Recycling hydrogen compressor online monitoring system based on data analysis

Abstract

The invention belongs to the technical field of hydrogen compressor supervision, and particularly relates to a circulating hydrogen compressor online monitoring system based on data analysis, which comprises a multi-parameter monitoring transmission module, an intelligent analysis module, an early warning mechanism triggering module and an operation supervision end, the multi-parameter monitoring and transmitting module is used for monitoring operation of the recycle hydrogen compressor, the intelligent analysis module is used for processing and analyzing all collected parameter data, an alarm is given out when it is recognized that the operation state of equipment is abnormal or potential faults exist, and the reliability and safety of operation of the recycle hydrogen compressor are improved; operation inspection is conducted on all the sensors through the sensor inspection and judgment module so as to judge the abnormal operation probability of each sensor, and the monitoring influence evaluation module comprehensively analyzes the influence degree on online monitoring of the recycle hydrogen compressor based on the operation conditions of all the sensors, so that effective monitoring of the recycle hydrogen compressor is guaranteed; and the operation safety and stability of the circulating hydrogen compressor are further improved.

Description

Technical Field

[0001] The invention relates to the technical field of hydrogen compressor supervision, and in particular to an online monitoring system for a circulating hydrogen compressor based on data analysis. Background Art

[0002] A circulating hydrogen compressor is a compressor used in the chemical industry to increase the circulating hydrogen pressure to overcome the system pressure drop and ensure the circulating gas volume required by the process. It is mainly used in industrial production processes under high temperature and high pressure environments. The stability and reliability of its operating state directly affect the overall efficiency of the production line and product quality.

[0003] At present, it is difficult to achieve effective monitoring and abnormal identification and early warning of the circulating hydrogen compressor during its operation, and it is impossible to collect abnormal judgments on various sensors involved and reasonably evaluate the degree of impact on the monitoring of the circulating hydrogen compressor, which is not conducive to ensuring the safe and stable operation of the circulating hydrogen compressor;

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an online monitoring system for a circulating hydrogen compressor based on data analysis, which solves the problem that the prior art is difficult to achieve effective monitoring and abnormal identification and early warning of the circulating hydrogen compressor, and is unable to collect abnormal judgments on the various sensors involved and reasonably evaluate the degree of impact on the monitoring of the circulating hydrogen compressor, which is not conducive to ensuring the safe and stable operation of the circulating hydrogen compressor.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An online monitoring system for a circulating hydrogen compressor based on data analysis, comprising a multi-parameter monitoring transmission module, an intelligent analysis module, an early warning mechanism triggering module and an operation supervision terminal;

[0008] The multi-parameter monitoring and transmission module monitors the operation of the circulating hydrogen compressor through several sensors arranged on the circulating hydrogen compressor, collects various parameter data of the circulating hydrogen compressor, and sends the various parameter data of the circulating hydrogen compressor to the intelligent analysis module;

[0009] The intelligent analysis module uses machine learning algorithms to process and analyze all collected parameter data, identify the operating status and potential faults of the circulating hydrogen compressor, and send the analysis and identification information to the early warning mechanism trigger module;

[0010] When the equipment is in an abnormal operating state or has a potential fault, the early warning mechanism trigger module triggers the alarm mechanism and generates corresponding alarm information, and sends the alarm information to the operation supervision end; when the operation supervision end receives the alarm information, it displays it and emits an alarm sound.

[0011] Furthermore, the early warning mechanism triggering module is connected to the sensor inspection and judgment module in communication, and the sensor inspection and judgment module obtains all sensors included in the multi-parameter monitoring transmission module, and marks the corresponding sensor as the target sensor i, where i is a natural number greater than 1;

[0012] An operation inspection is performed on the target sensor i to determine the probability of abnormal operation of the target sensor i, and a normal operation signal or a suspicious operation signal of the target sensor i is generated accordingly, and the suspicious operation signal of the target sensor i is sent to the early warning mechanism trigger module; when the early warning mechanism trigger module receives the suspicious operation signal, the alarm mechanism is triggered and corresponding alarm information is generated, and the alarm information is sent to the operation supervision end, which displays the alarm information and emits an alarm sound when receiving it.

[0013] Furthermore, the analysis process of the sensor inspection and judgment module is as follows:

[0014] The sensor inspection coefficient of the target sensor i is obtained by analysis, and the sensor inspection coefficient is numerically compared with the preset sensor inspection coefficient threshold. If the sensor inspection coefficient exceeds the preset sensor inspection coefficient threshold, a suspicious operation signal of the target sensor i is generated; if the sensor inspection coefficient does not exceed the preset sensor inspection coefficient threshold, a normal operation signal of the target sensor i is generated.

