Fault detection device for compressed air energy storage multistage centrifugal compressor

Abstract

The utility model relates to the technical field of compressors, in particular to a compressed air energy storage multistage centrifugal compressor fault detection device which is characterized by comprising an acquisition end, a first communication end and a management end which are connected in sequence, the collection end comprises a plurality of collection assemblies and a plurality of first transmission assemblies, the collection assemblies are used for collecting operation data of the multistage centrifugal compressors, the collection assemblies and the multistage centrifugal compressors are arranged in a one-to-one correspondence mode, and the collection assemblies and the first transmission assemblies are connected in a one-to-one correspondence mode; the first communication end is respectively connected with the plurality of first transmission assemblies and a second transmission assembly of the management end, and the first communication end sends the operation data transmitted by the plurality of first transmission assemblies to the second transmission assembly; the management end is used for determining the target centrifugal compressor with the fault according to the operation data received by the second transmission assembly. Therefore, the problem that real-time fault monitoring and fault prediction cannot be carried out on the compressor in the prior art is solved, and remote monitoring and management of the compression system are achieved.

Description

Technical Field

[0001] This application relates to the field of compressor technology, and in particular to a fault detection device for a multi-stage centrifugal compressor with compressed air energy storage. Background Technology

[0002] The intermittency and instability of renewable energy sources pose challenges to grid operation. Compressed air energy storage systems can balance grid supply and demand by converting surplus renewable energy power generation into compressed air stored in an air storage device and then releasing the energy to generate electricity when needed.

[0003] In this system, the centrifugal compressor, as a key component of compressed air, is crucial to the system's performance and reliability due to its stable operation. Centrifugal compressors typically operate in high-temperature, high-pressure, and high-speed environments, making their components susceptible to wear and damage, such as bearings, seals, and blades. A malfunction can lead not only to decreased system performance and energy loss but also to safety hazards and equipment damage, severely impacting the entire system's operation.

[0004] To address this issue, relevant technologies typically employ a combination of regular inspections and preventative maintenance. However, compressors are generally difficult to monitor manually during operation, making real-time fault monitoring and prediction impossible. Furthermore, manual inspections also increase system operation and maintenance costs to some extent, making fault monitoring and maintenance complex and challenging. Utility Model Content

[0005] This application provides a fault detection device for a multi-stage centrifugal compressor with compressed air energy storage, which solves the problem that compressors are usually inconvenient to monitor manually during operation and cannot achieve real-time fault monitoring and fault prediction. It can monitor the operating status of the compression system in real time and realize remote monitoring and management of the compression system.

[0006] The first aspect of this application provides a fault detection device for a multi-stage centrifugal compressor with compressed air energy storage, comprising a data acquisition terminal, a first communication terminal, and a management terminal connected in sequence, wherein...

[0007] The acquisition terminal includes multiple acquisition components and multiple first transmission components for acquiring operating data of a multi-stage centrifugal compressor. The multiple acquisition components are configured one-to-one with the multi-stage centrifugal compressor, and the multiple acquisition components are connected one-to-one with the multiple first transmission components.

[0008] The first communication terminal is connected to the plurality of first transmission components and the second transmission component of the management terminal respectively, and the first communication terminal sends the running data transmitted by the plurality of first transmission components to the second transmission component;

[0009] The management terminal is used to determine the target centrifugal compressor with a fault based on the operating data received by the second transmission component, so as to perform fault management on the target centrifugal compressor.

[0010] Optionally, the management terminal further includes:

[0011] A processing unit for processing the running data, the processing unit being connected to the second transmission component.

[0012] Optionally, the management terminal further includes:

[0013] A storage unit for storing processed runtime data, the storage unit being connected to the processing unit.

[0014] Optionally, the management terminal further includes:

[0015] A power supply unit is connected to the processing unit and is used to supply power to the management terminal.

[0016] Optionally, the management terminal further includes:

[0017] A second communication terminal is used to transmit the processed running data, and the second communication terminal is connected to the processing unit.

[0018] Optionally, the management terminal further includes:

[0019] A diagnostic unit for determining diagnostic results, the diagnostic unit being connected to the second communication terminal.

