KR20200006251A - Device monitoring method and system using artificial neural network-based algorithm - Google Patents

Abstract

The present invention relates to a device monitoring method and system using an artificial neural network based algorithm. The device monitoring method using an artificial neural network based algorithm according to an embodiment of the present invention comprises the steps of: collecting sensor data from a target device sensor installed in the first target device; generating an operation signal by monitoring the detection result of the target device sensor through an artificial neural network based algorithm; and driving a haptic feedback device installed in a second target device based on the operation signal.

Description

Device monitoring method and system using artificial neural network-based algorithm

The present invention relates to a device monitoring method and system using an artificial neural network based algorithm.

Haptic technology (haptic) is a technology that implements the feeling of touch by applying force, vibration, motion to the user. In other words, the user's input devices, such as a keyboard, mouse, joystick, and touch screen, make the user feel power and movement through the sense of touch.

Haptic feedback can be implemented in the device using vibration motors, capacitive actuation or other electromagnetic techniques.

Artificial neural networks (ANN) are computational modeling techniques inspired by the human central nervous system capable of machine learning and pattern recognition. ANNs are typically implemented as interconnected neuronal systems that can enter information over a network and calculate input values.

The ANN generally includes a set of adaptive weights, that is, numerical parameters tuned by the learning algorithm. Applied weights conceptually represent the strength of the connection between the trains that are activated during training and prediction.

If the ANN is configured for a specific application, the network can be trained. Initial weights are chosen through a trained user guess or randomly to start the training processor. In supervised learning, both inputs and desired outputs are provided to ANN. The ANN then processes the input and compares the result with the desired output. If the results do not match, an error is passed back through the ANN, which causes the ANN to adjust its weight. As the input and desired output, i.e. the amount of data, increases, the ANN will fine tune the selected weight. If the ANN is properly trained, the weights can be fixed and can continue to be learned and adjusted while using the ANN.

Korean Patent Publication No. 10-2010-0058836

The present invention is directed to providing a method and system for training artificial neural network based algorithms designed to monitor a first device to provide haptic feedback to a second device.

The embodiment may include collecting sensor data from a target device sensor installed in the first target device; Generating an operation signal by monitoring the detection result of the target device sensor through an artificial neural network based algorithm; And driving a haptic feedback device installed in a second target device based on the operation signal.

In some embodiments, the generating of the operation signal by monitoring the detection result of the target device sensor through an artificial neural network based algorithm may include generating a first operation signal based on the sensor data; And generating a second operation signal by monitoring the first target device using an artificial neural network based algorithm based on the sensor data.

In some embodiments, the driving of the haptic feedback device installed in the second target device based on the operation signal may include driving the haptic feedback device with the second operation signal when the first and second operation signals coincide with each other. A device monitoring method using an artificial neural network based algorithm may be provided.

In some embodiments, the first target device; A target device sensor installed in the first target device; Haptic feedback devices; A computing device installed with a haptic program that generates a first operation signal based on sensor data received from the target device sensor; The second operation signal is compared with a device monitoring program for monitoring the first target device using an artificial neural network based algorithm based on the sensor data, and a second operation signal generated from the device monitoring program and the first operation signal are compared with each other. A server equipped with a training module for training the device monitoring program to match the first operating signal; The haptic feedback device may provide a device monitoring system using an artificial neural network based algorithm that operates based on the second operation signal.

In some embodiments, the training module provides a device monitoring system using an artificial neural network based algorithm for adjusting a parameter of an artificial neural network based algorithm to cause the device monitoring program to output a second operating signal that matches the first operating signal. can do.

In some embodiments, the haptic feedback device can provide a device monitoring system using an artificial neural network based algorithm installed in the second target device.

In some embodiments, the target device sensor may provide a device monitoring system using an artificial neural network based algorithm installed in a plurality of spaced apart from each other in the first target device.

In some embodiments, the target device sensor, the computing device, the server, and the haptic feedback device may provide a device monitoring system using an artificial neural network based algorithm that communicates data with one another via a network.

In some embodiments, the server may provide a device monitoring system using an artificial neural network-based algorithm that notifies the computing device if the second operation signal matches the first operation signal.

In some embodiments, the target device sensor may provide a device monitoring system using an artificial neural network-based algorithm for detecting vibration of the first target device.

In some embodiments, receiving sensor data from a target device sensor installed in a first target device; Generating a first operation signal based on the sensor data; Monitoring the first target device with an artificial neural network based algorithm based on the sensor data to generate a second operation signal; Comparing the first and second operation signals with each other; Adjusting a parameter of an artificial neural network based algorithm such that the second operating signal matches the first operating signal; And driving the haptic feedback device based on the second operation signal when the second operation signal and the first operation signal coincide with each other after adjusting the parameter. Can provide.

The present invention can provide a method and system for training artificial neural network based algorithms designed to monitor a first device to provide haptic feedback to a second device.

1 shows diagrams of a system in accordance with an embodiment of the present invention.
2 is a flow chart of the steps of a haptic program executed within the system of FIG.
3 is a flowchart of steps of a training module executed within the system of FIG. 1.
4 illustrates a block diagram of components of a server and a computing device in accordance with an embodiment of the present invention.

