Method and system for optimizing acceleration and deceleration values in a machine tool

Abstract

A system (100) for optimizing acceleration and deceleration values in a machine tool (102) is disclosed. The system comprises a remote server (110), an apparatus (106) for optimizing acceleration and deceleration values in the machine tool, and a controller (104) communicatively connected with the apparatus. The machine learning is trained in the remote server using the data obtained from the multi-physics model of the machine tool. Further, the machine learning model is deployed in the apparatus to determine optimum acceleration and deceleration values of the machine tool. Furthermore, the controller receives the determined optimum acceleration and deceleration values and controls the machine tool by setting the optimum acceleration and deceleration values.

Description

[0001] Description

[0002] METHOD AND SYSTEM FOR OPTIMIZING ACCELERATION AND DECELERATION

[0003] VALUES IN A MACHINE TOOL

[0004] The present disclosure relates to optimizing machining processes, and more particularly relates to a method and system for optimizing acceleration and deceleration values in a machine tool.

[0005] Manufacturing industry constantly seeks ways to improve productivity, precision, and efficiency in manufacturing processes. Machine tools, including CNC (computer numerical control) systems, are essential for creating parts with high accuracy, reliability, and speed. In order to meet the growing market demands, these high precision machine tools are operated at their maximum capacity for a prolonged period. Such prolonged usage results in drop in accuracy of the machined parts, failure of components of machine tool, increased downtime so on and so forth.

[0006] The overall performance of the machine tool and various components of the machine tool is dependent on various cutting parameters. Particularly, parameters such as acceleration, deceleration and jerk of machine tool influences the machine life and performance.

[0007] Conventional methods for controlling acceleration and deceleration in machine tools involves manual adjustment of parameters and these manual techniques are often based on experience of human operator. The human intervention, while effective to some extent, is often prone to error and inaccuracies. The automatic method of controlling the parameters is based on operational parameters motor inertia and machine dynamics. However, the parameters such as acceleration, deceleration are a fixed value irrespective of the loading and operating conditions. The fixed values are determined by averaging the extreme loading conditions of the machine tool and hence does not consider real-time loading condition of the machine tool.

[0008] Thus, there exists a need for a system and method that can automatically optimize the acceleration and deceleration of machine tools thereby improving the efficiency of the machine tool and improving the life of the machine tool.

[0009] Therefore, it is an object of the present invention to provide a computer-implemented method for optimizing acceleration and deceleration values in a machine tool.

[0010] The term “machine tool” refers to a powered mechanical device used for shaping or machining metal, wood, or other rigid materials by selectively removing material from a workpiece. Typically operated under computer numerical control (CNC) or manual control, machine tools perform precise cutting, grinding, drilling, milling, turning, or shaping operations to create parts with specific dimensions and tolerances. The machine tool comprises various components, such as a spindle, cutting tool, tool holder, and workpiece fixture, and is designed to maintain the alignment, rigidity, and accuracy necessary to perform repetitive operations efficiently.

[0011] The term “Acceleration and deceleration” of a machine tool refer to the controlled increase or decrease in the speed of its moving components, such as the spindle or linear axes, during operation. Acceleration involves increasing the velocity of these components from a stationary or low-speed state to a desired operational speed, while deceleration is the process of reducing their velocity, typically to bring the tool or workpiece to a controlled stop or to transition between machining processes.

[0012] The term “multi-physics model” of a machine tool refers to a comprehensive computational representation that integrates multiple physical domains such as mechanical, thermal, and electrical domains to simulate and analyze the complex interactions within the machine tool during operation. This model incorporates the effects of various factors, including structural dynamics, heat generation, cutting forces, vibration, and lubrication flow, to predict the machine tool's performance under real-world conditions.

[0013] The method for optimizing acceleration and deceleration values in a machine tool comprises obtaining, by a processing unit, data relating to operational parameters of the machine tool from a multi-physics model of the machine tool. The operational parameters of the machine tool include acceleration, deceleration, and jerk of the machine tool.

