Safety state assessment method and system for compressed air energy storage power station

Abstract

The invention relates to the technical field of compressed air energy storage power station safety, and discloses a compressed air energy storage power station safety state assessment method comprising the following steps: collecting equipment operation state data of a compressed air energy storage power station for standardization processing, and constructing an equipment operation state twin model of the compressed air energy storage power station; the running state of the equipment is monitored in real time to obtain prediction data; comparing the prediction data with the real-time monitoring data to judge whether the equipment operation state of the compressed air energy storage power station is abnormal or not; when the equipment operation state of the compressed air energy storage power station is abnormal, predicting the equipment abnormality rate based on a preset BP neural network model; recording the number of devices when the abnormal rate of the devices exceeds a set value, and calculating the safety coefficient of the compressed air energy storage power station according to the number of the devices. The equipment operation condition of the compressed air energy storage power station is monitored in real time, so that hidden dangers can be found and eliminated in time, and the stable and safe operation of the compressed air energy storage power station is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of safety of compressed air energy storage power stations, and particularly relates to a method and system for evaluating the safety status of a compressed air energy storage power station. Background Art

[0002] Compressed air energy storage refers to a energy storage method that uses off-peak electricity, abandoned wind power, abandoned photovoltaic power, etc. to compress air, and seals the high-pressure air in underground salt caverns, underground mine caves, expired oil and gas wells, and newly built gas storage balloons, and releases the compressed air to drive a turbine to generate electricity during the peak load period of the power grid. As a large-scale physical energy storage technology, compressed air energy storage has good application prospects due to its advantages such as large capacity, high efficiency, fast startup, and flexible response. However, there are many and large-scale equipment in a compressed air energy storage power station, which involves many specialties such as materials, thermal energy and power, electrical engineering, automatic control, and non-destructive testing, and the daily operation and maintenance work is relatively heavy. At the same time, after a long-term operation of the compressed air energy storage power station, fatigue phenomena occur in subsystems of key equipment such as compressors, expanders, heat exchangers, and gas storage reservoirs, resulting in faults such as corrosion, scaling, and air leakage of the equipment. These abnormal states will inevitably affect the safe and stable operation of the power station. The traditional equipment monitoring methods have limitations and lags, and cannot perform real-time and accurate monitoring, resulting in the inability to monitor the equipment of the compressed air energy storage power station in real time and accurately, and reducing the safety of the compressed air energy storage power station. Summary of the Invention

[0003] The present invention provides a method and system for evaluating the safety status of a compressed air energy storage power station, which can monitor the operation status of the equipment of the compressed air energy storage power station in real time, so as to timely discover and eliminate potential hazards, and ensure the stable and safe operation of the compressed air energy storage power station.

[0004] The present invention provides a method for evaluating the safety status of a compressed air energy storage power station, including:

[0005] Collecting the equipment operation status data of the compressed air energy storage power station, and performing standardization processing on the equipment operation data to obtain standardized status data;

[0006] Constructing a twin model of the equipment operation status of the compressed air energy storage power station according to the standardized status data to monitor the equipment operation status in real time and obtain prediction data;

[0007] Comparing the prediction data with the real-time monitoring data to determine whether the equipment operation status of the compressed air energy storage power station is abnormal;

[0008] When the equipment operation status of the compressed air energy storage power station is abnormal, predicting the equipment abnormality rate based on a preset BP neural network model;

[0009] Record the number of devices when the abnormal rate of the device exceeds the set value, and calculate the safety factor of the compressed air energy storage power station according to the number of devices.

[0010] Further, the step of collecting the device operation status data of the compressed air energy storage power station and performing standardization processing on the device operation data to obtain standardized status data includes:

[0011] Collect the device operation status data of the compressed air energy storage power station, extract the minimum value and the maximum value in the data, and calculate their difference.

[0012] Use the difference between the maximum value and the minimum value to eliminate the difference and obtain a normalized value. The formula is:

[0013]

[0014] where X is the original data; X min is the minimum value in the data; X max is the maximum value in the data; Z is the standardized data processing.

[0015] Further, the step of constructing a device operation status twin model of the compressed air energy storage power station according to the standardized status data to perform real-time monitoring on the device operation status and obtain prediction data includes:

[0016] Create a geometric model of the device based on data such as the specifications, length, and width of the device, and integrate the relevant attribute values of the device into the geometric model.

