A condition monitoring and fault prediction system for hydrogen compressors

Abstract

This invention belongs to the field of hydrogen energy, specifically relating to a condition monitoring and fault prediction system for hydrogen compressors. The system includes a data acquisition module, a data preprocessing module, a condition baseline module, and a safety risk monitoring module. The data acquisition module collects the operating parameters of the hydrogen compressor; the data preprocessing module preprocesses these parameters; the condition baseline module establishes an operating condition baseline based on the operating parameters; and finally, the safety risk monitoring module monitors deviations and hydrogen embrittlement risks. This invention provides a condition monitoring and fault prediction system for hydrogen compressors, aiming to solve the problem of existing technologies being unable to monitor the operating status of hydrogen compressors.

Description

Technical Field

[0001] This invention belongs to the field of hydrogen energy, specifically relating to a condition monitoring and fault prediction system suitable for hydrogen compressors. Background Technology

[0002] Hydrogen energy, as a clean and efficient secondary energy source, is rapidly expanding its applications in transportation, energy storage, and industry, and has become one of the key pathways to achieve decarbonization of energy systems. As a crucial piece of equipment in the hydrogen energy industry chain, the hydrogen compressor undertakes the core functions of hydrogen pressurization, transportation, and storage. The operating status of the hydrogen compressor directly affects the safety and efficiency of the entire hydrogen energy system.

[0003] However, existing technologies lack methods for monitoring the operating status of hydrogen compressors, making it impossible to monitor their operation in real time. Consequently, it is impossible to predict in a timely manner whether a hydrogen compressor will malfunction, which is detrimental to the normal operation of the system. Summary of the Invention

[0004] This invention provides a condition monitoring and fault prediction system for hydrogen compressors, which aims to solve the problem that existing technologies cannot monitor the operating status of hydrogen compressors.

[0005] To achieve the above objectives, the present invention provides a condition monitoring and fault prediction system suitable for hydrogen compressors, comprising: a data acquisition module for acquiring the operating parameters of the hydrogen compressor; a data preprocessing module connected to the data acquisition module for preprocessing the acquired data; a state baseline module connected to the data preprocessing module for establishing an operating state baseline based on the operating parameters; and a safety risk monitoring module connected to the data preprocessing module and the state baseline module, wherein the safety risk monitoring module receives data from the data preprocessing module and performs deviation monitoring, trend analysis, correlation analysis, and hydrogen embrittlement risk monitoring.

[0006] Preferably, the operating parameters collected by the data acquisition module include mechanical parameters, electrical parameters, fluid parameters, and safety parameters.

[0007] Preferably, the mechanical parameters include bearing vibration parameters, cylinder temperature, piston temperature, sealing ring sealing performance, and cylinder pressure fluctuation curve.

[0008] The electrical parameters include the current, voltage, power factor, and winding temperature of the drive motor, as well as the output frequency and harmonic content of the frequency converter.

[0009] The fluid parameters include inlet and outlet pressures, pressure loss, inlet and outlet temperatures, inlet and outlet temperature difference, hydrogen flow rate, and cooling system flow rate.

[0010] The safety parameters include the hydrogen concentration around the equipment, the hydrogen content in the lubricating oil, and the stress and strain of the cylinder and pipeline.

[0011] Preferably, the data preprocessing module preprocesses the working parameters including noise reduction filtering, outlier correction, and data calibration.

[0012] Preferably, the working status baseline established by the status baseline module includes a static baseline, a dynamic baseline, and a working condition baseline.

[0013] Preferably, the safety risk monitoring module monitors deviations by calculating the deviation rate D.

[0014] ;

[0015] in, Here are the real-time parameter values ​​at time t. The baseline parameter value for the working state at time t.

[0016] Preferably, the safety risk monitoring module performs trend analysis using a slope k.

[0017] ;

[0018] Where y is the specific value of the running time, and x is the running time.

[0019] Preferably, the safety risk monitoring module monitors hydrogen embrittlement risk by calculating the hydrogen embrittlement risk index (HRI).