[0014] The step of obtaining data relating to operational parameters of the machine tool from a multiphysics model of the machine tool comprises creating, using the processing unit, the multi-physics model of the machine tool using kinematic models and electrical models of the components of the machine tool. In an embodiment, the multi-physics model of the machine tool is created for different configurations of the same machine tool by altering design aspects of the machine tool

[0015] The step comprises calibrating the multi-physics model of the machine tool using Bayesian calibration to optimize design parameters of the multi-physics model of the machine tool.

[0016] The step comprises optimizing the multi-physics model of the machine tool, using the processing unit, based on the calibration of the multi-physics model. The multi-physics model of the machine tool is optimized using a deep neural network model configured to determine optimum design parameters of the machine tool. The deep neural network model is trained using data relating to modelling of the machine tool and validated using the design parameters data obtained from the machine tool.

[0017] The step comprises simulating, using the processing unit, the multi-physics model of the machine tool for different loading conditions of the machine tool. In an embodiment, the simulation of multi- physics model of the machine tool comprises static loading condition and dynamic loading condition of the machine tool.

[0018] Advantageously, simulation can be performed for different configurations of the machine tool by modifying the multi-physics model of the machine tool. Thus, the time and cost involved in obtaining operational parameters for different configurations of the machine tool are reduced.

[0019] The step comprises obtaining, using the processing unit, data relating to operational parameters of the machine tool from the simulation of the multi-physics model of the machine tool.

[0020] The method comprises training a machine learning model using the obtained data relating to operational parameters of the machine tool to determine the optimum acceleration and deceleration of the machine tool for different loading conditions of the machine tool. The loading conditions include weight of the workpiece, orientation of the workpiece and load distribution on machine table.

[0021] The method comprises validating the machine learning model, by the processing unit, using realtime operational parameters of the machine tool measured using a plurality of sensors deployed on the machine tool.

[0022] The method comprises obtaining, by the processing unit, real-time loading condition of the machine tool using vibrations sensor and strain gauges deployed on the machine tool to measure the loading conditions of the machine tool.

[0023] The method comprises determining, using the machine learning model, the optimum acceleration and deceleration values corresponding to the obtained real-time loading conditions of the machine tool.

[0024] The method comprises setting, by a controller, the optimum acceleration and deceleration values determined by the machine learning model in the machine tool.

[0025] Advantageously, the method offers a solution to automatically optimize the acceleration and deceleration of the machine tool based on the real-time loading conditions of the machine tool. Therefore, the damages to the components of the machine tool due to improper acceleration and deceleration of the machine tool is prevented using the present invention.

[0026] The method further comprises receiving, by the processing unit, feedback input from a user to optimize the machine learning model based on the set optimum acceleration and deceleration values in the machine tool. The method comprises updating the machine learning model, using the processing unit, based on the feedback input received from the user.

[0027] The method further comprises identifying, by the processing unit, zones on the machine tool that are subject to excessive vibrations based on the simulation of the multi-physics model of the machine tool.

[0028] The method comprises monitoring, using vibration sensors, vibrations at the identified zones on the machine tool that are subject to excessive vibrations by deploying the vibration sensors at the identified zones.

[0029] The method comprises notifying the user, if the vibration at the identified zones exceeds a predefined threshold limit. Advantageously, if any abnormality in vibrations is observed the system can automatically detect it and notify the user thus preventing potential damages to the machine tool.

[0030] The object of the present invention is achieved by an apparatus for optimizing acceleration and deceleration values in a machine tool. The apparatus comprises one or more processing units, and a memory communicatively coupled to the one or more processing units. The memory comprises a module stored in the form of machine-readable instructions executable by the one or more processing units, wherein the module is configured to perform the method steps mentioned above.

[0031] The object of the present invention is achieved by a system for optimizing acceleration and deceleration values in a machine tool. The system comprises a remote server, an apparatus for optimizing acceleration and deceleration values in the machine tool, and a controller communicatively connected with the apparatus. The machine learning is trained in the remote server using the data obtained from the multi-physics model of the machine tool. Further, the machine learning model is deployed in the apparatus to determine optimum acceleration and deceleration values of the machine tool. Furthermore, the controller receives the determined optimum acceleration and deceleration values and controls the machine tool by setting the optimum acceleration and deceleration values.