As the invention allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the written description. Effects and features of the present invention, and methods for achieving them will be apparent with reference to the embodiments described below in detail in conjunction with the drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various forms. In the following embodiments, the terms first, second, etc. are used for the purpose of distinguishing one component from other components rather than a restrictive meaning. Also, the singular forms “a”, “an” and “the” include plural forms unless the context clearly indicates otherwise. In addition, the terms including or have means that the features or components described in the specification are present, and does not exclude in advance the possibility that one or more other features or components will be added. In addition, in the drawings, the components may be exaggerated or reduced in size for convenience of description. For example, the size and thickness of each component shown in the drawings are arbitrarily shown for convenience of description, and thus the present invention is not necessarily limited to the illustrated.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, and the same or corresponding components will be denoted by the same reference numerals, and redundant description thereof will be omitted. .

As will be appreciated by those skilled in the art, embodiments of the present invention may be embodied as a system, method or computer program. Accordingly, embodiments of the present invention may take the form of an overall hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.) or an embodiment combining software and hardware aspects that can all be referred to in general. In addition, aspects of the present invention may take the form of a computer program product implemented with one or more computer readable medium (s) having computer readable program code / information, wherein the instructions are embodied.

Any combination of computer readable media can be used. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any suitable combination of the foregoing. More specific examples (non-limiting list) of computer readable storage media include electrical connections, portable computer diskettes, hard disks, random access memory (RAM), read (ROM), erasable programmable read only memory having one or more wires. (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any type of medium that can contain or store a program for use by or in connection with an instruction execution system, device or device.

The computer readable signal medium may include, for example, a propagated data signal having computer readable program code implemented at baseband or as part of a carrier wave. Such propagated signals may take any of a variety of forms, including but not limited to electromagnetic, optical or any suitable combination thereof. The computer readable signal medium is not a computer readable storage medium and may be any computer readable medium capable of delivering, propagating or transmitting a program for use by or in connection with an instruction execution system, device or device.

Computer program code for performing operations on aspects of the present invention may be implemented in one or more programming languages, including object-oriented programming languages such as Java (registered trademark), Smalltalk (registered trademark), C ++, and the like, and conventional procedural programming languages. It can be described in any combination, such as a C programming language or similar programming language. The program code may be executed, in part, on the user's computer, partly on the user's computer, in a standalone software package, partly on the user's computer, partly on the remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or through an external computer (eg, May be connected to the user's computer (via the Internet using an Internet service provider).

Aspects of the invention are described below with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the invention. It will be appreciated that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing device to generate a machine, and instructions, flowcharts and / or instructions executed through the processor of the computer or other programmable data processing device. Or block diagram creates means for implementing the functions / acts specified in the block or blocks.

In addition, these computer program instructions may be stored on a computer readable medium to instruct the computer, other programmable data processing device, or other device to function in a particular manner, such that the instructions stored on the computer readable medium are stored in an article flow chart and / or Block diagrams also include articles of manufacture that contain instructions that implement a particular function / act in a block or blocks.

In addition, the computer program instructions may be loaded on a computer, another programmable data processing device, or another device such that the instructions for executing a series of operating steps on the computer or other programmable device are performed on the computer, another programmable device, or another device. And / or block diagrams provide processes for implementing the functions / acts specified in the block (s).

1 shows a diagram according to one embodiment of the invention.

1 provides a description of the embodiments only and does not imply any limitation on the environment in which the different embodiments may be implemented.

Referring to FIG. 1, system 10 includes a target device sensor 110 interconnected via a computing device 40, a server 50, and a network 20. Network 20 includes a local area network (LAN), the Internet, any combination thereof, or any combination of connections and protocols that will support communication between server 50 and computing device 40 in accordance with embodiments of the present invention. can do. The network 20 may include a wired, wireless or fiber optic connection. System 10 may include additional computing devices, servers, computers, or other devices not shown.

The target device sensor (s) 110 are one or more sensors operably attached to the target device. A target device is a device or entity that can cause vibrations during use or operation. For example, target devices may include pumps, fans, motors, generators, compressors, diesel engines, turbines, machine tools (e.g., cutting, boring, grinding, shearing, or any other form of machine tool), or suitable use of medical equipment. Training equipment (eg, tooth models) for evaluation. The target device sensor (s) 110 may include a sensor that measures vibration or movement, such as a gyroscope, accelerometer or other sensor. Target device sensors 110 may include sensors that measure amplitude and frequency. In one embodiment, the target device sensor (s) 110 include one or more microelectromechanical system (MEMS) accelerometers. Sensors that measure vibration and motion can be used to collect data to be used by the haptic program 120 to operate the haptic feedback device 60.

In some embodiments, a sensor for measuring information about the area of motion and the area of vibration, additional sensors externally, temperature, flow rate, pressure, energy consumed, operating time or other types of information may further include the target device sensor (s) ( 110 may be included. The target device sensor (s) 110 may measure the target device and / or individual components within or around the target device. In some embodiments, target device sensor (s) 110 may include an optical sensor and / or an ultrasonic sensor. In some embodiments, target device sensor (s) 110 may include a camera, microphone, and / or other device for transmitting audio visual data.