[0020] ;

[0021] in, , , Let be the weighting coefficient, satisfying =1; This is the normalized value of the hydrogen content in the lubricating oil; This is the normalized value of the actual stress in the cylinder block; This is the normalized value of the cumulative running time.

[0022] Preferably, the system further includes an early warning module, which is connected to the security risk monitoring module, and the early warning module provides tiered early warnings based on the results of the security risk monitoring module.

[0023] Preferably, it also includes a data synchronization and storage module, which is connected to the data preprocessing module, the status baseline module, and the security risk monitoring module.

[0024] The beneficial effects of this invention are as follows: This system collects the operating parameters of the hydrogen compressor through a data acquisition module; then preprocesses the data to ensure the accuracy of subsequent predictions; then establishes an operating status baseline based on the operating parameters; and finally monitors for anomalies through a safety risk monitoring module.

[0025] Through the above process, this system can monitor the operating status of the hydrogen compressor, helping users to promptly determine whether the hydrogen compressor will malfunction and ensuring the normal operation of the entire system. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of a condition monitoring and fault prediction system suitable for hydrogen compressors.

[0027] The attached diagram includes the following reference numerals: 1. Data acquisition module; 2. Data preprocessing module; 3. Status baseline module; 4. Security risk monitoring module; 5. Early warning module; 6. Data synchronization and storage module. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention.

[0029] The basic implementation examples are as follows: Figure 1 As shown, a condition monitoring and fault prediction system for hydrogen compressors includes a data acquisition module 1, a data preprocessing module 2, a condition baseline module 3, a safety risk monitoring module 4, an early warning module 5, and a data synchronization and storage module 6.

[0030] In this embodiment, the data acquisition module 1 is used to collect the operating parameters of the hydrogen compressor, enabling subsequent risk prediction based on these parameters. The operating parameters collected in this embodiment specifically include mechanical parameters, electrical parameters, fluid parameters, and safety parameters. By collecting multiple parameters, the system ensures a comprehensive capture of the mechanical, electrical, fluid, and safety operating status of the hydrogen compressor, avoiding monitoring blind spots caused by parameter omissions and providing a complete data foundation for subsequent analysis.

[0031] The mechanical parameters in this embodiment specifically include bearing vibration parameters, cylinder temperature, piston temperature, piston ring sealing performance, and pressure fluctuation curves within the piston cylinder. Specifically, bearing vibration parameters can be acquired using piezoelectric vibration sensors; cylinder and piston temperatures can be acquired using a combination of infrared thermometers and thermocouples; piston ring sealing performance can be detected using a high-frequency dynamic pressure transmitter; and the pressure fluctuation curves within the piston cylinder can be obtained by measuring stress and strain using foil strain gauges. By monitoring the mechanical parameters of the hydrogen compressor, signs of mechanical failure such as bearing wear, piston overheating, and piston ring leakage can be quickly identified, providing accurate information for early maintenance of the hydrogen compressor and reducing downtime losses caused by mechanical failures.

[0032] The electrical parameters in this embodiment specifically include the three-phase current, voltage, power factor, and winding temperature of the drive motor, as well as the inverter output frequency and harmonic content. The three-phase current, voltage, and power factor of the drive motor can be obtained by setting a Hall current sensor and a corresponding fixed resistor. The winding temperature of the drive motor can be measured using a fiber optic grating temperature sensor. The inverter output frequency can be directly read through the RS485 / Modbus communication interface, and the harmonic content is obtained using a harmonic sensor. By monitoring the electrical parameters of the hydrogen compressor in real time, electrical faults such as motor overload, winding overheating, and inverter aging can be detected promptly, preventing equipment downtime or safety accidents caused by electrical system failures and improving the operational reliability of the hydrogen compressor.

