Risk processing method and device based on dynamic determination of multi-unit joint vibration area, computer equipment and storage medium

Abstract

The invention relates to a risk processing method and device based on dynamic determination of a multi-unit combined vibration area, computer equipment and a storage medium. The method comprises the following steps: inputting a vibration area parameter and a unit output range of a joint control unit of a power plant under a current water head into a trained adjustable interval prediction model to obtain a fusion adjustable interval of the joint control unit under the current water head; determining a combined vibration area of the power plant according to the fusion adjustable interval, and performing risk processing on the power plant according to the combined vibration area; when it is detected that the current water head changes, according to the changed water head corresponding to the joint control unit, the vibration area parameters are updated, and the updated vibration area parameters are obtained. By adopting the method, the risk processing accuracy of the power plant can be improved.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a risk management method, apparatus, computer equipment, computer-readable storage medium, and computer program product based on the dynamic determination of the joint vibration zone of multiple generating units. Background Technology

[0002] Currently, in order to ensure the safe operation of power plants, it is crucial to accurately manage the risks associated with them.

[0003] In traditional technologies, risk management for power plants is generally carried out using manual experience; however, this manual experience-based approach is subject to subjective factors and prone to errors, resulting in low accuracy in power plant risk management. Summary of the Invention

[0004] Therefore, it is necessary to provide a risk management method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of unit risk management based on the dynamic determination of the joint vibration zone of multiple units, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a risk management method based on the dynamic determination of vibration zones of multiple units, including:

[0006] Obtain the vibration zone parameters and unit output range of the power plant's interconnected units under the current water head;

[0007] The vibration zone parameters and the unit output range are input into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0008] From the preset adjustable intervals, the preset adjustable interval with the highest predicted probability is selected as the adjustable interval of the joint control unit under the current water head;

[0009] The adjustable range is fused to obtain the fused adjustable range of the joint control unit under the current water head;

[0010] Based on the aforementioned adjustable range, the combined vibration zone of the power plant is determined;

[0011] If a change in the current water head is detected, the vibration zone parameters are updated according to the changed water head corresponding to the control unit to obtain the updated vibration zone parameters.

[0012] The updated vibration zone parameters are used as the new vibration zone parameters, and the process jumps to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the predicted probability of the joint control unit under each preset adjustable range. This continues until no change in the current head is detected. Then, based on the last obtained joint vibration zone, the risk handling instruction corresponding to the power plant is determined, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0013] In one embodiment, the step of merging the adjustable range to obtain the merged adjustable range of the joint control unit under the current head includes:

[0014] Based on the vibration zone parameters, the adjustable range is divided to obtain the adjustable sub-range corresponding to the control unit;

[0015] The adjustable sub-intervals corresponding to each of the aforementioned control units are combined to obtain multiple combined adjustable sub-intervals;

[0016] The multiple combined adjustable sub-intervals are merged to obtain the integrated adjustable interval of the joint control unit under the current water head.

[0017] In one embodiment, obtaining the vibration zone parameters and unit output range of the power plant's interconnected generating units under the current water head includes:

[0018] Obtain the current head information, current operating time information, and current flow information of the power plant's interconnected units under the current water head;

[0019] The current head information is used as the main data, and the current running time information and the current flow rate information are used as auxiliary data. These are input into multiple trained vibration zone parameter prediction models to obtain multiple predicted vibration zone parameters.

[0020] Based on the model weights of each trained vibration zone parameter prediction model, the multiple predicted vibration zone parameters are fused to obtain the vibration zone parameters.

[0021] In one embodiment, updating the vibration zone parameters based on the changed head corresponding to the controlled unit to obtain the updated vibration zone parameters includes:

[0022] Based on the changed head information corresponding to the joint control unit, the correspondence between the head information and the vibration zone parameters is queried to obtain the target vibration zone parameters corresponding to the changed head information.

[0023] Obtain the first weight corresponding to the target vibration zone parameters and the second weight corresponding to the vibration zone parameters;

[0024] Based on the first weight and the second weight, the target vibration zone parameters and the vibration zone parameters are fused to obtain the updated vibration zone parameters.

