A gas power generation safety early warning method and system

Abstract

The present invention belongs to the field of gas-fired power generation, and provides a gas-fired power generation safety warning method and system, including: obtaining historical operation data of a gas engine, the historical operation data including the input gas pressure value of the gas engine and the corresponding gas engine vibration data; performing periodic analysis on the vibration data to obtain a periodic vibration signal of each vibration data; analyzing the periodic vibration signal to obtain multiple vibration indicators; fitting an input gas pressure value-vibration indicator curve for each vibration indicator according to the input gas pressure value and the corresponding multiple vibration indicators; obtaining the real-time input gas pressure value of the gas engine and the corresponding real-time gas engine vibration indicator; if the real-time gas engine vibration indicator corresponding to a preset number of real-time input gas pressure values ​​deviates from the corresponding input gas pressure value-vibration indicator curve by more than a preset value, a warning is issued. The above scheme can improve the accuracy of safety warnings.

Description

Technical Field

[0001] The present invention belongs to the field of gas-fired power generation, and in particular relates to a gas-fired power generation safety early warning method and system. Background Art

[0002] Gas-fired power generation safety early warning is designed to ensure the safe operation of gas-fired power generation equipment by identifying, monitoring and warning potential safety risks in advance. Its main goal is to ensure the safety of equipment during operation, prevent accidents, and reduce casualties and property losses.

[0003] The safety management of gas-fired power generation systems usually includes gas equipment safety, such as the safety of the gas-fired power generation equipment itself; gas supply safety, such as the safety of gas pipelines, the stability of gas quality, the prevention of gas leaks, etc.; fire and explosion protection, including the establishment of fire monitoring systems, the implementation of fire and explosion prevention measures, the setting up of fire escape routes, etc.; gas leakage monitoring and protection, gas leakage is one of the main causes of fire and explosion.

[0004] The safety of the gas-fired power generation equipment itself is the primary consideration. In the prior art, key parameters of gas-fired power generation equipment such as temperature, vibration, gas concentration, etc. are usually monitored to detect equipment abnormalities in advance and issue early warnings. However, gas-fired power generation equipment is usually used for power supplementation and peak load regulation, and often uses unstable fuels such as mine gas, resulting in unstable gas supply pressure. Unstable gas pressure leads to unstable operating status of gas turbines, and the vibration data obtained by monitoring has a wide fluctuation range, making it difficult to accurately issue early warnings. Summary of the invention

[0005] In order to solve the problems in the prior art, the present invention provides a gas power generation safety early warning method, comprising: obtaining historical operation data of a gas engine, the historical operation data including an input gas pressure value of the gas engine and corresponding gas engine vibration data; performing periodic analysis on the vibration data to obtain a periodic vibration signal of each vibration data; analyzing the periodic vibration signal to obtain a plurality of vibration indices; fitting an input gas pressure value-vibration index curve for each vibration index according to the input gas pressure value and the corresponding plurality of vibration indices; obtaining a real-time input gas pressure value of the gas engine and the corresponding real-time gas engine vibration index; and issuing an early warning if the real-time gas engine vibration index corresponding to a preset number of real-time input gas pressure values ​​deviates from the corresponding input gas pressure value-vibration index curve by more than a preset value.

[0006] Furthermore, an autocorrelation function is used to obtain a time-domain periodic vibration signal of each vibration data.

[0007] Furthermore, the vibration index includes: peak index: peak acceleration, peak velocity, peak displacement, effective value index: effective acceleration, effective velocity, effective displacement; peak-to-valley factor, frequency spectrum peak, root mean square frequency, pulse index.

[0008] Furthermore, the preset number is 5.

[0009] Furthermore, the preset value is an absolute value or a percentage of a preset indicator.