[0020] Optionally, the second communication terminal includes at least one of an Ethernet communication module, a 3G communication module, a 4G communication module, a 5G communication module, and a WIFI communication module.

[0021] Optionally, the management terminal further includes:

[0022] An alarm unit is connected to the processing unit and is used to issue an alarm when the processed operating data exceeds a corresponding limit threshold.

[0023] Optionally, the acquisition end includes at least one set of sensors corresponding to each stage of the centrifugal compressor, wherein each set of sensors includes at least one of the following: pressure sensor, temperature sensor, vibration sensor, current sensor, oil sensor, filter differential pressure sensor, exhaust temperature sensor, sealing status sensor, thermal imager, ultrasonic sensor, and camera.

[0024] Optionally, the management terminal further includes:

[0025] The third communication terminal connected to the processing unit is used to send the processed running data to the cloud.

[0026] Therefore, by sequentially connecting a data acquisition terminal, a first communication terminal, and a management terminal, the following method is achieved: the data acquisition terminal includes multiple acquisition components and multiple first transmission components for collecting operating data from multi-stage centrifugal compressors. Each acquisition component corresponds one-to-one with a multi-stage centrifugal compressor and is connected to a corresponding first transmission component. The first communication terminal is connected to a second transmission component of the management terminal, transmitting the operating data from the first transmission components to the second transmission components. The management terminal uses the operating data received by the second transmission components to determine the target centrifugal compressor with a fault. This solves the problem that related technologies cannot perform real-time fault monitoring and fault prediction of compressors, enabling remote monitoring and management of the compression system.

[0027] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0028] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0029] Figure 1 This is a block diagram of a multi-stage centrifugal compressor fault detection device for compressed air energy storage provided according to an embodiment of this application;

[0030] Figure 2 This is a schematic diagram of a fault detection device for a multi-stage centrifugal compressor with compressed air energy storage according to an embodiment of this application;

[0031] Figure 3 This is a schematic diagram illustrating the detection principle of a multi-stage centrifugal compressor fault detection device for compressed air energy storage provided according to an embodiment of this application;

[0032] Figure 4 This is a schematic diagram of a fault detection device for a multi-stage centrifugal compressor with compressed air energy storage provided according to an embodiment of this application. Detailed Implementation

[0033] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0034] The following describes a fault detection device for a multi-stage centrifugal compressor with compressed air energy storage according to an embodiment of this application, with reference to the accompanying drawings. Addressing the problem mentioned in the background art that related technologies cannot perform real-time fault monitoring and prediction of compressors, this application provides a fault detection device for a multi-stage centrifugal compressor with compressed air energy storage. This device comprises a data acquisition terminal, a first communication terminal, and a management terminal connected in sequence. The data acquisition terminal includes multiple acquisition components and multiple first transmission components for collecting operating data from the multi-stage centrifugal compressor. Each acquisition component corresponds to a multi-stage centrifugal compressor and is connected to a corresponding first transmission component. The first communication terminal is connected to a second transmission component of the management terminal, and transmits the operating data transmitted by the first transmission components to the second transmission components. The management terminal determines the target centrifugal compressor with a fault based on the operating data received by the second transmission components. This solves the problem that related technologies cannot perform real-time fault monitoring and prediction of compressors, enabling remote monitoring and management of the compression system.

[0035] Specifically, Figure 1 This is a schematic diagram of a fault detection device for a multi-stage centrifugal compressor for compressed air energy storage provided in an embodiment of this application.

[0036] like Figure 1 As shown, the fault detection device for the multi-stage centrifugal compressor with compressed air energy storage includes: a data acquisition terminal 100, a first communication terminal 200, and a management terminal 300 connected in sequence.

[0037] The acquisition terminal 100 includes multiple acquisition components and multiple first transmission components for acquiring operating data of multi-stage centrifugal compressors. Each acquisition component is configured to correspond one-to-one with a multi-stage centrifugal compressor, and each acquisition component is connected to a corresponding first transmission component. The first communication terminal 200 is connected to the multiple first transmission components and the second transmission component of the management terminal 300. The first communication terminal 200 sends the operating data transmitted by the multiple first transmission components to the second transmission components. The management terminal 300 is used to determine the target centrifugal compressor with a fault based on the operating data received by the second transmission components, so as to perform fault management on the target centrifugal compressor.

