartphones 971 are built on mobile operating systems and offer greater computing power and connectivity than feature phones. The grinding setting selection system may be an installed application, accessible through a website on the internet, or another suitable configuration accessible by the smart device 971.

[0066] FIG. 10 is a block diagram of a computing environment that can be used in the embodiments shown in the preceding figures.

[0067] 10 is an example of a computing environment in which elements of the systems and methods described herein, or portions thereof (for example), may be deployed. Referring to FIG. 10, an exemplary system for implementing some embodiments includes a general-purpose computing device in the form of a computer 1010. Components of the computer 1010 may include, but are not limited to, a processing unit 1020 (which may include a processor), a system memory 1030, and a system bus 1021 that couples various system components, including the system memory, to the processing unit 1020. The system bus 1021 may be any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The memory and programs described with respect to the systems and methods described herein may be deployed in the corresponding portions of FIG. 10.

[0068] The computer 1010 typically includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by the computer 1010, including both volatile and nonvolatile media, removable and non-removable media. By way of example, and not limitation, computer-readable media can include computer storage media and communication media. Computer storage media is distinct from and does not include modulated data signals or carrier waves. Computer storage media includes hardware storage media, including both volatile and nonvolatile, removable and non-removable media, implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disk (DVD), or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by the computer 1010. Communication media may embody computer-readable instructions, data structures, program modules, or other data in a transport mechanism and include any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.

[0069] The system memory 1030 includes computer storage media in the form of volatile and / or nonvolatile memory such as read-only memory (ROM) 1031 and random access memory (RAM) 1032. A basic input / output system 1033 (BIOS), containing the basic routines that help to transfer information between elements within the computer 1010, such as during start-up, is typically stored in ROM 1031. RAM 1032 typically contains data and / or program modules that are immediately accessible to and / or presently being operated on by the processing unit 1020. By way of example, and not limitation, FIG. 10 illustrates operating system 1034, application programs 1035, other program modules 1036, and program data 1037.

[0070] The computer 1010 may also include other removable / non-removable, volatile / non-volatile computer storage media. By way of example only, Figure 10 illustrates a hard disk drive 1041, a non-volatile magnetic disk 1052, an optical disk drive 1055, and a non-volatile optical disk 1056, which read from or write to non-removable, non-volatile magnetic media. The hard disk drive 1041 is typically connected to the system bus 1021 through a non-removable memory interface, such as interface 1040, and the optical disk drive 1055 is typically connected to the system bus 1021 by a removable memory interface, such as interface 1050.

[0071] Alternatively, or in addition, the functions described herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include Field-Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application-Specific Standard Products (ASSPs), System-on-a-Chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0072] The drives and their associated computer storage media, discussed above and illustrated in Figure 10, provide storage of computer-readable instructions, data structures, program modules, and other data for the computer 1010. In Figure 10, for example, hard disk drive 1041 is illustrated as storing operating system 1044, application programs 1045, other program modules 1046, and program data 1047. Note that these components can either be the same as or different from operating system 1034, application programs 1035, other program modules 1036, and program data 1037.

[0073] A user may enter commands and information into the computer 1010 through input devices such as a keyboard 1062, a microphone 1063, and a pointing device 1061, such as a mouse, trackball, or touchpad. Other input devices (not shown) may include a joystick, game pad, satellite receiver, scanner, or the like. These and other input devices are often connected to the processing unit 1020 through a user input interface 1060 that is coupled to the system bus, although they may be connected by other interface and bus structures. A visual display 1091 or other type of display device is also connected to the system bus 1021 via an interface, such as a video interface 1090. In addition to the monitor, computers may also include other peripheral output devices such as speakers 1097 and printer 1096, which may be connected through an output peripheral interface 1095.

[0074] The computer 1010 operates in a networked environment using logical connections, such as a local area network (LAN) or a wide area network (WAN), to one or more remote computers, such as a remote computer 1080.

[0075] When used in a LAN networking environment, the computer 1010 is connected to the LAN 1071 through a network interface or adapter 1070. When used in a WAN networking environment, the computer 1010 typically includes a modem 1072 or other means for establishing communications over the WAN 1073, such as the Internet. In a networked environment, program modules may be stored in remote memory storage devices. Figure 10 illustrates, for example, that remote application programs 1085 may reside on the remote computer 1080.