[0017] Set up a data interface to establish the association between the status quantity data signal and the geometric model, and reflect and integrate the operation behavior and logic of the device in the model.

[0018] Construct a device operation status twin model using the "condition - status - event" method.

[0019] Modify the device operation status twin model according to the device information and the device simulation results, and predict the operation status of the device in the digital environment according to the modified device operation status twin model to obtain prediction data.

[0020] Further, in the step of constructing a device operation status twin model using the "condition - status - event" method, the device operation status twin model is expressed as:

[0021]

[0022] where F is the twin device; F 1Let the actual device be \(D\); the set of device geometric models be \(I\); the set of device entity attributes be \(P\); the set of device operation logic models be \(R\); the set of device operation action behaviors be \(K\); \(O\) represents the real-time attribute settings regarding the device health status; \(B\) represents the device operation behaviors when the real-time attribute set of the device operation state matches.

[0023] Further, the step of comparing the prediction data with the real-time monitoring data to determine whether the device operation state of the compressed air energy storage power station is abnormal includes:

[0024] Calculate the comparison threshold between the prediction data and the real-time monitoring data, and its formula is:

[0025]

[0026] where \(h\) is the error; \(\hat{Y}\) 1 is the prediction data; \(Y\) 2 is the real-time monitoring data, and \(G\) is the comparison threshold;

[0027] When the difference between the prediction data and the real-time monitoring data is greater than the threshold, determine that the device operation state is abnormal and issue an alarm. When the difference between the prediction data and the real-time monitoring data is equal to the threshold, determine that the device operation state needs to be checked.

[0028] Further, in the step of predicting the device abnormality rate based on a preset BP neural network model when the device operation state of the compressed air energy storage power station is abnormal, the preset BP neural network model includes:

[0029] Set the structure of the neural network, including setting the number of nodes in the input layer as \(n_1\) 1 , the number of nodes in the hidden layer as \(n_2\) 2 , and the number of nodes in the output layer as \(n_3\) 3 ;

[0030] Initialize the network weights and thresholds, and use random numbers to generate the initial weight matrix \(W\) (l) and the threshold vector \(b\) (l) , where \(l\) represents the number of layers of the neural network, and the initialization formula is:

[0031]

[0032] where \(rand(-\epsilon,\epsilon)\) generates a random number in the interval \([-\epsilon,\epsilon]\), and \(\epsilon\) represents a small value during initialization;

[0033] Calculate the forward propagation. Using the current weights and thresholds, calculate the output result of the neural network through forward propagation. For the neuron nodes in the \(l\)th layer, calculate its activation value using the following formula

[0034]

[0035] Among them, is the weight of the l-th layer; is the activation value of the (l-1)-th layer; is the threshold of the l-th layer; σ is the activation function;

[0036] Calculate the error and gradient, and adopt the mean square error loss function:

[0037]

[0038] Among them, m is the number of samples; is the actual output value; is the predicted output value of the neural network;

[0039] Update the weights and thresholds, and the parameter update formula is as follows:

[0040]

[0041] Among them, α is the learning rate, which is used to control the step size of each iteration; and are the corresponding partial derivatives;

[0042] During the process of updating the weights and thresholds, the WOA algorithm is introduced for optimization.

[0043] Furthermore, in the step of recording the number of devices when the device exception rate exceeds the set value and calculating the safety factor of the compressed air energy storage power station according to the number of devices, the calculation formula is:

[0044]

[0045] Among them, S represents the safety factor of the compressed air energy storage power station, N represents the number of devices when the device exception rate exceeds the set value, and N 总 represents the total number of devices of the compressed air energy storage power station.

[0046] The present invention also provides a safety status evaluation system for a compressed air energy storage power station, including:

[0047] An acquisition module, which is used to acquire the device operation status data of the compressed air energy storage power station and perform standardization processing on the device operation data to obtain standardized status data;

[0048] A construction module, which is used to construct a device operation status twin model of the compressed air energy storage power station according to the standardized status data to monitor the device operation status in real time and obtain prediction data;

[0049] A determination module, configured to compare the predicted data with real-time monitoring data to determine whether the operating status of the equipment in the compressed air energy storage power station is abnormal;

[0050] A prediction module, configured to predict the equipment abnormality rate based on a preset BP neural network model when the operating status of the equipment in the compressed air energy storage power station is abnormal;

[0051] A calculation module, configured to record the number of equipment when the equipment abnormality rate exceeds a set value, and calculate the safety factor of the compressed air energy storage power station according to the number of equipment.

