Power plant unit operation state intelligent monitoring system based on big data

Abstract

The invention relates to the field of power plant operation, and discloses a power plant unit operation state intelligent monitoring system based on big data, which comprises a monitoring acquisition module, and the monitoring acquisition module comprises a temperature sensor, a pressure sensor, a vibration frequency sensor and a current sensor. The monitoring acquisition module is used for acquiring and monitoring various parameters of the power plant unit and transmitting various acquired and monitored parameter values to the central control module, and the monitoring acquisition module is connected with the central control module. According to the invention, the prediction module is arranged, and a fault probability prediction formula and a fault time prediction formula are used for calculation according to historical parameters and fault information of a unit, so that the future fault occurrence time is predicted. Through the prediction functions, workers can know possible faults of the unit in advance, so that when the faults occur, the workers carry tools for emergency rescue at the first time, and the overall efficiency of the power plant unit is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power plant operation, and in particular to an intelligent monitoring system for the operation status of power plant units based on big data. Background Art

[0002] With the rapid development of the power industry, power plant units are evolving towards large capacity and high parameters, and their structures and operating principles are becoming increasingly complex. In this case, ensuring the safe, stable and efficient operation of power plant units has become a vital issue.

[0003] Traditional power plant unit monitoring uses sensors to collect various parameters of the power plant units and transmits them to monitoring equipment. The monitoring equipment compares and analyzes the parameters to understand the operating status of the power plant units and prevent failure to promptly alert staff when power plant units fail, thereby affecting the service life and overall work efficiency of the power plant units.

[0004] Considering that fault feedback is usually prompted through real-time comparison, it is easy for the staff to fail to prepare for rescue or maintenance when they receive the fault feedback for the first time. It still takes a lot of time to select appropriate repair tools based on the cause of the fault, resulting in low maintenance efficiency after the power plant unit failure, delaying the normal operation efficiency of the power plant unit. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent monitoring system for the operating status of power plant units based on big data, which solves the problem that the existing power plant unit monitoring system mainly provides real-time comparison reminders for fault feedback, and the staff are often not prepared for rescue or maintenance when receiving the feedback, and need to spend a lot of time selecting repair tools, resulting in low efficiency of power plant unit fault maintenance.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent monitoring system for the operation status of power plant units based on big data, including a monitoring and acquisition module, the monitoring and acquisition module including a temperature sensor, a pressure sensor, a vibration frequency sensor, and a current sensor. By installing the above sensor equipment on the power plant units, various parameters of the power plant units are collected and monitored, and the collected and monitored parameter values ​​are transmitted to the central control module. The monitoring and acquisition module is connected to the central control module. The central control module serves as the core of the entire system, coordinates the workflow and data interaction between the modules, and receives the data collected by the monitoring and acquisition module. The central control module collects various parameters and coordinates the data analysis and processing module to read the parameters. The central control module is connected to the data analysis and processing module. The data analysis and processing module is provided with a preset threshold. After receiving various parameters of the real-time power plant units, the parameters are compared with the threshold to judge the operating status of the power plant units. The data analysis and processing module is connected to a prediction module. The prediction module uses a formula to calculate according to the historical parameters and fault information of the unit, so as to predict the fault problem of the unit. The data analysis and processing module is connected to an interactive module. The interactive module sends the real-time operating status and prediction conclusion of the power plant units to the staff.

[0007] Preferably, the data analysis and processing module is connected to a threshold module, which stores pre-set threshold ranges for various operating parameters of the power plant units. The specific threshold ranges include: temperature parameter threshold range, pressure parameter threshold range, vibration frequency parameter threshold range and current parameter threshold range.

[0008] Preferably, the threshold module is connected to a comparison and analysis module, which compares various parameters of the real-time power plant unit with the threshold range. When it is found that a parameter exceeds or is lower than the threshold range, the preset solution module is started to judge the specific fault information of the power plant unit according to the overall data of multiple groups or one group of parameters exceeding the threshold range. The comparison and analysis module is connected to a preset solution module, and different fault solutions are stored in the preset solution module. Specific fault solutions include: abnormal temperature fault solution; abnormal pressure fault solution; abnormal vibration frequency fault solution; abnormal current fault solution.