In some embodiments, the process of reading the collected data from the target device sensor (s) 110 may be performed on a computing device 40 or a controller (not shown) communicatively coupled to the target device sensor (s) 110. It can be made by. Such computing device 40 may allow readings to be transmitted as data over the network 20.

For example, computing device 40 may collect sensor readings collected for use by haptic program 120, device monitoring program 130, and / or training module 140 to computing device 40 or server 50. ) Can be sent. In some embodiments, computing device 40 transmits the collected sensor readings to server 50 for storage in a file or database, such as server monitoring database 150.

Computing device 40 may be a management server, a web server, or any other electronic device or computing system capable of receiving and transmitting data. In some embodiments, computing device 40 includes a laptop computer, tablet computer, netbook computer, personal computer (PC), desktop computer, personal digital assistant (PDA), smartphone, server 50. Computing device 40 includes a haptic program 120. In some embodiments, computing device 40 includes haptic feedback device 60. In another embodiment, computing device 40 is communicatively connected to a haptic feedback device, such as haptic feedback device 60. Computing device 40 may include components as described and described in more detail with respect to FIG. 4.

The haptic feedback device 60 is a device capable of providing tactile feedback and using touch sensations by applying force, vibration, or movement to the user.

Haptic feedback device 60 is a device capable of reproducing vibrations of a target device using data collected from one or more target device sensor (s) 110.

In some embodiments, the haptic feedback device 60 can generate a physical property or provide a mechanical stimulus that simulates the feel of the surface of a component of the target device.

For example, the haptic feedback device 60 may use a series of motors to simulate the presence of a defect on a rough or flat surface of the target device.

In this example, the haptic feedback device 60 may use the display to provide a virtual image of a particular device under simulation as well as the location of the area that provides tactile sensation. In some embodiments, haptic feedback device 60 is a display having both visual and haptic functions such as vibration.

In other embodiments, haptic feedback device 60 may be an object or surface that includes one or more motors, capacitive actuators, or other devices capable of replicating a range of vibration patterns.

In some embodiments, haptic feedback device 60 may be a mobile device capable of replicating a range of vibration patterns, such as a smartphone or tablet. In another embodiment, the haptic feedback device 60 may be an object designed to replicate the viewing and feeling of the target device.

In such embodiments, the haptic feedback device 60 may include a motor, capacitive actuator, and / or to cause the haptic feedback device 60 to repeat vibrations on a particular surface of the haptic feedback device 60 corresponding to a location on the actual target device. It may contain other internal components.

The haptic program 120 can operate based on sensor data received by a haptic feedback device, such as the haptic feedback device 60.

In another embodiment, the device monitoring program 130 transmits sensor data via the network 20 to the computing device 40 and the haptic program 120.

In some embodiments, the haptic program 120 operates to receive motion decision recommendations (motion signals). For example, a user of computing device 40 may interact with a user interface of haptic program 120 to input an operation signal.

Such an operation signal may be based on information obtained by the user viewing or touching the haptic feedback device 60 or based on additionally presented audio or visual information.

The operation signal may include a determination related to maintenance or monitoring of the target device.

As described above, the target device sensor (s) 110 can be operatively attached to the target device and positioned so that meaningful information and data can be collected.

In some embodiments, the operation signal suggests no service, repair, replacement, action, or take other action with respect to the target device and / or various components constituting the target device.

In some embodiments, the haptic program 120 operates to deliver the received motion signals to the device monitoring program 130 and / or the training module 140.

In another embodiment, the haptic program 120 can reside on another server, another computing device, or the server 50 if the haptic program 120 is accessible to the device monitoring program 130 and the training module 140. . The haptic program 120 is provided to access the device monitoring program 130, the training module 140, and the device monitoring database 150.

Server 50 may be a management server, a web server, or any other electronic device or computing system capable of receiving and transmitting data.

In some embodiments, server 50 is capable of communicating with a laptop computer, tablet computer, netbook computer, personal computer (PC), desktop computer, personal digital assistant (PDA), smartphone, or computing. It may be performed by the electronic device 40 and the target device sensor (s) 110.

In other embodiments, server 50 may represent a server computing system that uses multiple computers as server systems, such as in a cloud computing environment.

The server 50 includes a device monitoring program 130, a training module 140, and a device monitoring database 150. Server 50 may include components as shown and described with respect to FIG. 4.

The device monitoring program 130 operates to monitor the target device using the target device sensor (s) 110 and generate an operation signal for the target device.

In an embodiment of the present invention, the device monitoring program 130 uses an artificial neural network (ANN) based algorithm.

In the ANN, each input (e.g., sensor readings, component information, operating time, etc.) is multiplied by a weight and then calculated by a math module that can determine the output of the algorithm.

In this embodiment, the input may include sensory information associated with vibration data, temperature sensor, part model information, or other information related to wear and tear of the target device depending on the specificity of the target device.

For example, if the target device is a water pump, the inputs include vibration, temperature, flow rate, pump pressure, water quality, energy consumed by the motor in the pump, pump efficiency, number of hours of operation, manufacturer and model of the individual components, pump cost, Include various types of information, including the cost of individual components, service costs, replacement costs, event logs, or other types of information.

The weights may be positive and negative, and each weight may initially be determined according to an educational guess or random selection of the user.

Training module 140 is a supervised learning process that can be used to train device monitoring program 130 based on given input information and desired output information.