[0015] Furthermore, the analysis and acquisition method of the sensor inspection coefficient is as follows:

[0016] Obtain the parameter data collected by the target sensor i, compare the parameter data with the set normal data collection range, and assign a collection abnormality symbol LP-1 if the parameter data is not within the corresponding normal data collection range;

[0017] The number of times the target sensor i is assigned the collection abnormality symbol LP-1 per unit time is obtained and marked as the collection abnormality detection value, as well as all the collection times of the corresponding parameter data of the target sensor i are obtained, and the time difference between two adjacent groups of collection times is calculated to obtain the collection time difference;

[0018] The acquisition time difference is numerically compared with the corresponding preset acquisition time difference range. If the acquisition time difference is not within the corresponding preset acquisition time difference range, the corresponding acquisition time difference is marked as an abnormal acquisition time difference. The number of abnormal acquisition time differences per unit time is obtained and marked as an abnormal acquisition detection value, and the sensor verification coefficient is obtained by numerically calculating the acquisition abnormal detection value and the abnormal acquisition detection value.

[0019] Further, the sensor inspection and judgment module is communicatively connected to the monitoring impact assessment module, and the sensor inspection and judgment module sends the inspection and judgment information of all sensors to the monitoring impact assessment module, and the monitoring impact assessment module comprehensively analyzes the impact degree on the online monitoring of the circulating hydrogen compressor based on the operating conditions of all sensors, and generates a monitoring high impact signal or a monitoring low impact signal accordingly;

[0020] The monitored high-impact signal is sent to the early warning mechanism trigger module. When the early warning mechanism trigger module receives the monitored high-impact signal, the alarm mechanism is triggered and corresponding alarm information is generated. The alarm information is sent to the operation supervision end. When the operation supervision end receives the alarm information, it is displayed and an alarm sound is issued.

[0021] Furthermore, the analysis process of the monitoring impact assessment module includes:

[0022] A detection period is set, the number of times the target sensor i generates suspicious operation signals during the detection period is collected and marked as a suspicious operation value, and the suspicious operation value is numerically compared with the corresponding preset suspicious operation threshold. If the suspicious operation value exceeds the corresponding preset suspicious operation threshold, the target sensor i is marked as a non-optimal sensor;

[0023] If there is a non-optimal sensor during the detection period, a monitoring high impact signal is generated.

[0024] Furthermore, if there is no non-optimal sensor during the detection period, several monitoring periods are set during the detection period, the number of times the suspicious signal is generated during the monitoring period is collected and marked as a suspicious frequency value, and the suspicious frequency value is numerically compared with a preset suspicious frequency threshold. If the suspicious frequency value exceeds the preset suspicious frequency threshold, the corresponding monitoring period is marked as an abnormal period;

[0025] The number of abnormal time periods in the detection period is obtained and the ratio thereof is calculated with the total number of monitoring periods to obtain the abnormal time condition value, and the suspicious frequency values ​​of all monitoring periods are averaged to obtain the suspicious frequency table value, and the maximum value of the suspicious frequency value in the detection period is marked as the suspicious frequency amplitude value;

[0026] The monitoring influence coefficient is obtained by numerically calculating the abnormal time condition value, the suspicious frequency table value and the suspicious frequency amplitude value, and the monitoring influence coefficient is numerically compared with the preset monitoring influence coefficient threshold. If the monitoring influence coefficient exceeds the preset monitoring influence coefficient threshold, a high monitoring influence signal is generated; if the monitoring influence coefficient does not exceed the preset monitoring influence coefficient threshold, a low monitoring influence signal is generated.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. In the present invention, the operation of the circulating hydrogen compressor is monitored by a multi-parameter monitoring and transmission module, and the intelligent analysis module processes and analyzes all the collected parameter data. When an abnormal operation state of the equipment or a potential fault is identified, the operation monitoring end sends an alarm, thereby improving the reliability and safety of the operation of the circulating hydrogen compressor;

[0029] 2. In the present invention, all sensors are subjected to operation inspection through the sensor inspection and judgment module to determine the probability of abnormal operation of each sensor. The monitoring impact assessment module comprehensively analyzes the impact on the online monitoring of the circulating hydrogen compressor based on the operating conditions of all sensors, which is conducive to ensuring the effective monitoring of the circulating hydrogen compressor and further improving the operating safety and stability of the circulating hydrogen compressor. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0031] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0032] Figure 2 This is a system block diagram of Embodiment 2 and Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0033] 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 only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Embodiment 1: Figure 1 As shown, the present invention proposes an online monitoring system for a circulating hydrogen compressor based on data analysis, comprising a multi-parameter monitoring transmission module, an intelligent analysis module, an early warning mechanism triggering module and an operation supervision terminal;