[0076] A grinding setting selection system for a robotic grinding system is presented. The system includes an abrasive rotational speed acquirer that acquires a current rotational speed of a grinder in the robotic grinding system. The system also includes an end effector load acquirer that receives a current end effector load of an end effector in the robotic grinding system. The system also includes an in situ parameter sensor that senses in situ grinding parameters of a current grinding operation. The system also includes a material removal predictor that predicts an in situ material removal rate based on the acquired rotational speed, end effector load, and in situ grinding parameters. The system also includes a setting adjuster that provides setting adjustments for the robotic grinding system based on the predicted in situ removal rate. The setting adjustments change mechanical settings of the robotic grinding system. The system also includes a setting communicator that communicates the setting adjustments to the robotic grinding system.

[0077] The grinding setting selection system may be implemented such that the in situ parameter sensor is a grinder motor power sensor that detects a current grinder motor power, and the material removal predictor predicts a material removal rate based on the current grinder motor power.

[0078] The grinding setting selection system may be implemented such that the in situ parameter sensor is a reaction force sensor that senses a reaction force applied to the end effector by the abrasive article, and the material removal predictor predicts the material removal rate based on the reaction force.

[0079] The grinding setting selection system may be implemented such that the material removal rate predictor also predicts the material removal rate based on the pressure of the end effector, the grinding angle of the grinder, or the lateral velocity of the robot arm.

[0080] The grinding setting selection system can be implemented such that the mechanical settings include a new pressure force, a new rotational speed, or a new grinding angle for the end effector.

[0081] The grinding setting selection system may be implemented to also include a workpiece surface parameter acquirer.

[0082] The grinding setting selection system can be implemented such that the workpiece surface parameter acquirer acquires the composition, hardness, or surface roughness of the workpiece surface.

[0083] The grinding setting selection system may be implemented such that the workpiece surface parameter acquirer acquires the current spark state or current grinding sound of the workpiece surface.

[0084] The grinding setting selection system may also be implemented to include an abrasive parameter obtainer.

[0085] The grinding setting selection system may be implemented such that the abrasive parameter obtainer obtains the type, composition, or grade of the abrasive article.

[0086] The grinding setting selection system may be implemented such that the abrasive parameter obtainer obtains the current abrasive color or the current abrasive temperature of the abrasive article.

[0087] The grinding setting selection system can be implemented such that the abrasive condition evaluator determines the abrasive condition of the abrasive article based on the obtained abrasive parameters.

[0088] The grinding setting selection system can be implemented such that the material removal rate predictor includes a regression model.

[0089] The grinding setting selection system can be implemented such that the current rotational speed and end effector load are obtained directly from the robotic grinding system.

[0090] The grinding setting selection system may be implemented such that the setting communicator also communicates the setting adjustments to the database in a format available for later retrieval.

[0091] The grinding setting selection system may be implemented such that the setting communicator also communicates setting adjustments to the user interface generator for display on the user interface.

[0092] The grinding setting selection system can be implemented such that the predicted material removal rate is compared to a reference material removal rate, and the setting adjuster provides a setting adjustment based on the comparison.

[0093] The grinding setting selection system can be implemented such that the current rotational speed and end effector load are periodically obtained, a predicted material removal rate is calculated, and setting adjustments are automatically provided based on instructions.

[0094] The grinding setting selection system can be implemented so that the indication is a time period, a detected start time of operation, or an operator command.

[0095] A method for adjusting grinding parameters in a robotic grinding system is presented. The method includes receiving a set of current grinding operation parameters. The set of current grinding operation parameters includes a grinder rotational speed, an end effector load, and in situ parameter sensors sensed for the current grinding operation. The method also includes estimating a current material removal rate using a material removal rate predictor based on the received set of current grinding operation parameters. The method also includes selecting a new set of grinding operation parameters for the robotic grinding system based on the estimated removal rate. The method also includes automatically adjusting the robotic grinding system from the current grinding operation parameters to the new grinding operation parameters.

[0096] The method may be implemented such that it includes calculating grinding effectiveness using a grinding effectiveness calculator by comparing a current material removal rate to an expected material removal rate, and the selected set of new grinding operation parameters is based on the calculated grinding effectiveness.

[0097] The method can be implemented such that the in situ parameter sensor includes a sensed reaction force experienced by the end effector.

[0098] The method may be implemented such that the in situ parameter sensors include sensed current grinder motor power.