In one embodiment, the device monitoring program 130 resides on the server 50.

In another embodiment, if the device monitoring program 130 is accessible to the haptic program 120 and the training module 140 and the device monitoring program 130 can access the haptic, another server, another computing device or computing device Program 120, training module 140, and device monitoring database 150.

The training module 140 operates to compare an operation signal received from the haptic program 120 with an operation signal generated by the device monitoring program 130.

If the training module 140 determines that the motion signals do not match (eg, the device monitoring program 130 provides a message that is not the same as the motion signal received from the haptic program 120), the training module 140 For example, the weight will be adjusted until the output operating signal of the device monitoring program 130 is the same as the operating signal received from the haptic program 120 while using the sensor data.

In some embodiments, the training module 140 uses the historical data, including sensor readings and operating signals associated with these sensor readings, to fine-tune the weights of the device monitoring program 130 according to the input data and desired results. The device monitoring program 130 consistently generates an operation signal that matches the operation signal received from the haptic program 120.

In order to obtain a desired output, ie an operation signal received from the haptic program 120 from the device monitoring program 130, various algorithms that can adjust the weight of the ANN used by the device monitoring program 130 may be used.

Such an algorithm may cause the generation of an operating signal that may be inaccurate at first, but with additional data inputs and desired outputs, the weight may be gradually adjusted to increase the reliability of the device monitoring program 130.

In some embodiments, once the threshold is reached, the training module 140 may no longer be needed.

For example, the device monitoring program 130 may generate the same operation signal as the operation signal received from the haptic program 120 for a specific period or more than a certain ratio when compared with all received operation signals.

In another embodiment, whenever the target device is repaired, replaced or repaired, the training module 140 will continue to operate for a period of time. Running the training module 140 after component repair, replacement or service, the training module 140 may adjust any weights that require some modification due to changes in the target device as a result of the service performed.

The device monitoring database 150 may be a repository that may be recorded and read by the device monitoring program 130 and the training module 140.

Other historical data, such as device monitoring program weights, device monitoring program weighted histories, and past sensor readings and associated decisions received from the haptic program 120 may be stored in the device monitoring database 150.

In some embodiments, additional information such as component model information, operating time, cost factor, local inventory availability, and history issues or event logs may be stored in the device monitoring database 150.

In one embodiment, the device monitoring database 150 resides on the server 50.

In other embodiments, the device monitoring database 150 may reside on another server, another computing device, or computing device 40 if the device monitoring program 130 and training module 140 are accessible.

2 shows a flow chart of the steps of a haptic program 120 executed within the system of FIG.

Haptic program 120 operates to receive data from target device sensor (s) 110 and use the data to cause operation of haptic feedback device 60.

In addition, the haptic program 120 operates to receive an operation signal and transmit an operation signal to the server 50 via the network 20 for analysis in the device monitoring program 130.

In one embodiment, initially, various sensors, such as target device sensor (s) 110, are operatively attached to the target device.

The target device sensor (s) 110 include at least one sensor capable of collecting data related to movement and / or vibration.

In some embodiments, target device sensor (s) 110 may include additional sensors that collect additional information.

Target device sensor (s) 110 may further include a camera, microphone, or other device capable of capturing and transmitting audio or video signals.

The target device can be any device in which vibrations or moving parts can cause wear, so that those skilled in the art can determine the operation signal based in part on the vibrations. For example, the target device may be a training equipment, water pump, fan, motor, or other device for evaluating proper use of medical equipment.

In step S210, the haptic program 120 receives sensor data. Sensor data includes any data collected by the target device sensor (s) 110.

In some embodiments, data other than sensor data, historical data, computer generated data, or other data sources may be used.

For example, you can create a computer-generated model of your target device, simulate it to replicate vibration or behavior of the device, and simulate sensor data generation.

In some embodiments, haptic program 120 may receive sensor data from a computing device (not shown) communicatively coupled to target device sensor (s) 110, wherein the computing device may receive the target device sensor (s). Monitor and store data collected from 110.

In another embodiment, the haptic program 120 accesses and retrieves sensor data from the target device sensor (s) 110.

In step S220, the haptic program 120 causes the haptic feedback device 60 to operate using sensor data received from the target device sensor (s) 110.

In one embodiment, the haptic program 120 controls and replicates motors, capacitive actuators, and / or other components of the haptic feedback device 60 using sensor data from the target device sensor (s) 110. Vibration and / or one or more components within the target device or target device generate a motion or vibration that is to be done.

In another embodiment, the haptic program 120 uses sensor data from the target device sensor (s) 110 to control motors, capacitive actuators, and other components of the haptic feedback device 60 to surface the components. Other simulations are provided to simulate the tactile feel of.

For example, an optical sensor or other sensor can be used to detect the roughness or cavity formed on the surface of the component, and the haptic program 120 uses this sensor data to provide mechanical stimulation to the haptic feedback device 60. Or simulates the feeling of the component surface.

In some embodiments, haptic program 120 may transmit sensor data to another program designed to control a haptic feedback device, such as haptic feedback device 60. The haptic program 120 can cause the haptic feedback device 60 to replicate the vibration pattern and / or motion of the individual components that make up the target device.

