Abnormality monitoring method and system for hydrogen compressor

Abstract

The invention relates to the technical field of data processing, in particular to an abnormity monitoring method and system for a hydrogen compressor, and the method comprises the steps: collecting the operation data of the hydrogen compressor; calculating a performance reference quantity by using the normalized operation data, wherein the performance reference quantity reflects the performance state of the hydrogen compressor at the time i; and calculating the fluctuation degree of the operation data of the time i. According to the method, the operation data of the hydrogen compressor are monitored, when abnormal data occur, the abnormal data are found in time, an alarm is given, the upper limit value and the lower limit value corresponding to the data are calculated according to the real-time data, and the problem that the abnormal data are detected inaccurately due to the fact that the upper limit and the lower limit are fixed in an existing IQR algorithm is solved. The operation efficiency and safety of the hydrogen compressor are effectively improved, the breakdown time is shortened, the service life of equipment is prolonged, and the stability and safety of hydrogen supply are ensured.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to a method and system for monitoring abnormality of a hydrogen compressor. Background Art

[0002] A hydrogen compressor is a device specifically used to compress hydrogen. Its purpose is to compress hydrogen to a high pressure state to meet the needs of hydrogen energy applications. In order to ensure the normal operation of the hydrogen compressor, it can be used more efficiently during storage and transportation. It is a device used to process hydrogen. By increasing the pressure of hydrogen, it occupies a smaller volume and is convenient for storage and transportation. Testing the performance of the hydrogen compressor is crucial.

[0003] Hydrogen compressors are key equipment in the production and transportation of hydrogen energy. Their normal operation is crucial to ensuring the stability and safety of hydrogen supply. Therefore, it is very important to effectively monitor the abnormalities of hydrogen compressors. Real-time monitoring and data collection can be achieved by installing various sensors (such as temperature sensors, pressure sensors, vibration sensors, etc.) to collect key parameters in the operation of the compressor in real time. These data can be used to monitor the status of the compressor in real time and detect potential problems in a timely manner.

[0004] In the related technology, for example, a Chinese patent application document with publication number CN117536849A discloses an intelligent detection method and system for the performance of a hydrogen compressor. The method first determines the voltage data, current data, temperature data, pressure data and vibration data of multiple hydrogen compressors as performance data of multiple operating performances, then obtains the historical data of the hydrogen compressor to be detected, determines the benchmark data of each operating performance of the hydrogen compressor to be detected based on the historical data, and finally judges whether the performance of the hydrogen compressor to be detected is normal based on the benchmark data and the real-time performance data.

[0005] Hydrogen compressors need to monitor multiple data. Currently, the IQR (interquartile range) algorithm is often used for anomaly detection of multiple data. However, in this algorithm, the upper and lower limits of detecting abnormal values ​​are usually fixed, which makes the changing data often have detection errors, making it impossible to detect abnormal data in time, resulting in the failure to discover abnormalities in time and the failure to perform maintenance in time, causing economic losses. Summary of the invention

[0006] The present invention provides a method and system for monitoring the abnormality of a hydrogen compressor, aiming to solve the problem in the related art that the upper and lower limits are usually fixed, so that the changing data often have detection errors, making it impossible to detect abnormal data in time, resulting in the failure to discover the abnormality in time, the failure to perform maintenance in time, and causing economic losses.

[0007] In a first aspect, the present invention provides a method for monitoring an abnormality of a hydrogen compressor, comprising: obtaining operating data of the hydrogen compressor; calculating a performance reference quantity using normalized operating data, wherein the performance reference quantity reflects the performance status of the hydrogen compressor at time i; and calculating the degree of fluctuation of the operating data at time i, wherein the degree of fluctuation is positively correlated with the difference between the performance reference quantity at time i and its adjacent time points within a time period, wherein the time period is composed of a preset number of adjacent time points around time i; and calculating the change difference value of the operating data at time i. , the calculation formula is: ; In the formula, Indicates the degree of fluctuation of the operating data at time i, Indicates the fluctuation degree of the pth running data before time i in the time period, Indicates the fluctuation degree of the qth running data after time i in the time period, or Indicates the number of running data before or after time i in the time period; obtains the minimum value of the product of the running data and its corresponding change difference value in the time period, and obtains the upper limit value and the lower limit value based on the product of the minimum value and the upper limit coefficient and the lower limit coefficient, wherein the upper limit coefficient is greater than the lower limit coefficient; monitors the running data based on the upper limit value and the lower limit value. The upper limit value and the lower limit value of the data at each time are obtained according to the data characteristics, and the data at each time are detected, and the data outside the upper limit value and the lower limit value range are marked as abnormal data, which can be detected in real time. When abnormal data occurs, the problem can be discovered in time.

