Three-layer artificial intelligence detection system

Abstract

To provide a three-layer artificial intelligence detection system that processes, manages and executes detection data and related programs in the layers, thereby reducing failure rates and improving data processing capabilities. [Solution] The three-layer artificial intelligence detection system includes at least one sensor 10, a gateway 20, and a server platform 30. The sensor senses a device 40 to obtain sensory signal data of the device, and includes a first artificial intelligence module 11 and a first communication module 12. The first artificial intelligence module performs one of processing the sensory signal data, basic judgment of the sensory signal data, and OTA. The gateway includes a second artificial intelligence module 21 and a second communication module 22. The gateway is connected to and communicates with the first communication module via the second communication module.

Description

[Technical field]

[0001] The present invention relates to a detection system, and more particularly to a three-layer artificial intelligence detection system that processes, manages and executes detection data and related programs in layers, processes large amounts of data in real time and synchronously, and improves data processing capabilities. [Background technology]

[0002] AIoT (Artificial Intelligence of Things) smart network technology introduces artificial intelligence (AI) systems into the IoT (Internet of Things), applying traditional IoT technologies to closely link multiple devices; for example, commonly seen functions such as automation, remote control, and device connectivity are all included in the scope of IoT applications.

[0003] As AIoT smart network technology gradually develops and matures, the innovative use of AIoT smart networks is gradually increasing in industry and daily life. AIoT has the ability to learn from external data, make predictions, analyses, and judgments, and provide customized services through the accumulation of data.

[0004] Traditionally, AIoT smart network technology has been applied to device detection systems, and its structure includes a perception layer, a network layer, and an application layer. The perception layer is applied to sensors and the like, and can obtain device perception signal data anytime and anywhere. The network layer uses a gateway to transmit perception signal data to an intermediary and send commands, accurately transmitting device information. The application layer uses a server to store, analyze, and reuse data, improving management efficiency and providing better services.

[0005] The above-mentioned conventional equipment detection system can collect a large amount of data from the equipment, improve the analysis and prediction effect, predict equipment failure, and reduce the adverse impact of maintenance caused by failure, but generally rely on the server to analyze and process the collected big data and messages in large quantities, and smartly control the equipment. Therefore, the server has to bear a large burden in receiving, processing, and controlling the data, which can reduce the efficiency and speed of data processing performed by the entire system. Summary of the Invention [Problem to be solved by the invention]

[0006] The objective of the present invention is to provide a three-layer artificial intelligence detection system, which processes, manages and executes detection data and related programs in the layers, thereby reducing the failure rate and improving data processing ability. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, the invention of claim 1 provides a three-layer artificial intelligence detection system comprising at least one sensor, a gateway, and a server platform, The sensor senses a device to obtain sensory signal data of the device, and includes a first artificial intelligence module and a first communication module, the first artificial intelligence module performs one of processing the sensory signal data, basic judgment of the sensory signal data, and OTA (Over-the-Air); the gateway includes a second artificial intelligence module and a second communication module, the second artificial intelligence module performs one of collecting the sensory signal data, cleaning the sensory signal data, high-level judgment of the sensory signal data, and OTA management; the gateway communicates with the first communication module via the second communication module; the server platform includes a third artificial intelligence module, a data storage management module, and a third communication module, the third artificial intelligence module and the data storage management module perform one of big data collection, trend analysis, device management, customer management, and OTA records; and the server platform communicates with the second communication module via the third communication module.

[0008] The three-layer artificial intelligence detection system of the invention of claim 2 is characterized in that the device is one of a motor, a pump, or a high-voltage electrical device, and the sensory signal data is one of sound, vibration, electromagnetic waves, and electric current.

[0009] The three-tier artificial intelligence detection system of the invention of claim 3 is characterized in that the gateway is an edge gateway.

[0010] The three-layer artificial intelligence detection system of the invention of claim 4 is characterized in that the first communication module, the second communication module and the third communication module are connected and communicate with each other via a wired or wireless method.

[0011] The three-layer artificial intelligence detection system of the invention of claim 5 is characterized in that the third communication module and the second communication module are connected and communicate with each other via Ethernet (registered trademark), WiFi (registered trademark), Bluetooth (registered trademark) or RF (Radio Frequency).