For example, if the target device is a water pump, the haptic program 120 may use different combinations of sensor data from the target device sensor (s) 110 to cause the haptic feedback device to be a motor, pump, casing or subcomponent ( To replicate vibrations on the motor shaft or rotor). In some embodiments, a user of computing device 40 may select individual components or devices through a user interface.

In this embodiment, once the component or system is selected, the haptic program 120 causes the haptic feedback device 60 to duplicate the vibration or motion of the component or device based on sensor data applicable to the selected component or device.

In some embodiments, haptic program 120 may cause audio, visual or other information to be displayed based on information available from target device sensor (s) 110.

For example, the target device sensor (s) 110 can include a temperature sensor, and the haptic program 120 can cause the temperature information to be displayed on the display device.

In another example, a camera or microphone may be included in the target device sensor (s) 110 and the haptic program may display video on the display device and / or audio via one or more speakers.

In step S230, the haptic program 120 receives an operation signal.

The operational signal may be, for example, a decision not to service, repair, replace or take any action with respect to the target device.

The details of these operational signals depend on the type of target device (ie what type of device the target device is).

Typically, the received operational signal is received from a user accessing the haptic program 120 via the computing device 40.

For example, the operation signal may be a determination made by the user at computing device 40 based on vibrations or movements generated by haptic feedback device 60.

In some embodiments, the haptic program 120 may prompt the user for a request for an operation signal through a pop-up window or other method.

In another embodiment, a user at computing device 40 may enter a motion signal by initiating haptic program 120 or selecting an option within a user interface of haptic program 120.

In some embodiments, the haptic program 120 will associate the received operation signal with sensor data received from the target device sensor (s) 110.

The haptic program 120 may associate a time range relative to the received motion signal, sensor data collected within the time range of the motion signal, or other portion of the received sensor data.

In step S240, the haptic program 120 transmits an operation signal received through the network 20 to the server 50 for analysis by the device monitoring program 130.

In some embodiments, haptic program 120 will further transmit sensor data received from target device sensor (s) 110 associated with the received motion signal.

In some embodiments, the transmitted data may be stored in the device monitoring database 150.

3 shows a flow chart of the steps of the training module 140, which is a function of the device monitoring program 130, executed within the system of FIG. 1.

Referring to FIG. 3, according to an embodiment of the present disclosure, the training module 140 compares an operation signal received from the haptic program 120 with an operation signal generated by the device monitoring program 130.

In one embodiment, the haptic program 120 receives sensor data, causes the haptic feedback device to operate, and receives a motion signal from the user at the computing device 40.

In some embodiments, the received operation signal may be based on tactile interaction with the haptic feedback device 60.

In some embodiments, audio, video or other factors may have been considered by the user prior to submitting their motion signal.

After the haptic program 120 receives the motion signal, the haptic program 120 transmits the motion signal to the device monitoring program 130 for analysis by the training module 140.

In step S310, the training module 140 receives an operation signal from the haptic program 120. In some embodiments, the haptic program 120 may transmit the received motion signal to the training module 140.

In another embodiment, the training module 140 may monitor the haptic program 120 and retrieve an operation signal from the haptic program 120. In some embodiments, the training module 140 stores the sensor data associated with the motion signal, the time at which the motion signal was made, and the collected data set before receiving the motion signal by the haptic program 120.

In step S320, the training module 140 compares the received first operating signal with the second operating signal generated by the device monitoring program 130.

An embodiment of the device monitoring program 130 uses an artificial neural network (ANN) based algorithm to monitor the target device via the target device sensor (s) 110.

The ANN based algorithm of the device monitoring program 130 includes inputs (eg, received data such as sensor data, operating time, part information, etc.) that are multiplied by one or more functions.

According to the result of the module, one or more operation signals are generated.

In some embodiments, the device monitoring program 130 notifies the training module 140 when an operation signal has been generated by the device monitoring program 130.

In another embodiment, the training module 140 monitors or accesses the device monitoring program 130 or the device monitoring database 150 to retrieve the operating signal generated by the device monitoring program 130.

In step S330, the training module 140 determines whether the operation signal generated by the device monitoring program 130 matches the operation signal received by the haptic program 120.

The training module 140 may determine whether the motion signal matches by examining a comparison between the motion signal received from the haptic program 120 and the motion signal generated by the device monitoring program 130.

If the operation signals match (eg, each recommends replacing the same component, each does not recommend service operation), the training module 140 may determine that the signals are the same.

When the operation signal is different (for example, when the device monitoring program 130 generates an operation signal for operating the component and the operation signals received from the haptic program 120 are different from each other), the training module 140 ) May determine that the operation signals are not the same.

The function is complete when the training module 140 determines that the motion signal generated by the device monitoring program 130 matches the motion signal received by the haptic program 120.

If the training module 140 determines that the operation signal generated by the device monitoring program 130 is different from the operation signal received by the haptic program 120, the training module 140 sends the device monitoring program 130 to the device monitoring program 130. The weight of the device monitoring program 130 may be adjusted such that the operation signal generated by the same is the same as the operation signal received from the haptic program 120 (step S340).

In some embodiments, the training module 140 may adjust the weights, parameters, and / or functions such that the device monitoring program 130 may generate the same motion signal as the motion signal received from the haptic program 120.

