Search

KR-20260063214-A - Sensors with on-device AI function Integrated wired/wireless communication drive Noise sensor, its system, and its operation method

KR20260063214AKR 20260063214 AKR20260063214 AKR 20260063214AKR-20260063214-A

Abstract

The present invention relates to a noise sensor with an integrated wired/wireless communication drive and on-device AI function, a system, and a method of operation thereof. By introducing smart functions and using machine learning via an Artificial Neural Network (ANN) to scan (capture data) the noise status of a measurement target within seconds, organize and label the data, distinguish between normal and abnormal conditions regarding abnormal noise, and derive normal and abnormal results to predict accidents, it is possible to prevent and avoid social and natural disasters in industrial infrastructure facilities in advance. The method of operation of a monitoring noise sensor according to the present invention comprises: (a) a step in which, when a noise source is input through a microphone and a running button of an external interface is interrupted, the AI of the on-device AI noise sensor operates to compute and store data of the noise source using an ANN algorithm of a storage device; (b) a step in which the noise state of a measurement target object is scanned through machine learning using the ANN algorithm, and data filtering and labeling is performed, and normal and abnormal conditions regarding abnormal noise are distinguished through machine learning, and normal and abnormal results are derived to predict an accident; and (c) a step in which a smart terminal, tablet PC, laptop, or PC is connected to the on-device AI noise sensor via WAN, LAN, Bluetooth, or USB to monitor the detection and result data of the sensor in real time, and to set and verify the data.

Inventors

  • 강언욱
  • 박상규
  • 정순현

Assignees

  • 주식회사 레스코

Dates

Publication Date
20260507
Application Date
20241030

Claims (7)

  1. In a method of operating a cylindrical noise sensor, (a) When a noise source is input through a microphone and the running button of an external interface is interrupted, the AI of the on-device AI noise sensor operates to compute and store data of the noise source using an ANN algorithm of a storage device; (b) a step of scanning the noise status of a measurement target through machine learning using the above ANN algorithm, filtering and labeling the data, distinguishing between normal and abnormal conditions for abnormal noise through machine learning, deriving normal and abnormal results, and predicting accidents; and (c) A step of transmitting normal and abnormal result data from the on-device AI noise sensor to an edge gateway device via wired/wireless communication such as wireless LAN, Bluetooth, or USB; A method of operation of a noise sensor including
  2. In a method of operating a cylindrical noise sensor, (a) When a noise source is input through a microphone and the running button of an external interface is interrupted, the AI of the on-device AI noise sensor operates to compute and store data of the noise source using an ANN algorithm of a storage device; (b) a step of scanning the noise status of a measurement target through machine learning using the above ANN algorithm, filtering and labeling the data, distinguishing between normal and abnormal conditions for abnormal noise through machine learning, deriving normal and abnormal results, and predicting accidents; and (c) A step of connecting to the above-mentioned on-device AI noise sensor via WAN, LAN, Bluetooth, or USB with a smart terminal, tablet PC, laptop, or PC to monitor the sensor's detection and result data in real time, and to set and verify the data; A method of operation of a noise sensor including
  3. In claim 1 or claim 2, The above-mentioned on-device AI noise sensor is, By applying machine learning to normal-state noise standard data and changed data, distinguishing between normal and abnormal conditions for abnormal noise and deriving normal and abnormal results, Method of operation of the noise sensor.
  4. In claim 1 or claim 2, The above-mentioned on-device AI noise sensor is, The above machine learning operation and the above normal and abnormal results are distinguished by color and displayed via an indicator LED, and in the case of an abnormal result, it is indicated by flashing red and provided as a voice message through a speaker. Displaying the above normal and abnormal results through a running indicator screen, Method of operation of the noise sensor.
  5. A cylindrical on-device AI noise sensor that, when a noise source is input through a microphone and the running button of an external interface is interrupted, operates the AI of the noise sensor to compute and store data of the noise source using an ANN algorithm of a storage device, scans the noise status of a measurement target object through machine learning using the said ANN algorithm, filters and labels the data, distinguishes normal and abnormal conditions regarding abnormal noise through the said machine learning, derives normal and abnormal results to predict accidents, and transmits the normal and abnormal result data to an edge gateway device via wired/wireless communication such as wireless LAN, Bluetooth, and USB; An edge gateway device that receives normal and abnormal result data of a measurement target from the above-mentioned on-device AI noise sensor via standardized Ethernet or wireless LAN, filters out duplicate data and abnormal noise data, and transmits the filtered normal and abnormal result data of the measurement target to a cloud server system via standardized Modebus RTU or Modebus TCP; and A cloud server system that stores and monitors result data regarding the normal and abnormal status of a measurement target received from the edge gateway device and the status of abnormalities of the sensor, and remotely controls the measurement target and the on-device AI noise sensor; A noise sensor system including
  6. A cylindrical on-device AI noise sensor that, when a noise source is input through a microphone and the running button of an external interface is interrupted, the AI of the noise sensor operates to compute and store data of the noise source using an ANN algorithm of a storage device, scans the noise status of a measurement target object through machine learning using the said ANN algorithm, filters and labels the data, distinguishes normal and abnormal conditions regarding abnormal noise through the said machine learning, derives normal and abnormal results to predict accidents, and transmits the normal and abnormal result data to an edge gateway device via wired/wireless communication such as wireless LAN, Bluetooth, and USB; and A smart terminal and a PC that connect to the above-mentioned on-device AI noise sensor via WAN, LAN, Bluetooth, and USB to monitor the sensor's detection and result data in real time and to set and verify data; A noise sensor system including
  7. A cylindrical body having a microphone for inputting a noise source positioned on one side of the exterior, and a speaker and a USB terminal positioned on the other side of the exterior; An upper cover configured on the upper part of the above body, having a transmitting/receiving antenna positioned in the center of the upper surface and an ON/OFF button and a Reset button positioned on the upper surface; and A lower cover configured at the lower part of the above body, with an attachment magnet disposed at the lower part; A noise sensor including