[0012] The three-tier artificial intelligence detection system of the invention of claim 6 is characterized in that the server platform is a cloud server or a local server.

[0013] The three-layer artificial intelligence detection system of the invention of claim 7 is characterized in that the gateway is connected to an abnormality alarm system and issues a warning message when an abnormality occurs in the operation of the device.

[0014] The three-tier artificial intelligence detection system of the invention of claim 8 is characterized in that the gateway and the server platform are connected via a switch to form a network bridge. Effect of the Invention

[0015] The three-layer artificial intelligence detection system of the present invention has the following advantages (1) to (7). (1) Distributed layer processing. (2)High efficiency. (3) High speed. (4) Low cost. (5)Easy development. (6)Continuous automated learning and updating of artificial intelligence models. (7) Large amounts of data can be processed simultaneously in real time. [Brief description of the drawings]

[0016] [Figure 1] 1 is a schematic diagram showing a three-layer artificial intelligence detection system according to an embodiment of the present invention; FIG. [Diagram 2]FIG. 1 is a block diagram showing a three-layer artificial intelligence detection system according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] In order to enable those skilled in the art to fully understand the objectives, features and effects of the present invention, the following describes in detail the technical content of the present invention in conjunction with the accompanying drawings, together with suitable embodiments of the present invention.

[0018] Please refer to Figure 1 and Figure 2. Figure 1 is a schematic diagram of a three-layer AI detection system according to an embodiment of the present invention. Figure 2 is a block diagram of a three-layer AI detection system according to an embodiment of the present invention.

[0019] As shown in Figures 1 and 2, a three-layer artificial intelligence detection system according to an embodiment of the present invention includes a sensor 10, a gateway 20 and a server platform 30, which will be described in detail below.

[0020] The sensor 10 detects a device 40 and obtains sensing signal data of the device 40. The sensor 10 includes a first artificial intelligence module 11 and a first communication module 12. The first artificial intelligence module 11 performs one of processing the sensing signal data, making basic judgments on the sensing signal data, and over-the-air (OTA).

[0021] The processing of the sensory signal data performed by the first artificial intelligence module 11 includes the following (1) and (2). (1) Data rationalization: When abnormal or unreasonable values ​​appear in the sensory signal data, for example, when most of the high and low changes in values ​​within an area are within a certain range, or when a value that is particularly higher or lower than the range suddenly appears, or when an area suddenly appears with no sensory numerical data at all, it is determined that erroneous sensory numerical data has appeared, and the first artificial intelligence module 11 automatically corrects and rationalizes the data. (2) Data noise reduction: Removing noise in the sensory signal data.

[0022] The OTA of this embodiment does not necessarily need to use a physical connection, and data transfer, software download, and update may be performed using wireless communication technology.

[0023] The gateway 20 includes a second artificial intelligence module 21 and a second communication module 22. The second artificial intelligence module 21 performs any one of the following: collection of sensory signal data, cleaning of sensory signal data, advanced judgment of sensory signal data, and OTA management. The gateway 20 is connected to and communicates with the first communication module 12 via the second communication module 22.

[0024] The server platform 30 includes a third artificial intelligence module 31, a data storage management module 32, and a third communication module 33. The third artificial intelligence module 31 and the data storage management module 32 perform any one of big data collection, trend analysis, device management, customer management, and OTA recording. The server platform 30 is connected to and communicates with the second communication module 22 via the third communication module 33.

[0025] In one embodiment of the present invention, the device 40 is one of a motor, a pump, and a high voltage electrical device, and the sensory signal data is one of a sound, a vibration, an electromagnetic wave, and an electric current.

[0026] In one embodiment of the present invention, the gateway 20 is an edge gateway.

[0027] In one embodiment of the present invention, the first communication module 12, the second communication module 22 and the third communication module 33 are connected and communicate with each other via wired or wireless communication.

[0028] In one embodiment of the present invention, the third communication module 33 and the second communication module 22 communicate with each other via Ethernet, WiFi, Bluetooth or RF (Radio Frequency).