In some embodiments, training module 140 stores historical data stored in device monitoring database 150 such that changes to various weights, parameters, and / or functions used by device monitoring program 130 do not conflict with operational signals. Received in advance from the haptic program 120.

In some embodiments, there may be a threshold or time frame such that the training module 140 can only use historical data from the device monitoring database 150 from designated time periods.

In another embodiment, the threshold may instruct the training module 140 to use only a certain number of historical data sets. Typically, you specify the data type to use these thresholds, the time frame to use the data, or the amount of data to use.

In step S350, the training module 140 stores the changes to the weights, parameters, and / or functions in the device monitoring database 150.

In some embodiments, training module 140 receives from haptic program 120 along with sensor data related to the recommendation and possibly other relevant information (eg, model number of component, operating time, last service date, etc.). The stored operation signal further.

The sensor data related to the operation signal may be sensor data when the operation signal is received or sensor data of a specific period when or before the operation signal is received.

In some embodiments, the device monitoring program 130 may record sensor data with a time stamp, and in such embodiments, the training module 140 may store a time stamp associated with an operation signal received from the haptic program 120. Can be.

The information stored by the training module 140 may be used by the device monitoring program 130 to monitor the target device via the target device sensor (s) 110 and generate future operational signals.

When historical data is received and stored, training module 140 may use the historical data to further refine the weights, parameters, and / or functions used by device monitoring program 130. In detail, the device monitoring program 130 generates the same operation signal as the operation signal received from the haptic program 120 more often. As a result, device monitoring program 130 may operate with minimal adjustment from training module 140.

In such a scenario, training module 140 may remain inactive until the service operation is performed on the target device or at various time periods for scheduled maintenance or testing.

4 illustrates a block diagram of components of computing device 40 and server 50 in accordance with an exemplary embodiment of the present invention.

In addition, FIG. 4 only provides a description of one implementation and does not imply any limitation on the environment in which other embodiments may be implemented. Many modifications can be made to the depicted environment.

Computing device 40 and server 50 are each computer processor 404, memory 406, persistent storage device 408, communication unit 410, and input / output (I / O) interface (s) 412. Communication fabric 402 providing communication between the < RTI ID = 0.0 >

Communication line 402 may be implemented in any architecture designed to convey data and / or control information between a processor (microprocessor, communication and network processor, etc.), system memory, peripheral devices, and any other hardware component within the system. have.

For example, communication line 402 may be implemented with one or more buses.

Memory 406 and persistent storage device 408 are computer readable storage media.

In this embodiment, memory 406 includes random access memory (RAM) 414 and cache memory 416.

In general, memory 406 may include any suitable volatile or nonvolatile computer readable storage medium.

The haptic program 120 is persistent for the computing device 40 for execution by one or more of each computer processor 404 of the computing device 40 through one or more memories of the memory 406 of the computing device 40. Stored in storage device 408.

The device monitoring program 130, the training module 140, and the device monitoring database 150 are one of each computer processor 404 for the server 50 through one or more memories of the memory 406 of the server 50. It is stored for execution and / or access by the above.

In this embodiment, persistent storage device 408 includes a magnetic hard disk drive.

Alternatively or in addition to a magnetic hard disk drive, persistent storage device 408 may be a semiconductor hard drive, semiconductor storage device, read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, or program instructions or Any other computer readable storage medium capable of storing digital information.

The media used by persistent storage device 408 may also be removable.

For example, a removable hard drive can be used for persistent storage device 408.

Other examples include optical and magnetic disks, drives, and smart cards that are inserted into a drive for transmission onto other computer readable storage media that is part of the persistent storage device 408.

In this embodiment, the communication unit 410 provides communication with other data processing systems or devices.

In these examples, communication unit 410 includes one or more network interface cards.

The communication unit 410 may provide communication through the use of one or both of physical and wireless communication links.

The haptic program 120 can be downloaded to the persistent storage device 408 of the computing device 40 via the communication unit 410 of the computing device 40.

The device monitoring program 130 and training module 140 may be downloaded to the persistent storage device 408 of the server 50 via the communication unit 410 of the server 50.

I / O interface (s) 412 allow input and output of data along with other devices that may be connected to computing device 40 or server 50.

For example, I / O interface 412 may provide a connection to external device 418 such as a keyboard, keypad, touch screen, and / or other suitable input device.

External devices 418 may also include portable computer-readable storage media such as, for example, drives, portable optical or magnetic disks, and memory cards.

Software and data, such as the haptic program 120, used to practice embodiments of the invention may be stored on a portable computer-readable storage medium and may be stored in the computing device 40 via the I / O interface (s) 412. Persistent storage device 408 may be stored in computing device 40.

Software and data used to practice embodiments of the invention, such as device monitoring program 130, training module 140, and device monitoring database 150 may be stored on a portable computer-readable storage medium. And the persistent storage device of the server 50 and also the I / O interface (s) 412 connect to the display 420.

Display 420 provides a mechanism for displaying data to a user, and may be, for example, a computer monitor.

The programs described herein are identified based on the applications implemented in certain embodiments of the present invention.

However, it is to be understood that any particular program name herein is used for convenience only and therefore the invention should not be limited to use in any particular application identified and / or implied by such nomenclature.