[0009] Preferably, the specific calculation formula in the formula calculation module includes:

[0010] 1. Failure probability prediction formula:

[0011]

[0012] Among them: P(A) is the prior probability of fault A, which can be obtained through historical fault data statistics, specifically: the frequency of occurrence of a certain fault in the past year; P(B|A) is the probability of parameter B taking the current value under the condition that fault A occurs, which is obtained by analyzing the parameter changes in a large number of historical fault cases.

[0013] P(B) is the probability of parameter B taking the current value, which is calculated using the total probability formula. By monitoring the value of parameter B in real time and using the above calculation formula, the probability of fault A occurring under the current parameter state is calculated.

[0014] Preferably, the specific calculation formula in the formula calculation module also includes:

[0015] 2. Failure time prediction formula:

[0016] 1. Calculate its probability density function:

[0017] f ( t ) =λe -λt ,t≥0

[0018] 2. Calculate the probability of failure within the future time t:

[0019] P ( T≤t+t0|T>t 0) =1-e -λt

[0020] in:

[0021] t: represents time. In the probability density function f(t), t is a continuous time variable after the unit starts to operate. In the failure probability calculation, t represents the future predicted time; λ is the failure rate, which is a constant obtained by statistical analysis of historical failure data; t0 represents the time the unit has been running; f(t) is a probability density function, which is used to describe the distribution of the failure time T;

[0022] P(T≤t+t0|T>t0) is a conditional probability, which indicates the probability of a failure occurring within the future time t if the unit has been running for t0 time and has not yet failed.

[0023] Preferably, the formula calculation module is connected to a trend prediction module, which uses the calculation results of the formula calculation module and, based on the current change trends of the current, voltage and temperature parameters, predicts whether these parameters will exceed the normal range in the next few hours, as well as the rate of change.

[0024] Preferably, the specific prediction formula in the trend prediction module is:

[0025]

[0026] in:

[0027] represents the predicted value of the unit operating parameters at time t+1; y t is the actual observed value of the unit operating parameters at time t; is the predicted value of the unit operating parameters at time t, α is a smoothing constant, and its value range is between (0,1); by combining the actual observation value y at the current time t t and predicted values It is calculated according to the given smoothing constant α and is used to predict the future change trend of the operating parameters.

[0028] Preferably, the formula calculation module is connected to a trend prediction module, which uses the calculation results of the formula calculation module and, based on the current change trends of the current, voltage and temperature parameters, predicts whether these parameters will exceed the normal range in the next few hours, as well as the rate of change.

[0029] Preferably, the trend prediction module is connected to a risk assessment module, and the risk assessment module conducts a comprehensive assessment of the risks faced by the operation of the power plant units based on the formula calculation module and the conclusion of the trend prediction module.

[0030] Preferably, the interactive module is connected to a user interface module, which provides a platform for users to display system information through the platform. The user interface module is connected to an alarm and notification module, which sends the comparison and analysis module to the staff in a timely manner.

[0031] The present invention provides an intelligent monitoring system for the operation status of power plant units based on big data. It has the following beneficial effects:

[0032] 1. The present invention sets a prediction module and uses the fault probability prediction formula and the fault time prediction formula to calculate and predict the future fault occurrence time according to the historical parameters and fault information of the unit. These prediction functions enable the staff to understand the possible faults of the unit in advance and make preventive maintenance plans in advance, so that when a fault occurs, they can carry tools for rescue in the first time, thereby improving the overall efficiency of the power plant unit.

[0033] 2. The present invention uses a monitoring and acquisition module composed of multiple sensors to comprehensively collect various parameters of the power plant units, and transmits the data to the central control module, which is then analyzed by the data analysis and processing module. Compared with the traditional single monitoring method, this multi-parameter real-time monitoring method can more comprehensively and accurately grasp the operating status of the unit, avoid the fault monitoring blind spots caused by the omission of some parameters, and effectively improve the timeliness and accuracy of fault warning.