[0010] Another aspect of the present invention further provides a gas power generation safety early warning system, comprising the following modules:

[0011] An acquisition module, used for acquiring historical operation data of the gas engine, wherein the historical operation data includes an input gas pressure value of the gas engine and corresponding gas engine vibration data;

[0012] An analysis module is used to perform periodic analysis on the vibration data to obtain a periodic vibration signal of each vibration data; analyze the periodic vibration signal to obtain multiple vibration indices; and fit an input gas pressure value-vibration index curve to each vibration index according to the input gas pressure value and the corresponding multiple vibration indices;

[0013] A real-time acquisition module is used to obtain the real-time input gas pressure value of the gas engine and the corresponding real-time gas engine vibration index;

[0014] The early warning module is used to issue an early warning if the real-time gas engine vibration index corresponding to a preset number of real-time input gas pressure values ​​deviates from the corresponding input gas pressure value-vibration index curve by more than a preset value.

[0015] Furthermore, an autocorrelation function is used to obtain a time-domain periodic vibration signal of each vibration data.

[0016] Furthermore, the vibration index includes: peak index: peak acceleration, peak velocity, peak displacement, effective value index: effective acceleration, effective velocity, effective displacement; peak-to-valley factor, frequency spectrum peak, root mean square frequency, pulse index.

[0017] Furthermore, the preset number is 5.

[0018] Furthermore, the preset value is an absolute value or a percentage of a preset indicator.

[0019] The present invention can produce the following beneficial effects through the above technical solution:

[0020] By analyzing historical operating data and vibration characteristics, possible problems with gas engines can be identified, so that potential faults or abnormal conditions can be discovered in advance. At the same time, the problem of difficulty in identifying abnormalities caused by changes in vibration signals due to different input gas pressures can be avoided, and identification accuracy can be improved. Problems can be discovered in a timely manner and preventive maintenance measures can be taken to detect equipment operation abnormalities in a timely manner and ensure the safety of equipment and personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 is a schematic diagram of peak acceleration distribution;

[0023] Figure 2 is a schematic diagram of peak velocity distribution;

[0024] Figure 3 is a schematic diagram of peak displacement distribution;

[0025] Figure 4 is the peak acceleration curve;

[0026] Figure 5 is the peak velocity curve graph;

[0027] Figure 6 is the peak displacement curve;

[0028] Figure 7 It is a schematic diagram of real-time peak acceleration deviation. DETAILED DESCRIPTION

[0029] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0030] This embodiment solves the above problem through the following steps:

[0031] In one embodiment, the present invention provides a gas-fired power generation safety early warning method.

[0032] A gas generator is a device that uses gas (such as natural gas, liquefied petroleum gas, etc.) as fuel to generate electricity through an internal combustion engine to rotate a generator. It usually consists of two parts: a gas engine and a generator. The gas engine is the main component of a gas generator. It is similar to a car engine, but is specifically designed for gas-fired power generation. When a gas engine burns gas, it produces high-temperature and high-pressure gas, which drives the piston to move, thereby rotating the generator. The generator is a device that converts the mechanical energy generated by the gas engine into electrical energy. When the engine rotates, the rotor in the generator also rotates, generating current through the principle of electromagnetic induction, thereby generating electricity.

[0033] Failure of a gas engine may cause unstable engine operation, gas leakage, and even cause safety accidents such as fire and explosion, posing a threat to personnel and equipment. The generator part has a simple and stable structure and usually does not have accidents. Therefore, the gas power generation safety described in this embodiment is mainly aimed at gas engines.

[0034] The input gas pressure value of a gas engine refers to the pressure level of the gas entering the engine. In a gas-fired power generation system, the gas is usually transported to the engine through a pipeline for combustion, and the input gas pressure value indicates the pressure of the gas in this process.

[0035] The vibration of a gas engine mainly comes from the moving parts inside the engine, such as the piston, crankshaft, connecting rod, etc. The high-temperature and high-pressure gas generated during the combustion process pushes the piston to move, causing mechanical vibration. The characteristics of these vibrations can reflect the operating status and possible faults inside the engine. By monitoring and analyzing vibration signals, problems inside the engine can be discovered in a timely manner, preventing and avoiding engine failures that may lead to safety accidents.

[0036] The vibration of a gas engine can be used to detect faults in the following areas: bearings are one of the components in an engine that is prone to failure. Wear, looseness or damage to bearings can cause abnormal engine vibrations; wear or damage to piston rings can cause unstable piston movement and produce abnormal vibrations; an unbalanced crankshaft can increase engine vibrations and affect overall operating stability.