[0033] The fluid parameters in this embodiment specifically include hydrogen inlet pressure, hydrogen exhaust pressure, inlet and outlet pressure loss, hydrogen inlet temperature, inlet and outlet temperature difference loss, hydrogen exhaust temperature, hydrogen flow rate, and cooling system flow rate. The hydrogen inlet pressure and hydrogen exhaust pressure are measured using a Hastelloy absolute pressure transmitter, while the inlet and outlet pressure loss can be obtained by calculating the difference between the hydrogen inlet pressure and the hydrogen exhaust pressure. The hydrogen inlet temperature and hydrogen exhaust temperature are measured using a type-T thermocouple, and the inlet and outlet temperature difference can be obtained by calculating the difference between the hydrogen inlet temperature and the hydrogen exhaust temperature. The hydrogen flow rate and cooling system flow rate are obtained using a Coriolis mass flow meter. By monitoring these fluid parameters, the hydrogen compression efficiency and cooling system heat dissipation capacity can be monitored in real time, allowing for timely detection of hydrogen leaks, insufficient cooling, and other problems, ensuring efficient and stable compressor operation, and preventing efficiency drops or equipment damage due to fluid abnormalities.

[0034] The safety parameters in this embodiment specifically include the hydrogen concentration around the equipment, the hydrogen content in the lubricating oil, and the stress and strain of the cylinder and pipelines. The hydrogen concentration around the equipment can be measured using an explosion-proof electrochemical sensor. Hydrogen leak monitoring can employ a redundant multi-sensor arrangement; a leak risk is identified when the concentration at a single point exceeds a set value one or when the concentration at multiple points exceeds a set value two. The hydrogen content in the lubricating oil can be measured using an online gas chromatograph, and the stress and strain of the cylinder and pipelines can be measured using a laser Raman spectroscopy sensor. By monitoring these safety parameters, potential safety hazards such as hydrogen leaks, hydrogen embrittlement of materials, and structural cracking can be identified, providing core protection for the safe operation of the hydrogen compressor and reducing the incidence of safety accidents.

[0035] After acquiring the mechanical, electrical, fluid, and safety parameters of the hydrogen compressor, this embodiment sets up a data preprocessing module 2 connected to the data acquisition module 1 to ensure the accuracy of subsequent predictions. The data preprocessing module 2 is used to preprocess the operating parameters acquired by the data acquisition module 1. Specific preprocessing operations include noise reduction filtering, outlier correction, and data calibration of the operating parameters. Noise reduction filtering of the operating parameters is mainly achieved using wavelet transform or Kalman filtering algorithms; outlier correction of the operating parameters can use the 3σ criterion to identify and remove jump values, while interpolating missing data based on the trend of adjacent time points; data calibration of the operating parameters is mainly achieved by combining the sensor's factory calibration curve with periodic on-site calibration results. This solution, through targeted preprocessing of the operating parameters, can effectively eliminate noise interference, correct abnormal data, and ensure measurement accuracy, providing a high-quality data foundation for subsequent baseline establishment and anomaly detection, and avoiding misjudgments or omissions caused by data errors.

[0036] The data preprocessing module 2 is connected to the status baseline module 3. It acquires the equipment's operating parameters through the data acquisition module 1, and after the data is purified by the data preprocessing module 2, the status baseline module 3 defines the operating boundaries of the equipment during normal operation. The operating status baseline specifically includes the static baseline, dynamic baseline, and working condition baseline.

[0037] In this embodiment, the static baseline is the initial threshold of each parameter determined by the equipment's factory parameters and the initial stable operation data during the fault-free period; while the dynamic baseline is the threshold of each parameter adjusted in real time by an adaptive algorithm combined with changes in load and environmental conditions; the operating condition partition baseline establishes parameter characteristic curves for the compressor's start-up, full-load, and shutdown operation modes respectively.

[0038] Once the operational baseline is established, the safety risk monitoring module 4 can begin risk monitoring. Specifically, the safety risk monitoring module 4 is connected to the data preprocessing module 2 and the operational baseline module 3. The data preprocessing module 2 feeds back the preprocessed data to the safety risk monitoring module 4, which then processes and analyzes the acquired data against the operational baseline established by the operational baseline module 3. The safety risk monitoring module 4 primarily performs deviation monitoring, trend analysis, correlation analysis, and hydrogen embrittlement risk monitoring.