[0029] In one embodiment of the present invention, the server platform 30 is either a cloud server or a local server.

[0030] In one embodiment of the present invention, the gateway 20 connects with an abnormality alarm system 50 to issue an alarm message when an abnormality occurs in the operation of the device 40.

[0031] Control is exercised via communication signals to command the device 40 to automatically shut down operation, preventing the device 40 from continuing to operate under abnormal conditions.

[0032] In one embodiment of the present invention, the gateway 20 and the server platform 30 are connected via a switch 60 to form a network bridge.

[0033] The above is an introduction of an embodiment of the three-layer artificial intelligence detection system of the present invention. Next, the features and functions of the present invention will be introduced.

[0034] The present invention utilizes multi-layered artificial intelligence technology means to process, manage and execute the received detection data and associated programs in the layers.

[0035] The sensor 10 of the present invention may perform initial artificial intelligence data processing (e.g., noise reduction of sensory signal data, basic judgment of sensory signal data, etc.) in the perception layer through the first artificial intelligence module 11, and apply it to sensing a different device 40. For example, when the sensor 10 replaces the sensor motor device originally possessed by the sensor high-voltage device, when the first artificial intelligence module 11 detects the difference in the current sensor signal data, it determines that the originally sensed device 40 has been changed to another device 40, and automatically updates it via OTA to generate an artificial intelligence sensing model corresponding to the different device. Therefore, the sensor signal data of the different device 40, such as voice, vibration, electromagnetic wave, and current, can be applied to the present invention.

[0036] One advantage of the present invention is as follows:

[0037] The device sensory signal data sensed by the sensor 10 of the present invention is continuously uploaded to the server platform 30 by the gateway 20, for data storage, analysis and management.

[0038] When the same device 40 is used and operated for a certain period of time, or when the device 40 becomes worn out, differences will occur in the sensory signal data generated by the device, and the AI ​​sensing model originally possessed by the sensor 10 will no longer be applicable. Therefore, the server platform 30 of the present invention can immediately determine that there is a difference in the sensory signal data of the device based on the sensory signal data continuously collected within a certain period of time, and determine that the current AI sensing model possessed by the sensor 10 is no longer applicable, and automatically update the AI ​​sensing model for the sensor 10 via OTA, thereby improving the effect of analysis and prediction, and accurately predicting whether the device will become worn out and break down.

[0039] Other advantages of the present invention are as follows:

[0040] When multiple sensors 10 detect devices 40 with the same attributes, for example, when the devices 40 are pumps of the same manufacturer and model, one of the pump devices frequently breaks down and uploads the fault sensing data to the server platform 30, and the server platform 30 of the present invention receives the sensory signal data of all the devices 40 and stores, analyzes and manages this data. The other devices are not broken, but they are devices with the same attributes, so the server platform 30 can also apply a suitable and new artificial intelligence sensing model to these broken devices based on the originally stored fault sensing data, thereby improving the effect of analysis and prediction.

[0041] In addition, the gateway 20 may be located across countries and regions. For example, if one of the gateways 20 is in Taiwan and the other gateway 20 is in the United States, as described above, when the device 40 in Taiwan breaks down, the server platform 30 provides a suitable and new artificial intelligence sensing model for the non-failed devices in the United States based on the stored fault sensing data of the device 40 in Taiwan. That is, the present invention collects and analyzes big data through the server platform 30. If different or multiple types of faults occur in the devices 40 in countries and regions such as Taiwan, the United States, Japan, and Europe, the gateway 20 may upload the fault sensing data of the devices in different countries to the server platform 30, collect it in a unified manner, analyze and predict it, and provide a suitable and new artificial intelligence sensing model for various fault conditions of the devices to all the gateways 20 and sensors 10 via OTA, thereby improving the effect of analysis and prediction.

[0042] Further advantages of the present invention are as follows:

[0043] The sensors 10 transmit sensory signals to the gateway 20. The gateway 20 may perform high-level artificial intelligence data processing at the network layer via a second artificial intelligence module 21.