[0032] The object of the present invention is achieved by a computer-program product, having computer- readable instructions stored therein, that when executed by a processing unit, cause the processing unit to perform the above-mentioned method steps.

[0033] The object of the present invention is achieved by a computer readable medium on which program code sections of a computer program are saved, the program code sections being loadable into and / or executable in a system to make the system execute the above method steps. The present invention is further described hereinafter with reference to illustrated embodiments shown in the accompanying drawings, in which:

[0034] FIG 1 illustrates a system 100 for optimizing acceleration and deceleration values in the machine tool, according to an embodiment of the present invention;

[0035] FIG 2 illustrates a block diagram of an apparatus 106 for optimizing acceleration and deceleration values in the machine tool, according to one embodiment of the present invention;

[0036] FIG 3 is a flowchart 300 of a method for optimizing acceleration and deceleration values in the machine tool, according to an embodiment of the present invention;

[0037] FIG 4 is a flowchart of a method 400 for obtaining data relating to operational parameters of the machine tool from a multi-physics model of the machine tool, according to an embodiment of the present invention; and

[0038] FIG 5 is a flowchart of a method 500 for monitoring zones of the machine tool that are subject to excessive vibrations, according to an embodiment of the present invention.

[0039] Hereinafter, embodiments for carrying out the present invention are described in detail. The various embodiments are described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purpose of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident that such embodiments may be practiced without these specific details.

[0040] FIG. 1 illustrates a system 100 for optimizing acceleration and deceleration values in the machine tool 102, according to an embodiment of the present invention. The system 100 comprises a machine tool 102, a controller 104 operatively connected to the machine tool 102, an apparatus 106 for optimizing acceleration and deceleration values, a remote server 110, and a communication network 108. The controller 104 is configured to control the operational parameters of the machine tool 102 based on the inputs received from the apparatus 106.

[0041] The apparatus 106 is configured to determine the optimum acceleration and deceleration values of the machine tool 102 based on the real-time loading conditions of the machine. The apparatus 106 uses a machine learning model 210 that is trained using machine tool 102 data determine the optimum acceleration and deceleration values corresponding to the obtained real-time loading conditions of the machine tool 102. The determined optimum acceleration and deceleration values of the machine tool 102 is provided as an input to the controller 104 which further operates the machine tool 102 based on the input.

[0042] The apparatus may be deployed as an edge computing device configured to simulate the multiphysics model in a digital environment and analyze the simulation to obtain the operational parameters of the machine tool operating at different loading conditions.

[0043] The machine learning model 210 is trained on the remote server 1 10 using the data related to the operating conditions of the machine tool 102. The remote server 110 refers to a computer or networked device that may reside at a location separate from the apparatus 106, providing computational resources, data storage, or specific services through a network connection, typically the Internet or a private intranet. It can host various services, such as data storage, web applications, analytics, and machine learning model 210, enabling centralized data processing and scalable resource allocation.

[0044] The communication network 108 enables bi-directional communication between the apparatus 106, remote server 1 10, and the controller 104. The communication network 108 may include, but are not limited to, any one or more different types of networks such as, for example, cable networks, public networks (e.g., the Internet), private networks (e.g., frame-relay networks), wireless networks, cellular networks, telephone networks (e.g., a public switched telephone network), cloud based networks, or any other suitable private or public packet switched or circuit switched networks. Such network(s) may have any suitable communication range associated therewith and may include, for example, global networks (e.g., the Internet), metropolitan area networks (MANs), wide area networks (WANs), local area networks (LANs), or personal area networks (PANs).

[0045] The "remote server" refers to a computing device or system that may be located at a different physical location from the apparatus. This server is accessible over a network, such as the internet or an intranet, and is responsible for training machine learning model, processing requests, storing data, and providing services or resources to the apparatus. As an example, the remote server may be a cloud computing environment.