[0052] The present invention also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0053] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0054] The beneficial effects of the present invention are as follows:

[0055] The present invention collects the equipment operating status data of the compressed air energy storage power station to construct a twin model of the equipment operating status of the compressed air energy storage power station for real-time monitoring to obtain predicted data; compares the predicted data with the real-time monitoring data to determine whether the equipment operating status is abnormal, and at the same time predicts the equipment abnormality rate based on a preset BP neural network model, and finally calculates the safety factor of the compressed air energy storage power station according to the number of equipment when the equipment abnormality rate exceeds a set value. By using the preset BP neural network, the accuracy and generalization ability of the equipment abnormality rate prediction model of the compressed air energy storage power station are effectively improved, and the real-time monitoring of the equipment operating conditions of the compressed air energy storage power station is realized, so as to timely discover and eliminate potential hazards and ensure the stable and safe operation of the compressed air energy storage power station. Description of the Drawings

[0056] Figure 1 It is a schematic flowchart of the method according to an embodiment of the present invention.

[0057] Figure 2 It is a schematic structural diagram of the device according to an embodiment of the present invention.

[0058] Figure 3 It is a schematic internal structure diagram of the computer device according to an embodiment of the present invention.

[0059] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0060] It should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0061] As Figure 1 shown, the present invention provides a safety status assessment method for a compressed air energy storage power station, including:

[0062] S1. Collect the equipment operation status data of the compressed air energy storage power station, and perform standardization processing on the equipment operation data to obtain standardized status data;

[0063] Arrange sensors on the equipment of the compressed air energy storage power station according to the characteristics of the equipment and the monitoring requirements, and set the parameters of the sensors: according to the specifications of the sensors, such as the power supply voltage, working temperature, and specifications, etc., set and adjust the parameters of the sensors to ensure that the sensors can work normally. Start the sensors to make them start monitoring the operation status data of the equipment. It is necessary to collect various parameters at a determined time interval to avoid affecting the response efficiency of subsequent safety monitoring. Introduce a data acquisition timer to ensure that the time interval of data acquisition is consistent and reasonable.

[0064] According to the acquisition result of the equipment operation status information data, performing virtual-real mapping on the equipment operation status information data is an important link in forming intelligent monitoring. During the virtual-real mapping process, it is necessary to perform standardization processing on the equipment operation status information data. The standardization method can effectively eliminate the differences in dimensions and quantities between data, thereby realizing the comparison and analysis of data. That is, step S1 specifically includes:

[0065] S101. Collect the equipment operation status data of the compressed air energy storage power station, extract the minimum value and the maximum value in the data, and calculate their difference;

[0066] S102. Use the difference between the maximum value and the minimum value to eliminate the difference and obtain a normalized value. The formula is:

[0067]

[0068] where X is the original data; X min is the minimum value in the data; X max is the maximum value in the data; Z is the standardized data processing. Through the above formula, the original data can be converted into the form of a standard normal distribution. The data processed in this way has better comparability and consistency and can better reflect the actual operation status of the equipment.

[0069] S2. Construct a twin model of the equipment operation status of the compressed air energy storage power station according to the standardized status data to perform real-time monitoring of the equipment operation status and obtain prediction data;

[0070] Step S2 specifically includes:

[0071] S201. Create a geometric model of the device based on data such as the device's specifications, length, and width, and integrate the relevant attribute values of the device into the geometric model.

[0072] S202. Set up a data interface to establish the association between the status quantity data signal and the geometric model, in order to achieve the preliminary integration of the actual device and the virtual device, and reflect and integrate the operation behavior and logic of the device in the model.

[0073] S203. Construct a twin model of the device operation state using the "condition - state - event" method; the twin model of the device operation state is expressed as:

[0074]

[0075] where F is the twin device; F 1 is the actual device; I is the set of device geometric models; P is the set of device entity attributes; R is the set of device operation logic models; K is the set of device operation action behaviors; 0 represents the real - time attribute settings regarding the device health status; B represents the device operation behavior when the real - time attribute set of the device operation state is matched. Import the obtained status signal into the above - mentioned model, and the virtual - real mapping of the status information data can be realized, improving the accuracy and real - time performance of device monitoring.