[0034] 3. The present invention uses a special calculation formula, substitutes various historical parameters, and performs calculations, so that the prediction results are more accurate, providing strong support for the monitoring system to accurately judge faults and grasp the operation trends of the units, thereby improving the accuracy of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a system flow chart of the present invention;

[0036] Figure 2 It is a flow chart of the prediction module of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the specification 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.

[0038] Example:

[0039] Please refer to the attached Figure 1 - Attachment Figure 2The embodiment of the present invention provides an intelligent monitoring system for the operation status of power plant units based on big data, including a monitoring and acquisition module, wherein the monitoring and acquisition module includes a temperature sensor, a pressure sensor, a vibration frequency sensor, and a current sensor. By installing the above-mentioned sensor devices on the power plant units, various parameters of the power plant units are collected and monitored, and the values ​​of the collected and monitored parameters are transmitted to the central control module. The monitoring and acquisition module is connected to the central control module. The central control module serves as the core of the entire system, coordinates the workflow and data interaction between various modules, receives various parameters collected from the monitoring and acquisition module, and coordinates the data. The parameters are read by the data analysis and processing module. The central control module is connected to a data analysis and processing module. A preset threshold is set in the data analysis and processing module. After receiving various parameters of the real-time power plant units, the parameters are compared with the threshold to determine the operating status of the power plant units. The data analysis and processing module is connected to a prediction module. The prediction module uses a formula to calculate according to the historical parameters and fault information of the unit, so as to predict the fault problems of the unit and play an early warning effect. The data analysis and processing module is connected to an interaction module, and the interaction module sends the real-time operating status and prediction conclusion of the power plant units to the staff.

[0040] The data analysis and processing module is connected to a threshold module, and the threshold module stores a preset threshold range for each operating parameter of the power plant unit, and the specific threshold ranges include: a temperature parameter threshold range, a pressure parameter threshold range, a vibration frequency parameter threshold range and a current parameter threshold range;

[0041] The threshold module is connected to a comparison and analysis module, which compares various parameters of the real-time power plant unit with the threshold range. When it is found that a parameter exceeds or is lower than the threshold range, the preset solution module is started to judge the specific fault information of the power plant unit according to the overall data of multiple groups or one group of parameters exceeding. The comparison and analysis module is connected to a preset solution module, and different fault solutions are stored in the preset solution module. The specific fault solutions include:

[0042] Abnormal temperature fault solution: When the temperature is too high, check whether the fuel supply system is abnormal, such as whether the fuel volume is too much or the burner is faulty, and check whether the ventilation system is normal to ensure the appropriate amount of air; when the temperature is too low, check whether the water inlet temperature is too low, whether there is an abnormal increase in the water flow, and check whether the fuel supply is insufficient or the combustion is insufficient;

[0043] Abnormal pressure fault solution: When overpressure occurs, check whether the safety valve and regulating valve are working properly, check whether the outlet valve is closed or the opening is abnormal, and whether the water pump is running abnormally, resulting in excessive head. When underpressure occurs, check the combustion condition of the boiler, whether the evaporation capacity is normal, and check whether there is leakage in the pipeline;

[0044] Abnormal vibration frequency fault solution: Conduct on-site inspection to check whether there is obvious mechanical looseness or component damage, and then use professional vibration detection equipment to further analyze the frequency spectrum characteristics of the vibration to determine whether it is caused by rotor imbalance, misalignment, or bearing failure;

[0045] Abnormal current fault solution: When an overload fault occurs, check whether the winding insulation of the generator itself is good, whether there is a turn-to-turn short circuit problem, whether the load is stuck or overloaded, and whether the motor protection device is operating normally. When an underload fault occurs, check whether the load of the generator or motor is suddenly reduced, check whether the electrical connection is loose, resulting in abnormal current transmission, and also check whether the output power of the prime mover is normal.