[0037] However, when the input gas pressure value changes, it will affect the combustion process and the airflow inside the engine, which in turn affects the vibration of the engine. Too high or too low input gas pressure may cause incomplete or unstable combustion of the gas, causing turbulence in the airflow inside the engine and increasing the vibration. Changes in gas pressure may cause uneven injection and mixing of the gas, causing an unstable combustion process, which in turn increases the vibration of the engine. Changes in input gas pressure may cause vibration of system components such as pipes and connectors, which will be transmitted to the engine structure and increase the overall vibration.

[0038] Different input gas pressure values ​​will produce different natural vibrations for the gas engine. Therefore, when performing vibration detection on the gas engine, the input gas pressure during detection should be considered to eliminate the influence of different gas pressure values ​​on vibration and determine the real fault vibration signal. Therefore, this embodiment first obtains the historical operation data of the gas engine, and the historical operation data includes the input gas pressure value of the gas engine and the corresponding gas generator vibration data.

[0039] Specifically, the corresponding sensors and data acquisition systems need to be installed first. Data acquisition sensors are installed at key parts of the gas engine, such as the gas inlet and the engine structure, to monitor the gas pressure and engine vibration. The data acquisition system records the operating data of the gas engine in real time, including the input gas pressure value and vibration data. The data is stored in a database or data storage system with a timestamp. After the data is stored, it is used for analysis in subsequent steps.

[0040] Since vibration is caused by periodic force or motion, vibration data is collected continuously, obtained by real-time monitoring through sensors, or obtained by discrete sampling within a certain time range. When the mechanical system is running, various moving parts will be affected by various forces, which will cause the mechanical system to vibrate. The piston movement and crankshaft rotation inside the gas engine will produce periodic vibrations. These vibration signals can be collected by vibration sensors and converted into electrical signals for recording and analysis. In vibration data, periodic vibrations are usually manifested as repetitive patterns of vibration signals. In order to determine the vibration characteristics, this embodiment needs to perform periodic analysis on the vibration data to obtain the periodic vibration signal of each vibration data.

[0041] Exemplarily, the time-domain periodic vibration signal of each vibration data is obtained using an autocorrelation function such as:

[0042] Apply the autocorrelation function to the time domain data of the vibration signal. The autocorrelation function represents the correlation between the signal and itself at different time delays. The autocorrelation function graph usually reaches a peak at the position where the time delay is zero, indicating that the vibration signal is completely correlated with itself. At other time delays, the autocorrelation function value decreases as the delay time increases. If the vibration signal is periodic, the autocorrelation function graph will also have peaks at integer multiples of the period. Based on the characteristics of the autocorrelation function graph, the period of the vibration signal is determined. The period usually corresponds to the main peak position in the autocorrelation function graph. The period of the vibration signal can be determined by measuring the time interval between peaks.

[0043] The vibration signal is a waveform in the time domain, and the waveform is not easy to observe under different air pressure indicators. Therefore, this implementation needs to further analyze the periodic vibration signal to obtain multiple vibration indicators. Specifically, the following indicators are obtained for each periodic vibration signal:

[0044] Peak indicators: including peak acceleration, peak velocity, peak displacement, etc., indicating the maximum amplitude value of the vibration signal within a specific time.

[0045] Effective value indicators: including effective acceleration, effective velocity, effective displacement, etc., represent the root mean square value of the vibration signal and reflect the overall energy level of the vibration signal.

[0046] Peak-to-valley factor: It indicates the ratio of the peak value to the valley value of the vibration signal. It is used to evaluate the difference between the peak value and the valley value of the vibration signal, and reflects the waveform characteristics of the vibration signal.

[0047] Frequency spectrum peak: Analyze the peak in the frequency spectrum to identify and locate the main vibration frequency components and possible fault frequency components.

[0048] RMS frequency: represents the frequency-weighted RMS value of the vibration signal, which is used to comprehensively evaluate the energy distribution of the vibration signal in different frequency ranges.