[0035] The multi-parameter monitoring and transmission module monitors the operation of the circulating hydrogen compressor through several sensors (including temperature sensors, pressure sensors, vibration sensors, etc.) installed on the circulating hydrogen compressor, collects various parameter data of the circulating hydrogen compressor (including vibration, temperature, pressure and other parameters), and uses wireless communication technology (such as Wi-Fi, LoRa, NB-IoT, etc., which have the characteristics of low power consumption, high reliability and long-distance transmission to ensure the real-time and accuracy of data) to send the various parameter data of the circulating hydrogen compressor to the intelligent analysis module, thereby providing data support for the analysis process of the intelligent analysis module.

[0036] The intelligent analysis module uses machine learning algorithms (such as support vector machines, neural networks, etc.) to process and analyze all collected parameter data, identify the operating status and potential faults of the circulating hydrogen compressor, and send the analysis and identification information to the early warning mechanism trigger module; for example, by analyzing vibration characteristics, temperature changes, and pressure fluctuations, the operating status and potential faults of the circulating hydrogen compressor can be identified.

[0037] When the equipment is operating in an abnormal state or there is a potential fault, the early warning mechanism trigger module triggers the alarm mechanism and generates corresponding alarm information, and sends the alarm information to the operation supervision end; when the operation supervision end receives the alarm information, it displays it and sounds an alarm to remind management personnel to take timely response measures. It can comprehensively and effectively monitor the operating status of the circulating hydrogen compressor and discover potential faults in time, improve the reliability and safety of the circulating hydrogen compressor operation, and reduce maintenance costs and usage risks.

[0038] Embodiment 2: Figure 2 As shown, the difference between this embodiment and the first embodiment is that the early warning mechanism trigger module is connected to the sensor inspection and judgment module in communication, the sensor inspection and judgment module obtains all sensors included in the multi-parameter monitoring transmission module, marks the corresponding sensor as the target sensor i, and i is a natural number greater than 1; performs an operation inspection on the target sensor i, judges the probability of abnormal operation of the target sensor i, and generates a normal operation signal or a suspicious operation signal of the target sensor i accordingly, and sends the suspicious operation signal of the target sensor i to the early warning mechanism trigger module;

[0039] When the early warning mechanism trigger module receives a suspicious operation signal, it triggers the alarm mechanism and generates corresponding alarm information, and sends the alarm information to the operation supervision end. When the operation supervision end receives the alarm information, it displays it and emits an alarm sound to remind the management personnel to check and analyze the corresponding sensors in time, and take reasonable control measures for the corresponding sensors to ensure the accurate and stable operation of each sensor, which is conducive to the effective monitoring of the circulating hydrogen compressor; the analysis process of the sensor inspection and judgment module is as follows:

[0040] Obtain the parameter data collected by the target sensor i, compare the parameter data with the set normal data collection range, and assign the collection abnormality symbol LP-1 if the parameter data is not within the corresponding normal data collection range (for example, the corresponding parameter data is obviously too large or too small, indicating that the probability of inaccurate data collection of the target sensor i is high).

[0041] The number of times the target sensor i is assigned the collection abnormality symbol LP-1 per unit time is obtained and marked as the collection abnormality detection value, as well as all the collection times of the corresponding parameter data of the target sensor i are obtained, and the time difference between two adjacent groups of collection times is calculated to obtain the collection time difference;

[0042] Compare the acquisition time difference with the corresponding preset acquisition time difference range. If the acquisition time difference is not within the corresponding preset acquisition time difference range, it indicates that the acquisition efficiency of the corresponding data acquisition process does not meet the requirements, and the corresponding acquisition time difference is marked as an abnormal acquisition time difference; obtain the number of abnormal acquisition time differences per unit time and mark it as an abnormal acquisition detection value;

[0043] The sensor inspection coefficient Li is obtained by numerically calculating the collected abnormal detection value Yi and the abnormal detection value Si through the formula Li=w×Yi+q×Si; wherein w and q are preset weight coefficients with values ​​greater than zero, and the larger the value of the sensor inspection coefficient Li, the more abnormal the operation of the target sensor i in a unit time is, and the greater the probability that the target sensor i has an abnormality;

[0044] The sensor inspection coefficient Li is numerically compared with the preset sensor inspection coefficient threshold. If the sensor inspection coefficient Li exceeds the preset sensor inspection coefficient threshold, it indicates that the operation of the target sensor i per unit time is abnormal and the probability of an abnormality is high, then a suspicious operation signal of the target sensor i is generated; if the sensor inspection coefficient Li does not exceed the preset sensor inspection coefficient threshold, it indicates that the probability of an abnormality of the target sensor i per unit time is low, then a normal operation signal of the target sensor i is generated.

