Systems and methods for vibration analysis

Abstract

A system and method for providing anomaly diagnosis for a mechanical device having one or more components. A sensor system having one or more sensor devices detects movement / vibration of one or more observed components of a mechanical device. The control system determines vibration measurements for the one or more components based on the detected motion / vibration of the one or more components. Abnormal operation of one or more components is determined using one or more machine learning (ML) and / or artificial intelligence (AI) techniques by comparing a determined vibration measurement of an observed component to an expected normal vibration measurement of the component during operation of the mechanical equipment. An abnormal operation is determined when the determined vibration measurement of the observed component exceeds its expected normal vibration measurement by a threshold.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. patent application serial number 63 / 527,851 filed on July 20, 2023, which is incorporated herein by reference in its entirety. Technical Field

[0003] The illustrated embodiments relate generally to the field of vibration analysis, and more particularly, but not by way of limitation, to analyzers and control systems, and methods of determining abnormal operation of mechanical equipment through vibration analysis using artificial intelligence (AI) and / or machine learning (ML) techniques. Background Art

[0004] The reliable mechanical operation and condition of appliances, machines, and equipment (e.g., industrial appliances) is essential not only to the economic success of an operation or business, but also to the safety of personnel, property, and the equipment itself. Such operations and businesses may include, for example, factories, refineries, hospitals, storage facilities, data centers, retail establishments, and manufacturing facilities. Therefore, regular and routine maintenance and testing of the mechanical operation and condition of such equipment is necessary and critical. Similarly, when equipment parts become worn or damaged, these conditions should be quickly identified and corrected as necessary.

[0005] Unfortunately, while regular and routine maintenance is necessary and critical, it is often time consuming, requires specialized knowledge, often requires specialized technicians and equipment, and is expensive and disruptive. Depending on the operation or process (e.g., manufacturing), the time that equipment is offline to perform testing can interrupt production schedules and harm overall business operations. There is a significant risk of inadvertently damaging equipment during disassembly and reassembly (often required) for testing or performing tests incorrectly. Any unexpected or mishandled step can unnecessarily extend equipment downtime, resulting in operational losses. In addition, many test procedures are inefficient, imprecise, improperly performed, and can result in the replacement of parts that do not need to be replaced. All of these issues can result in significant financial losses.

[0006] Similarly, testing itself can be expensive, separate from the other issues just discussed. For a variety of reasons, businesses often do not have the financial resources to hire technicians to perform the required testing, and the cost of hiring third-party contractors can also be financially challenging. Yet, such testing is critical to the economic viability of operations and to providing a safe operating environment to protect life and property.

[0007] Furthermore, such performance testing of the mechanical operation of the equipment may be inaccurate and lead to erroneous conclusions. For example, testing the mechanical operation of large mechanical equipment (such as grinding equipment) is difficult, time-consuming, and the results may be incorrect. Summary of the invention

[0008] Objects and advantages of the exemplary embodiments described below will be set forth in and apparent from the following description. Additional advantages of the illustrated embodiments will be realized and attained by the devices, systems and methods particularly pointed out in the written description and claims hereof as well as the appended drawings.

[0009] To achieve these and other advantages, and in accordance with the purposes of the illustrated embodiments, in one aspect, a system and method for providing abnormal diagnosis of a mechanical device having one or more components is described. A sensor system having one or more sensor devices detects movement / vibration of one or more observed components of the mechanical device during operation of the mechanical device. A control system is operably coupled to the sensor system for receiving detected movement / vibration data of one or more observed components of the mechanical device from the sensor system. The control system is configured and operated to determine vibration measurements of one or more components based on the detected movement / vibration of the one or more components. One or more machine learning (ML) and / or artificial intelligence (AI) techniques are preferably used to determine abnormal operation of one or more components by comparing the determined vibration measurement of the observed component with the expected normal vibration measurement of the component during operation of the mechanical device. Abnormal operation is determined when the determined vibration measurement of the observed component exceeds a threshold value of its expected normal vibration measurement. The control system is preferably further operable and configured to provide a notification of abnormal operation of one or more components when it is determined that one or more components have abnormal operation based on their vibration measurement.

[0010] For example, it should be understood and appreciated that monitoring / determining how the vibration of one or more components of a mechanical device increases with speed promotes optimal performance of the mechanical device. For example, the highest output rate that does not cause excessive wear on the equipment can be found and used to extend the life of the equipment / machinery in the factory. In one aspect of the illustrated embodiment, using a non-contact sensor to measure vibration is preferable to wiring and installing accelerometers throughout the factory. For example, image capture can be used to monitor large areas of a factory and see multiple vibration points at the same time (e.g., it can detect vibrations in unexpected locations).

[0011] According to certain illustrated embodiments, images of one or more components of a mechanical device may be captured and magnified for use with AI / ML techniques to optimize the performance of the mechanical device and also predict possible failures of equipment that affect production. An example market segment is metals, minerals, and mining, with an example field being the grinding and concentration phase of the market segment.

[0012] According to the illustrated embodiment, several key points to consider are the wear associated with one or more components of the mechanical equipment, which is a key issue associated with vibration, and if identified early, preventive maintenance can be used to manage better production cycles associated with the mechanical equipment. Controlling vibration can generally extend the life of the machine and optimize its production performance.