[0046] FIG. 2 illustrates a block diagram of an apparatus 106 for optimizing acceleration and deceleration values in a machine tool 102, according to one embodiment of the present invention. The apparatus 106 may include a processing unit 202, one or more memory 204, a database 206, a network interface 214, an input unit 216, and an output unit 218. The apparatus 106 may further include one or more buses 220 that functionally couple various components of the apparatus 106. The memory 204 may include volatile memory (memory that maintains its state when supplied with power) such as random access memory (RAM) and / or non-volatile memory (memory that maintains its state even when not supplied with power) such as read-only memory (ROM), flash memory, ferroelectric RAM (FRAM), and so forth. Persistent data storage, as that term is used herein, may include non-volatile memory. In certain example embodiments, volatile memory may enable faster read / write access than non-volatile memory. However, in certain other example embodiments, certain types of non-volatile memory (e.g., FRAM) may enable faster read / write access than certain types of volatile memory. In certain example, the database may be equivalent to the memory. In various implementations, the memory may include multiple different types of memory such as various types of static random access memory (SRAM), various types of dynamic random access memory (DRAM), various types of unalterable ROM, and / or writeable variants of ROM such as electrically erasable programmable read-only memory (EEPROM), flash memory, and so forth. The memory may include main memory as well as various forms of cache memory such as instruction cache(s), data cache(s), translation lookaside buffer(s) (TLBs), and so forth. Further, cache memory such as a data cache may be a multi-level cache organized as a hierarchy of one or more cache levels (LI, L2, etc.).

[0047] The memory 204 may include a module stored in the form of machine-readable instructions executable by the one or more processing unit 202. The memory 204 may include multiple modules such as multi-physics model 208, machine learning model 210, and feedback module 212. The multiple modules interact with each other for optimizing acceleration and deceleration values in a machine tool 102.

[0048] The database 206 may include removable storage and / or non-removable storage including, but not limited to, magnetic storage, optical disk storage, and / or tape storage. The database 206 may provide non-volatile storage of computer-executable instructions and other data.

[0049] The database 206 may store computer-executable code, instructions, or the like that may be loadable into the memory and executable by the processing unit 202 to cause the processing unit 202 to perform or initiate various operations such as the operations required for generating recommendations for optimizing a process. The database may store historical data of operational parameters comprising control variables and critical parameters associated with the process in the form of tables or structured knowledge graphs and that may be copied to memory for use by the processing unit 202 during the execution of the computer-executable instructions. Moreover, output data generated as a result of execution of the computer-executable instructions by the processing unit 202 may be stored initially in memory and may ultimately be copied to the database for non-volatile storage. More specifically, the database 206 is configured to access the memory; and one or more program module, applications, engines, managers, computer-executable code, scripts, or the like such as, for example, the various modules of the memory such as multi-physics model 208, machine learning model 210, and feedback module 212. Any of the components depicted as being stored in the database may include any combination of software, firmware, and / or hardware. The software and / or firmware may include computer-executable instructions (e.g., computer-executable program code) that may be loaded into the memory for execution by one or more of the processing units 202 to perform any of the corresponding operations described earlier.

[0050] The processing unit 202 may be configured to access the memory and execute computerexecutable instructions loaded therein. For example, the processing unit 202 may be configured to execute computer-executable instructions of the various program module, applications, engines, managers, or the like of the multi-physics model 208, machine learning model 210, and feedback module 212 to cause or facilitate various operations to be performed in accordance with one or more embodiments of the disclosure. The processing unit 202 may include any suitable processing unit 202 capable of accepting data as input, processing the input data in accordance with stored computer-executable instructions, and generating output data. The processing unit 202 may include any type of suitable processing unit 202 202 including, but not limited to, a central processing unit 202, a microprocessor, a Reduced Instruction Set Computer (RISC) microprocessor, a Complex Instruction Set Computer (CISC) microprocessor, a microcontroller 104, an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a System 100 -on-a-Chip (SoC), a digital signal processor (DSP), and so forth. Further, the processing unit 202 may have any suitable microarchitecture design that includes any number of constituent components such as, for example, registers, multiplexers, arithmetic logic units, cache controller 104s for controlling read / write operations to cache memory, branch predictors, or the like. The microarchitecture design of the processing unit 202 may be capable of supporting any of a variety of instruction sets.

