CN-122018579-A - Edge computing terminal, system and gate control method

CN122018579ACN 122018579 ACN122018579 ACN 122018579ACN-122018579-A

Abstract

The invention discloses an edge computing terminal, an edge computing system and a gate control method, which relate to the technical field of automatic control, wherein the terminal comprises a pluggable I/O component, a sensor group and an external executing mechanism; the system comprises a dam gate control part, a heterogeneous calculation module, a mixed energy management module, a real-time microcontroller unit and a control module, wherein the heterogeneous calculation module comprises an application processor unit and the real-time microcontroller unit, the mixed energy management module is used for supplying power in self-powered equipment when external power supply and power failure are detected, and triggering an external power failure instruction to control the real-time microcontroller unit to control the dam gate to be closed within a preset time period through the dam gate control part.

Inventors

ZHANG TAIQIN
ZHANG CHUAN
HUANG LIAN
Deng Zedong
Kou Jingyue
LI JIAN
LI LINPENG

Assignees

重庆新世杰电气股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260225

Claims (10)

1. An edge computing terminal, comprising: The device comprises a pluggable I/O component, a sensor group and an external executing mechanism, wherein the sensor group comprises a water level gauge and a flow rate meter; The system comprises a dam gate control component, a heterogeneous calculation module, a real-time microcontroller unit, a dam gate control component and a dam gate control component, wherein the heterogeneous calculation module comprises an application processor unit and the real-time microcontroller unit, the application processor unit is used for generating a gate opening sequence corresponding to water level prediction information in a preset future time period according to sensor data acquired by the sensor group and generating an opening control instruction corresponding to the gate opening sequence; And when the external power supply and the power failure are detected, the self-powered equipment is utilized to supply power, and an external power failure instruction is triggered to control the real-time microcontroller unit to control the dam gate to be closed within a preset time period through the dam gate control component.
2. The edge computing terminal of claim 1, wherein the heterogeneous computing module further comprises a shared memory to which the application processor unit and the real-time microcontroller unit are both connected; The application processor unit is used for generating an emergency control instruction according to the external power-off instruction, writing the emergency control instruction into the shared memory and triggering high-priority interrupt; The real-time microcontroller unit is used for reading the emergency control instruction from the shared memory according to the high-priority interrupt, and controlling the dam gate to be closed within the preset time period through the dam gate control component according to the emergency control instruction.
3. The edge computing terminal according to claim 1, wherein the application processor unit is specifically configured to generate water level prediction information within the preset future time period by using a long-short-term memory network model according to the sensor data, generate the gate opening sequence by using a gate-hydraulics coupling model according to the water level prediction information, and generate the opening control instruction according to the gate opening sequence.
4. The edge computing terminal of claim 3, wherein the long-term memory network model includes a high-precision prediction model and a lightweight prediction model, wherein the generating water level prediction information within the preset future time period using the long-term memory network model based on the sensor data includes: When the preset triggering condition is not met, generating water level prediction information in the preset future time period by utilizing the lightweight prediction model according to target sensor data, wherein the target sensor data are acquired by partial sensors in the sensor group; When a preset triggering condition is met, water level prediction information in the preset future time period is generated by utilizing the high-precision prediction model according to the sensor data, wherein the preset triggering condition comprises at least one of a water level change rate exceeding a change rate threshold value, a water level prediction error reaching an error threshold value, a preset external control instruction received and data abnormality acquired by a key sensor in the sensor group.
5. The edge computing terminal of claim 1, wherein the external actuator further comprises a decontamination device; The application processor unit is further used for detecting whether a target control strategy is met or not according to the water level prediction information and the sensor data, and if yes, a preset opening control sequence and/or a preset cleaning instruction corresponding to the target control strategy are generated to control the real-time microcontroller unit to drive the dam gate control component and/or the cleaning equipment, wherein the target control strategy is any preset control strategy.
6. The edge computing terminal of claim 1, wherein the self-powered device comprises a super capacitor, a lithium battery, and a diesel generator; The hybrid energy management module is specifically used for switching to use the super capacitor, the lithium battery and the diesel generator to supply power when external power supply and power failure are detected.
7. The edge computing terminal of claim 1, further comprising a communication unit, wherein the communication unit comprises a mobile communication module and a satellite communication module; And the heterogeneous computing module is used for sending alarm information through the satellite communication module when the signal quality of the mobile communication module does not meet the communication requirement.
8. The edge computing terminal of any one of claims 1 to 7, wherein the sensor group further comprises at least one of a rain gauge, a weather meter, and a sediment concentration meter; The pluggable I/O component is further used for being connected with an artificial intelligent visual ball machine, the external execution mechanism further comprises a cleaning device, and the application processor unit is further used for generating a cleaning control instruction according to the event information to be cleaned output by the artificial intelligent visual ball machine so as to control the real-time microcontroller unit to drive the cleaning device to clean.
9. An edge computing system comprising an edge computing terminal according to any one of claims 1 to 8 and a sensor group connected to the edge computing terminal.
10. A gate control method, applied to the edge computing terminal according to any one of claims 1 to 8, comprising: receiving sensor data acquired by a sensor group by utilizing a pluggable I/O component, wherein the sensor group comprises a water level gauge and a flowmeter; Generating a gate opening sequence corresponding to water level prediction information in a preset future time period according to the sensor data by using an application processor unit, and generating an opening control instruction corresponding to the gate opening sequence; Controlling a dam gate control part to adjust the opening of the dam gate by using a real-time microcontroller unit according to the opening control instruction; and the real-time microcontroller unit is used for controlling the dam gate to be closed within a preset time period through the dam gate control component according to an external power-off instruction triggered by the hybrid energy management module, wherein the hybrid energy management module is used for supplying power in self-powered equipment when external power supply and power off are detected, and triggering the external power-off instruction.