[0076] S204. Modify the twin model of the device operation state according to the device information and the device simulation results, and predict the operation state of the device in the digital environment based on the modified twin model of the device operation state to obtain prediction data.

[0077] Collect the historical information data of the device, including the information data collected by various types of monitoring terminals; perform data processing on the device information, and the methods include non - zero - crossing half - trapezoid, zero - crossing half - trapezoid, full trapezoid, point distribution, zero - crossing segmented linear distribution, and non - zero - crossing segmented linear distribution methods; use the entropy weight method, analytic hierarchy process, and combined weight method to obtain the weight values of each device component, and then obtain the simulation result of the comprehensive state of the device; compare the simulation result of the comprehensive state of the device with the actual operation data of the device. When the deviation exceeds the set range, use a deep neural network to extract the features of the simulation result and the actual operation result, output the correction coefficient, and then modify the twin model of the device operation state; finally, realize the mapping and matching between the physical entity device and its corresponding digital twin model, achieve the comprehensive visual perception of the device operation state, and finally predict the operation state of the device in the digital environment based on the modified digital twin model.

[0078] S3. Compare the prediction data with the real - time monitoring data to determine whether the operation state of the equipment in the compressed air energy storage power station is abnormal.

[0079] Using sensors to monitor the device in real time and convert it into real digital signals can provide a more accurate understanding of the device's real-time status, promptly detect potential problems, and take corresponding measures. The result of virtual-real mapping provides a digital model. Based on this, by comparing the difference between the real-time monitoring data and the model prediction value, it is determined whether the device is operating normally. If there is a large difference between the real-time data and the predicted value, it indicates that the device may have an abnormality. At this time, an alarm is issued to alert the staff and corresponding measures are taken for investigation and handling. To determine whether the device is operating normally, a reasonable threshold needs to be set. That is, step S3 specifically includes:

[0080] S301. Calculate the comparison threshold between the predicted data and the real-time monitoring data, and its formula is:

[0081]

[0082] where h is the error; Y 1 is the predicted data; Y 2 is the real-time monitoring data, and G is the comparison threshold;

[0083] S302. When the difference between the predicted data and the real-time monitoring data is greater than the threshold, determine that the device is operating abnormally and issue an alarm; when the difference between the predicted data and the real-time monitoring data is equal to the threshold, determine that the device's operating status needs to be checked, that is, the device may be in a normal state or close to the normal range. In this case, no early warning will be issued, but the device's operating status will continue to be monitored.

[0084] S4. When the device of the compressed air energy storage power station is operating abnormally, predict the device abnormality rate based on a preset BP neural network model; the preset BP neural network model uses an improved WOA-BP neural network, which combines the WOA algorithm with the BP neural network to improve the accuracy and convergence speed of the prediction model.

[0085] Steps for constructing the improved WOA-BP neural network model:

[0086] 1) Set the structure of the neural network: Let the number of nodes in the input layer be n 1 , the number of nodes in the hidden layer be n 2 , and the number of nodes in the output layer be n 3 ;

[0087] 2) Initialize the network weights and thresholds: Use random numbers to generate the initial weight matrix W (l) and the threshold vector b (l) , where l represents the number of layers of the neural network, and the initialization formula is:

[0088]

[0089] Among them, rand(-∈,∈) generates a random number within the interval [-∈,∈], and ∈ represents a small value at initialization;

[0090] 3) Calculate the forward propagation: Using the current weights and thresholds, calculate the output result of the neural network through forward propagation. For the neuron node in the l-th layer, calculate its activation value using the following formula

[0091]

[0092] Among them, is the weight of the l-th layer; is the activation value of the (l-1)-th layer; is the threshold of the l-th layer; σ is the activation function;

[0093] 4) Calculate the error and gradient: Adopt the mean square error loss function (MSE):

[0094]

[0095] Among them, m is the number of samples; is the actual output value; is the predicted output value of the neural network;

[0096] 5) Update the weights and thresholds. The parameter update formula is as follows:

[0097]

[0098] Among them, α is the learning rate, which is used to control the step size of each iteration; and are the corresponding partial derivatives;

[0099] 6) Apply the WOA algorithm: During the process of updating the weights and thresholds, introduce the WOA algorithm for optimization.

