Intelligent Electrical Terminal Monitoring and Alarm Platform of Pumping Station

Classification:

During application of water conservancy pumping stations in the actual project, 35kV and below power supply systems, low-voltage power supply and distribution system in the long-term operation have various types of failures, such as equipment failures in the operating mechanism failure, arrester failures, transformer failures, cabinet condensation, capacitor failures, etc., line failures such as insulation failures at cable joint, busbar insulation failures, inspection failures and other problems. This will bring hidden danger to the safety of the equipment itself and the reliable operation of the power grid. This will directly affect the safe and stable operation of power supply and distribution. In addition, the power distribution system has a large number of equipment, the distributed scattered inspection area is large, resulting in greater difficulties for the industry's traditional manual inspection operation and maintenance management mode.

According to the characteristics of electrical equipment, our company has gradually promoted the construction of ubiquitous connectivity edge layer, data cloud, equipment cloud, inspection cloud, system intelligent fusion platform, and developed intelligent power distribution IOT terminals.

1. Core Features

◆ Intelligent power distribution IOT terminal

Intelligent IOT terminal is located in the core of medium and low-voltage distribution IOT, which adopts standard platform hardware design and edge computing architecture, supports in situ data storage and decision-making analysis. The terminal adopts modular, scalable, low-power, maintenance-free design standards, thereby adapting to the complex operating environment, with high reliability and stability.

◆ Longitudinal Big Data Analysis

The smart IoT device is equipped with a longitudinal big data analysis feature. This allows it to analyze all historical scene perception data from important feeder circuits, forming a longitudinal data chain for online analysis. This feature enables data analysis of crucial feeder circuits and has the capability to analyze and discern large sets of historical data from a single point. It also allows for dynamic grading (excellent, good, pass, poor) of the operational status of important feeder circuits and equipment. It can adaptively calculate inspections, automatically generate status evaluation reports, and store them. The accuracy of the evaluation time is no less than one month.

◆ AI Online Analysis

The smart IoT device possesses an intelligent model for identifying important feeder circuits and an artificial analysis theoretical model. It can perform human-like analysis to analyze the online status of important feeder circuits, make judgments, and output reports.

Through a sensor network, it can analyze data, upload results, and draw conclusions about the status of inspected equipment such as transformers and switch cabinets using its integrated expert analysis system.

◆ Future State Prediction

The smart IoT device can analyze past data law to predict the future operational status of important feeder circuits. It is able to calculate the probability of future equipment malfunctions.

The system has a dual-layer future prediction feature, namely the MEMS (Micro-Electro-Mechanical Systems) prediction and the control cloud prediction. The MEMS prediction is responsible for uploading single-scene data prediction results to the cloud service platform, while the control cloud prediction analyzes the judgment results of all equipment, synthesizes them, and draws system-wide conclusions.

◆ Warning Function

The smart IoT device is equipped with various warning functions such as abnormal sound warning, abnormal travel warning, abnormal environmental warning, and abnormal status warning.

2.Key Outcomes of IoT Implementation in Pump Stations

The intelligent maintenance model for equipment malfunctions keeps track of the operational status of crucial components in key equipment. It gathers data on conditions such as temperature, noise, vibration, and radial and axial displacement. By integrating environmental data, historical operational data, and maintenance records, it deeply analyzes and uncovers equipment failure patterns based on underlying mechanisms. This model understands the progression and degradation trends of malfunctions. Using big data extrapolation, it can predict equipment failure trends and send proactive alerts. This changes traditional methods like scheduled equipment maintenance, reduces the occurrence of sudden major malfunctions, minimizes equipment downtime, and cuts down on losses due to failures.