[0046] The prediction module is connected to a data sorting module, which sorts out the parameters, fault problems and fault time nodes of the power plant units under long-term operation, and transmits the sorted data to the formula calculation module. The data sorting module is connected to a formula calculation module, which uses a special formula to substitute various parameters sorted and collected by the data sorting module to predict the fault problems and fault time of the power plant units. The specific calculation formula is:

[0047] 1. Failure probability prediction formula:

[0048]

[0049] Among them: P(A) is the prior probability of fault A, which can be obtained through historical fault data statistics, specifically: the frequency of occurrence of a certain fault in the past year; P(B|A) is the probability of parameter B taking the current value under the condition that fault A occurs, which is obtained by analyzing the parameter changes in a large number of historical fault cases.

[0050] P(B) is the probability of parameter B taking the current value, which is calculated using the total probability formula. By monitoring the value of parameter B in real time and using the above calculation formula, the probability of fault A occurring under the current parameter state is calculated.

[0051] 2. Failure time prediction formula:

[0052] 1. Calculate its probability density function:

[0053] f( t ) =λe -λt ,t≥0

[0054] 2. Calculate the probability of failure within the future time t:

[0055] P ( T≤t+t0|T>t 0) =1-e -λt

[0056] in:

[0057] t: represents time. In the probability density function f(t), t is a continuous time variable after the unit starts to operate. In the failure probability calculation, t represents the future predicted time; λ is the failure rate, which is a constant obtained by statistical analysis of historical failure data; t0 represents the time the unit has been running; f(t) is a probability density function, which is used to describe the distribution of the failure time T;

[0058] P(T≤t+t0|T>t0) is a conditional probability, which indicates the probability of a failure occurring within the next t time if the unit has been running for t0 time and has not yet failed.

[0059] The formula calculation module is connected to a trend prediction module, which uses the calculation results of the formula calculation module and predicts whether these parameters will exceed the normal range in the next few hours and the rate of change according to the current current, voltage and temperature parameter change trends. The specific prediction formula is:

[0060]

[0061] in:

[0062] represents the predicted value of the unit operating parameters at time t+1; y t is the actual observed value of the unit operating parameters at time t; is the predicted value of the unit operating parameters at time t, α is a smoothing constant, and its value range is between (0,1); by combining the actual observation value y at the current time t t and predicted values It is calculated according to the given smoothing constant α and is used to predict the future change trend of the operating parameters.

[0063] The trend prediction module is connected to a risk assessment module, which comprehensively assesses the risks faced by the operation of the power plant units based on the formula calculation module and the conclusion of the trend prediction module;

[0064] The interactive module is connected to a user interface module, which provides a platform for users to display system information through the platform, making it convenient for staff to watch. The user interface module is connected to an alarm and notification module, which sends the comparison and analysis module to the staff in a timely manner, thereby achieving the effect of fault warning and timely reminder of faults.

[0065] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent monitoring system for the operation status of power plant units based on big data, characterized in that: The system comprises a monitoring and acquisition module, wherein the monitoring and acquisition module comprises a temperature sensor, a pressure sensor, a vibration frequency sensor, and a current sensor. By installing the above-mentioned sensor devices on the power plant unit, various parameters of the power plant unit are collected and monitored, and the values ​​of various parameters collected and monitored are transmitted to the central control module. The monitoring and acquisition module is connected to the central control module. The central control module, as the core of the entire system, coordinates the workflow and data interaction between various modules, receives various parameters collected from the monitoring and acquisition module, and coordinates the data analysis and processing module to read the parameters. The central control module is connected to the data analysis and processing module, and a preset threshold is set in the data analysis and processing module. After receiving various parameters of the real-time power plant unit, the parameters are compared with the threshold to judge the operating status of the power plant unit. The data analysis and processing module is connected to the prediction module. The prediction module uses a formula to calculate according to the historical parameters and fault information of the unit, so as to predict the fault problem of the unit and play an early warning effect. The data analysis and processing module is connected to the interaction module, and the interaction module sends the real-time operating status and prediction conclusion of the power plant unit to the staff.

2. According to the big data-based intelligent monitoring system for power plant unit operation status according to claim 1, it is characterized in that: The data analysis and processing module is connected to a threshold module, which stores pre-set threshold ranges for various operating parameters of power plant units. The specific threshold ranges include: temperature parameter threshold range, pressure parameter threshold range, vibration frequency parameter threshold range and current parameter threshold range.