[0013] With respect to the use of camera sensor components to detect vibrations, it is possible to view a wider area in order to then select multiple points and measure vibrations at parallel points. For example, image magnification can be used to amplify deviations in order to find faults. The deflection of a single pixel can be measured and used to measure vibration frequency and amplitude. Vibrations may be associated with process automation control settings for mechanical equipment used to extend the life of the equipment. In addition, by combining vibration measurements from camera sensors with alarms, equipment operators can be notified that conditions are deteriorating so that the operator can take preventive measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Therefore, those skilled in the art to which the present invention pertains will readily understand how to make and use the apparatus and method of the present invention without undue experimentation, and preferred illustrative embodiments thereof will be described in detail below with reference to certain drawings, wherein:

[0015] Figure 1 An example communication network for use with one or more of the illustrated embodiments is shown;

[0016] Figure 2 An example network device / node for use with one or more of the illustrated embodiments is shown;

[0017] Figure 3 A schematic diagram depicting an artificial intelligence (AI) device for use with one or more illustrated embodiments is shown;

[0018] Figure 4 A schematic diagram depicting an AI server for use with one or more illustrated embodiments is shown;

[0019] Figure 5 shows a system-level schematic diagram depicting certain system components used with one or more illustrated embodiments; and

[0020] Figure 6 A flow chart depicting a method of operation according to one or more illustrated embodiments is shown. DETAILED DESCRIPTION

[0021] The illustrated embodiments are now described more fully with reference to the accompanying drawings, wherein like reference numerals denote similar structural / functional features. The illustrated embodiments are not limited in any way to what is shown, as the illustrated embodiments described below are merely exemplary and, as understood by those skilled in the art, may be implemented in various forms. Therefore, it should be understood that any structural and functional details disclosed herein should not be interpreted as limiting, but merely as a basis for the claims, and as a representation to teach those skilled in the art to use the discussed embodiments in various ways. In addition, the terms and phrases used herein are not intended to be limiting, but rather to provide an understandable description of the illustrated embodiments.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which these illustrated embodiments belong. Although any methods and materials similar or equivalent to those described herein can also be used in the practice or testing of the illustrated embodiments, exemplary methods and materials are now described.

[0023] It must be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a stimulus" includes a plurality of such stimuli and reference to "a signal" includes reference to one or more signals and equivalents thereof known to those skilled in the art, and so forth.

[0024] It should be understood that the illustrated embodiments discussed below preferably include software algorithms, programs or codes residing on a computer usable medium having control logic for enabling execution on a machine having a computer processor. The machine typically includes a memory storage configured to provide an output of the execution of the computer algorithm or program.

[0025] As used herein, the term "software" is meant to be synonymous with any code or program that can be in a processor of a host computer, regardless of whether the implementation is in hardware, firmware, or as a software computer product available on a disk, memory storage device, or for downloading from a remote machine. The embodiments described herein include such software to implement the above equations, relationships, and algorithms. Based on the above embodiments, those skilled in the art will understand more features and advantages of the illustrated embodiments. Therefore, the illustrated embodiments are not limited to what has been specifically shown and described, except as indicated by the appended claims.

[0026] Turning descriptively now to the drawings, wherein like reference numerals represent like elements throughout the several views, Figure 1An exemplary communication network 100 is depicted in which the embodiments shown below can be implemented. It should be understood that the communication network 100 is a collection of geographically distributed nodes interconnected by communication links and network segments for transmitting data between terminal nodes, such as personal computers, workstations, smart phone devices, tablet computers, televisions, sensors and / or other devices, such as cars, etc. Many types of networks are available, from local area networks (LANs) to wide area networks (WANs). LANs typically connect nodes via dedicated private communication links located in the same physical location (such as a building or campus). On the other hand, WANs typically connect geographically dispersed nodes via long-distance communication links, such as public carrier telephone lines, optical paths, synchronous optical networks (SONET), synchronous digital hierarchy (SDH) links, or power line communications (PLC), etc.

[0027] Figure 1 1 is a schematic block diagram of an exemplary communication network 100, which includes nodes / devices 101-108 (e.g., intelligent computing device 101, sensor 102, client computing device 103, smart phone device 105, web server 106, router 107, switch 108, database, etc.) interconnected by various communication methods. For example, link 109 can be a wired link or can include a wireless communication medium, in which certain nodes communicate with other nodes, such as based on distance, signal strength, current operating state, location, etc. In addition, as will be understood by those skilled in the art, each device can communicate data packets (or frames) 142 with other devices using predefined network communication protocols (e.g., various wired protocols and wireless protocols, etc.) where appropriate. In this context, the protocol consists of a set of rules that define how nodes interact with each other. Those skilled in the art will understand that any number of nodes, devices, links, etc. can be used in a computer network, and the views shown herein are for simplicity. In addition, although embodiments are shown herein with reference to a general network cloud, the description herein is not limited thereto and can be applied to hardwired networks.

[0028] As will be appreciated by those skilled in the art, aspects of the illustrated embodiments may be embodied as systems, methods, or computer program products. Thus, aspects of the illustrated embodiments may take the form of a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, which are generally referred to herein as "circuits," "modules," or "systems." In addition, aspects of the illustrated embodiments may take the form of a computer program product contained in one or more computer-readable media having computer-readable program code thereon.

[0029] Any combination of one or more computer-readable media may be utilized. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or apparatus, or any suitable combination of the foregoing. More specific examples (non-exhaustive) of computer-readable storage media would include the following: an electrical connector having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this article, a computer-readable storage medium may be any tangible medium capable of containing or storing a program used by or in conjunction with an instruction execution system, device or apparatus. A computer-readable signal medium may include a propagated data signal containing a computer-readable program code, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including but not limited to electromagnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0030] The program code included in the computer readable medium can use any suitable medium to transmit, including but not limited to wireless, wired, fiber optic cable, RF etc. or any suitable combination as mentioned above.The computer program code for performing the operation of the various aspects of the illustrated embodiment can be written with any combination of one or more programming languages, including object-oriented programming languages, such as Java, Smalltalk, C++ etc., and traditional process programming languages, such as " C " programming language or similar programming languages.Program code can be performed completely on the user's computer as an independent software package, partly on the user's computer, partly on the user's computer, partly on the user's computer, partly on a remote computer, or completely on a remote computer or server.In the latter case, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, by using the Internet of an Internet service provider).