[0025] In one embodiment, obtaining the first weight corresponding to the target vibration zone parameters and the second weight corresponding to the vibration zone parameters includes:

[0026] Obtain the first initial weight corresponding to the target vibration zone parameters, and the second initial weight corresponding to the vibration zone parameters;

[0027] Based on the current water head and the changed water head, the change in water head is determined. Based on the change in water head, the first initial weight and the second initial weight are updated to obtain the first updated weight corresponding to the target vibration zone parameter and the second updated weight corresponding to the vibration zone parameter.

[0028] Based on the first updated weight, a first weight corresponding to the target vibration zone parameter is obtained, and based on the second updated weight, a second weight corresponding to the vibration zone parameter is obtained.

[0029] In one embodiment, the trained adjustable interval prediction model is obtained by training in the following manner:

[0030] The parameters of the first vibration zone and the output range of the first unit of the sample power plant under the sample head are obtained, as well as the parameters of the second vibration zone and the output range of the second unit of the target unit of the sample power plant under the sample head; the target unit is used to represent the unit in the sample power plant whose similarity to the sample unit is greater than a preset similarity.

[0031] Based on the first vibration zone parameters and the second vibration zone parameters, the sample vibration zone parameters of the sample control unit under the sample head are obtained, and based on the output range of the first unit and the output range of the second unit, the sample unit output range of the sample control unit under the sample head is obtained.

[0032] The sample vibration zone parameters and the sample unit output range are input into the adjustable range prediction model to be trained to obtain the sample prediction probability of the sample joint control unit under each preset adjustable range.

[0033] From the preset adjustable intervals, the preset adjustable interval with the highest sample prediction probability is selected as the prediction adjustable interval of the sample control unit under the sample head.

[0034] The actual adjustable range of the sample control unit under the sample head is obtained. Based on the difference between the predicted adjustable range and the actual adjustable range, the adjustable range prediction model to be trained is iteratively trained to obtain the trained adjustable range prediction model.

[0035] Secondly, this application also provides a risk management device based on the dynamic determination of the joint vibration zone of multiple units, including:

[0036] The data acquisition module is used to acquire the vibration zone parameters and output range of the power plant's interconnected units under the current water head;

[0037] The model prediction module is used to input the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0038] The interval filtering module is used to filter out the preset adjustable interval with the highest predicted probability from the preset adjustable intervals, and use it as the adjustable interval of the joint control unit under the current water head;

[0039] The interval fusion module is used to fuse the adjustable intervals to obtain the fused adjustable interval of the joint control unit under the current water head;

[0040] The vibration zone determination module is used to determine the combined vibration zone of the power plant based on the integrated adjustable range;

[0041] The parameter update module is used to update the vibration zone parameters according to the changed water head corresponding to the control unit when the current water head is detected to obtain the updated vibration zone parameters.

[0042] The parameter processing module is used to take the updated vibration zone parameters as the new vibration zone parameters and jump to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range. Until no change in the current head is detected, the risk handling instruction corresponding to the power plant is determined according to the last obtained joint vibration zone, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0043] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0044] Obtain the vibration zone parameters and unit output range of the power plant's interconnected units under the current water head;

[0045] The vibration zone parameters and the unit output range are input into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0046] From the preset adjustable intervals, the preset adjustable interval with the highest predicted probability is selected as the adjustable interval of the joint control unit under the current water head;

[0047] The adjustable range is fused to obtain the fused adjustable range of the joint control unit under the current water head;

[0048] Based on the aforementioned adjustable range, the combined vibration zone of the power plant is determined;

[0049] If a change in the current water head is detected, the vibration zone parameters are updated according to the changed water head corresponding to the control unit to obtain the updated vibration zone parameters.

[0050] The updated vibration zone parameters are used as the new vibration zone parameters, and the process jumps to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the predicted probability of the joint control unit under each preset adjustable range. This continues until no change in the current head is detected. Then, based on the last obtained joint vibration zone, the risk handling instruction corresponding to the power plant is determined, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0051] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0052] Obtain the vibration zone parameters and unit output range of the power plant's interconnected units under the current water head;

[0053] The vibration zone parameters and the unit output range are input into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0054] From the preset adjustable intervals, the preset adjustable interval with the highest predicted probability is selected as the adjustable interval of the joint control unit under the current water head;

[0055] The adjustable range is fused to obtain the fused adjustable range of the joint control unit under the current water head;

[0056] Based on the aforementioned adjustable range, the combined vibration zone of the power plant is determined;

[0057] If a change in the current water head is detected, the vibration zone parameters are updated according to the changed water head corresponding to the control unit to obtain the updated vibration zone parameters.