Description

Edge computing terminal, system and gate control method Technical Field The invention relates to the technical field of automatic control, in particular to an edge computing terminal, an edge computing system and a gate control method. Background In the operation management of a front pool dam of a small and medium-sized unmanned hydropower station, accurate prediction of the relation between water level and reservoir capacity is a key basis for guaranteeing flood control safety, optimizing water storage power generation and realizing intelligent regulation and control of a gate. However, the water level monitoring mode of the centralized control center in the related technology is mostly dependent on a small amount of telemetry data of a single sensor (such as a float water level gauge), lacks of prejudging capability on future water level trend, causes response lag under sudden conditions such as storm, flood and the like, lacks of foresight in regulation and control decision, and is difficult to drive a 10kW gate motor to complete full-stroke closing once locally when external electricity is lost and the flood is sudden upstream, so that great potential safety hazards exist. Therefore, how to realize high-precision and low-delay local water level prediction and gate control and improve the automation and safety of the operation of the hydropower station is an urgent problem to be solved nowadays. Disclosure of Invention The invention aims to provide an edge computing terminal, an edge computing system and a gate control method, which are used for improving the automation and the safety of the operation of a hydropower station by means of high-precision and low-delay local water level prediction and gate control. In order to solve the above technical problems, the present invention provides an edge computing terminal, including: The device comprises a pluggable I/O component, a sensor group and an external executing mechanism, wherein the sensor group comprises a water level gauge and a flow rate meter; The system comprises a dam gate control component, a heterogeneous calculation module, a real-time microcontroller unit, a dam gate control component and a dam gate control component, wherein the heterogeneous calculation module comprises an application processor unit and the real-time microcontroller unit, the application processor unit is used for generating a gate opening sequence corresponding to water level prediction information in a preset future time period according to sensor data acquired by the sensor group and generating an opening control instruction corresponding to the gate opening sequence; And when the external power supply and the power failure are detected, the self-powered equipment is utilized to supply power, and an external power failure instruction is triggered to control the real-time microcontroller unit to control the dam gate to be closed within a preset time period through the dam gate control component. In another aspect, the heterogeneous computing module further includes a shared memory to which the application processor unit and the real-time microcontroller unit are both connected; The application processor unit is used for generating an emergency control instruction according to the external power-off instruction, writing the emergency control instruction into the shared memory and triggering high-priority interrupt; The real-time microcontroller unit is used for reading the emergency control instruction from the shared memory according to the high-priority interrupt, and controlling the dam gate to be closed within the preset time period through the dam gate control component according to the emergency control instruction. In another aspect, the application processor unit is specifically configured to generate water level prediction information in the preset future time period by using a long-short-term memory network model according to the sensor data, generate the gate opening sequence by using a gate-hydraulic coupling model according to the water level prediction information, and generate the opening control instruction according to the gate opening sequence. In another aspect, the long-short-term memory network model includes a high-precision prediction model and a lightweight prediction model, and the generating water level prediction information within the preset future time period according to the sensor data using the long-short-term memory network model includes: When the preset triggering condition is not met, generating water level prediction information in the preset future time period by utilizing the lightweight prediction model according to target sensor data, wherein the target sensor data are acquired by partial sensors in the sensor group; When a preset triggering condition is met, water level prediction information in the preset future time period is generated by utilizing the high-precision prediction model according to the sensor data, wherein the p