[0031] Aspects of the illustrated embodiments are described below with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to the illustrated embodiments. It will be understood that each frame of the flowchart and / or block diagram and the combination of frames in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a computer, a special-purpose computer or other programmable data processing device to produce a machine so that instructions executed by a processor of a computer or other programmable data processing device create a device for implementing the functions / actions specified in one or more frames of the flowchart and / or block diagram.

[0032] These computer program instructions may also be stored in a computer-readable medium, which can direct a computer, other programmable data processing apparatus, or other device to operate in a specific manner so that the instructions stored in the computer-readable medium produce an article of manufacture including instructions for implementing the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0033] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operating steps to be performed on the computer, other programmable apparatus, or other devices, thereby producing a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0034] Figure 2 1 is a schematic block diagram of an example network computing device 200 (e.g., client computing device 103, server 106, etc.) that may be used with one or more embodiments described herein, for example, as one of the nodes shown in network 100, including control system 500 described further below. As described above, in various embodiments, these various devices are configured to communicate with each other in any suitable manner, such as via communication network 100.

[0035] Device 200 is intended to represent any type of computer system capable of executing the teachings of the various illustrated embodiments. Device 200 is merely an example of a suitable system and is not intended to impose any limitations on the scope of use or functionality of the illustrated embodiments described herein. Regardless, computing device 200 is capable of implementing and / or performing any of the functions set forth herein.

[0036] The computing device 200 can operate with numerous other general or special computing system environments or configurations. Examples of well-known computing systems, environments and / or configurations suitable for the computing device 200 include, but are not limited to, personal computer systems, server computer systems, thin clients, fat clients, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, and distributed data processing environments including any of the above systems or devices. The computing device 200 can be described in the general context of computer system executable instructions such as program modules executed by a computer system. Typically, a program module can include routines, programs, objects, components, logic, data structures, etc. that perform specific tasks or implement specific abstract data types. The computing device 200 can be implemented in a distributed data processing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed data processing environment, program modules can be located in local and remote computer system storage media including memory storage devices. According to the illustrated embodiment, the computing device 200 is configured and operated to utilize vibration measurements received from one or more sensor devices (510) indicating vibrations of one or more components of the mechanical device (520) to determine abnormal operation of the mechanical device (520) through analysis of the vibration measurements.

[0037] The components of device 200 may include, but are not limited to, one or more processors or processing units 216, system memory 228, and a bus 218 that connects various system components including system memory 228 to processor 216. Bus 218 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. As an example and not limitation, such architectures include an industry standard architecture (ISA) bus, a microchannel architecture (MCA) bus, an enhanced ISA (EISA) bus, a video electronics standards association (VESA) local bus, and a peripheral component interconnect (PCI) bus. Computing device 200 typically includes various computer system readable media. Such media can be any available media accessible to device 200, and it includes volatile and non-volatile media, removable and non-removable media.

[0038] The system memory 228 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 230 and / or cache memory 232. The computing device 200 may also include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 234 may be provided for reading from and writing to a non-removable, non-volatile magnetic medium (not shown, and commonly referred to as a "hard drive"). Although not shown, a disk drive for reading from and writing to a removable, non-volatile disk (e.g., a "floppy disk") may be provided, as well as an optical drive for reading from or writing to a removable, non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media). In this case, each may be connected to the bus 218 via one or more data media interfaces. As will be further depicted and described below, the memory 228 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of an embodiment of the illustrated embodiment.

[0039] By way of example and not limitation, a program / utility 240 having a set (at least one) of program modules 215 (e.g., a distribution module), as well as an operating system, one or more application programs, other program modules, and program data may be stored in memory 228. Each or some combination of the operating system, one or more application programs, other program modules, and program data may include an implementation of a network environment. The program modules 215 generally perform the functions and / or methods of the illustrated embodiments as described herein, including analyzing vibration measurements detected from one or more sensor devices (510) indicating vibration of one or more components of the mechanical device (520) to preferably determine abnormal operation of the mechanical device (520) in real time.

[0040] The device 200 may also communicate with one or more external devices 214, such as a keyboard, a pointing device, a display 224, etc.; one or more devices that enable a user to interact with the computing device 200; and / or any device that enables the computing device 200 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 222. In addition, the device 200 may communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), and / or a public network (e.g., the Internet) via a network adapter 220. As shown, the network adapter 220 communicates with other components of the computing device 200 via a bus 218. It should be understood that, although not shown, other hardware and / or software components may be used in conjunction with the device 200. Examples include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archiving storage systems, etc.

[0041] Figure 1 and Figure 2 It is intended to provide a brief general description of an illustrative and / or suitable exemplary environment in which the embodiments described below may be implemented. Figure 1 and 2 The examples of suitable environments are not intended to impose any limitations on the structure, scope of use, or functionality of the illustrated embodiments. A specific environment should not be interpreted as having any dependency or requirement on any one of the components or combinations thereof shown in the exemplary operating environment. For example, in some cases, one or more elements of the environment may be considered unnecessary and omitted. In other cases, one or more other elements may be considered necessary and added.