[0099] The method may be implemented such that the set of current grinding operation parameters also includes workpiece surface parameters.

[0100] The method may be implemented such that the workpiece surface parameter includes workpiece surface composition, workpiece surface hardness, or surface roughness.

[0101] The method may be implemented such that the set of current grinding operation parameters also includes abrasive article parameters.

[0102] The method can be implemented such that the abrasive article parameter is the type, composition, or color of the abrasive article.

[0103] The method may be implemented such that the set of current grinding operation parameters also includes the current grinding sound, the current presence of sparks, or the color of detected sparks.

[0104] The method may be implemented to include calculating an abrasive article condition based on the abrasive article parameters. The set of new grinding operation parameters is also based on the calculated abrasive article condition.

[0105] The method may be implemented such that the expected material removal rate is the reference material removal rate.

[0106] The method may be implemented such that the reference material removal rate comprises a range from a lower acceptable material removal rate to an upper acceptable material removal rate.

[0107] The method may be implemented such that the material removal rate is calculated using Gaussian process regression.

[0108] The method may be implemented such that the receiving, calculating, determining, and adjusting steps are performed automatically based on instructions.

[0109] The method may be implemented such that the indication is time since last adjustment, time since detected start of work, or operator input.

[0110] The method may be implemented to further include communicating the new set of grinding operation parameters to a robotic grinding system that is remote from the grinding effectiveness calculator.

[0111] The method may be implemented to further include storing the new set of grinding parameters in a database.

[0112] The method may be implemented to further include communicating the new set of grinding operation parameters to a user interface generator for display on a user interface.

[0113] A robotic grinding system is presented that includes an abrasive article configured to contact a workpiece surface at an angle. The system also includes a grinder configured to maintain the angle of the abrasive article. The system also includes an end effector configured to apply an end effector load to the abrasive article and receive a reaction force from the abrasive article. The system also includes a motor having a grinder motor drive that drives rotation of the abrasive article at a rotational speed. The system also includes a settings selector configured to acquire the rotational speed, the end effector load, and in situ grinding parameters, calculate a predicted material removal rate based on the acquired rotational speed, the end effector load, and the in situ grinding parameters, and compare the predicted material removal rate to a reference predicted removal rate. The system also includes selecting a new set of settings for the mechanical settings of the robotic grinding system. The system also includes a settings communicator that communicates the new settings to the grinder, the end effector, and the motor and automatically adjusts operating settings from a current set of settings to the new settings.

[0114] The robotic grinding system can be implemented such that new settings are selected to increase the predicted material removal rate.

[0115] The robotic grinding system can be implemented such that the in situ grinding parameters include a current grinder motor power and calculate a predicted material removal rate based on the current grinder motor power.

[0116] The robotic grinding system can be implemented such that the in situ grinding parameters include reaction forces and calculate a predicted material removal rate based on the reaction forces.

[0117] The robotic grinding system may also be implemented to include an abrasive article parameter obtainer that obtains the color of the abrasive article, the grinding sound, the presence of sparks, or the color of the sparks.

[0118] The robotic grinding system may also be implemented to include an abrasive condition evaluator that evaluates the condition of the abrasive article.

[0119] The robotic grinding system can be implemented such that the setting adjuster provides setting adjustments based on the condition of the abrasive article.

[0120] The robotic grinding system can be implemented to provide setting adjustments that reduce grinding temperatures.

[0121] The robotic grinding system can be implemented such that the mechanical setting is the pressure force of the end effector, the grinding angle of the grinder, or the lateral velocity of the robot arm.

[0122] The robotic grinding system can be implemented such that calculating the predicted material removal rate includes applying Gaussian process regression.

[0123] The robotic grinding system may be implemented such that the settings communicator communicates new settings to the database in a format available for later retrieval.

[0124] The robotic grinding system may be implemented such that the settings communicator also communicates the new settings to the user interface generator for display on the user interface.

[0125] The robotic grinding system may be implemented such that the baseline expected removal rate is a range of expected removal rates.

[0126] The robotic grinding system may be implemented such that the setting selector periodically obtains, calculates, compares, and selects a new set of settings based on instructions.

[0127] The robotic grinding system can be implemented such that the indication is a time period, a detected start time of the motion, or an operator command. [Example]

[0128] Example 1 Figure 11 shows an experiment evaluating a simple feedback algorithm to maintain a consistent removal rate by varying the rotational speed of the abrasive disc. Experiment 16 was compared to Experiments 8-13, which demonstrate traditional force control without feedback.