[0038] Specifically, such as Figure 2 As shown, in order to realize non-manual real-time fault monitoring of multi-stage centrifugal compressors in compressed air energy storage systems, this utility model provides a remote fault monitoring system for multi-stage centrifugal compressors in compressed air energy storage systems based on wireless sensor networks. The system includes a data acquisition terminal 100, a first communication terminal 200, and a management terminal 300. The data acquisition terminal 100 includes sensor nodes, and the management terminal includes aggregation nodes and management nodes.

[0039] Specifically, this utility model constructs a multi-level centrifugal compressor wireless sensor monitoring network based on a ZigBee tree topology. Secondly, it combines a ZigBee coordinator and a microprocessor to construct an aggregation node for local data processing, storage, and connection between the sensor network and management nodes. Finally, based on the sensor network data transmitted through the aggregation node, a management node for fault diagnosis, prediction, and remote equipment control is constructed through a multi-sensor data fusion diagnostic framework.

[0040] Optionally, the acquisition terminal 100 includes at least one set of sensors corresponding to each stage of the centrifugal compressor, wherein each set of sensors includes at least one of a pressure sensor, a temperature sensor, a vibration sensor, a current sensor, an oil sensor, a filter differential pressure sensor, an exhaust temperature sensor, a sealing status sensor, a thermal imager, an ultrasonic sensor, and a camera.

[0041] Understandably, a single sensor can only acquire fault information from a fixed location and is easily affected by the sensor's own performance, making it difficult to reflect the overall operating status of the compressor. Multi-source sensor data fusion can obtain more fault information, providing equipment operation and maintenance personnel with more reliable maintenance decisions.

[0042] Specifically, the acquisition terminal 100 of this invention uses ZigBee to construct a wireless sensor network with a tree topology. Each sensor of each compressor is connected to the GPIO port, I2C bus or other corresponding interface of the ZigBee module according to its interface type. Then, each terminal node is connected to the corresponding ZigBee router to achieve data separation of each level of compressor terminal, prevent data confusion and provide comparison for subsequent fault analysis. Then, these sensors transmit data to the aggregation node through ZigBee and then from the aggregation node to the management node to analyze the data in real time and identify potential fault signs.

[0043] For example, abnormal vibration patterns may indicate bearing failure, while abnormal temperatures may suggest problems with the lubrication system. Once an abnormality is detected, the system can automatically send an alarm to notify relevant personnel to carry out inspection or maintenance, thereby preventing serious failures in a timely manner, reducing maintenance costs, and improving the reliability and safety of the system.

[0044] The data acquisition unit 100 is used for comprehensive monitoring of all parameters and environmental conditions of the multi-stage centrifugal compressor for compressed air energy storage. It includes an industrial IoT communication module for data transmission and numerous sensors. These sensors are installed at key locations around the compressor to monitor the system's operating status in real time, providing the necessary data for fault diagnosis. The sensors may include:

[0045] (1) Pressure sensor: used to monitor the pressure at the inlet and outlet.

[0046] (2) Temperature sensor: used to monitor the temperature inside the compressor and the surrounding environment.

[0047] (3) Vibration sensor: used to monitor the vibration of mechanical parts.

[0048] (4) Current sensor: used to monitor the current of the motor that drives the compressor.

[0049] (5) Oil sensor: used to monitor the quality and level of lubricating oil.

[0050] (6) Filter differential pressure sensor: used to monitor the degree of clogging of the filter.

[0051] (7) Exhaust temperature sensor: used to monitor the compressor exhaust temperature.

[0052] (8) Sealing status sensor: used to monitor the status of the seal and prevent gas leakage.

[0053] (9) Thermal imager: used to detect the operating temperature of the compressor body to prevent local overheating.

[0054] (10) Ultrasonic sensor: used to detect whether there are obvious defects on the outside and inside of the compressor.