Description

Sensors with on-device AI function, Integrated wired/wireless communication drive, Noise sensor, its system, and its operation method The present invention relates to a noise sensor with an integrated wired/wireless communication drive and an on-device AI (Artificial Intelligence) function, a system thereof, and a method of operation thereof. More specifically, the invention relates to a noise sensor with an integrated wired/wireless communication drive and an on-device AI function that can check the condition of building structures, machinery, and equipment, collect real-time data, and analyze and predict potential risks such as wear, damage, and destruction of an object, a system thereof, and a method of operation thereof. Generally, in the case of architectural structures or mechanical devices, phenomena appearing inside or outside the facility, such as wall cracks caused by external forces, physical vibrations, impacts, and loads, and significant defects can be identified through safety inspections of the facility. Conventional noise sensors are used for industrial purposes by simply using the sound pressure level (dB(A)) of the noise to be measured directly by inspectors or managers, or applied to display boards or FNDs (7-segment) for display. Conventional noise sensors are provided as standalone components, and measurements are taken using various controller converters and control analyzers from different manufacturers. Additionally, during measurement, the noise and vibration frequency (Hz), amplitude, and sound intensity (dB) can be verified using an oscilloscope or monitor. On the other hand, conventional noise sensors have difficulty verifying whether the noise data matches the suitability for the relevant environmental conditions. In addition, since the noise level is measured primarily by converting only the sound intensity into dB, there is a problem in that it is difficult to accurately detect abnormal defects along with the frequency, amplitude, and sound intensity of the measurement target when judging and predicting defect conditions of the measurement target. In addition, due to sensors from different manufacturers and various sensor drivers (signal converters, communication transmission devices), issues regarding communication and wired/wireless compatibility, as well as protocol compatibility mismatches, have occurred. In addition, conventional noise sensors transmit only raw data converted into electrical signals of the sensor signal, thereby providing an unreasonable environment unsuitable for artificial intelligence processing of small and medium-sized data, which involves re-computing and processing the raw data in the storage of a stored cloud server system to implement AI as big data. In addition, conventional noise sensors are standardized into mostly passive sensor products by quantizing analog signals to convert them into digital, receiving the converted data, and displaying it on the device itself or on an LCD monitor, electronic display board, instrument panel, etc., which serve as a means of display. In addition, there are difficulties in users or safety managers individually inspecting and maintaining the object to be measured in a confined space exposed to danger in order to measure the noise status of the object. FIG. 1 is a block diagram of a noise sensor system with an integrated wired/wireless communication drive and on-device AI function according to the first embodiment of the present invention. FIG. 2 is a block diagram of a noise sensor system with an integrated wired/wireless communication drive and an on-device AI function according to a second embodiment of the present invention. FIGS. 3 to 11 illustrate a noise sensor with an integrated wired/wireless communication drive and an on-device AI function according to an embodiment of the present invention. FIGS. 3 and FIGS. 4 are perspective views, and Fig. 5 is a front view, and Fig. 6 is a rear view, and Fig. 7 is a plan view, and Fig. 8 is a bottom view, and FIGS. 9 to 11 are exploded perspective views. Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the invention in the drawings, parts unrelated to the description have been omitted, and similar parts throughout the entire description of the invention are described using similar reference numerals. Hereinafter, specific technical details to be implemented in the present invention will be described in detail with reference to the attached drawings. First embodiment of a noise sensor system FIG. 1 is a block diagram of a noise sensor system with an integrated wired/wireless communication drive and an on-device AI function according to a first embodiment of the present invention. A