Flow diagrams and block diagrams of the drawings illustrate the structure, function, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure.

In this regard, each block in the flowchart or block diagram may represent a module, segment or code portion that includes one or more executable instructions for implementing a particular logical function (s).

It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures.

For example, two blocks shown in succession may be executed substantially concurrently, or blocks may sometimes be executed in reverse order, depending on the functionality involved.

In addition, each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by special purpose hardware based systems that perform particular functions or operations, or may be special purpose hardware and computer instructions May contain a combination of

5 is a diagram for explaining an application example according to an embodiment.

The embodiment according to FIG. 5 can be appropriately positioned by placing the scale tip at the site of the procedure, and the suitability of scaling to facilitate the detection of the contact area with the scale tip among the artificial teeth and the gingival area of the tooth model can be easily performed. This is an exemplary diagram of a system for evaluating and implementing an environment capable of obtaining and evaluating objective data of a scaling exercise.

The scaler 600 of the practitioner is composed of a scaler tip 610 and a handpiece 620.

Scaler tip 610 is composed of a coupling portion 610a engaging with the handpiece 620, a support portion 610b extending from the coupling portion 610a, a contact portion 610c extending from the support portion 610b. The contact detection sensor 611 is installed at the contact portion 610c of the scaler tip 610. The contact detection sensor 611 is composed of a plurality of pressure detection sensors located apart from each other.

The contact unit 610c includes a plurality of sensing regions spaced apart from each other and a boundary region surrounding each of the plurality of sensing regions. The touch sensor 611 includes a pressure sensitive electrode 6112, and the pressure sensitive electrode 6112 is provided in each of the plurality of sensing regions.

The pressure sensitive electrode 6112 is composed of a conductive thin film and a support for supporting the conductive thin film, and cracks are formed in the conductive thin film.

The handpiece 620 is provided with a first detection device 621 that receives sensor information from the touch sensor 611.

The first detection device 621 detects a resistance value of the conductive thin film that changes with the movement of the crack surface according to the pressure applied to the pressure sensitive electrode 6112.

The first detection device 621 detects an area where contact with the target device has occurred in the area of the contact portion 610c of the scaler tip 610 based on the sensor data from the contact detection sensor 611, and the handpiece ( The tilt angle of the handpiece 620 is detected based on the sensor data of the gyro sensor provided in the 620. The detected data is converted into visual graphics and displayed via a display provided on the handpiece 620 or via an external computing device.

The scaler 600 is used to practice scaling using the tooth model 700. The dental model 700 includes artificial teeth, artificial teeth covering the artificial teeth, artificial teeth and artificial teeth are installed on the second detection device 710 and the second detection device for detecting an electrical change caused by contact with the contact portion 610c ( The data detection processor 720 detects an area in which the contact portion 610c contacts the tooth model 700 based on the sensor data of the 710. The artificial dentition includes a plurality of artificial teeth forming a row, the artificial tooth includes a first area exposed to the outside, a second area covered by the free gingival area of the artificial gingiva, and a third area attached to the gingival area of the artificial gingiva. In addition, the second detection device 710 may be installed in at least one of the first region, the second region, and the dental boundary region of the second region and the third region. In addition, the second detection device 710 includes a tooth electrode portion 711 provided in the first region. The tooth electrode part 711 includes a receiving electrode 712 and a transmitting electrode 713 positioned to cross each other. The data detection processor 720 may determine a position where the contact unit 610c contacts the tooth model 700 by detecting an amount of change in capacitance between the receiving electrode 712 and the transmitting electrode 713. This determination result is displayed via the display of handpiece 620 or an external computing device.

The target device sensor 110 may be installed in plural on the artificial tooth of the dental model 700. The target device sensor 110 senses a vibration generated by the contact of the contact portion 610c and the tooth model 700.

The haptic program 120 replicates vibration generated by the contact of the contact unit 610c and the tooth model 700 based on the sensor data received from the target device sensor 110, and through the haptic feedback device 60. Allows the duplicated vibration to be output. As described above, the motion signal (vibration motion signal) generated by the device monitoring program 130 and the motion signal (vibration motion signal) generated by the haptic program 120 are generated through an ANN based algorithm as described above. Can be identical to each other. The haptic feedback device 60 may be mounted to the supervisor's scaler 800. Therefore, the vibration of the dental model 700 according to the contact between the practitioner scaler 600 and the tooth model 700 may be duplicated when the practitioner performs the scaling exercise, thereby causing the supervisor's scaler to vibrate. If the practitioner scales the tooth model 700 with the scaler 600 at a strength greater than the recommendation (eg, scraping the artificial tooth, etc.), the vibration of the artificial tooth will be displayed on the scaler of the supervisor.