[0055] (11) Camera: While monitoring the environment, it performs a rough scan and record of defects on the surface of the compressor.

[0056] (12) Decibels: monitor the noise level of on-site equipment to protect the hearing health of on-site personnel; at the same time, record abnormal operating sounds and compare them with abnormalities detected by other sensors to provide important data for subsequent fault prediction.

[0057] Optionally, the management terminal 300 further includes a processing unit for processing operational data, the processing unit being connected to the second transmission component.

[0058] Optionally, the management unit 300 also includes a storage unit for storing processed running data, the storage unit being connected to the processing unit.

[0059] Optionally, the management terminal 300 also includes a power supply unit, which is connected to the processing unit and is used to supply power to the management terminal 300.

[0060] Optionally, the management terminal 300 further includes a second communication terminal for transmitting processed running data, the second communication terminal being connected to the processing unit.

[0061] Optionally, the management terminal 300 further includes a diagnostic unit for determining diagnostic results, the diagnostic unit being connected to the second communication terminal.

[0062] Optionally, the management terminal 300 also includes an alarm unit connected to the processing unit, which is used to issue an alarm when the processed operating data exceeds the corresponding limit threshold.

[0063] Optionally, the management terminal 300 may also include a third communication terminal connected to the processing unit for sending the processed running data to the cloud.

[0064] Specifically, the management terminal 300 of this utility model may include an aggregation node and a management node. The aggregation node includes a microprocessor, a memory, and a communication module. Its main function is to collect data from multiple sensor nodes and aggregate it to reduce the amount of data transmission in the network, improve network efficiency, and reduce energy consumption. Simultaneously, the aggregation node is responsible for transmitting data from the sensor nodes to the node at the target location. It optimizes data transmission efficiency by selecting the best transmission path and ensures reliable data transmission. The management node includes a real-time equipment fault monitoring and management platform, as well as a remote panel control platform for remote equipment control, enabling remote monitoring and management of centrifugal compressor equipment within the sensor wireless network.

[0065] Specifically, the aggregation node connects the router corresponding to each stage compressor to the coordinator for communication with the sensor network and data transmission. The aggregation node microprocessor uses TI's MSP430 low-power microprocessor and communicates with the ZigBee coordinator via a serial protocol. It integrates data collected by the terminal nodes and performs local backup storage (using an SD card as the local storage medium) to prevent data loss or corruption in the cloud. Simultaneously, based on real-time data, it can perform simple handling of compressor faults locally. Thresholds for pressure, temperature, vibration, current, seal tightness, lubrication level, and filter clogging are set based on experience. When the operating data is below the corresponding threshold, a green light illuminates, indicating no fault; when the data reaches or exceeds the threshold but slightly, a yellow light illuminates, indicating a fault; when the data significantly exceeds the threshold, a red light illuminates, indicating a serious fault, and the equipment operation is immediately stopped. The display screen shows the specific parameters exceeding the limits and the corresponding compressor location of the fault in real time.

[0066] The communication network utilizes existing internet and mobile communication networks. Wired communication uses Ethernet to transmit massive amounts of data to the local fixed master management node, ensuring efficient and accurate data transmission and guaranteeing the accuracy of subsequent fault monitoring and prediction functions. 3G / 4G / 5G mobile communication is used to transmit monitoring results to remote mobile management terminal nodes without a network connection, ensuring the portability of information transmission.

[0067] The management node's host computer primarily includes equipment fault monitoring and prediction functions, as well as remote equipment control functions. The remote control function is used for timely intervention in equipment operation when the compressor malfunctions, and for rapid error correction when the lower-level machine misjudges based on empirical values. Control information is transmitted to the equipment via network communication and a ZigBee coordinator. The fault monitoring and prediction function uses a multi-sensor data fusion diagnostic framework based on self-attention-convolutional neural networks to extract and fuse features from multi-dimensional sensor parameters, and then analyze and predict faults. This fully utilizes massive amounts of data and the relationships between them to prevent misjudgments based on empirical values. The specific diagnostic process is as follows: Figure 2 , Figure 3 and Figure 4 As shown:

[0068] Step 1: Obtain real-time operating data of the multi-stage centrifugal compressor collected by the sensor network from the aggregation node via communication methods such as Ethernet.