[0100] S5. Record the number of devices when the device exception rate exceeds the set value, and calculate the safety factor of the compressed air energy storage power station according to the number of devices. The calculation formula is:

[0101]

[0102] Among them, S represents the safety factor of the compressed air energy storage power station, N represents the number of devices when the device exception rate exceeds the set value, and N 总 represents the total number of devices in the compressed air energy storage power station.

[0103] The present invention collects the equipment operation status data of a compressed air energy storage power station to construct a twin model of the equipment operation status of the compressed air energy storage power station for real-time monitoring, and obtains prediction data; the prediction data is compared with the real-time monitoring data to determine whether the equipment operation status is abnormal, and at the same time, the equipment abnormality rate is predicted based on a preset BP neural network model. Finally, the safety factor of the compressed air energy storage power station is calculated according to the number of equipment when the equipment abnormality rate exceeds the set value. By using the preset BP neural network, the accuracy and generalization ability of the equipment abnormality rate prediction model of the compressed air energy storage power station are effectively improved, and the real-time monitoring of the equipment operation status of the compressed air energy storage power station is realized, so as to timely discover and eliminate potential hazards and ensure the stable and safe operation of the compressed air energy storage power station.

[0104] As Figure 2 shown, the present invention also provides a safety status evaluation system for a compressed air energy storage power station, including:

[0105] A collection module 1, configured to collect the equipment operation status data of the compressed air energy storage power station, and perform standardization processing on the equipment operation data to obtain standardized status data;

[0106] A construction module 2, configured to construct a twin model of the equipment operation status of the compressed air energy storage power station according to the standardized status data to perform real-time monitoring on the equipment operation status and obtain prediction data;

[0107] A determination module 3, configured to compare the prediction data with the real-time monitoring data to determine whether the equipment operation status of the compressed air energy storage power station is abnormal;

[0108] A prediction module 4, configured to predict the equipment abnormality rate based on a preset BP neural network model when the equipment operation status of the compressed air energy storage power station is abnormal;

[0109] A calculation module 5, configured to record the number of equipment when the equipment abnormality rate exceeds the set value, and calculate the safety factor of the compressed air energy storage power station according to the number of equipment.

[0110] In one embodiment, the collection module 1 includes:

[0111] An extraction unit, configured to collect the equipment operation status data of the compressed air energy storage power station, extract the minimum value and the maximum value in the data, and calculate their difference;

[0112] A calculation unit, configured to eliminate the difference by using the difference between the maximum value and the minimum value to obtain a normalized value, and its formula is:

[0113]

[0114] where X is the original data; X minis the minimum value in the data; X max is the maximum value in the data; Z is the standardized data processing.

[0115] In one embodiment, the construction module 2 includes:

[0116] An integration unit for creating a geometric model of the device based on data such as the specifications, length, and width of the device, and integrating the relevant attribute values of the device into the geometric model;

[0117] An establishment unit for establishing a data interface to establish an association between the status quantity data signal and the geometric model, and reflecting and integrating the operating behavior and logic of the device in the model;

[0118] A construction unit for constructing a twin model of the device operating state using the "condition - status - event" method;

[0119] A correction unit for correcting the twin model of the device operating state according to the device information and the device simulation results, and predicting the operating state of the device in the digital environment based on the corrected twin model of the device operating state to obtain prediction data.

[0120] In one embodiment, in the construction unit, the twin model of the device operating state is expressed as:

[0121]

[0122] Among them, F is the twin device; F 1 is the actual device; I is the set of device geometric models; P is the set of device entity attributes; R is the set of device operation logic models; K is the set of device operation action behaviors; 0 represents the real - time attribute setting regarding the device health status; B represents the device operation behavior when the real - time attribute set of the device operation state matches.

[0123] In one embodiment, the determination module 3 includes:

[0124] A threshold calculation unit for calculating the comparison threshold between the prediction data and the real - time monitoring data, and its formula is:

[0125]

[0126] Among them, h is the error; Y 1 is the prediction data; Y 2 is the real - time monitoring data, and G is the comparison threshold;

[0127] A determination unit for determining that the operating state of the device is abnormal and issuing an alarm when the difference between the prediction data and the real - time monitoring data is greater than the threshold, and determining that the operating state of the device needs to be checked when the difference between the prediction data and the real - time monitoring data is equal to the threshold.

