Water-turbine generator set sediment characteristic online detection and fault prediction system

Abstract

The utility model discloses a water-turbine generator set sediment characteristic on-line detection and fault prediction system, which structurally comprises a vibration sensor, a flow velocity sensor, an integrated throw-in type liquid level meter sensor, a turbidity sensor, a laser particle size analyzer data acquisition module, a Raspberry Pi, a network database data processing module and a transmission storage module, and an online platform data display module. According to the utility model, by collecting and analyzing data of various sensors, reservoir basic information, reservoir sediment characteristics and specific information of the proportion of clay mineral components can be displayed to a user in the forms of a textbox, a data pie chart and the like, data uploaded to a MySQL database by a monitoring platform can be read in real time, and data visualization is realized in the forms of a broken line chart and the like; and displaying various data obtained by each sensor, including depth, pressure, surface velocity, sediment content and sediment particle size, and fusing a neural network model obtained by Keras deep learning framework training into a page system to predict the sediment content.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrological monitoring, and particularly to an online monitoring and fault prediction management system for sediment content of hydro-generator units. Background Art

[0002] There are many hydropower stations in China. Due to reasons such as soil erosion, it brings great difficulties to the operation and maintenance of hydro-generator units. For a long time, the sediment content monitoring of hydro-generator units has become the focus of attention. Real-time sediment content monitoring is an important part of hydrological surveys and a key part of the normal operation of hydro-generator units.

[0003] Currently, the main method for measuring sediment content in hydrology is: manual sampling and using the drying method to measure sediment content. This method requires a large amount of manpower, material resources and time from sample collection to analysis, and has a long measurement cycle, a cumbersome operation process, a large labor intensity, and it is difficult to monitor the change of sediment content in real time online.

[0004] Currently, there is no system for online detection of sediment characteristics and fault prediction of hydro-generator units. Staff cannot conveniently view the situation of hydro-generator units and cannot obtain early warnings of faults in hydro-generator units. Utility Model Content

[0005] In view of the deficiencies of the prior art, the present utility model provides an online detection and fault prediction system for sediment characteristics of hydro-generator units, which solves the problems of being unable to monitor the sediment passing situation of hydro-generator units in real time, being unable to conveniently view the situation of hydro-generator units, and being unable to obtain early warnings of faults in hydro-generator units.

[0006] To achieve the above objectives, the present utility model is realized through the following technical solutions: An online detection and fault prediction system for sediment characteristics of hydro-generator units includes a vibration sensor, a flow velocity sensor, an integrated immersion type liquid level gauge sensor, a turbidity sensor, a laser particle size analyzer, a Raspberry Pi, a network database, and an online platform.

[0007] Each sensor transmits the monitored data to the Raspberry Pi, and the Raspberry Pi processes the data and uploads it to the network database for the online platform to call.

[0008] This system can provide multiple typical reservoirs for users to choose. After confirmation of the selection, the specific information and various basic data of the selected reservoir will be displayed.

[0009] This system displays the basic information of the reservoir, the sediment characteristics of the reservoir, and the specific information of the proportion of clay mineral components to users in the form of text boxes and data pie charts, etc.

[0010] The system can read the data uploaded to the MySQL database by the monitoring platform in real time, and realize data visualization in the form of line charts and other ways, displaying various data obtained by each sensor, including: depth, pressure, surface flow velocity, sediment content, sediment particle size.

[0011] The system integrates the neural network model obtained by training the Keras deep learning framework into the page system, and can realize the prediction of sediment content. Description of the Drawings

[0012] Figure 1 It is a flowchart of an on-line detection and fault prediction system for sediment characteristics of a hydro-generator set. Detailed Embodiments

[0013] Next, the technical solutions in the embodiments of the present invention will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0014] Please refer to Figure 1 , the present invention provides a technical solution for an on-line detection and fault prediction system for sediment characteristics of a hydro-generator set: an on-line detection and fault prediction system for sediment characteristics of a hydro-generator set, including a vibration sensor, a flow velocity sensor, an integrated submersible level gauge sensor, a turbidity sensor, a laser particle size analyzer, a Raspberry Pi, a network database, and an online platform.

[0015] Install a vibration sensor on the hydro-generator unit.

[0016] Place a flow velocity sensor on the water surface.

[0017] Place an integrated submersible level gauge sensor, a turbidity sensor, and a laser particle size analyzer on the underwater platform.

[0018] Connect each sensor to the Raspberry Pi through a data cable.

[0019] The Raspberry Pi processes the data of each sensor and uploads it to the network database.

[0020] In the online platform, the staff logs in to the system through the account password on the login page, and then selects the hydropower station to be observed on the selection page to view various data.

[0021] Working principle of the utility model: When in use, data signals are monitored and generated by vibration sensors, flow rate sensors, integrated submersible liquid level sensors, turbidity sensors, and laser particle size analyzers, and the data signals are transmitted to the Raspberry Pi through RS-485 communication. After the data is processed by the Raspberry Pi, the processed data is uploaded to the network database, and the online platform calls the content in the network database to display various data to the staff.

Claims

1. An online detection and fault prediction system for sediment characteristics of a hydro-generator set, the system structure of which includes a vibration sensor, a flow rate sensor, an integrated immersion level meter sensor, a turbidity sensor, a laser particle size analyzer data acquisition module, a Raspberry Pi, a network database, and an online platform data display module. The network database includes a network database data processing, transmission and storage module; The data collected by the vibration sensor, flow rate sensor, integrated immersion level meter sensor, turbidity sensor, and laser particle size analyzer are transmitted to the Raspberry Pi through the RS-485 communication protocol. The data is processed by the Raspberry Pi and uploaded to the network database. The online platform data display module facilitates access by calling the data in the network database. The data includes: Depth, pressure, surface velocity, sediment content, and sediment particle size.

2. The system for online detection and fault prediction of sediment characteristics of a hydro-generator set according to claim 1 is characterized in that: The vibration sensor is located on the hydro-turbine unit and performs real-time monitoring of the vibration of the hydro-turbine generator unit.

3. The system for online detection and fault prediction of sediment characteristics of a hydro-generator set according to claim 1 is characterized in that: The flow velocity sensor is located on the water surface and uses a multi-spectral camera to monitor the flow velocity conditions in the water area near the hydro-generator set.

4. The system for online detection and fault prediction of sediment characteristics of a hydro-generator set according to claim 1 is characterized in that: The integrated submersible level meter sensor transmits the water pressure and water depth of the underwater platform to the Raspberry Pi for real-time monitoring.

5. The on-line detection and fault prediction system for sediment characteristics of a hydro-generator set according to claim 1 is characterized in that: The turbidity sensor is located on an underwater platform and monitors turbidity in real time based on the principle of light backscattering.

6. The on-line detection and fault prediction system for sediment characteristics of a hydro-generator set according to claim 1 is characterized in that: The laser particle size analyzer is located on an underwater platform.

Images