[0069] Step 2: Process the sensor signals and divide the data into training sample set, validation sample set and test sample set. The training sample set and validation sample set are used to train the model, and the test sample set is used to validate the model.

[0070] Step 3: Initialize model parameters and input the training and validation sample sets into the model. Optimize model parameters using the backpropagation algorithm.

[0071] Step 4: Determine if the model has converged. If it has converged, complete the training and save the model parameters. If it has not converged, return to step 3.

[0072] Step 5: Input the test sample set into the trained model, then extract features through the model, and finally output the fault diagnosis and prediction results.

[0073] The compressed air energy storage multi-stage centrifugal compressor fault detection device proposed in this application comprises a data acquisition terminal, a first communication terminal, and a management terminal connected in sequence. The data acquisition terminal includes multiple acquisition components and multiple first transmission components for collecting operating data from the multi-stage centrifugal compressor. Each acquisition component corresponds to a different multi-stage centrifugal compressor and is connected to a corresponding first transmission component. The first communication terminal is connected to a second transmission component of both the first transmission components and the management terminal, transmitting the operating data from the first transmission components to the second transmission components. The management terminal determines the target centrifugal compressor with a fault based on the operating data received by the second transmission components. This solves the problem of related technologies being unable to perform real-time fault monitoring and fault prediction of compressors, enabling remote monitoring and management of the compression system.

[0074] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0075] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0076] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0077] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0078] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0079] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A compressed air energy storage multi-stage centrifugal compressor fault detection apparatus, characterized by, include: The data acquisition terminal, the first communication terminal, and the management terminal are connected in sequence, among which, The acquisition terminal includes multiple acquisition components and multiple first transmission components for acquiring operating data of a multi-stage centrifugal compressor. The multiple acquisition components are configured one-to-one with the multi-stage centrifugal compressor, and the multiple acquisition components are connected one-to-one with the multiple first transmission components. The first communication terminal is connected to the plurality of first transmission components and the second transmission component of the management terminal respectively, and the first communication terminal sends the running data transmitted by the plurality of first transmission components to the second transmission component; The management terminal is used to determine the target centrifugal compressor with a fault based on the operating data received by the second transmission component, so as to perform fault management on the target centrifugal compressor.

2. The apparatus of claim 1, wherein, The management terminal also includes: A processing unit for processing the running data, the processing unit being connected to the second transmission component.

3. The apparatus of claim 2, wherein, The management terminal also includes: A storage unit for storing processed runtime data, the storage unit being connected to the processing unit.

4. The apparatus of claim 2, wherein, The management terminal also includes: A power supply unit is connected to the processing unit and is used to supply power to the management terminal.

5. The apparatus of claim 2, wherein, The management terminal also includes: A second communication terminal is used to transmit the processed running data, and the second communication terminal is connected to the processing unit.

6. The apparatus of claim 5, wherein, The management terminal also includes: A diagnostic unit for determining diagnostic results, the diagnostic unit being connected to the second communication terminal.

7. The apparatus of claim 5, wherein, The second communication terminal includes at least one of an Ethernet communication module, a 3G communication module, a 4G communication module, a 5G communication module, and a WIFI communication module.

8. The apparatus of claim 2, wherein, The management terminal also includes: An alarm unit is connected to the processing unit and is used to issue an alarm when the processed operating data exceeds a corresponding limit threshold.

9. The apparatus of claim 2, wherein, The acquisition terminal includes at least one set of sensors corresponding to each stage of the centrifugal compressor. Each set of sensors includes at least one of the following: a pressure sensor, a temperature sensor, a vibration sensor, a current sensor, an oil sensor, a filter differential pressure sensor, an exhaust temperature sensor, a sealing status sensor, a thermal imager, an ultrasonic sensor, and a camera.

10. The apparatus of claim 2, wherein, The management terminal also includes: The third communication terminal connected to the processing unit is used to send the processed running data to the cloud.

Images