Search

CN-122014652-A - Multistage rotating speed coordination control method and device for three-stage magnetic suspension air compressor

CN122014652ACN 122014652 ACN122014652 ACN 122014652ACN-122014652-A

Abstract

The invention discloses a multistage rotating speed coordination control method and device for a three-stage magnetic suspension air compressor, comprising the following steps: and acquiring running state data of each level of compressor, and respectively installing a plurality of groups of sensors at the low-pressure level, the medium-pressure level and the high-pressure level of the compressor, wherein the plurality of groups of sensors comprise a pressure sensor, a temperature sensor, a vibration sensor, a rotating speed sensor and a power sensor. The sensors of each stage monitor and record the gas pressure, temperature change, rotation speed fluctuation, vibration condition and power consumption of each stage of the compressor in real time. According to the invention, the data acquisition and processing precision is obviously improved by combining the quantum sensor and the quantum computation according to the running state data of the compressor transmitted to the central control unit through the data bus, and particularly in the aspects of high-frequency dynamic control and micro disturbance monitoring, the delay and the error in the traditional computing mode can be greatly reduced by the powerful parallel processing capacity of the quantum computation.

Inventors

  • WU XUN
  • ZHANG XINGTIAN
  • WEI WENBIN
  • ZHAN YINGJIE
  • YANG PENG
  • LIU FENG
  • WANG BAIQUAN
  • XU WEIQIANG
  • ZHU YINGJIE
  • LI ZHENJIANG
  • MA LEI
  • LUO BIN
  • CHEN GUANGJIAN
  • Dan Runtang
  • YU CHANGKAI
  • LI ZHOU
  • ZHANG DANPING
  • Yuan Mingda
  • ZHOU JIALIANG
  • YAN YIJIE
  • WANG MIAOMIAO

Assignees

  • 华能重庆珞璜发电有限责任公司
  • 华能核能技术研究院有限公司

Dates

Publication Date
20260512
Application Date
20260116

Claims (10)

  1. 1. A multistage rotating speed coordination control method of a three-stage magnetic suspension air compressor is characterized by comprising the following steps: acquiring running state data of each level of compressor, respectively installing a plurality of groups of sensors at a low-voltage level, a medium-voltage level and a high-voltage level of the compressor, transmitting the running state data of the compressor to a central control unit through a data bus, and carrying out data preprocessing, noise reduction, filtering and real-time analysis by a real-time computing platform; Based on a multi-mode data fusion algorithm, carrying out time sequence synchronization on the data of the plurality of groups of sensors, and carrying out feature extraction on real-time data by combining a deep learning model; And constructing a reinforcement learning model, inputting real-time data, optimizing multi-stage rotation speed and load distribution of the compressor in real time, controlling the rotation speed proportion and start-stop time of each stage of the compressor based on comprehensive energy efficiency of a reward mechanism, equipment health condition and load balance factors, and automatically realizing energy-saving operation.
  2. 2. The method of claim 1, wherein the plurality of sets of sensors include pressure sensors, temperature sensors, vibration sensors, rotational speed sensors, and power sensors, the sensors being disposed in compressor components of the low pressure stage, the medium pressure stage, and the high pressure stage, respectively, the compressor components including an air inlet, an air outlet, a rotor bearing, and a motor location, parameters of gas flow, pressure, vibration, and power consumption of the compressor being monitored in real time.
  3. 3. The method of claim 1, wherein the magnetic bearing location of the compressor is equipped with a magnetic bearing sensor that monitors changes between the rotor and the bearing, and wherein the data bus transmission is based on a data bus and transmitted using a real-time communication protocol.
  4. 4. The method of claim 1, wherein the deep learning model combines a convolutional neural network and a long-short-term memory network to extract spatial features and time sequence features respectively, and constructs a dynamic health assessment model of each level of operation state of the compressor.
  5. 5. The method of claim 1, wherein the reinforcement learning model dynamically adjusts the load distribution to speed ratio of each stage of the compressor via a real-time feedback mechanism, the rewarding mechanism further comprising automatically adjusting the compressor speed and load distribution based on real-time data, including speed data, pressure data, and load data, the health of the device, and the load distribution effect.
  6. 6. The method of claim 1, further comprising performing anomaly detection and fault pattern matching on the sensor data in real time through the edge computing node and generating a fault pre-warning.
  7. 7. The method of claim 1, wherein the cloud platform performs real-time analysis on long-term operation data based on big data analysis and migration learning, and the cloud platform automatically identifies and adjusts an energy efficiency scheduling strategy of the compressor through multi-device data cluster analysis.
  8. 8. The method according to claim 1, wherein the method further comprises: based on the edge computing node, performing fault diagnosis and anomaly detection on the real-time data acquired by the sensor, finding potential faults and generating early warning information; uploading locally processed monitoring data and fault early warning information to a cloud platform, and carrying out cluster analysis on long-term operation data of the equipment by the cloud platform through a big data analysis model.
  9. 9. A multistage rotational speed coordination control device of a three-stage magnetic suspension air compressor is characterized by comprising: The acquisition module is used for acquiring the running state data of each level of compressor, respectively installing a plurality of groups of sensors at the low-voltage level, the medium-voltage level and the high-voltage level of the compressor, transmitting the running state data of the compressor to the central control unit through the data bus, and carrying out data preprocessing, noise reduction, filtering and real-time analysis by the real-time calculation platform; The data extraction module is configured to perform time sequence synchronization on the data of the plurality of groups of sensors based on a multi-mode data fusion algorithm, and perform feature extraction on real-time data by combining a deep learning model; The rotating speed control module is configured to construct a reinforcement learning model, input real-time data, optimize multistage rotating speed and load distribution of the compressor in real time, control rotating speed proportion and start-stop time of each stage of the compressor based on comprehensive energy efficiency of a reward mechanism, equipment health condition and load balance factors, and automatically realize energy-saving operation.
  10. 10. An electronic device, comprising a processor, a memory and a communication interface, wherein the memory stores a computer program, and the processor implements a three-stage magnetic levitation air compressor multi-stage rotation speed coordination control method according to any one of claims 1 to 8 when executing the computer program.