[0042] It should be understood that the embodiments described herein are preferably provided with self-learning / artificial intelligence (AI) for analyzing vibration data received from one or more sensor devices (510) indicating vibration of one or more components of the mechanical device (520) to preferably determine abnormal operation of the mechanical device (520) in real time. Therefore, preferably, integrated into the control system 500 (having one or more components of the computer system 200) connected to multiple external databases / data sources is an AI system (e.g., an expert system) that implements machine learning and artificial intelligence algorithms to perform one or more of the above-mentioned tasks, including analyzing vibration data received from one or more sensor devices (510) indicating vibration of one or more components of the mechanical device (520) to determine abnormal operation of the mechanical device (520) through analysis of vibration measurements. For example, the AI ​​system may include two subsystems: a first subsystem that learns from historical data; and a second subsystem for identifying and recommending one or more parameters or methods based on the learning. It should be understood that although the AI ​​system may be described as two different subsystems, the AI ​​system may also be implemented as a single system that combines the functions and features described with respect to the two subsystems.

[0043] According to the illustrated embodiments described herein, artificial intelligence refers to a field that studies artificial intelligence or methods for making artificial intelligence, and machine learning refers to a field that defines various problems handled in the field of artificial intelligence and studies methods for solving various problems. Machine learning is defined as an algorithm that enhances the performance of a specific task through stable experience with the specific task.

[0044] Also according to the illustrated embodiment, an artificial neural network (ANN) is a model used in machine learning, and can represent an overall model of problem-solving capabilities consisting of artificial neurons (nodes) connected by synapses to form a network. An artificial neural network can be defined by a connection pattern between neurons in different layers, a learning process for updating model parameters, and an activation function for generating output values. An artificial neural network can include an input layer, an output layer, and optionally one or more hidden layers. Each layer includes one or more neurons, and the artificial neural network can include synapses linking neurons to neurons. In an artificial neural network, each neuron can output a function value of an activation function of an input signal, a weight, and a bias input through a synapse.

[0045] Model parameters refer to parameters determined by learning, and include weight values ​​of synaptic connections and deflections of neurons. Hyperparameters refer to parameters to be set in a machine learning algorithm before learning, and include learning rate, number of repetitions, minimum batch, and initialization function. The purpose of artificial neural network learning may be to determine model parameters that minimize the loss function. The loss function may be used as an indicator for determining optimal model parameters during the learning process of the artificial neural network. According to the learning method, machine learning can be divided into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning may refer to a method of learning an artificial neural network in a state where a label for learning data is given, and the label may represent the correct answer (or result value) that the artificial neural network must infer when the learning data is input to the artificial neural network. Unsupervised learning may refer to a method of learning an artificial neural network in a state where no label for learning data is given. Reinforcement learning may refer to a learning method in which an agent defined in a certain environment learns to select a behavior or sequence of behaviors that maximizes cumulative compensation in each state.

[0046] Machine learning implemented as a deep neural network (DNN) including a plurality of hidden layers in an artificial neural network is also called deep learning, and deep learning is a part of machine learning.

[0047] Figure 3 An AI device 300 is shown in accordance with an embodiment of the illustrated embodiment. According to the illustrated embodiment, the AI ​​device 300 may be implemented by a control system 500 operably coupled to one or more sensor devices 510 configured to detect vibration measurements associated with a mechanical device 520, as further described herein.

[0048] Reference now Figure 3 , combined with Figure 1 and Figure 2 According to the illustrated embodiments described herein, the AI ​​device 300 is operably connected to the computing device 200 or integrated with the computing device 200. The AI ​​device 300 preferably includes a communication unit 310, an input unit 320, a learning processor 330, a sensing unit 340, an output unit 350, a memory 370, and a processor 380. The communication unit 310 can send and receive data to and from external devices such as other AI devices 300a to 300e and the AI ​​server 400 by using wired / wireless communication technology. For example, the communication unit 310 can send and receive sensor information, user input, learning models, and control signals to and from external devices.

[0049] The communication technology used by the communication unit 310 preferably includes GSM (Global System for Mobile Communications), CDMA (Code Division Multiple Access), LTE (Long Term Evolution), 5G, WLAN (Wireless Local Area Network), Wi-Fi (Wireless Fidelity), Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), ZigBee, NFC (Near Field Communication), etc.

[0050] The input unit 320 may acquire various data, including but not limited to vibration measurements received from one or more sensor devices (510). The input unit 320 may acquire learning data for model learning and input data to be used when obtaining output by using the learning model. The input unit 320 may acquire raw input data. In this case, the processor 380 or the learning processor 330 may extract input features by preprocessing the input data. The learning processor 330 may learn a model composed of an artificial neural network by using the learning data. The learned artificial neural network may be referred to as a learning model. The learning model may be used to infer the result value of new input data instead of the learning data, and the inferred value may be used as a basis for determining whether to perform a specific operation.

[0051] At this time, the learning processor 330 may perform AI processing together with the learning processor 330 of the AI ​​server 400, and the learning processor 330 may include a memory integrated or implemented in the AI ​​device 300. Alternatively, the learning processor 330 may be implemented by using the memory 370, an external memory directly connected to the AI ​​device 300, or a memory stored in an external device. The sensing unit 340 may acquire at least one of internal information about the AI ​​device 300, surrounding environment information about the AI ​​device 300, and user information by using various sensors.

[0052] The output unit 350 preferably includes a display unit for outputting / displaying relevant information to the user according to the illustrated embodiments described herein. The memory 370 preferably stores data supporting various functions of the AI ​​device 300. For example, the memory 370 can store input data acquired by the input unit 320, learning data, learning models, learning history, etc.