[0128] In one embodiment, in the prediction module 4, the preset BP neural network model includes:

[0129] Set the structure of the neural network, including setting the number of nodes in the input layer to n 1 , the number of nodes in the hidden layer is n 2 , and the number of nodes in the output layer is n 3 ;

[0130] Initialize the network weights and thresholds, and use random numbers to generate the initial weight matrix W (l) and the threshold vector b (l) , where l represents the number of layers of the neural network, and the initialization formula is:

[0131]

[0132] where rand-∈,∈) generates a random number in the interval p-∈,∈], and ∈ represents a small value during initialization;

[0133] Calculate the forward propagation. Using the current weights and thresholds, calculate the output result of the neural network through forward propagation. For the neuron nodes in the l-th layer, calculate its activation value using the following formula

[0134]

[0135] where, is the weight of the l-th layer; is the activation value of the (l-1)-th layer; is the threshold of the l-th layer; σ is the activation function;

[0136] Calculate the error and gradient, and adopt the mean square error loss function:

[0137]

[0138] where m is the number of samples; is the actual output value; is the predicted output value of the neural network;

[0139] Update the weights and thresholds, and the parameter update formula is as follows:

[0140]

[0141] where α is the learning rate, which is used to control the step size of each iteration; and are the corresponding partial derivatives;

[0142] During the process of updating the weights and thresholds, introduce the WOA algorithm for optimization.

[0143] In one embodiment, in the prediction module 5, the calculation formula is as follows:

[0144]

[0145] where S represents the safety factor of the compressed air energy storage power station, N represents the number of devices when the device abnormality rate exceeds the set value, and N 总 represents the total number of devices in the compressed air energy storage power station.

[0146] Each of the above modules and units is used to correspondingly execute each step in the above safety state assessment method of the compressed air energy storage power station. The specific implementation manner refers to the method embodiments described above and will not be elaborated here.

[0147] As Figure 3 shown, the present invention also provides a computer device, which can be a server, and its internal structure can be as Figure 3 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required for the process of the safety state assessment method of the compressed air energy storage power station. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the safety state assessment method of the compressed air energy storage power station.

[0148] Those skilled in the art can understand that Figure 3 the structure shown in

[0149] is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.

[0150] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in this application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0151] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, device, article, or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, device, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, device, article, or method including that element.

[0152] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for evaluating the safety status of a compressed air energy storage power station, characterized in that: include: Collecting equipment operation status data of the compressed air energy storage power station, and performing standardization processing on the equipment operation data to obtain standardized status data; Constructing a twin model of the equipment operation status of the compressed air energy storage power station according to the standardized status data to monitor the equipment operation status in real time and obtain prediction data; Comparing the predicted data with the real-time monitoring data to determine whether the equipment operating status of the compressed air energy storage power station is abnormal; When the equipment operating status of the compressed air energy storage power station is abnormal, the equipment abnormality rate is predicted based on the preset BP neural network model; The number of devices when the abnormal rate of the devices exceeds the set value is recorded, and the safety factor of the compressed air energy storage power station is calculated based on the number of devices.

2. The method for evaluating the safety status of a compressed air energy storage power station according to claim 1, characterized in that: The step of collecting the equipment operation status data of the compressed air energy storage power station and performing standardization processing on the equipment operation data to obtain standardized status data includes: Collect the equipment operation status data of the compressed air energy storage power station, extract the minimum and maximum values ​​in the data, and calculate their difference; The difference between the maximum and minimum values ​​is used to eliminate the difference and obtain the normalized value, the formula is: Among them, X is the original data; X min is the minimum value in the data; X max is the maximum value in the data; Z is the standardized data processing.