[0008] Furthermore, obtaining the operating data of the hydrogen compressor includes: obtaining multiple types of operating data, including five types, wherein the operating data at least includes vibration amplitude data, vibration frequency data, temperature data, intake pressure data, and exhaust pressure data; according to the preset time interval for collecting the operating data, establishing a data group corresponding to each operating data to obtain a data group of the corresponding type. The use of the above multiple data can accurately reflect the performance status of the hydrogen compressor and improve the accuracy of subsequent monitoring of the hydrogen compressor.

[0009] Furthermore, the operation data is monitored based on the upper limit value and the lower limit value, including: if the operation data is outside the range from the upper limit value to the lower limit value, the operation data is marked as abnormal data and an alarm is issued.

[0010] Furthermore, the performance reference of the running data corresponding to the calculation time i is , the calculation formula is ; In the formula, Indicates the intake pressure data corresponding to time i, Indicates the exhaust pressure data corresponding to time i, represents the temperature data corresponding to time i, represents the vibration amplitude data corresponding to time i, represents the vibration frequency data corresponding to time i, Represents the standard normalization function. It reduces the dimension of the data, reduces the amount of subsequent calculations, and maintains the data characteristics so that the reduced-dimensional data can continue to reflect the characteristics of the data.

[0011] Furthermore, the fluctuation degree of the running data at time i is calculated , the calculation formula is: ; In the formula, represents the performance reference corresponding to the operating data at time i, It represents the performance reference quantity corresponding to the operation data of the adjacent time j in the time period corresponding to time i, It represents the correction coefficient of the performance reference quantity, and n represents the number of operating data in the time period corresponding to time i. The greater the fluctuation, the greater the change of the above data in the continuous time period, and the greater the difference between the performance reference quantity of time i and its adjacent time points in the time period, the greater the probability of abnormal operation data at time i.

[0012] Furthermore, the method for determining the correction coefficient of the performance reference quantity includes: presetting a constant as the correction coefficient of the performance reference quantity; or sorting the operating data in each of the data groups from large to small or from small to large, and determining the average of the sequence number differences between the operating data at time i and the operating data at time j in the corresponding time period after sorting in the five data groups, as the correction coefficient.

[0013] Furthermore, based on the product of the minimum value and the upper limit coefficient and the lower limit coefficient, the upper limit value and the lower limit value are obtained, including: ; In the formula, represents the upper limit of the running data at time i, Indicates the lower limit of the operating data at time i, Indicates the change difference value corresponding to the jth running data in the time period corresponding to time i, Indicates the temperature data of the jth operating data in the time period corresponding to time i, is a constant, is the upper limit coefficient, is the lower limit coefficient, and n represents the number of operating data in the time period corresponding to time i. The corresponding upper and lower limits can be calculated based on the operating data collected at each time point, and the upper and lower limits can be changed in real time according to each operating data, thereby improving the accuracy of abnormal data detection.

[0014] Furthermore, the preset time interval is 60 seconds.

[0015] In a second aspect of the present invention, a hydrogen compressor abnormality monitoring system is provided, comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above hydrogen compressor abnormality monitoring methods.

[0016] Beneficial effects: The operating data of the hydrogen compressor can be monitored in real time. When abnormal data appears, it can be discovered and alarmed in time. The corresponding upper and lower limits of the data can be calculated for the real-time data, avoiding the problem of inaccurate detection of abnormal data caused by the fixed upper and lower limits in the current IQR (interquartile range) algorithm. It can effectively improve the operating efficiency and safety of the hydrogen compressor, reduce downtime, extend the life of the equipment, and ensure the stability and safety of the hydrogen supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The following detailed description is read with reference to the accompanying drawings, which illustrate several embodiments of the present invention in an exemplary and non-limiting manner, and in which like or corresponding reference numerals represent like or corresponding parts, wherein: Figure 1 is a flowchart schematically illustrating detection of abnormal data according to an embodiment of the present invention; Figure 2 FIG. 1 is a schematic diagram schematically showing a system structure according to an embodiment of the present invention.