[0058] The updated vibration zone parameters are used as the new vibration zone parameters, and the process jumps to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the predicted probability of the joint control unit under each preset adjustable range. This continues until no change in the current head is detected. Then, based on the last obtained joint vibration zone, the risk handling instruction corresponding to the power plant is determined, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0059] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0060] Obtain the vibration zone parameters and unit output range of the power plant's interconnected units under the current water head;

[0061] The vibration zone parameters and the unit output range are input into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0062] From the preset adjustable intervals, the preset adjustable interval with the highest predicted probability is selected as the adjustable interval of the joint control unit under the current water head;

[0063] The adjustable range is fused to obtain the fused adjustable range of the joint control unit under the current water head;

[0064] Based on the aforementioned adjustable range, the combined vibration zone of the power plant is determined;

[0065] If a change in the current water head is detected, the vibration zone parameters are updated according to the changed water head corresponding to the control unit to obtain the updated vibration zone parameters.

[0066] The updated vibration zone parameters are used as the new vibration zone parameters, and the process jumps to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the predicted probability of the joint control unit under each preset adjustable range. This continues until no change in the current head is detected. Then, based on the last obtained joint vibration zone, the risk handling instruction corresponding to the power plant is determined, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0067] The aforementioned risk management method, device, computer equipment, storage medium, and computer program product based on the dynamic determination of the joint vibration zone of multiple units first acquire the vibration zone parameters and unit output range of the power plant's jointly controlled units under the current head. These parameters are then input into a trained adjustable range prediction model to obtain the predicted probability of the jointly controlled units under each preset adjustable range. Next, the preset adjustable range with the highest predicted probability is selected as the adjustable range of the jointly controlled units under the current head. The adjustable ranges are then fused to obtain the fused adjustable range of the jointly controlled units under the current head. Finally, based on the fused adjustable range... The combined vibration zone of the power plant is determined. Then, when a change in the current head is detected, the vibration zone parameters are updated according to the changed head of the controlled unit, resulting in updated vibration zone parameters. Finally, the updated vibration zone parameters are used as the new vibration zone parameters, and the process jumps to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the controlled unit under each preset adjustable range. This process continues until no change in the current head is detected. Then, based on the last obtained combined vibration zone, the corresponding risk handling instruction for the power plant is determined, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction. In this way, when performing risk management for power plants, a robust and adjustable fusion range is obtained based on vibration and output data under the current head through model prediction and fusion processing. The combined vibration zone determined accordingly can accurately reflect the safety boundary of the unit. At the same time, by monitoring head changes in real time and dynamically updating parameters and iteratively optimizing the combined vibration zone, it is ensured that the risk assessment is always adapted to the latest operating conditions. Finally, risk management instructions are generated based on the combined vibration zone that best fits the current reality. This avoids the lag error caused by fixed parameters and reduces the deviation of single data or models through multi-stage verification, so that risk management can accurately match the actual safety requirements of the unit, which is conducive to improving the accuracy of power plant risk management. Moreover, the whole process does not require human intervention, avoiding the subjective factors and errors that are prone to occur when using manual experience, which leads to low accuracy in power plant risk management, further improving the accuracy of power plant risk management. Attached Figure Description

[0068] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0069] Figure 1 This is a flowchart illustrating a risk management method based on the dynamic determination of vibration zones of multiple units in one embodiment.

[0070] Figure 2 This is a flowchart illustrating the steps for obtaining the integrated adjustable range of the joint control unit under the current head in one embodiment;

[0071] Figure 3 This is a flowchart illustrating a risk management method based on dynamic determination of the joint vibration zone of multiple units, as described in another embodiment.

[0072] Figure 4 This is a structural block diagram of a risk management device based on dynamic determination of the joint vibration zone of multiple units in one embodiment;

[0073] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0075] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0076] In one exemplary embodiment, such as Figure 1 As shown, a risk management method based on the dynamic determination of vibration zones of multiple generator units is provided. This embodiment illustrates the application of this method to a server; it is understood that this method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; the server can be a standalone server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0077] Step S101: Obtain the vibration zone parameters and unit output range of the power plant's interconnected units under the current water head.