[0045] Embodiment 3: Figure 2 As shown, the difference between this embodiment and the first and second embodiments is that the sensor inspection and judgment module is communicatively connected to the monitoring impact assessment module, the sensor inspection and judgment module sends the inspection and judgment information of all sensors to the monitoring impact assessment module, and the monitoring impact assessment module comprehensively analyzes the impact degree on the online monitoring of the circulating hydrogen compressor based on the operating conditions of all sensors, and generates a monitoring high impact signal or a monitoring low impact signal accordingly;

[0046] The monitoring high impact signal is sent to the early warning mechanism trigger module. When the early warning mechanism trigger module receives the monitoring high impact signal, the alarm mechanism is triggered and the corresponding alarm information is generated, and the alarm information is sent to the operation supervision end. When the operation supervision end receives the alarm information, it is displayed and an alarm sound is issued. When the management personnel receive the alarm, they strengthen the subsequent supervision of the sensor and replace the corresponding sensor as needed to ensure the subsequent effective monitoring of the circulating hydrogen compressor. The analysis process of the monitoring impact assessment module is as follows:

[0047] A detection period is set, and the number of times that the target sensor i generates suspicious operation signals during the detection period is collected and marked as a suspicious operation value. The suspicious operation value is numerically compared with the corresponding preset suspicious operation threshold. If the suspicious operation value exceeds the corresponding preset suspicious operation threshold, it indicates that the operation performance of the target sensor i is extremely poor, and the target sensor i is marked as a non-optimal sensor. If a non-optimal sensor exists during the detection period, it indicates that it is not conducive to ensuring effective monitoring of the circulating hydrogen compressor, and a high-impact monitoring signal is generated.

[0048] Furthermore, if there is no non-optimal sensor during the detection period, several monitoring periods are set during the detection period, the number of times the suspicious signal is generated during the monitoring period is collected and marked as a suspicious frequency value, and the suspicious frequency value is numerically compared with a preset suspicious frequency threshold. If the suspicious frequency value exceeds the preset suspicious frequency threshold, the corresponding monitoring period is marked as an abnormal period;

[0049] The number of abnormal time periods in the detection period is obtained and the ratio thereof is calculated with the total number of monitoring periods to obtain the abnormal time condition value, and the suspicious frequency values ​​of all monitoring periods are averaged to obtain the suspicious frequency table value, and the maximum value of the suspicious frequency value in the detection period is marked as the suspicious frequency amplitude value;

[0050] The monitoring influence coefficient X is obtained by numerically calculating the abnormal time value N, the suspicious frequency table value T and the suspicious frequency amplitude value Q through the formula X=u×N+(t×T+b×Q) / 2; wherein u, t, and b are preset weight coefficients, and u>t>b>0; and the larger the value of the monitoring influence coefficient X, the worse the operation coordination performance of all sensors during the detection period, which is less conducive to ensuring effective monitoring of the circulating hydrogen compressor;

[0051] The monitoring influence coefficient X is numerically compared with the preset monitoring influence coefficient threshold. If the monitoring influence coefficient X exceeds the preset monitoring influence coefficient threshold, it indicates that the operation coordination performance of all sensors during the detection period is poor, which is not conducive to ensuring effective monitoring of the circulating hydrogen compressor, and a high monitoring influence signal is generated; if the monitoring influence coefficient X does not exceed the preset monitoring influence coefficient threshold, it indicates that the operation coordination performance of all sensors during the detection period is good, which is conducive to ensuring effective monitoring of the circulating hydrogen compressor, and a low monitoring influence signal is generated.

[0052] The working principle of the present invention is as follows: when in use, the operation of the circulating hydrogen compressor is monitored and its various parameter data are collected through the multi-parameter monitoring and transmission module. The intelligent analysis module uses a machine learning algorithm to process and analyze all the collected parameter data. When it is identified that the equipment operation status is abnormal or there is a potential fault, the early warning mechanism trigger module triggers the alarm mechanism to make the operation supervision end issue an alarm, which can comprehensively and effectively monitor the operation status of the circulating hydrogen compressor and timely discover potential faults, improve the reliability and safety of the operation of the circulating hydrogen compressor, reduce maintenance costs and use risks, and perform operation inspections on all sensors through the sensor inspection and judgment module to determine the probability of abnormal operation of each sensor, which is conducive to ensuring the accurate and stable operation of each sensor, and through the monitoring impact assessment module, comprehensively analyze the impact on the online monitoring of the circulating hydrogen compressor based on the operating conditions of all sensors, and strengthen the subsequent supervision of the sensors when generating high-impact monitoring signals to ensure effective monitoring of the circulating hydrogen compressor.