[0053] The processor 380 preferably determines at least one executable operation of the AI ​​device 300 based on information determined or generated by using a data analysis algorithm or a machine learning algorithm. The processor 380 can control the components of the AI ​​device 300 to perform the determined operation. To this end, the processor 380 can request, search, receive or utilize data from the learning processor 330 or the memory 370. The processor 380 can control the components of the AI ​​device 300 to perform a predicted operation or an operation determined to be desired in at least one executable operation. When the connection of an external device is required to perform a determined operation, the processor 380 can generate a control signal for controlling the external device, and the generated control signal can be sent to the external device. The processor 380 can obtain the intention information input by the user, and can determine the user's requirements based on the acquired intention information.

[0054] The processor 380 may acquire intent information corresponding to the user input by using at least one of a speech-to-text (STT) engine for converting the voice input into a text string or a natural language processing (NLP) engine for acquiring intent information of a natural language.

[0055] At least one of the STT engine or the NLP engine may be configured as an artificial neural network, at least a portion of which is learned according to a machine learning algorithm. At least one of the STT engine or the NLP engine may be learned by the learning processor 330, may be learned by the learning processor 340 of the AI ​​server 400, or may be learned by their distributed processing. The processor 380 may collect historical information including the operation content of the AI ​​device 300 or the user's feedback on the operation, and may store the collected historical information in the memory 370 or the learning processor 330, or send the collected historical information (e.g., related to the operation of the mechanical device 510) to an external device such as the AI ​​server 400. The collected historical information may be used to update the learning model.

[0056] The processor 380 may control at least some components of the AI ​​device 300 so as to drive the application program stored in the memory 370. In addition, the processor 380 may operate two or more components included in the AI ​​device 300 in combination so as to drive the application program.

[0057] Figure 4An AI server 400 according to the illustrated embodiment is shown. It should be understood that the AI ​​server 400 may refer to a device that learns an artificial neural network or uses a learned artificial neural network by using a machine learning algorithm. The AI ​​server 400 may include multiple servers to perform distributed processing, or may be defined as a 5G network. At this time, the AI ​​server 400 may be included as a partial configuration of the AI ​​device 300, and at least a portion of the AI ​​processing may be performed together. The AI ​​server 400 may include a communication unit 410, a memory 430, a learning processor 440, a processor 460, and the like. The communication unit 410 may send data to and receive data from an external device such as the AI ​​device 300. The memory 430 may include a model storage unit 431. The model storage unit 431 may store a model (or an artificial neural network 431a) that is being learned or has been learned through the learning processor 440.

[0058] The learning processor 440 can learn the artificial neural network 431a by using the learning data. The learning model can be used in a state installed on the AI ​​server 400 of the artificial neural network, or can be used in a state installed on an external device such as the AI ​​device 300. The learning model can be implemented in hardware, software, or a combination of hardware and software. If all or part of the learning model is implemented in software, one or more instructions constituting the learning model can be stored in the memory 430. The processor 460 can infer the result value of the new input data by using the learning model, and can generate a response or control command based on the inferred result value.

[0059] With the exemplary communication network 100 ( Figure 1 )、Computing device 200( Figure 2 )、AI devices 300( Figure 3 ) and AI server 400( Figure 4 ) is generally shown and discussed above, and reference will now be made to Figure 5 and 6 To provide a description of certain illustrated embodiments. It should be understood and appreciated that Figure 1-6 It is intended to provide a brief general description of an illustrative and / or suitable exemplary environment in which the embodiments described below may be implemented. Figure 1-6 The examples of suitable environments are not intended to impose any limitations on the structure, scope of use, or functionality of the illustrated embodiments. A specific environment should not be interpreted as having any dependency or requirement on any one of the components or combinations thereof shown in the exemplary operating environment. For example, in some cases, one or more elements of the environment may be considered unnecessary and omitted. In other cases, one or more other elements may be considered necessary and added.

[0060] It should be understood and realized that Figure 1-4 An exemplary embodiment of one or more components of a mechanical device (520) involves utilizing vibration measurements received from one or more sensor devices (510) indicating vibration of one or more components of a mechanical device (520) for determining abnormal operation of the mechanical device (520) by preferably artificial intelligence (AI) / machine learning (ML) analysis of the vibration measurements. Figure 5 and Figure 6 In the illustrated embodiment, the sensor device (510) is preferably a non-contact sensor (e.g., a camera device) that utilizes a non-contact optical method of measuring vibration, combined with process control provided by the control system 500 (also described below), to detect abnormal operation of a mechanical device 510 having one or more moving parts, thereby extending the life of the mechanical device, among other advantages. For example, in one example implementation, the camera sensor device 510 is positioned to capture an image of an industrial equipment 520 (e.g., a rotating drum having an application for processing minerals, metals, and material outputs), whereby the software is configured and operated to isolate a region of interest (e.g., a spatial point) in the image. In an exemplary scenario, motion amplification is used, the pixel movement becomes larger, and AI techniques are used to detect changes in the normal vibration range of the industrial equipment. For example, what may be detected may be an increase in motion, a change in raw materials, which are input to the control system 500. In addition, the preferred inputs to the control system 500 are operating parameters associated with the mechanical device 520 (e.g., machine context and process context data). As described in more detail below, in one exemplary scenario, the control system 500 utilizes one or more AI / ML techniques to compare increases in vibration to the operating speed of a moving component (e.g., a rotating drum) of the equipment 520 in order to predict the effect on wear. The one or more AI / ML techniques can detect early signs of wear, thereby accurately predicting the expected life of the equipment 520. In addition, if the vibration (movement) of such a component of the equipment 520 increases, the control system 500 can generate a warning signal and provide it to a designated person (e.g., a plant maintenance engineer). Other illustrative embodiments include the control system 500 determining one or more corrective operating settings for the equipment 520 to mitigate abnormal operation of the equipment 520 so that the equipment 520 operates within the tolerance of normal operation relative to its current operating parameters (e.g., machine context and process context data), thereby extending the life of the equipment 520, as well as other advantages.