[0129] A system such as that shown in Figure 1, a robotic repair unit available from Fanuc, and an end effector unit such as that described in Japanese Patent Publication No. 2020049599 were used. The abrasive disc used was available from 3M Company under the product name Cubitron 2™ Fiber Disc 987C. The workpiece was a 6 mm wide, 300 mm long stainless steel 400 plate. The device settings were 20 mm / s, a contact angle of 10 degrees, and a load of 1.45 kgf. This resulted in the experimental results shown in Figure 11. Example 2

[0130] Figure 12 shows the simulation results obtained using the same setup parameters as in Example 1. Simulations were performed to evaluate the performance of the removal rate prediction model by using various previously collected data sets. The power consumed in friction was calculated from the reaction torque measured at the connection between the arm and the end effector. Additional parameters used were the end effector geometry, workpiece geometry, disk radius, rotation angle, contact angle, and feed rate.

[0131] The results were normalized to a maximum of 1. The material removal rate is the actual material removal rate measured in a series of previous experiments. The sliding friction power is the estimated power consumed in a horizontal plane due to sliding friction between the workpiece and the abrasive surface. The abrasive rotation speed combined with the load value corresponds to the relative velocity multiplied by the load in Preston's law. It was calculated by multiplying the two set values. The wear amount was the weight loss of the abrasive disc. The predicted removal rate is the average value of the output from the removal rate generation model. Since the model is based on a Gaussian process, the predictions are expressed as the mean and standard deviation. The Y-axis in Figure 12 shows the average value of the output of the Gaussian process model.

Claims

1. 1. A method for adjusting grinding parameters in a robotic grinding system, comprising: receiving a set of current grinding operation parameters, the set of current grinding operation parameters including a grinder rotational speed, an end effector load, and in situ parameters sensed during the current grinding operation; estimating a current material removal rate using a material removal rate predictor based on the received set of current grinding operation parameters; selecting a new set of grinding operation parameters for the robotic grinding system based on the estimated removal rate; and automatically adjusting the robotic grinding system from the current grinding operating parameters to the new grinding operating parameters; Including, The method, wherein the in situ parameters include at least one of grinding sounds, presence of sparks, and color of sparks produced by a current grinding operation.

2. 2. The method of claim 1, further comprising: calculating grinding effectiveness by comparing the current material removal rate to an expected material removal rate using a grinding effectiveness calculator; and wherein the selected set of new grinding operation parameters is based on the calculated grinding effectiveness.

3. The method of claim 2 , wherein the expected material removal rate is a reference material removal rate.

4. The method of any one of claims 1 to 3, wherein the material removal rate is calculated using Gaussian process regression.

5. The method of claim 2 or 3, further comprising communicating the new set of grinding operation parameters to the robotic grinding system, the robotic grinding system being remote from the grinding effectiveness calculator.

6. 1. A robotic grinding system comprising: an abrasive article configured to contact a work surface at an angle; a grinder configured to maintain the angle of the abrasive article; an end effector configured to apply an end effector load to the abrasive article and receive a reaction force from the abrasive article; a motor having a grinder motor power for driving rotation of the abrasive article at a rotational speed; a setting selector, obtaining the rotational speed, the end effector load, and in situ grinding parameters; calculating a predicted material removal rate based on the obtained rotational speed, end effector load, and in situ grinding parameters; comparing the predicted material removal rate to a baseline predicted material removal rate; selecting a new set of settings for the mechanical settings of the robotic grinding system; a setting selector configured to: a settings communicator that communicates the new settings to the grinder, the end effector, and the motor, and automatically adjusts operating settings from a current set of settings to the new settings; Equipped with The robotic grinding system, wherein the in situ grinding parameters include at least one of grinding sounds, presence of sparks, and color of sparks generated by a current grinding operation.

7. The robotic grinding system of claim 6 , wherein the new settings are selected to increase a predicted material removal rate.

8. 8. The robotic grinding system of claim 6 or 7, wherein the in situ grinding parameters include a current grinder motor power, and the predicted material removal rate is calculated based on the current grinder motor power.

9. The robotic grinding system according to any one of claims 6 to 8, wherein the in situ grinding parameters include a reaction force, and the predicted material removal rate is calculated based on the reaction force.

Images