[0078] Among them, power plant can refer to hydroelectric power plant.

[0079] Among them, the joint control unit refers to a cluster of multiple hydro-turbine generator units that achieve coordinated operation and joint control within a power plant through a unified control system (such as a distributed control system).

[0080] The current head refers to the actual water level difference between the power plant and the control unit at the current time.

[0081] Among them, the vibration zone parameter refers to the key quantitative indicator of the vibration state of the inverse control unit, which is used to determine whether the inverse control unit is within the safe vibration range.

[0082] The unit output range refers to the entire range of power generation that the jointly controlled unit can achieve by adjusting the guide vane opening and other methods.

[0083] For example, in response to a request for information on the joint vibration zone of a power plant, the server obtains the current head of the power plant's joint control unit using a water level sensor (such as an ultrasonic level gauge) corresponding to the unit. It then obtains the vibration frequency (obtained through spectrum analysis) and vibration amplitude (displacement / velocity / acceleration value) of the joint control unit at the current head using vibration sensors installed in key parts of the unit (such as the turbine main shaft, bearings, and stator base), which serve as parameters for the vibration zone of the joint control unit at the current head. Finally, the server gradually adjusts the guide vane opening of the joint control unit through the power plant's automatic power generation control system to obtain the minimum output value (lower limit) and maximum output value (upper limit) for stable operation of the unit. Finally, the server combines the minimum output value (lower limit) and the maximum output value to obtain the unit's output range at the current head.

[0084] Step S102: Input the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0085] Among them, the adjustable range prediction model refers to the network model that can predict the adjustable range of the joint control unit under the current head, such as the convolutional neural network model.

[0086] Among them, the preset adjustable range refers to the adjustable range that is set in advance.

[0087] The prediction probability refers to the likelihood that the trained adjustable interval prediction model will correctly determine the preset adjustable interval.

[0088] For example, the server inputs the vibration zone parameters and the unit output range into the feature extraction model to obtain the feature vectors of the vibration zone parameters and the unit output range. Then, the server fuses the feature vectors of the vibration zone parameters and the unit output range to obtain a fused feature vector. Finally, the server inputs the fused feature vector into the trained adjustable range prediction model to obtain the prediction probability of the jointly controlled unit in each preset adjustable range.

[0089] Step S103: Select the preset adjustable range with the highest predicted probability from each preset adjustable range, and use it as the adjustable range of the joint control unit under the current water head.

[0090] The adjustable range refers to the safe power range of the joint control unit under the current water head.

[0091] For example, the server selects the preset adjustable interval with the highest predicted probability from each preset adjustable interval, and verifies the preset adjustable interval (comparing the deviation of the adjustable interval with the historical best adjustable interval at the same head; if the deviation exceeds a preset threshold, the model input data needs to be checked back), and obtains the verification result of the preset adjustable interval; if the verification result indicates that the preset adjustable interval has passed the verification, the preset adjustable interval is used as the adjustable interval of the joint control unit under the current head.

[0092] Step S104: Perform fusion processing on the adjustable range to obtain the fused adjustable range of the joint control unit under the current head.

[0093] Among them, the adjustable range after fusion refers to the adjustable range after fusion processing.

[0094] For example, the server performs fusion processing on the adjustable range according to a preset fusion method to obtain the fused adjustable range of the joint control unit under the current water head.

[0095] Step S105: Determine the combined vibration zone of the power plant based on the fusion adjustable range.

[0096] The joint vibration zone refers to the power output zone (non-adjustable risk area) that is not covered by the integrated adjustable range of all the jointly controlled units in the power plant.

[0097] For example, the server determines the total power output range of the power plant, and from the total power output range, determines a continuous range outside the integrated adjustable range as the joint vibration zone of the power plant.

[0098] Step S106: When a change in the current water head is detected, the vibration zone parameters are updated according to the changed water head of the control unit to obtain the updated vibration zone parameters.

[0099] The changed head refers to the new actual water level difference between the water flow and the control unit in a hydroelectric power plant.

[0100] Among them, the updated vibration zone parameters refer to the updated vibration zone parameters.