[0018] Reference numerals 1. Processor; 2. Communication bus; 3. Memory; 4. Communication interface. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] When conducting effective abnormal monitoring of the hydrogen compressor, multiple data during the operation of the hydrogen compressor can be used for detection, such as vibration monitoring, temperature monitoring and pressure monitoring.

[0022] In one embodiment, vibration monitoring is an important means of evaluating the health of mechanical components. By installing a vibration sensor, the vibration frequency and amplitude of the compressor can be monitored to determine the operating status of the equipment. Vibration monitoring can detect problems such as bearing wear, imbalance, looseness, etc., and repairs can be performed in a timely manner. Through vibration data, the operating performance of the compressor can be evaluated and the operating parameters can be optimized. Temperature monitoring temperature is an important parameter reflecting the operating status of the equipment. By installing a temperature sensor, the temperature changes of various parts of the compressor can be monitored in real time. Overheating protection can be performed to detect overheating in time and prevent equipment damage. At the same time, efficiency evaluation can be performed. Through temperature data, the operating efficiency of the compressor can be evaluated and the operating parameters can be optimized.

[0023] Pressure monitoring is one of the key parameters in compressor operation. By installing a pressure sensor, the intake and exhaust pressures can be monitored in real time to ensure that the compressor operates within the normal range. Abnormal pressure, such as blockage, leakage, etc., can be detected in time to ensure safe operation. Through pressure data, the performance of the compressor can be evaluated and the operating parameters can be optimized. The abnormal monitoring method of hydrogen compressor can effectively improve the operating efficiency and safety of the equipment, reduce downtime, extend equipment life, and ensure the stability and safety of hydrogen supply through real-time monitoring, data analysis, fault diagnosis and other means. These methods have important application value in modern industry.

[0024] like Figure 1 As shown, S101: obtaining the operating data of the hydrogen compressor.

[0025] In one embodiment, corresponding professional sensors can be used to collect vibration data, temperature data and pressure data of the hydrogen compressor to obtain operating data. It should be noted that the vibration data includes vibration amplitude and vibration frequency, and the pressure data includes intake pressure and exhaust pressure. Therefore, five types of operating data can be collected through the above steps, and the five types of operating data correspond to vibration amplitude data, vibration frequency data, temperature data, intake pressure data and exhaust pressure data, respectively. It should be noted that after obtaining the operating data, it needs to be normalized to facilitate subsequent calculations.

[0026] In one embodiment, according to the preset time interval for collecting operating data, a data group corresponding to each operating data is established to obtain a data group of a corresponding type. In this embodiment, the preset time interval is 60 seconds. In other embodiments, the preset time interval can be 30 seconds or 40 seconds, etc., which can be adjusted according to the specific implementation situation.

[0027] S102: Calculate the performance reference of the operating data.

[0028] In one embodiment, vibration amplitude data, vibration frequency data, temperature data, intake pressure data and exhaust pressure data are recorded at each time point, and these data can reflect the operation of the hydrogen compressor at this time point. For example: a sudden drop or rise in pressure may cause unstable airflow and cause vibration. The increase in temperature may cause thermal expansion of the material, change the gap and alignment inside the compressor, and thus affect the vibration. The increase in temperature will increase the temperature of the gas during the compression process, resulting in an increase in exhaust pressure. When the temperature decreases, the temperature of the gas decreases during the cooling process, resulting in a decrease in exhaust pressure. When the pressure increases, the pressure of the gas increases during the compression process, resulting in an increase in temperature. When the pressure decreases, the pressure of the gas decreases during the expansion process, resulting in a decrease in temperature. Therefore, the performance status of the hydrogen compressor can be reflected by the above characteristics. However, the amount of data above is too large, so it is necessary to reduce the dimension of the data to reduce the amount of subsequent calculations, while maintaining the data characteristics so that the reduced-dimensional data can continue to reflect the characteristics of the data.