3. The method for evaluating the safety status of a compressed air energy storage power station according to claim 1, characterized in that: The step of constructing a twin model of the equipment operation status of the compressed air energy storage power station according to the standardized status data to monitor the equipment operation status in real time and obtain prediction data includes: Creating a geometric model of the device based on data such as specifications, length, and width of the device, and integrating relevant attribute values ​​of the device into the geometric model; A data interface is established to establish a relationship between the state quantity data signal and the geometric model, and the operation behavior and logic of the equipment are reflected and integrated in the model; Use the "condition-state-event" method to build a twin model of equipment operation status; The device operation status twin model is modified according to the device information and the device simulation result, and the operation status of the device is predicted in a digital environment according to the modified device operation status twin model to obtain prediction data.

4. The method for evaluating the safety status of a compressed air energy storage power station according to claim 3, characterized in that: In the step of constructing the equipment operation status twin model using the "condition-state-event" method, the equipment operation status twin model is expressed as: Among them, F is the twin device; F1 is the actual device; I is the device geometry model set; P is the set of device entity attributes; R is the set of device operation logic models; K is the set of device operation action behaviors; 0 represents the real-time attribute setting about the health status of the device; B represents the device operation behavior when the real-time attribute set of the device operation status matches.

5. The method for evaluating the safety status of a compressed air energy storage power station according to claim 1, characterized in that: The step of comparing the predicted data with the real-time monitoring data to determine whether the equipment operation status of the compressed air energy storage power station is abnormal includes: The comparison threshold between the predicted data and the real-time monitoring data is calculated as follows: Among them, h is the error; Y1 is the predicted data; Y2 is the real-time monitoring data, and G is the comparison threshold; When the difference between the predicted data and the real-time monitoring data is greater than a threshold, it is determined that the operating status of the equipment is abnormal and an alarm is issued. When the difference between the predicted data and the real-time monitoring data is equal to the threshold, it is determined that the operating status of the equipment needs to be checked.

6. The method for evaluating the safety status of a compressed air energy storage power station according to claim 1, characterized in that: When the equipment operating state of the compressed air energy storage power station is abnormal, in the step of predicting the equipment abnormality rate based on the preset BP neural network model, the preset BP neural network model includes: Set the structure of the neural network, including setting the number of nodes in the input layer to n 1 , the number of nodes in the hidden layer is n 2 , the number of nodes in the output layer is n 3 ; Initialize network weights and thresholds, and use random numbers to generate the initial weight matrix W (l) and threshold vector b (l) , where l represents the number of layers of the neural network, the initialization formula is: Among them, rand(-∈,∈) generates a random number in the interval [-∈,∈], and ∈ represents a small value at the time of initialization; Calculate the forward propagation, use the current weight and threshold, calculate the output of the neural network through forward propagation, for the neuron node in the lth layer, use the following formula to calculate its activation value in, is the weight of the lth layer; is the activation value of the (l-1)th layer; is the threshold of the lth layer; σ is the activation function; Calculate the error and gradient, using the mean square error loss function: Where m is the number of samples; is the actual output value; is the predicted output value of the neural network; Update weights and thresholds. The parameter update formula is as follows: Among them, α is the learning rate, which is used to control the step size of each iteration; and is the corresponding partial derivative; In the process of updating weights and thresholds, the WOA algorithm is introduced for optimization.

7. The method for evaluating the safety status of a compressed air energy storage power station according to claim 1, characterized in that: In the step of recording the number of devices when the device abnormality rate exceeds the set value, and calculating the safety factor of the compressed air energy storage power station according to the number of devices, the calculation formula is: Among them, S represents the safety factor of the compressed air energy storage power station, N represents the number of devices when the equipment abnormality rate exceeds the set value, and N 总 Represents the total number of devices in the compressed air energy storage power station.

8. A safety status assessment system for a compressed air energy storage power station, characterized in that: include: The acquisition module is used to collect the equipment operation status data of the compressed air energy storage power station and perform standardization processing on the equipment operation data to obtain standardized status data; A construction module is used to construct a twin model of the equipment operation status of the compressed air energy storage power station according to the standardized status data, so as to monitor the equipment operation status in real time and obtain prediction data; A determination module, used to compare the predicted data with the real-time monitoring data to determine whether the equipment operation status of the compressed air energy storage power station is abnormal; The prediction module is used to predict the equipment abnormality rate based on the preset BP neural network model when the equipment operating status of the compressed air energy storage power station is abnormal; The calculation module is used to record the number of devices when the abnormal rate of the device exceeds a set value, and calculate the safety factor of the compressed air energy storage power station based on the number of devices.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images