[0053] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An online monitoring system for circulating hydrogen compressor based on data analysis, characterized in that: It includes a multi-parameter monitoring and transmission module, an intelligent analysis module, an early warning mechanism triggering module and an operation supervision terminal; the multi-parameter monitoring and transmission module monitors the operation of the circulating hydrogen compressor through a number of sensors arranged on the circulating hydrogen compressor, collects various parameter data of the circulating hydrogen compressor, and sends the various parameter data of the circulating hydrogen compressor to the intelligent analysis module; The intelligent analysis module uses machine learning algorithms to process and analyze all collected parameter data, identify the operating status and potential faults of the circulating hydrogen compressor, and send the analysis and identification information to the early warning mechanism trigger module; When the equipment is in an abnormal operating state or there is a potential fault, the early warning mechanism trigger module triggers the alarm mechanism and generates corresponding alarm information, and sends the alarm information to the operation supervision end.

2. The online monitoring system for circulating hydrogen compressor based on data analysis according to claim 1 is characterized in that: The early warning mechanism trigger module is connected to the sensor inspection and judgment module in communication. The sensor inspection and judgment module obtains all sensors included in the multi-parameter monitoring transmission module and marks the corresponding sensor as the target sensor i, where i is a natural number greater than 1; Perform an operation inspection on the target sensor i, determine the probability of abnormal operation of the target sensor i, generate a normal operation signal or a suspicious operation signal of the target sensor i based on the probability, and send the suspicious operation signal of the target sensor i to the early warning mechanism trigger module; When the early warning mechanism trigger module receives a suspicious operation signal, it triggers the alarm mechanism and generates corresponding alarm information, and sends the alarm information to the operation supervision end.

3. The online monitoring system for circulating hydrogen compressor based on data analysis according to claim 2 is characterized in that: The analysis process of the sensor inspection and judgment module is as follows: The sensor inspection coefficient of the target sensor i is obtained by analysis, and if the sensor inspection coefficient exceeds a preset sensor inspection coefficient threshold, a suspicious operation signal of the target sensor i is generated; If the sensor verification coefficient does not exceed the preset sensor verification coefficient threshold, a normal operation signal of the target sensor i is generated.

4. The online monitoring system for circulating hydrogen compressor based on data analysis according to claim 3 is characterized in that: The analysis and acquisition method of the sensor verification coefficient is as follows: The number of times the target sensor i is assigned the acquisition abnormality symbol LP-1 per unit time is obtained and marked as the acquisition abnormality detection value, and the number of abnormal acquisition time differences per unit time is obtained and marked as the abnormal acquisition detection value. The sensor verification coefficient is obtained by numerically calculating the acquisition abnormality detection value and the abnormal acquisition detection value.

5. The online monitoring system for circulating hydrogen compressor based on data analysis according to claim 2 is characterized in that: The sensor inspection and judgment module is communicatively connected to the monitoring impact assessment module. The sensor inspection and judgment module sends the inspection and judgment information of all sensors to the monitoring impact assessment module. The monitoring impact assessment module comprehensively analyzes the impact on the online monitoring of the circulating hydrogen compressor based on the operating conditions of all sensors, and generates a high-impact monitoring signal or a low-impact monitoring signal accordingly. When the early warning mechanism trigger module receives a high-impact monitoring signal, it triggers the alarm mechanism and generates corresponding alarm information, and sends the alarm information to the operation supervision end.

6. The online monitoring system for circulating hydrogen compressor based on data analysis according to claim 5 is characterized in that: The analysis process of the monitoring impact assessment module includes: A detection period is set, and the number of times that the target sensor i generates suspicious operation signals during the detection period is collected and marked as a suspicious operation value. If the suspicious operation value exceeds the corresponding preset suspicious operation threshold, the target sensor i is marked as a non-optimal sensor; if there is a non-optimal sensor during the detection period, a high-impact monitoring signal is generated.

7. The online monitoring system for circulating hydrogen compressor based on data analysis according to claim 6 is characterized in that: If there is no non-optimal sensor during the detection period, the monitoring influence coefficient is obtained by numerically calculating the abnormal time condition value, the suspicious frequency table value and the suspicious frequency amplitude value. If the monitoring influence coefficient exceeds the preset monitoring influence coefficient threshold, a high monitoring influence signal is generated; otherwise, a low monitoring influence signal is generated.

Images