[0029] In one embodiment, for the operation data at any time point, a performance reference quantity of the operation data can be calculated, and the performance reference quantity reflects the performance status of the hydrogen compressor at the time point.

[0030] In one embodiment, taking the operation data collected at time i as an example, the performance reference quantity of the operation data corresponding to time i is calculated. , the calculation formula is: ; In the formula, Indicates the intake pressure data corresponding to time i, Indicates the exhaust pressure data corresponding to time i, represents the temperature data corresponding to time i, represents the vibration amplitude data corresponding to time i, represents the vibration frequency data corresponding to time i, Represents the standard normalization function.

[0031] S103: Calculate the fluctuation degree of the operating data.

[0032] In one embodiment, because the data of the hydrogen compressor is continuous over time, under normal operation, the operation of the hydrogen compressor is stable. Whether it is adjusted during operation or in continuous stable operation, the data generated by the hydrogen compressor in continuous time is relatively coherent, so the difference in the data in continuous time will not be too large. If the difference in the data in continuous time is too large, it is possible that the hydrogen compressor has an abnormality.

[0033] In one embodiment, the fluctuation degree of the operation data at time i is calculated, and the fluctuation degree reflects the change amplitude of the operation data in the continuous time period and the difference between the performance reference quantity of time i and its adjacent time points in the continuous time period. The greater the fluctuation degree, the greater the change amplitude of the above data in the continuous time period, the greater the difference between the performance reference quantity of time i and its adjacent time points in the time period, and the greater the probability that the operation data at time i is abnormal.

[0034] In one embodiment, a time period is composed of a preset number of time points adjacent to and around time i, and the preset number may be 2, 3, or 4, which may be adjusted according to specific implementation conditions. Exemplarily, the preset number is two, and taking time i as an example, two adjacent time points to and around time i are obtained, and this time period is defined as the time period of time i. For example: i-2, i-1, i, i+1, and i+2 are the time periods corresponding to time i.

[0035] In one embodiment, the fluctuation degree of the operating data is calculated, and the fluctuation degree is positively correlated with the difference between the performance reference amount of time i and its adjacent time points within the time period. The larger the difference between the performance reference amount of time i and its adjacent time points within the time period, the greater the fluctuation degree of the operating data.

[0036] In one embodiment, the fluctuation degree of the operating data is calculated, and the calculation formula is obtained as follows: ; In the formula, Indicates the degree of fluctuation of the operating data at time i, represents the performance reference corresponding to the operating data at time i, It represents the performance reference quantity corresponding to the operation data of the adjacent time j in the time period corresponding to time i, represents the correction coefficient of the performance reference quantity, and n represents the number of operating data in the time period corresponding to time i. Among them, sorting the operating data in the five data groups includes: sorting the operating data in each of the data groups from large to small or from small to large.

[0037] In one embodiment, for the correction factor , a constant can be preset as a correction coefficient of the performance reference quantity, for example, the correction coefficient is 1 or 2, etc., which can be adjusted according to the specific implementation situation.

[0038] In another embodiment, for obtaining the correction coefficient , first sort the operating data in each of the data groups from large to small or from small to large, and determine the average of the sequence number differences between the operating data at time i and the operating data at time j in the corresponding time period after sorting in the five data groups, as the correction coefficient. Using this method, the variation range of the operating data of the hydrogen compressor in a continuous time period is taken into account, so that the fluctuation degree of the operating data is calculated more accurately.

[0039] In one embodiment, the mean of the ranking difference between the operation data at time i and the operation data at time j in the corresponding time period is calculated in five data groups. Exemplarily, taking the operation data of temperature data as an example, five operation data (temperature data) are collected in the time period, namely F1, F2, F3, F4 and F5. If F2 is the operation data collected at time i and F3 is the operation data collected at time j. Then F1, F2, F3, F4 and F5 are arranged in order from large to small, and the ranking is F5, F3, F1, F4, F2. At this time, time i is ranked 5th and time j is ranked 2nd, so the ranking difference between time i and time j is 3. According to the above steps, the ranking difference between time i and time j in the other four data groups can be obtained, and finally the mean value can be calculated.