[0051] The processing unit 202 is configured to obtain data relating to operational parameters of the machine tool 102 from a multi-physics model 208 of the machine tool 102. The operational parameters include acceleration, deceleration, and jerk of the machine tool 102. The operational parameters of the machine tool 102 may be obtained from a multi-physics model 208 of the machine tool 102. The multi-physics model 208 of the machine tool 102 may be created using a design program and simulated at different loading conditions. The operational parameters of the machine tool 102 for different loading conditions may be recorded and further retrieved by the processing unit 202. The processing unit 202 is configured to train a machine learning model 210 using the obtained data relating to operational parameters of the machine tool 102. The machine learning model 210 is trained to determine the optimum acceleration and deceleration of the machine tool 102 for different loading conditions of the machine tool 102. The loading conditions may include weight of the workpiece, orientation of the workpiece and load distribution on machine table.

[0052] The processing unit 202 is configured to validate the machine learning model 210 using real-time operational parameters of the machine tool 102 measured using a plurality of sensors deployed on the machine tool 102. The validation of machine learning model 210 ensures that the determined optimum acceleration and deceleration of the machine tool 102 is accurate.

[0053] The processing unit 202 is configured to obtain real-time loading condition of the machine tool 102 using vibrations sensor and strain gauges deployed on the machine tool 102 to measure the loading conditions of the machine tool 102.

[0054] The processing unit 202 is configured to determine the optimum acceleration and deceleration values corresponding to the obtained real-time loading conditions of the machine tool 102.

[0055] The processing unit 202 further is configured to set using a controller 104 the optimum acceleration and deceleration values determined by the machine learning model 210 in the machine tool 102. Thus, the optimum acceleration and deceleration values are automatically set on the machine tool 102 based on the real-time loading conditions of the machine tool 102.

[0056] The input unit 216 and the output unit 218 may facilitate the receipt of input information by the various modules from one or more I / O devices as well as the output of information from the modules to the one or more I / O devices. The I / O devices may include any of a variety of components such as a display or a display screen having a touch surface or a touchscreen; an audio output device for producing sound, such as a speaker; an audio capture device, such as a microphone; an image and / or video capture device, such as a camera; a haptic unit; and so forth. The I / O devices may further include, for example, any number of peripheral devices such as data storage devices, printing devices, and so forth.

[0057] The network interface 214 may include communication links and associated networking devices (e.g., link-layer switches, routers, etc.) for transmitting network traffic over any suitable type of medium including, but not limited to, coaxial cable, twisted-pair wire (e.g., twisted-pair copper wire), optical fiber, a hybrid fiber-coaxial (HFC) medium, a microwave medium, a radio frequency communication medium, a satellite communication medium, or any combination thereof.

[0058] The bus 220 may include at least one of a system 100 bus, a memory bus, an address bus, or a message bus, and may permit the exchange of information (e.g., data (including computer- executable code), signaling, etc.) between various components of the apparatus 106. The bus may include, without limitation, a memory bus or a memory controller 104, a peripheral bus, an accelerated graphics port, and so forth.

[0059] FIG. 3 is a flowchart of a method for optimizing acceleration and deceleration values in the machine tool 102, according to an embodiment of the present invention. At step 302, the processing unit 202 obtains data relating to operational parameters of the machine tool 102 from a multi-physics model 208 of the machine tool 102. The operational parameters include acceleration, deceleration, and jerk of the machine tool 102.

[0060] At step 304, the obtained data relating to the operational parameters of the machine tool 102 is used to train the machine learning model 210. The machine learning model 210 is trained to determine the optimum acceleration and deceleration of the machine tool 102 for different loading conditions of the machine tool 102. The loading conditions of the machine tool 102 includes weight of the workpiece, orientation of the workpiece and load distribution on machine table.

[0061] At step 306, the machine learning model 210 is validated by the processing unit 202 using realtime operational parameters of the machine tool 102. The real-time operational parameters of the machine tool 102 are measured using a plurality of sensors deployed on the machine tool 102. The sensors could include motion sensor, speed sensor, vibration sensor, temperature sensor so on and so forth deployed at various regions of the machine tool 102.

[0062] At step 308, the real-time loading conditions of the machine tool 102 is obtained using vibrations sensor and strain gauges deployed on the machine tool 102. The vibrations sensor and strain gauges are configured to measure the loading conditions of the machine tool 102.