[0044] The gateway 20 may transmit the sensory signal data of the sensor 10 to the server platform 30. If the server platform 30 already has a suitable new artificial intelligence sensing model, the gateway 20 determines and then OTA allocates and transmits it to the sensor 10 that needs it. The gateway 20 monitors whether the artificial intelligence sensing model transmitted to the sensor 10 has already been updated successfully.

[0045] In addition to performing OTA management, the gateway 20 also stores sensory signal data and transmits the sensory signal data to the server platform 30. The server platform 30 has the sensory signal data of all the sensors 10. If the data of the server platform 30 is lost or damaged, the gateway 20 is used again to transmit new sensory signal data to the server platform 30, and the server platform 30 obtains new sensory signal data.

[0046] The server platform 30 is connected to a plurality of gateways 20 and receives data sent from the gateways 20. The gateways 20 may be located across countries and regions, and each gateway 20 may be connected to a plurality of sensors 10. Thus, the server platform 30 receives data transmitted from the plurality of gateways 20 and the plurality of sensors 10, collects big data, and the third artificial intelligence module 31 performs trend analysis and reporting for the plurality of detection data, and provides customized device management and customer management according to customer needs, subscription, membership, and other levels. That is, the artificial intelligence model is continuously updated as necessary for the gateway 20 and the plurality of sensors 10 via OTA, and the present invention can provide customers with favorable device management effects and better device detection services.

[0047] As can be seen from the above, the three-layer artificial intelligence detection system of the present invention has the following advantages (1) to (7). (1) Distributed layer processing. (2)High efficiency. (3) High speed. (4) Low cost. (5)Easy development. (6)Continuous automated learning and updating of artificial intelligence models. (7) Large amounts of data can be processed simultaneously in real time. [Explanation of symbols]

[0048] 10 Sensors 11 First Artificial Intelligence Module 12 First communication module 20. Gateway 21 Second Artificial Intelligence Module 22 Second communication module 30 Server Platforms 31 Third Artificial Intelligence Module 32 Data storage management module 33 Third communication module 40 equipment 50 Abnormality Warning System 60 Switch

Claims

1. A three-tier artificial intelligence detection system comprising at least one sensor, a gateway, and a server platform, The sensor senses a device to obtain sensory signal data of the device, and includes a first artificial intelligence module and a first communication module, and the first artificial intelligence module performs one of processing the sensory signal data, basic judgment of the sensory signal data, and OTA (Over-the-Air); The gateway includes a second artificial intelligence module and a second communication module, the second artificial intelligence module performs one of the following: collection of the sensory signal data, cleaning of the sensory signal data, high-level judgment of the sensory signal data, and OTA management, and the gateway is connected to and communicates with the first communication module through the second communication module; A three-layer artificial intelligence detection system, characterized in that the server platform includes a third artificial intelligence module, a data storage and management module, and a third communication module, the third artificial intelligence module and the data storage and management module perform one of big data collection, trend analysis, device management, customer management, and OTA recording, and the server platform communicates with the second communication module via the third communication module.

2. The device is one of a motor, a pump, and a high-voltage electrical device; The three-layer artificial intelligence detection system according to claim 1, wherein the sensory signal data is any one of sound, vibration, electromagnetic wave, and electric current.

3. The three-tier artificial intelligence detection system according to claim 1, characterized in that the gateway is an edge gateway.

4. The three-layer artificial intelligence detection system as described in claim 1, characterized in that the first communication module, the second communication module and the third communication module are connected and communicate with each other via a wired or wireless method.

5. The three-layer artificial intelligence detection system of claim 1, characterized in that the third communication module and the second communication module are connected and communicate with each other via Ethernet (registered trademark), WiFi (registered trademark), Bluetooth (registered trademark) or RF (Radio Frequency).

6. The three-tier artificial intelligence detection system according to claim 1, characterized in that the server platform is a cloud server or a local server.

7. The three-layer artificial intelligence detection system of claim 1, characterized in that the gateway is connected to an abnormality alarm system and issues a warning message when an abnormality occurs in the operation of the device.

8. The three-layer artificial intelligence detection system according to claim 1, wherein the gateway and the server platform are connected through a switch to form a network bridge.

Images