[0039] During deviation monitoring, if the deviation of the equipment's current operating parameters from the static baseline, dynamic baseline, or operating condition baseline exceeds the allowable deviation range specified by the static baseline, dynamic baseline, or operating condition baseline, this situation is marked as abnormal. Specifically, deviation monitoring is mainly performed by calculating the deviation rate D. The deviation rate is calculated as follows: ,in, These are the real-time parameter values ​​at time t (e.g., real-time values ​​of compressor operating parameters such as pressure, flow rate, and temperature). The parameter values ​​for the static baseline, dynamic baseline, or operating condition baseline at time t. When D > 20%, that is, when the deviation exceeds 20% of the static baseline, dynamic baseline, or operating condition baseline, it is marked as a suspected anomaly.

[0040] When performing trend analysis, the process involves linearly or exponentially fitting a slowly changing parameter, triggering an alert when the slope k exceeds the normal range. The slope k is calculated as follows: Where y is the specific parameter value of the running time, and x is the running time (h). For example, when performing linear fitting on the hydrogen content of lubricating oil, , where y is the hydrogen content of the lubricating oil (ppm); x is the running time (h); k is the trend slope (ppm / h); and b is the bias term (ppm).

[0041] During correlation analysis, multi-parameter cross-validation eliminates false alarms from single sensors, and a dynamically adjustable baseline definition ensures that normal operating boundaries match the actual operating conditions of the equipment. Simultaneously, combining multi-dimensional anomaly detection methods accurately identifies instantaneous faults, slow degradation, and multi-parameter correlated faults, significantly improving the accuracy of early anomaly identification and reducing false alarms and missed alarms. For example, when performing correlation analysis on exhaust pressure and hydrogen flow rate, their Pearson correlation coefficient r can be calculated:

[0042]

[0043] in, For the i-th sample value of exhaust pressure, This represents the sample mean of the exhaust pressure; Let i be the i-th sample value of hydrogen flow rate. The value represents the sample mean of hydrogen flow rate. Under normal operating conditions, r ≈ 0.9 indicates a strong positive correlation; when |r| < 0.7, it is considered an abnormal correlation.

[0044] Hydrogen embrittlement risk monitoring is primarily conducted using the Hydrogen Embrittlement Risk Index (HRI). The formula for calculating the HRI is: ,in, , , Let be the weighting coefficient, satisfying =1, This is the normalized value of the hydrogen content in the lubricating oil. This is the normalized value of the actual stress in the cylinder block. This is a normalized value of the cumulative operating time. The hydrogen embrittlement risk monitoring system integrates the hydrogen content of the lubricating oil, cylinder stress, and operating time to calculate the hydrogen embrittlement risk index (HRI). When the HRI > 0.7, it indicates that the machine needs to be stopped for inspection.

[0045] After the safety risk monitoring module 4 obtains the monitoring results, the early warning module 5 issues a corresponding early warning. The early warning module 5 is connected to the safety risk monitoring module 4. The early warning module 5 can issue graded early warnings based on the monitoring results of the safety risk monitoring module 4. When an anomaly is detected, a response system of different levels is triggered accordingly, thereby better addressing problems existing in equipment operation. For example, in implementation, it can be divided into four levels of early warning: Level 1 warning: no risk, all parameters are within the dynamic baseline range; Level 2 warning: slight risk, potential degradation, parameters are close to the warning threshold but have not exceeded the standard, or a single non-core parameter is slightly abnormal; Level 3 warning: significant risk, intervention required, parameters exceed the standard but have not reached the emergency threshold, or multiple parameters are abnormally correlated; Level 4 warning: high risk, may cause an accident, parameters are seriously exceeded or there is a direct safety threat.