[0049] Pulse Index: Indicates the pulse characteristics of the vibration signal and is used to evaluate the impact properties of the vibration signal.

[0050] After calculating the vibration index for each periodic vibration signal, the relationship between the corresponding air pressure value and the vibration index can be obtained. After performing similar calculations on multiple vibration data, multiple sets of relationships between gas pressure and vibration index can be obtained. This implementation takes peak acceleration, peak velocity, and peak displacement as examples. Figure 1-3 As shown, the peak acceleration, peak velocity, and peak displacement corresponding to multiple gas pressures can be obtained and the data can be represented in a chart.

[0051] Furthermore, in order to obtain the relationship between the gas pressure value and the vibration index, the present embodiment further fits an input gas pressure value-vibration index curve for each vibration index in the vibration data according to the input gas pressure value and the corresponding multiple vibration indexes.

[0052] like Figure 4-6 As shown in FIG. 1 , curve fitting is performed on the peak acceleration, peak velocity, and peak displacement to obtain the corresponding curves of the respective indicators. Similarly, for other indicators, such as effective value indicators, peak-valley factors, etc., similar methods can be used to perform curve fitting.

[0053] The specific method of curve fitting is not specifically limited in this embodiment, and most of the fitting methods in the prior art, including the emerging neural network (which is also rational fitting in essence), can be applied to this embodiment. The line shape of the curve fitting is affected by the specific data distribution. Those skilled in the art can select a specific line shape according to the specific data distribution when fitting, and this embodiment does not make any specific limitation.

[0054] After obtaining the curves of each indicator, the curves can be applied to real-time detection. Obtain the real-time input gas pressure value of the gas engine and the corresponding real-time gas engine vibration index. When the real-time gas engine vibration index is obtained, the aforementioned method of processing historical data can be used to first perform periodic analysis on the acquired data to obtain a periodic time domain signal, and then calculate the index of the signal of a period, which will not be repeated here.

[0055] If a preset number of real-time input gas pressure values ​​and corresponding real-time gas engine vibration indexes deviate from the corresponding input gas pressure value-vibration index curve by more than a preset value, a fault warning is issued.

[0056] When a gas engine has a safety hazard, such as when a gas engine component is mechanically damaged or worn, the vibration characteristics will change; the imbalance or imbalance of the gas engine will cause additional vibrations, which will cause changes in the vibration index; the combustion process of the gas engine is unstable, and the occurrence of gas detonation may cause changes in the vibration signal; for the same gas supply pressure, when the vibration signal changes, different vibration indicators will change accordingly. Therefore, this embodiment needs to monitor multiple indicators at the same time, such as the peak index, effective value index, peak-to-valley factor, frequency spectrum peak, root mean square frequency, and pulse index mentioned above, to form an observation collection. When multiple indicators in the observation collection deviate from their gas pressure value-vibration index curve, such as Figure 7 As shown in the figure, if the peak acceleration (indicated by the large black dot in the figure) at a certain moment deviates significantly from the fitting curve, it can be considered that the peak acceleration is abnormal at this time. Since vibration changes may cause changes in multiple indicators, in order to reduce false alarms, the gas engine is considered abnormal only when multiple indicators (such as 5) deviate from the normal fitting curve. The specific deviation preset value is not limited in this implementation. An absolute value can be set for each indicator, such as when the peak acceleration deviates by more than or less than 0.2g, it is considered abnormal. A percentage can also be set, such as when it deviates by 10%, it is considered abnormal.

[0057] The above technical solution can identify possible problems with the gas engine by analyzing historical operating data and vibration characteristics, thereby being able to discover potential faults or abnormal conditions in advance. At the same time, it can avoid the problem of difficulty in identifying abnormalities caused by changes in vibration signals due to different input gas pressures, improve recognition accuracy, discover problems in a timely manner and take preventive maintenance measures, discover equipment operation abnormalities in a timely manner, and ensure the safety of equipment and personnel.