[0063] At step 310, the machine learning model 210 determines the optimum acceleration and deceleration values corresponding to the obtained real-time loading conditions of the machine tool 102. The optimum acceleration and deceleration values are determined to minimize the wear and tear of the components of the machine tool 102 thereby increasing the efficiency of the machine tool 102. As an example, the machine learning model using the operational data such as type of machine tool, load in machine bed, load distribution in axes, vibration during motion, jerk in motion, and electric current drawn by motor determines the optimum acceleration, deceleration, jerk, and time constants to operate the machine tool.

[0064] Prediction of acceleration and deceleration is based on categorical data such as machine type, kinematic configuration, loading condition or the like, and numerical data such as inertia, current, vibration, load distribution or the like. Based on the input data, tree based regressor model or Deep Neural network is selected as the type of machine learning model suitable for determining optimum acceleration and deceleration values.

[0065] At step 312, the controller 104 sets the optimum acceleration and deceleration values determined by the machine learning model 210 in the machine tool 102. Thus, the optimum acceleration and deceleration values for a given loading condition is set automatically in the machine tool 102.

[0066] At step 314, feedback is received from the user using a feedback module 212 based on the determined optimum acceleration and deceleration values of the machine tool 102. The feedback may be in the form of a text query describing the accuracy of the determined acceleration and deceleration values.

[0067] At step 316, the processing unit 202 updates the machine learning model 210 based on the feedback received from the user. Therefore, the machine learning model 210 is additionally improved using human inputs to accurately determine the optimum acceleration and deceleration values.

[0068] FIG. 4 is a flowchart of a method for obtaining data relating to operational parameters of the machine tool 102 from a multi-physics model 208 of the machine tool 102, according to an embodiment of the present invention. At step 402, the multi-physics model 208 of the machine tool 102 is created by the processing unit 202 using kinematic models and electrical models of the components of the machine tool 102. As an example, the multi-physical model of the machine tool 102 may be created using a Computer-aided design (CAD) software.

[0069] As an example, the electrical modeling of the motor is developed to test the performance of the motor when subjected to various loading conditions. The modeling is done with required parameters like stator, rotor, no of poles, air gap so on and so forth. Similarly, kinematic models for different components of the machine tool are created and coupled to the electrical models to create the multi-physics model of the machine tool.

[0070] In an embodiment, the multi-physics model 208 of the machine tool 102 is created for different configurations of the same machine tool 102 by altering design aspects of the machine tool 102. Different configurations of the machine tool may include worktable design, tool guideway configuration, type of electrical drives so on and so forth.

[0071] At step 404, the multi-physics model 208 of the machine tool 102 is calibrated using Bayesian calibration to optimize design parameters of the multi-physics model 208 of the machine tool 102. Bayesian Calibration is used to refine the multi-physics model based on the observed real-time data. This method employs Bayes' theorem to update the probability distribution of the model parameters, thereby enhancing the model's predictive accuracy. At step 406, the multi-physics model 208 of the machine tool 102 is optimized using the processing unit 202 based on the calibration of the multi-physics model 208. In an embodiment, the multi-physics model 208 is optimized using a deep neural network model configured to determine optimum design parameters of the machine tool 102. The deep neural network model is trained using data relating to modelling of the machine tool 102. Further, the deep neural network model is validated using the design parameters data obtained from the machine tool 102.

[0072] At step 408, the multi-physics model 208 of the machine tool 102 is simulated for different loading conditions of the machine tool 102 using the processing unit 202. In an embodiment, the simulation of multi-physics model of the machine tool 102 comprises static loading condition and dynamic loading condition of the machine tool 102.

[0073] In the static analysis, the workpiece may be disposed on the table of the machine tool and static load analysis is performed. The stress-strain distribution of the workpiece on the table and its impact on the various components of the machine is analyzed under static conditions.

[0074] The dynamic analysis is performed by simulating the machine axis movements with different rates of acceleration and deceleration to observe the impact caused by these factors on the components of the machine tool.