[0061] With the exemplary communication network 100 ( Figure 1 )、Computing device 200( Figure 2 )、AI devices 300( Figure 3 ) and AI server 400( Figure 4 ) has been generally shown and discussed above, a description of certain illustrated embodiments will now be provided. Figure 5, showing the use of one or more of the aforementioned communication networks 100 ( Figure 1 )、Computing device 200( Figure 2 )、AI devices 300( Figure 3 ) and AI server 400( Figure 4 ) depicts a control system 500 that preferably utilizes one or more AI / ML techniques to analyze vibration data received from a sensor system 550 having one or more sensor devices 510 for detecting vibrations of one or more components of a mechanical device 520 to preferably determine abnormal operation of the mechanical device 520 in real time (and as will be described below with reference to Figure 6 600 is further described in detail).

[0062] For the purpose of illustration and description, a mechanical device 520 having one or more moving parts is referred to herein as a large industrial stone mill, and example types include (but are not limited to): a belt grinder, a centerless grinder, and a table grinder. In the exemplary device 520 discussed herein, the grinder 520 has at least one moving part consisting of a rotating drum, which is the object of the vibration detection analysis discussed herein. It should be appreciated and understood that the illustrated embodiments discussed herein should not be understood as being limited to such grinders for mechanical devices 520, as many mechanical devices having one or more moving (or non-moving) parts (e.g., a conveyor belt, a pipeline, or a gear box connected to a vibration source, etc.) will be included. For example, when a vibration change is detected on a component (e.g., a conveyor belt and / or a pipeline) that is isolated from process changes, the control system 500 can detect an abnormal event.

[0063] like Figure 5 As shown, the sensor system 550 preferably includes one or more sensor devices 510, which are capable of acquiring data from one or more moving parts (e.g., a rotating drum) of a mechanical device 520 (e.g., a millstone) for determining vibrations of one or more parts of the device 520 when analyzing the acquired sensor data. It should be understood that the one or more sensor devices 510 are preferably non-contact sensor devices (e.g., camera devices), but the illustrated embodiments should not be construed as being limited thereto, as they may also include contact sensor components. Figure 5As shown, one or more sensor devices 510 are comprised of a camera device positioned to capture images of a mechanical device 520. One or more cameras 510 may be coupled to motion capture software 512 that is configured and operated to isolate regions of interest in the captured images so as to utilize motion amplification to magnify pixel movements for vibration detection purposes. The sensor system 550 may additionally have software for removing / mitigating noise (e.g., dust) in retrieved images 514, and software for determining vibrations in captured images to measure deflections, displacements, movements, and vibrations that are not typically visible to the human eye. These measurements preferably include amplitudes and frequencies associated with detected vibrations of one or more components of the device 520. Examples of such sensor systems 550 may be obtained from RDI Technologies. TM Purchased from RDI Technologies TM The teachings of the components are incorporated herein.

[0064] Continue to refer to Figure 5 , the control system 500 is operably and communicatively coupled to the sensor system 550. According to the illustrated embodiment, the control system 500 is preferably remote from the sensor system 550 (e.g., located at a remote geographical location) and is coupled to the sensor system 550 via the communication network 100 (e.g., which may include the use of suitable TCP / IP communication technology) for transmitting data therebetween. For example, in certain embodiments, the control system 500 is operably coupled to a plurality of geographically located separate sensor systems 550 (each associated with a different mechanical device 520) in accordance with the teachings herein, so as to be operable and configured to detect (preferably in real time) abnormal vibration operation of a plurality of different geographically located mechanical devices 520.

[0065] The control system 500 preferably includes control logic (e.g., program module 215 of program / utility 240) that utilizes one or more AI / ML techniques to analyze vibration data received from the sensor system 550 to detect vibrations of one or more components of the mechanical equipment 520, thereby preferably determining abnormal operation of the mechanical equipment 520 in real time. Figure 6As further described in process 600, the control system 500 is preferably connected to a database 565 having vibration data 570 received from the sensor system 550, the vibration data 570 preferably being stored in association with machine context data 575 and process context data 580 associated with a component of the mechanical equipment 520 (e.g., a rotating drum) when the sensor system 550 detects vibration. As will be appreciated by those skilled in the art, process context data is typically operating state data that stores information about a particular process (e.g., it contains information needed to later restart the process of the mechanical equipment 520). And context data for machine learning typically includes historical data, environmental, and related factors that the machine learning model considers to make accurate predictions or decisions about the operation of the mechanical equipment 520. As described below in conjunction with Figure 6 The description of process 600 further describes that the control system 500 analyzes the vibration data 570 received from the sensor system 550, preferably in combination with its related machine context data 575 and process context data 580, utilizing one or more AI / ML techniques to determine: 1) abnormal detection / operation of the device 520 (585) (and providing notification of such abnormal operation of the device 520 (595)); and 2) determining one or more corrective actions (e.g., operating settings for the device 520), which can be input to the device 520 to eliminate its detected abnormal operation (590).

[0066] Figure 5 The exemplary control system 500 and sensor system 550 are generally shown and discussed above (in conjunction with Figure 1-4 ), now refer to Figure 6 (and continue to refer to Figure 1-5 ), a flowchart illustrating an implementation of a process 600 for analyzing vibration data 570 received from one or more sensor devices 510 of a sensor system 550 using AI / ML techniques 585, 590, the vibration data 570 indicating vibration of one or more components. Note that Figure 6 The order of steps of the process 600 shown in the embodiment is not required, so in principle, the steps may not be performed in the order shown. In addition, some steps may be skipped, different steps may be added or replaced, or selected steps or step groups may be performed in a separate application following the embodiments described herein.