The present invention is a method for learning an artificial neural network based algorithm designed to monitor a first device, the method comprising receiving first data and, by one or more processors, using the received first data and artificial neural network algorithm in a first device. Determine a first service action recommendation for the service. And allow the second device to provide haptic feedback using the received first data. And receive a second service operation recommendation for the first device based on the haptic feedback. And if, by one or more processors, determine that the second service operation recommendation is different from the first service operation recommendation, the ANN algorithm uses the received first data to determine a third service operation recommendation for the first device. At least one parameter of may be adjusted by one or more processors. And the third service operation recommendation is the same as the second service operation recommendation. In some embodiments, when receiving the first data, the first data is received from one or more sensors operatively attached to the first device. In some embodiments one or more sensors can collect amplitude and frequency data of vibrations of the first device. In addition, in some embodiments, a previously stored service operation recommendation for a first device associated with previously stored data and previously stored data is received, and the ANN algorithm uses the received first data to generate a third for the first device. At least one parameter of the ANN algorithm may be adjusted by one or more processors to determine a service operation recommendation, wherein the third service operation recommendation is the same as the second service operation recommendation.

Further, in some embodiments, the ANN algorithm uses the previously stored data to determine the fourth service operation recommendation for the first device and the ANN algorithm determines the third service operation recommendation for the third device. By adjusting at least one parameter of the ANN algorithm. The third service operation recommendation is the same as the second service operation recommendation, and the fourth service operation recommendation is the same as the previously stored service operation recommendation. Further, in some embodiments, the video feed may be displayed by receiving a video feed from one or more video recording devices representing at least a portion of the first device. Further, in some embodiments, the second service operation recommendation for the first device may be received based on the haptic feedback, and the second service operation recommendation for the first device may be received based on the haptic feedback and the video feed. In addition, in some embodiments, the tactile feedback may include physical properties generated to simulate how the surface of the components of the first device feel. Further, in some embodiments, at least one parameter may include a module and weights.

Embodiments according to the present invention described above can be implemented in the form of program instructions that can be executed by various computer components, and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the computer readable recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the computer software field. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. medium) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be modified with one or more software modules to perform the processing according to the present invention, and vice versa.

Particular implementations described in the present invention are embodiments and do not limit the scope of the present invention in any way. For brevity of description, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection or connecting members of the lines between the components shown in the drawings are illustrative of the functional connection and / or physical or circuit connections as an example, in the actual device replaceable or additional various functional connections, physical It may be represented as a connection, or circuit connections. In addition, unless specifically mentioned, such as "essential", "important" may not be a necessary component for the application of the present invention.

In addition, the detailed description of the present invention has been described with reference to a preferred embodiment of the present invention, but those skilled in the art or those skilled in the art having ordinary knowledge in the technical field described in the claims to be described later It will be understood that various modifications and variations can be made in the present invention without departing from the scope of the present invention. Therefore, the technical scope of the present invention should not be limited to the contents described in the detailed description of the specification but should be defined by the claims.

Claims (11)

Collecting sensor data from a target device sensor installed in the first target device;
Generating an operation signal by monitoring the detection result of the target device sensor through an artificial neural network based algorithm; And
Driving a haptic feedback device installed in a second target device based on the operation signal;
Device monitoring method using artificial neural network based algorithm. According to claim 1,
Monitoring the detection result of the target device sensor through an artificial neural network based algorithm to generate an operation signal,
Generating a first operation signal based on the sensor data; And
Monitoring the first target device with an artificial neural network based algorithm based on the sensor data to generate a second operation signal;
Device monitoring method using artificial neural network based algorithm. The method of claim 2,
Driving the haptic feedback device installed in the second target device based on the operation signal,
When the first and second operation signals coincide with each other, the haptic feedback device is driven by the second operation signal.
Device monitoring method using artificial neural network based algorithm. A first target device;
A target device sensor installed in the first target device;
Haptic feedback devices;
A computing device installed with a haptic program that generates a first operation signal based on sensor data received from the target device sensor;
The second operation signal is compared with a device monitoring program that monitors the first target device using an artificial neural network-based algorithm based on the sensor data, and the second operation signal generated from the device monitoring program and the first operation signal are compared with each other. A server equipped with a training module for training the device monitoring program to match the first operating signal;
The haptic feedback device is operated based on the second operation signal
Device monitoring system using artificial neural network based algorithm. The method of claim 4, wherein
The training module adjusts a parameter of an artificial neural network based algorithm to cause the device monitoring program to output a second operation signal that matches the first operation signal.
Device monitoring system using artificial neural network based algorithm. The method of claim 5,
The haptic feedback device is installed on the second target device
Device monitoring system using artificial neural network based algorithm. The method of claim 6,
The target device sensors may be spaced apart from each other and installed in the first target device.
Device monitoring system using artificial neural network based algorithm. The method of claim 7, wherein
The target device sensor, the computing device, the server and the haptic feedback device communicate data with each other via a network.
Device monitoring system using artificial neural network based algorithm. The method of claim 8,
The server notifies the computing device if the second operation signal matches the first operation signal.
Device monitoring system using artificial neural network based algorithm. The method of claim 9,
The target device sensor detects vibration of the first target device.
Device monitoring system using artificial neural network based algorithm. Receiving sensor data from a target device sensor installed in the first target device;
Generating a first operation signal based on the sensor data;
Monitoring the first target device with an artificial neural network based algorithm based on the sensor data to generate a second operation signal;
Comparing the first and second operation signals with each other;
Adjusting a parameter of an artificial neural network based algorithm such that the second operating signal matches the first operating signal; And
Driving the haptic feedback device based on the second operation signal if the second operation signal and the first operation signal coincide with each other after adjusting the parameter.
Device monitoring method using artificial neural network based algorithm.

Images