[0075] At step 410, data relating to operational parameters of the machine tool 102 is obtained from the simulation of the multi-physics model 208 of the machine tool 102. Thus, the operational parameters of the machine tool 102 are obtained from a digital multi-physics model 208 of the machine tool 102.

[0076] Operational data of the machine tool 102 can be easily obtained for multiple configurations and settings of the machine tool 102 just by modifying the multi-physics model 208 of the machine tool 102 accordingly.

[0077] FIG. 5 is a flowchart of a method for monitoring zones of the machine tool 102 that are subject to excessive vibrations, according to an embodiment of the present invention. At step 502, the processing unit 202 simulates the multi-physics model 208 of the machine tool 102 for different loading conditions.

[0078] At step 504, the processing unit 202 identifies zones on the machine tool 102 that are subject to excessive vibrations based on the simulation of the multi-physics model 208 of the machine tool 102.

[0079] At step 506, vibrations at the identified zones on the machine tool 102 that are subject to excessive vibrations are monitored using vibration sensors that are deployed at the identified zones. Additionally, the processing unit may identify any abnormal vibrations, and movement on the machine tool using the sensors that are deployed.

[0080] At step 508, if the vibration at the identified zones exceeds a predefined threshold limit the user is notified. The user may predefine the vibration threshold that affects the components of the machine tool. Additionally, the machine learning model may suggest a suitable corrective action for rectifying the excessive vibrations in the machine tool. The controller may set the suggested corrective actions in the machine tool accordingly.

[0081] Thus, the method offers a technical advancement, wherein the sensors monitor the vibrations in the machine tool and accordingly notifies the user in case of any abnormal vibrations from the machine tool thereby enabling earlier detection of abnormalities and preventing potential failure of components of the machine tool.

[0082] Once the method for optimizing the acceleration and deceleration values in a machine tool is implemented, the system may automatically determine the real-time loading conditions of the machine tool using sensors deployed on the machine tool. Further, the machine learning model automatically determines the optimum acceleration and deceleration values corresponding to the real-time loading conditions of the machine tool. The controller further sets the acceleration and deceleration values to the determined optimum values. Thus, the present invention minimizes the wear and tear of the components caused by improper acceleration and deceleration of the machine tool.

[0083] While the invention has been illustrated and described in detail with the help of a preferred embodiment, the invention is not limited to the disclosed examples. Other variations can be deducted by those skilled in the art without leaving the scope of protection of the claimed invention.

[0084] List of references

[0085] 100 - System for optimizing acceleration and deceleration values in a machine tool

[0086] 102 - Machine tool

[0087] 104 - Controller

[0088] 106 - Apparatus for optimizing acceleration and deceleration values in a machine tool

[0089] 108 - Communication network

[0090] 202 - Processing unit

[0091] 204 - Memory

[0092] 206 - Database

[0093] 208 - Multi-physics model

[0094] 210 - Machine learning model

[0095] 212 - Feedback module

[0096] 214 - Network interface

[0097] 216 - Input unit

[0098] 218 - Output unit

[0099] 220 - Bus

[0100] 300 - flowchart 300 of a method for optimizing acceleration and deceleration values in the machine tool

[0101] 400 - flowchart of a method 400 for obtaining data relating to operational parameters of the machine tool from a multi-physics model of the machine tool

[0102] 500 - flowchart of a method 500 for monitoring zones of the machine tool that are subject to excessive vibrations

Claims

Patent claimsWhat is claimed is:1 . A method for optimizing acceleration and deceleration values in a machine tool (102), wherein the method comprises: obtaining, by a processing unit (202), data relating to operational parameters of the machine tool (102) from a multi-physics model (208) of the machine tool (102), wherein the operational parameters include acceleration, deceleration, and jerk of the machine tool (102); training a machine learning model (210) using the obtained data relating to operational parameters of the machine tool (102) to determine the optimum acceleration and deceleration of the machine tool (102) for different loading conditions of the machine tool (102), wherein loading conditions include weight of the workpiece, orientation of the workpiece and load distribution on machine table; validating the machine learning model (210), by the processing unit (202), using real-time operational parameters of the machine tool (102) measured using a plurality of sensors deployed on the machine tool (102); obtaining, by the processing unit (202), real-time loading condition of the machine tool (102) using vibrations sensor and strain gauges deployed on the machine tool (102), wherein the vibrations sensor and strain gauges are configured to measure the loading conditions of the machine tool (102); determining, using the machine learning model (210), the optimum acceleration and deceleration values corresponding to the obtained real-time loading conditions of the machine tool (102); and setting, by a controller (104), the optimum acceleration and deceleration values determined by the machine learning model (210) in the machine tool (102).