[0067] Beginning at step 600, motion / vibration data of one or more components (e.g., a rotating drum) of a machine 520 (e.g., a millstone) observed and detected by one or more camera devices 510 of a sensor system 550 is input (via a communication network 100) to a control system 550. In certain illustrated embodiments, each camera sensor device 510 detects motion at a plurality of spatial points on the mechanical machine 520, wherein each camera sensor device 510 detects motion of one or more components (associated with the aforementioned spatial points) to at least detect vibrations associated with each detected spatial point of the mechanical machine 520. The control system 550 is preferably operated and configured using one or more AI / ML techniques to analyze the received motion data (step 610) to determine the vibratory movement (e.g., measured relative to a period of time) of one or more observed components of the machine 520, step 620. According to the illustrated embodiment, the motion data may include vibration spectrum measurements. It should be understood that when the sensor system 550 performs vibration detection, the aforementioned determined vibration movement 570 of one or more components of the equipment 520 is preferably stored in the database 565, associated with the machine context data 575 and process context data 580 associated with the components of the equipment 520 (e.g., the rotating drum).

[0068] At step 630, the control system 500 preferably utilizes one or more AI / ML techniques (e.g., 585) to determine abnormal vibration of one or more components by comparing the determined vibration measurement value (e.g., the determined vibration measurement spectrum) 570 of the detected component of the equipment 520 with the expected normal vibration measurement value of the component during operation of the mechanical equipment 520. Next, at step 640, when the determined vibration measurement value of the observed component exceeds its expected normal vibration measurement value by a threshold, abnormal operation of the observed component is determined.

[0069] According to the illustrated embodiment, one or more AI / ML techniques utilize machine context data 575 and process context data 580 associated with the operation of the mechanical equipment 520 to determine the observed abnormal operation of the vibrating component. For example, in some cases, the machine context data may include one or more configured operating parameters of one or more vibrating components, and the process context data may include output parameters of the mechanical equipment 520. It should also be understood and appreciated that one or more AI / ML techniques may include utilizing one or more of the XG Boost algorithm and the neural network algorithm techniques. For example, one or more AI / ML techniques may include applying images captured from one or more sensor devices 510 to a recursive convolutional neural network to determine when the detected vibration measurement spectrum 570 of the observed component of the mechanical equipment 510 exceeds its expected normal vibration measurement by a threshold. It should also be understood and appreciated that in certain illustrated embodiments, the control system 500 is operable and configured to preferably utilize one or more ML techniques to determine the expected normal vibration (e.g., vibration spectrum) of one or more vibrating components, preferably utilizing the machine context data 575 and process context data 580 associated with the operation of the mechanical equipment 520. It should also be further understood and appreciated that in certain illustrated embodiments, the control system 500 is operable and configured to train a machine learning (ML) model for determining expected normal vibration measurements (e.g., vibration spectra) of one or more observed vibrating components, which may utilize machine context data 575 and process context data 580 associated with the operation of the mechanical equipment 520. For example, training the aforementioned ML model may include utilizing images captured from one or more camera sensors 510 of the sensor system 500 for use in a recursive convolutional neural network for determining expected normal vibration spectra of one or more vibrating components of the equipment 520.

[0070] Next, in step 650, when abnormal vibration / operation of the aforementioned observed vibrating component of the mechanical equipment 520 is determined, an electronic notification signal 595 is preferably sent in a desired media format (e.g., SMS, MMS, email, etc.), preferably to one or more designated recipients (e.g., a plant manager), providing notification / alert of the determined abnormal operation of the observed component of the equipment 520.

[0071] In certain illustrated embodiments, at step 660, the control system 500 is further operative and configured to, upon determining that the observed component is determined to have abnormal vibration / operation (step 340), determine an adjustment to one or more operating parameters of the mechanical device 520 such that the determined abnormal vibration / operation component is operated within its expected normal vibration spectrum during operation of the mechanical device 520. Then, at step 670, the control system 500 provides a control signal 530 to the mechanical device 520, including the aforementioned adjustment parameters for the device 520, causing an adjustment to one or more operating parameters of the mechanical device 520 such that the determined abnormal operating component is operated within its expected normal vibration tolerance during operation of the mechanical device 520.

[0072] For certain illustrative embodiments described above, it should be understood that the various non-limiting embodiments described herein may be used alone, in combination, or in selective combination for specific applications. In addition, some of the various features of the above non-limiting embodiments may be used without corresponding use of other described features. Therefore, the foregoing description should be considered as merely an illustration of the principles, teachings, and exemplary embodiments of the illustrated embodiments, rather than a limitation thereof.

[0073] It should be understood that the above arrangement is only an illustration of the application of the principles of the illustrated embodiments. Many modifications and alternative arrangements may be devised by those skilled in the art without departing from the scope of the illustrated embodiments, and the appended claims are intended to cover these modifications and arrangements.

Claims

1. A method for abnormality diagnosis of a mechanical device, the mechanical device having one or more moving parts, the method comprising: receiving, in a computer control system, movement of the one or more components during operation of the mechanical device as detected by one or more sensor devices operatively associated with the mechanical device; determining, by a computer control system coupled to the one or more sensors, a vibration measurement spectrum of the one or more components based on the detected motion of the one or more components, wherein one or more machine learning (ML) techniques are used to determine abnormal operation of the one or more components by comparing the determined vibration measurement spectrum of the component with an expected normal vibration measurement spectrum of the component during operation of the mechanical equipment, such that the abnormal operation is determined when the determined vibration measurement spectrum of the component exceeds its expected normal vibration measurement spectrum by a threshold value; and When one or more of the components are determined to have abnormal operation, notification of the abnormal operation of the one or more components is provided by the control system.