[0040] S104: Calculate the change difference value of the operating data.

[0041] In one embodiment, there are multiple different stages in the operation of the hydrogen compressor, so the judgment of data anomalies needs to have different standards for different stages of the operation process. This can make the standards more accurate, ensure that the data can be accurately detected, and detect the anomalies of the hydrogen compressor in time during the operation process.

[0042] In one embodiment, the change difference value of the running data is calculated using the following formula: .

[0043] In the formula, Indicates the change difference value of the operating data at time i. The larger the value, the greater the possibility of abnormality. Indicates the degree of fluctuation of the operating data at time i, Indicates the fluctuation degree of the pth running data before time i in the time period, Indicates the fluctuation degree of the qth running data after time i in the time period, or Respectively represent the number of running data before or after time i in the time period.

[0044] S105: Calculate the upper limit and lower limit of the operation data.

[0045] In one embodiment, for any type of operating data, the minimum value of the product of the operating data and its corresponding change difference value within the time period is obtained, and the upper limit value and the lower limit value are obtained based on the product of the minimum value and the upper limit coefficient and the lower limit coefficient, respectively, wherein the upper limit coefficient is greater than the lower limit coefficient. In this embodiment, taking the operating data of temperature data as an example, the upper limit value and the lower limit value of the operating data of the temperature data at time i are calculated, and the calculation formula is: ; In the formula, represents the upper limit of the running data at time i, Indicates the lower limit of the operating data at time i, Indicates the change difference value corresponding to the jth running data in the time period corresponding to time i, Indicates the temperature data of the jth operating data in the time period corresponding to time i, is a constant, is the upper limit coefficient, is the lower limit coefficient, and n represents the number of running data in the time period corresponding to time i. is a constant ranging from 0 to 1. In this embodiment, The empirical value of is 0.25. In other embodiments, The value of can be 0.3 or 0.28, etc., and can be adjusted according to the specific implementation situation.

[0046] It should be noted that according to the above method, the upper and lower limits of five types of operating data at time i can be calculated, that is, the upper and lower limits of vibration amplitude data, vibration frequency data, temperature data, intake pressure data and exhaust pressure data at time i can be calculated to monitor the abnormal state of the hydrogen compressor.

[0047] S106: Monitoring the operation data based on the upper limit value and the lower limit value.

[0048] In one embodiment, if the operating data is outside the range from the upper limit value to the lower limit value, the operating data is marked as abnormal data and an alarm is issued. That is to say, the operating data greater than the upper limit value and less than the lower limit value is marked as abnormal operating data to monitor the abnormality of the hydrogen compressor.

[0049] For example, taking temperature data as an example, the value of the operating data collected at time i is F, and the upper limit value of the operating data at time i is calculated to be Z1 and the lower limit value is Z2. The value F of the operating data is compared with Z1 and Z2. If the value F of the operating data is within the range of Z1-Z2, the operating data is not abnormal operating data. If the value F of the operating data is outside the range of Z1-Z2, the operating data is marked as abnormal operating data, and an alarm is issued to monitor the hydrogen compressor.

[0050] Through the above steps, the operating data of the hydrogen compressor can be monitored in real time. When abnormal data appears, it can be discovered and alarmed in time, and the corresponding upper and lower limits of the data can be calculated for the real-time data, avoiding the problem of inaccurate detection of abnormal data caused by the fixed upper and lower limits in the current IQR (interquartile range) algorithm. Effectively improve the operating efficiency and safety of the hydrogen compressor, reduce downtime, extend equipment life, and ensure the stability and safety of hydrogen supply.

[0051] The present invention also provides an abnormality monitoring system for a hydrogen compressor. Figure 2 As shown, the system includes a processor 1 and a memory 3, wherein the memory 3 stores computer program instructions, and when the computer program instructions are executed by the processor 1, a method for monitoring an abnormality of a hydrogen compressor according to the first aspect of the present invention is implemented.

[0052] The system also includes other components well known to those skilled in the art, such as a communication bus 2 and a communication interface 4. The configuration and functions of these components are known in the art and thus will not be described in detail herein.