[0058] On the other hand, the present invention also provides a gas power generation safety early warning system, comprising:

[0059] An acquisition module, used for acquiring historical operation data of the gas engine, wherein the historical operation data includes an input gas pressure value of the gas engine and corresponding gas engine vibration data;

[0060] An analysis module is used to perform periodic analysis on the vibration data to obtain a periodic vibration signal of each vibration data; analyze the periodic vibration signal to obtain multiple vibration indices; and fit an input gas pressure value-vibration index curve to each vibration index according to the input gas pressure value and the corresponding multiple vibration indices;

[0061] A real-time acquisition module is used to obtain the real-time input gas pressure value of the gas engine and the corresponding real-time gas engine vibration index;

[0062] The early warning module is used to issue an early warning if the real-time gas engine vibration index corresponding to a preset number of real-time input gas pressure values ​​deviates from the corresponding input gas pressure value-vibration index curve by more than a preset value.

[0063] Furthermore, the specific implementation methods of the above-mentioned gas-fired power generation safety warning system are the same as a gas-fired power generation safety warning method, and all further technical solutions in a gas-fired power generation safety warning method are fully introduced into a gas-fired power generation safety warning system.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0065] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A gas power generation safety early warning method, characterized in that The method comprises the following steps: Acquiring historical operation data of the gas engine, wherein the historical operation data includes an input gas pressure value of the gas engine and corresponding gas engine vibration data; Performing periodic analysis on the vibration data to obtain a periodic vibration signal of each vibration data; Analyzing the periodic vibration signal to obtain multiple vibration indicators; According to the input gas pressure value and the corresponding multiple vibration indices, fitting an input gas pressure value-vibration index curve for each vibration index; Obtaining the real-time input gas pressure value of the gas engine and the corresponding real-time gas engine vibration index; If the real-time gas engine vibration index corresponding to a preset number of real-time input gas pressure values ​​deviates from the corresponding input gas pressure value-vibration index curve by more than a preset value, an early warning is issued.

2. A gas power generation safety early warning method according to claim 1, characterized in that Acquiring the periodic vibration signal of each vibration data includes: acquiring the time-domain periodic vibration signal of each vibration data by using an autocorrelation function.

3. A gas power generation safety early warning method according to claim 1, characterized in that The vibration indexes include: peak indexes: peak acceleration, peak velocity, peak displacement; effective value indexes: effective acceleration, effective velocity, effective displacement; peak-to-valley factor, frequency spectrum peak, root mean square frequency, and pulse index.

4. A gas power generation safety early warning method according to claim 1, characterized in that: The preset number is 5.

5. A gas power generation safety early warning method according to claim 1, characterized in that: The preset value is an absolute value or a percentage of a preset indicator.

6. A gas-fired power generation safety early warning system, characterized in that The system includes the following modules: An acquisition module, used for acquiring historical operation data of the gas engine, wherein the historical operation data includes an input gas pressure value of the gas engine and corresponding gas engine vibration data; An analysis module is used to perform periodic analysis on the vibration data to obtain a periodic vibration signal of each vibration data; analyze the periodic vibration signal to obtain multiple vibration indices; and fit an input gas pressure value-vibration index curve to each vibration index according to the input gas pressure value and the corresponding multiple vibration indices; A real-time acquisition module is used to obtain the real-time input gas pressure value of the gas engine and the corresponding real-time gas engine vibration index; The early warning module is used to issue an early warning if the real-time gas engine vibration index corresponding to a preset number of real-time input gas pressure values ​​deviates from the corresponding input gas pressure value-vibration index curve by more than a preset value.

7. A gas power generation safety early warning system according to claim 6, characterized in that Acquiring the periodic vibration signal of each vibration data includes: acquiring the time-domain periodic vibration signal of each vibration data by using an autocorrelation function.

8. A gas power generation safety early warning system according to claim 6, characterized in that The vibration indexes include: peak indexes: peak acceleration, peak velocity, peak displacement; effective value indexes: effective acceleration, effective velocity, effective displacement; peak-to-valley factor, frequency spectrum peak, root mean square frequency, and pulse index.

9. A gas-fired power generation safety early warning system according to claim 6, characterized in that: The preset number is 5.

10. A gas-fired power generation safety early warning system according to claim 6, characterized in that: The preset value is an absolute value or a percentage of a preset indicator.

Images