2. The method of claim 1 , wherein the one or more ML techniques utilize machine context data and process context data related to the operation of the mechanical equipment to determine abnormal operation of the one or more moving parts, wherein the machine context data includes operating parameters for one or more configurations of the one or more moving parts, and the process context data is related to parameters of an output of the mechanical equipment.

3. The method of claim 2 further comprising determining, by a control system using the one or more ML techniques, an expected normal vibration spectrum of the one or more moving parts using machine context data and process context data related to operation of the mechanical equipment.

4. The method of claim 3 further comprises, in response to determining that the component is determined to have abnormal operation, determining an adjustment to one or more operating parameters of the mechanical device so that during operation of the mechanical device, the determined abnormally operating component is operated within its expected normal vibration spectrum.

5. The method according to claim 4 further includes providing a control signal including the determined adjusted operating parameters from the control system to the mechanical equipment, resulting in adjustment of one or more operating parameters of the mechanical equipment so that the determined abnormal operating component operates within its expected normal vibration spectrum during operation of the mechanical equipment.

6. The method of claim 3, wherein the one or more ML techniques include utilization of one or more of an XG Boost algorithm and a neural network algorithm technique.

7. The method of claim 6, further comprising training a machine learning (ML) model to determine an expected normal vibration spectrum of the one or more moving parts using machine context data and process context data related to the operation of the mechanical equipment.

8. The method of claim 1, wherein the one or more sensor devices include one or more optical sensor devices, wherein each optical sensor device detects motion at a plurality of spatial points on the mechanical device.

9. A method according to claim 8, wherein one or more of the optical sensor devices are composed of camera devices, which are operatively connected to software for detecting movement of one or more components, and the software operates to detect vibrations associated with at least each detected spatial point of the mechanical device.

10. The method of claim 1, wherein the control system is operatively coupled to a plurality of geographically remote sensor systems, wherein each sensor system has one or more sensor devices operatively associated with a respective mechanical device.

11. The method of claim 8, wherein the one or more ML techniques include applying images captured from the one or more optical sensors to a recursive convolutional neural network for determining when a spectrum of detected vibration measurements of the component of mechanical equipment exceeds a threshold of expected normal vibration measurements thereof.

12. The method of claim 11, further comprising training a recursive convolutional neural network using images captured from the one or more optical sensors to determine an expected normal vibration spectrum of the one or more moving parts.

13. The method of claim 1, wherein the one or more moving parts include a rotating drum associated with the mechanical device, the mechanical device being used in one or more of mineral, metal, and material output applications.

14. The method of claim 1, wherein the motion data detected from the one or more sensor devices is wirelessly transmitted via a communications network to a computer diagnostic control system remote from the mechanical device.

15. The method of claim 1, wherein determining when the determined vibration measurement spectrum of the component exceeds its expected normal vibration measurement spectrum by a threshold is performed in real time.

16. A system for abnormality diagnosis of a mechanical device, the mechanical device having one or more moving parts, the system comprising: one or more sensor devices operatively associated with the mechanical device for detecting movement of one or more components during operation of the mechanical device; A computer control system coupled to the one or more sensors, the computer control system comprising: a database having a memory; and A processor is arranged to communicate with the memory and is configured to issue a plurality of instructions stored in the memory, wherein the instructions cause the processor to: determining a vibration measurement of the one or more components based on the detected movement of the one or more components; utilizing one or more machine learning (ML) techniques to determine abnormal operation of one or more components by comparing determined vibration measurements of the components with expected normal vibration measurements of the components during operation of the mechanical equipment, such that the abnormal operation is determined when the determined vibration measurements of the components exceed their expected normal vibration measurements by a threshold value; and When one or more of the components are determined to have abnormal operation, notification of the abnormal operation of the one or more components is provided.

17. The system of claim 16, wherein the one or more ML techniques utilize machine context data and process context data related to the operation of the mechanical equipment to determine abnormal operation of the one or more moving parts, wherein the machine context data includes operating parameters for one or more configurations of the one or more moving parts, and the process context data is related to parameters of an output of the mechanical equipment.

18. The system of claim 17, wherein the processor is further configured to: determining an adjustment to one or more operating parameters of the machine when it is determined that the component is determined to have abnormal operation; and A control signal is provided from the control system to the machine resulting in adjustment of one or more operating parameters of the machine such that the identified abnormally operating component is caused to operate within its expected normal vibration tolerances during operation of the machine.

19. The system of claim 16, wherein the one or more sensor devices include one or more optical sensor devices, wherein each optical sensor device detects motion at a plurality of spatial points on the mechanical device.

20. A method for abnormality diagnosis of a mechanical device, the mechanical device having one or more moving parts, the method comprising: receiving, in a computer controlled system, movement of the one or more components during operation of the mechanical device from one or more optical sensor devices, wherein each optical sensor device detects movement at a plurality of spatial points on the mechanical device; determining, by a computer control system coupled to the one or more optical sensor devices, vibration measurements of the one or more components based on the detected motion of the one or more components, wherein one or more machine learning (ML) techniques utilize machine context data and process context data related to operation of the mechanical device; and The control system utilizes ML technology to determine abnormal operation of the one or more components by comparing the determined vibration measurement value of the component with the expected normal vibration measurement value of the component during operation of the mechanical equipment, so that the abnormal operation is determined when the determined vibration measurement value of the component exceeds its expected normal vibration measurement value by a threshold value.

Images