3. According to claim 2, a big data-based intelligent monitoring system for power plant unit operation status is characterized in that: The threshold module is connected to a comparison and analysis module, which compares various parameters of the real-time power plant unit with the threshold range. When it is found that a parameter exceeds or is lower than the threshold range, the preset solution module is started to judge the specific fault information of the power plant unit according to the overall data of multiple groups or one group of parameters exceeding the threshold range. The comparison and analysis module is connected to a preset solution module, and different fault solutions are stored in the preset solution module. The specific fault solutions include: abnormal temperature fault solution; abnormal pressure fault solution; abnormal vibration frequency fault solution; abnormal current fault solution.

4. According to the big data-based intelligent monitoring system for power plant unit operation status according to claim 1, it is characterized in that: The prediction module is connected to a data sorting module, which sorts out the parameters, fault problems and fault time nodes of the power plant units under long-term operation, and transmits the sorted data to the formula calculation module. The data sorting module is connected to a formula calculation module, and the formula calculation module uses a special formula to substitute the various parameters sorted and collected by the data sorting module to predict the fault problems and fault time of the power plant units.

5. The intelligent monitoring system for power plant unit operation status based on big data according to claim 4 is characterized in that: The specific calculation formula in the formula calculation module includes:

1. Failure probability prediction formula: Where: P(A) is the prior probability of fault A, which can be obtained through historical fault data statistics, specifically: the frequency of occurrence of a certain fault in the past year; P(B|A) is the probability of parameter B taking the current value under the condition that fault A occurs, which is obtained by analyzing the parameter changes in a large number of historical fault cases; P(B) is the probability of parameter B taking the current value, which is calculated using the total probability formula. By monitoring the value of parameter B in real time and using the above calculation formula, the probability of fault A occurring under the current parameter state is calculated.

6. The intelligent monitoring system for power plant unit operation status based on big data according to claim 4 is characterized in that: The specific calculation formula in the formula calculation module also includes:

2. Failure time prediction formula:

1. Calculate its probability density function: f(t)=λe -λt ,t≥0 2. Calculate the probability of failure within the future time t: P(T≤t+t0|T>t0)=1-e -λt in: t: represents time. In the probability density function f(t), t is a continuous time variable after the unit starts running. In the failure probability calculation, t represents the future prediction time. λ is the failure rate, which is a constant obtained through statistical analysis of historical failure data; t0 represents the time the unit has been running; f(t) is the probability density function, which is used to describe the distribution of the failure time T; P(T≤t+t0|T>t0) is a conditional probability, which indicates the probability of a failure occurring within the future time t if the unit has been running for t0 time and has not yet failed.

7. The intelligent monitoring system for power plant unit operation status based on big data according to claim 4 is characterized in that: The formula calculation module is connected to a trend prediction module, which uses the calculation results of the formula calculation module and predicts whether these parameters will exceed the normal range in the next few hours and the rate of change based on the current, voltage and temperature parameter change trends.

8. The intelligent monitoring system for power plant unit operation status based on big data according to claim 7 is characterized in that: The specific prediction formula in the trend prediction module is: in: represents the predicted value of the unit operating parameters at time t+1; y t is the actual observed value of the unit operating parameters at time t; is the predicted value of the unit operating parameters at time t, α is a smoothing constant, and its value range is between (0,1); by combining the actual observation value y at the current time t t and predicted values It is calculated according to the given smoothing constant α and is used to predict the future change trend of the operating parameters.

9. The intelligent monitoring system for power plant unit operation status based on big data according to claim 7 is characterized in that: The trend prediction module is connected to a risk assessment module, and the risk assessment module comprehensively assesses the risks faced by the operation of the power plant units according to the formula calculation module and the conclusion of the trend prediction module.

10. The intelligent monitoring system for power plant unit operation status based on big data according to claim 1 is characterized in that: The interactive module is connected to a user interface module, which provides a platform for users to display system information through the platform. The user interface module is connected to an alarm and notification module, which sends the comparison and analysis module to the staff in a timely manner.

Images