[0046] To ensure the retention of relevant data, in this embodiment, the data preprocessing module 2, the status baseline module 3, the security risk monitoring module 4, and the early warning module 5 are all connected to the data synchronization and storage module 6. The data preprocessing module 2 feeds back the preprocessed data to the data synchronization and storage module 6 for recording and storage; the status baseline module 3 feeds back the established working status baseline data to the data synchronization and storage module 6 for recording and storage; the security risk monitoring module 4 feeds back the monitoring results data to the data synchronization and storage module 6 for recording and storage; and the early warning module 5 feeds back the early warning data to the data synchronization and storage module 6 for recording and storage.

[0047] The above description is merely an embodiment of the present invention, and common knowledge such as specific structures and characteristics in the solutions are not described in detail here. It should be noted that those skilled in the art can make various modifications and improvements without departing from the structure of the present invention, and these should also be considered within the scope of protection of the present invention. These modifications and improvements will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A condition monitoring and fault prediction system suitable for hydrogen energy compressors, characterized by: Comprising a data acquisition module (1) for acquiring working parameters of a hydrogen compressor, the working parameters including mechanical parameters, electrical parameters, fluid parameters and safety parameters; a data preprocessing module (2) connected with the data acquisition module (1), the data preprocessing module (2) being configured to preprocess the acquired data; a state baseline module (3) connected with the data preprocessing module (2), the state baseline module (3) being configured to establish a working state baseline according to the working parameters; and a safety risk monitoring module (4) connected with the data preprocessing module (2) and the state baseline module (3), the safety risk monitoring module (4) being configured to receive data from the data preprocessing module (2) and perform deviation monitoring, trend analysis, correlation analysis and hydrogen embrittlement risk monitoring. The safety risk monitoring module (4) performs hydrogen embrittlement risk monitoring by calculating a hydrogen embrittlement risk index (HRI). The mechanical parameters include bearing vibration parameters, cylinder temperature, piston temperature, sealing ring tightness and cylinder pressure fluctuation curve. ； wherein, , , is a weight coefficient, satisfying = 1; is a normalized value of hydrogen content of lubricating oil; is a normalized value of actual stress of cylinder; is a normalized value of cumulative running time.

2. The condition monitoring and failure prediction system for hydrogen energy compressors as claimed in claim 1 wherein: The electrical parameters include current, voltage, power factor, winding temperature of the driving motor, and frequency and harmonic content of the frequency converter output. The fluid parameters include inlet and outlet pressure, pressure loss, inlet and outlet temperature, inlet and outlet temperature difference, hydrogen flow and cooling system flow. The safety parameters include hydrogen concentration around the equipment, hydrogen content in lubricating oil, stress and strain of the cylinder and pipeline. The preprocessing of the working parameters by the data preprocessing module (2) includes noise reduction filtering, outlier correction and data calibration.

3. The condition monitoring and fault prediction system for hydrogen energy compressors as claimed in claim 1 wherein: The working state baseline established by the state baseline module (3) includes static baseline, dynamic baseline and working condition baseline.

4. The condition monitoring and failure prediction system for hydrogen energy compressors as claimed in claim 1 wherein: The safety risk monitoring module (4) performs trend analysis by using the slope k, 5. The condition monitoring and failure prediction system for hydrogen energy compressors as claimed in claim 1 wherein: The security risk monitoring module (4) performs deviation monitoring by calculating a deviation rate D, ; wherein, is a real-time parameter value at time t, is an operating state baseline parameter value at time t.

6. The condition monitoring and failure prediction system for hydrogen energy compressors as claimed in claim 1 wherein: where y is a specific value of the running time, and x is the running time. ； Further comprising a warning module (5) connected with the safety risk monitoring module (4), the warning module (5) being configured to perform graded warning according to the results of the safety risk monitoring module (4).

7. The condition monitoring and fault prediction system for hydrogen energy compressors as claimed in any one of claims 1 to 6, wherein: Further comprising a data synchronization and storage module (6) connected with the data preprocessing module (2), the state baseline module (3) and the safety risk monitoring module (4). 8.The state monitoring and fault prediction system for hydrogen energy compressor according to any one of claims 1-6, characterized in that: ​

Images