Description

Multistage rotating speed coordination control method and device for three-stage magnetic suspension air compressor Technical Field The invention relates to the technical field of air compressor control, in particular to a multi-stage rotating speed coordination control and device for a three-stage magnetic suspension air compressor. Background The magnetic suspension three-stage air compressor is widely applied to the fields of new energy, precision manufacture and the like due to the adoption of a magnetic suspension bearing (without mechanical contact and small abrasion) and a three-stage compression structure (high energy efficiency and large gas production), and the core of the three-stage magnetic suspension air compressor is a magnetic suspension system, so that no physical contact exists between a rotor and a stator by utilizing magnetic force, thereby greatly reducing friction loss and improving the efficiency of the compressor. The three stage system typically includes a low pressure stage (first stage) responsible for the preliminary compression of the gas. Medium pressure stage (second stage) the gas is further compressed. The high pressure stage (third stage) completes the final compression to achieve the desired working pressure. In this system, the rotational speed control of each stage needs to be highly coordinated to ensure an optimal balance of gas flow, pressure, and energy efficiency. The existing control method can only control the rotating speed of each level independently, neglecting coordination among the rotating speeds of all levels, and easily generating the conditions of overload work of some levels and low load of some levels. Because the control of the rotating speeds of all stages is not coordinated, the overall energy efficiency of the compressor is easily reduced, and the energy is wasted. Especially under the condition of large load fluctuation, the rotating speeds of all stages cannot be optimally adjusted according to real-time requirements, so that the energy efficiency is low. The load of the compressor is often affected by external environments and conditions of use, such as gas demand changes, temperature changes, etc., resulting in compressor load fluctuations. Existing control methods often fail to effectively distribute the load in real time, resulting in excessive or inefficient operation at a partial level. Different levels of compressors require load sharing as needed. If the load distribution is not reasonable, certain levels may be frequently started and stopped, so that the mechanical loss and the energy consumption are increased, and the stability of the system is affected. The existing control method often depends on a preset start-stop threshold value, and cannot be adaptively adjusted according to actual load and working condition changes. This can lead to frequent start-up and shut-down, resulting in mechanical damage and waste of energy. In a multi-stage system, a single level of overload may result in reduced performance or equipment damage to the overall system. In the existing method, the overload protection mechanism of the multistage system is often independently controlled, lacks global cooperative optimization, and cannot effectively protect the working states of each stage of the compressor in the whole system range. In a control system, a certain response delay is usually existed in multistage rotation speed adjustment of a compressor, which may cause low energy efficiency or uneven system load, thereby affecting working efficiency. For some working environments with rapid changes (such as instantaneous load changes or gas pressure fluctuation), the existing system may not realize real-time rapid adjustment, so that the system efficiency is greatly reduced, the rotation speed coordination of the multistage compressor system involves a plurality of variables, the complexity of a control algorithm is high, and the existing method often lacks proper optimization, so that the calculation burden is high, and a large amount of dynamic change data cannot be processed in real time. Traditional control algorithms may not be able to adapt adaptively to actual operating conditions, requiring more efficient scheduling and optimization strategies to be considered in the algorithm design. Disclosure of Invention The present invention aims to solve at least one of the technical problems in the related art to some extent. Therefore, a first object of the present invention is to provide a multi-stage rotation speed coordination control method for a three-stage magnetic suspension air compressor. The invention further aims at providing a multistage rotating speed coordination control device of the three-stage magnetic suspension air compressor. A third object of the invention is to propose a computer device. A fourth object of the present invention is to propose a non-transitory computer readable storage medium. In order to achieve the above object, an embodime