[0053] In the present invention, the aforementioned memory 3 may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0054] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0055] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0056] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for monitoring abnormality of a hydrogen compressor, characterized in that: include: Obtaining the operating data of the hydrogen compressor; Calculating a performance reference using the normalized operating data, wherein the performance reference reflects the performance status of the hydrogen compressor at time i; and calculating the degree of fluctuation of the operation data at time i, wherein the degree of fluctuation is positively correlated with the difference between the performance reference quantity at time i and its adjacent time points within the time period, wherein the time period is composed of a preset number of adjacent time points around time i; Calculate the change difference value of the running data at time i , the calculation formula is: ； In the formula, Indicates the degree of fluctuation of the operating data at time i, Indicates the fluctuation degree of the pth running data before time i in the time period, Indicates the fluctuation degree of the qth running data after time i in the time period, or Indicates the number of running data before or after time i in the time period; Obtain the minimum value of the product of the operating data and its corresponding change difference value within the time period, and obtain the upper limit value and the lower limit value based on the product of the minimum value and the upper limit coefficient and the lower limit coefficient, wherein the upper limit coefficient is greater than the lower limit coefficient; The operation data is monitored based on the upper limit value and the lower limit value.

2. The method for monitoring abnormality of a hydrogen compressor according to claim 1, characterized in that: Obtain the operating data of the hydrogen compressor, including: The types of acquiring multiple types of operating data include five types, wherein the operating data includes at least vibration amplitude data, vibration frequency data, temperature data, intake pressure data, and exhaust pressure data; According to the preset time interval for collecting the operation data, a data group corresponding to each operation data is established to obtain a data group of a corresponding type.

3. The method for monitoring abnormality of a hydrogen compressor according to claim 1, characterized in that: The operation data is monitored based on the upper limit value and the lower limit value, including: If the operating data is outside the range from the upper limit to the lower limit, the operating data is marked as abnormal data and an alarm is issued.

4. The method for monitoring abnormality of a hydrogen compressor according to claim 2, characterized in that: Calculate the performance reference of the running data corresponding to time i , the calculation formula is: ； In the formula, Indicates the intake pressure data corresponding to time i, Indicates the exhaust pressure data corresponding to time i, represents the temperature data corresponding to time i, represents the vibration amplitude data corresponding to time i, represents the vibration frequency data corresponding to time i, Represents the standard normalization function.

5. The method for monitoring abnormality of a hydrogen compressor according to claim 2, characterized in that: Calculate the fluctuation degree of the running data at time i , the calculation formula is: ； In the formula, represents the performance reference corresponding to the operating data at time i, It represents the performance reference quantity corresponding to the operation data of the adjacent time j in the time period corresponding to time i, It represents the correction coefficient of the performance reference quantity, and n represents the number of operating data in the time period corresponding to time i.

6. The method for monitoring abnormality of a hydrogen compressor according to claim 5, characterized in that: The method for determining the correction coefficient of the performance reference quantity includes: A constant is preset as a correction coefficient for the performance reference; or the operating data in each of the data groups are sorted from large to small or from small to large, and the average of the sequence number differences between the operating data at time i and the operating data at time j in the corresponding time period after sorting in the five data groups is determined as the correction coefficient.

7. The method for monitoring abnormality of a hydrogen compressor according to claim 2, characterized in that: Based on the product of the minimum value and the upper limit coefficient and the lower limit coefficient, the upper limit value and the lower limit value are obtained, including: ； In the formula, represents the upper limit of the running data at time i, Indicates the lower limit of the operating data at time i, Indicates the change difference value corresponding to the jth running data in the time period corresponding to time i, Indicates the temperature data of the jth operating data in the time period corresponding to time i, is a constant, is the upper limit coefficient, is the lower limit coefficient, and n represents the number of running data in the time period corresponding to time i.

8. The method for monitoring abnormality of a hydrogen compressor according to claim 2, characterized in that: The preset time interval is 60 seconds.

9. A hydrogen compressor abnormality monitoring system, comprising a processor and a memory, characterized in that: The memory stores a computer program, and the processor executes the computer program to implement the hydrogen compressor abnormality monitoring method according to any one of claims 1 to 8.

Images