2. The method according to claim 1 , wherein the obtaining data relating to operational parameters of the machine tool (102) from a multi-physics model (208) of the machine tool (102) comprises: creating, using the processing unit (202), the multi-physics model (208) of the machine tool (102) using kinematic models and electrical models of the components of the machine tool (102); calibrating the multi-physics model (208) of the machine tool (102) using Bayesian calibration to optimize design parameters of the multi-physics model (208) of the machine tool (102);optimizing the multi-physics model (208) of the machine tool (102), using the processing unit (202), based on the calibration of the multi-physics model (208); simulating, using the processing unit (202), the multi-physics model (208) of the machine tool (102) for different loading conditions of the machine tool (102); and obtaining, using the processing unit (202), data relating to operational parameters of the machine tool (102) from the simulation of the multi-physics model (208) of the machine tool (102).

3. The method according to any of the preceding claims, wherein the multi-physics model (208) of the machine tool (102) is optimized using a deep neural network model configured to determine optimum design parameters of the machine tool (102), wherein the deep neural network model is: trained using data relating to modelling of the machine tool (102); and validated using the design parameters data obtained from the machine tool (102).

4. The method according to any of the preceding claims, wherein the method further comprises: receiving, by the processing unit (202), feedback input from a user to optimize the machine learning model (210) based on the set optimum acceleration and deceleration values in the machine tool (102); and updating the machine learning model (210), using the processing unit (202), based on the feedback input received from the user.

5. The method according to any of the preceding claims, the method comprises: identifying, by the processing unit (202), zones on the machine tool (102) that are subject to excessive vibrations based on the simulation of the multi-physics model (208) of the machine tool (102); monitoring, using vibration sensors, vibrations at the identified zones on the machine tool (102) that are subject to excessive vibrations by deploying the vibration sensors at the identified zones; and notifying the user, if the vibrations at the identified zones exceeds a predefined threshold limit.

6. The method according to any of the preceding claims, wherein the simulation of multi-physics model of the machine tool (102) comprises static loading condition and dynamic loading condition of the machine tool (102).

7. The method according to any of the preceding claims, wherein the multi-physics model (208) of the machine tool (102) is created for different configurations of the same machine tool (102) by altering design aspects of the machine tool (102).

8. An apparatus (106) for optimizing acceleration and deceleration values in the machine tool (102), wherein the apparatus (106) comprises: one or more processing units (202); and a memory communicatively coupled to the one or more processing units (202), the memory comprising a module stored in the form of machine-readable instructions executable by the one or more processing units (202), wherein the module is configured to perform the method steps according to claims 1 to 7.

9. A system for optimizing acceleration and deceleration values in the machine tool (102), wherein the system comprises: a remote server (110), wherein the machine learning is trained in the remote server (1 10) using the data obtained from the multi-physics model (208) of the machine tool (102); an apparatus (106) for optimizing acceleration and deceleration values in the machine tool (102) according to claim 8, wherein the machine learning model (210) is deployed in the apparatus (106) to determine optimum acceleration and deceleration values of the machine tool (102); and a controller (104) communicatively connected with the apparatus (106), wherein the controller (104) is configured to: receive the determined optimum acceleration and deceleration values; and control the machine tool (102) by setting the optimum acceleration and deceleration values.

10. A computer-program product, having computer-readable instructions stored therein, that when executed by a processing unit (202), cause the processing unit (202) to perform method steps according to any of the claims 1 to 7.11 . A computer readable medium on which program code sections of a computer program are saved, the program code sections being loadable into and / or executable in a system to make the system execute the method steps according to any of the claims 1 to 7 when the program code sections are executed in the system.

Images