[0101] For example, when the server detects a change in the current water head, it determines the adjustment coefficient corresponding to the vibration zone parameters based on the changed water head of the linked unit; then, the server adjusts the vibration zone parameters according to the adjustment coefficient to obtain the updated vibration zone parameters.

[0102] Step S107: The updated vibration zone parameters are used as the new vibration zone parameters, and the process jumps to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range. This process continues until no change in the current head is detected. Then, based on the last obtained joint vibration zone, the risk handling instruction corresponding to the power plant is determined, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0103] Among them, risk handling instructions refer to specific operational instructions used to guide power plants to avoid vibration risks. These include the specific risk level (such as "moderate risk" or "high risk") and risk output range (such as "34.5MW-38.5MW needs to be avoided") corresponding to the joint vibration zone, as well as the corresponding risk handling measures of the power plant, including but not limited to load adjustment (such as "reduce the total output from 36MW to 34MW to avoid the vibration zone"), unit start-up and shutdown coordination (such as "start standby unit 2 to share the load and shut down unit 1 to avoid low load vibration risk"), and enhanced monitoring (such as "increase the vibration sensor acquisition frequency to 1 time / 5 seconds to track vibration data in real time").

[0104] For example, the server uses the updated vibration zone parameters as the new vibration zone parameters, and inputs the updated vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range; until no change in the current head is detected, the vibration zone information of the last obtained joint vibration zone is input into the trained risk handling instruction prediction model to obtain the risk handling instruction corresponding to the power plant; then, the server performs the corresponding risk handling for the power plant according to the risk handling instruction.

[0105] In the aforementioned risk management method based on the dynamic determination of the joint vibration zone of multiple units, the vibration zone parameters and unit output range of the power plant's jointly controlled units under the current head are first obtained. These parameters and output ranges are then input into a trained adjustable interval prediction model to obtain the prediction probability of the jointly controlled units under each preset adjustable interval. Next, the preset adjustable interval with the highest prediction probability is selected as the adjustable interval for the jointly controlled units under the current head. The adjustable intervals are then fused to obtain the fused adjustable interval for the jointly controlled units under the current head. Finally, based on the fused adjustable interval, the joint vibration of the power plant is determined. The process begins by identifying a change in the current head. Then, upon detecting a change in the current head, the vibration zone parameters are updated based on the changed head of the controlled unit. The updated vibration zone parameters are then used as the new vibration zone parameters, and the process jumps to inputting the vibration zone parameters and the unit's output range into the trained adjustable range prediction model to obtain the predicted probability of the controlled unit in each preset adjustable range. This process continues until no change in the current head is detected. Finally, based on the last obtained joint vibration zone, the corresponding risk handling instruction for the power plant is determined, and the power plant is subjected to the corresponding risk handling according to the instruction. In this way, when performing risk management for power plants, a robust and adjustable fusion range is obtained based on vibration and output data under the current head through model prediction and fusion processing. The combined vibration zone determined accordingly can accurately reflect the safety boundary of the unit. At the same time, by monitoring head changes in real time and dynamically updating parameters and iteratively optimizing the combined vibration zone, it is ensured that the risk assessment is always adapted to the latest operating conditions. Finally, risk management instructions are generated based on the combined vibration zone that best fits the current reality. This avoids the lag error caused by fixed parameters and reduces the deviation of single data or models through multi-stage verification, so that risk management can accurately match the actual safety requirements of the unit, which is conducive to improving the accuracy of power plant risk management. Moreover, the whole process does not require human intervention, avoiding the subjective factors and errors that are prone to occur when using manual experience, which leads to low accuracy in power plant risk management, further improving the accuracy of power plant risk management.

[0106] In one exemplary embodiment, such as Figure 2 As shown, step S101 above, which involves merging the adjustable range to obtain the merged adjustable range of the joint control unit under the current head, specifically includes the following steps:

[0107] Step S201: Based on the vibration zone parameters, the adjustable interval is divided to obtain the adjustable sub-intervals corresponding to the control unit.

[0108] Step S202: Combine the adjustable sub-intervals corresponding to each control unit to obtain multiple combined adjustable sub-intervals.

[0109] Step S203: Merge multiple combined adjustable sub-intervals to obtain the integrated adjustable interval of the joint control unit under the current head.

[0110] Among them, the adjustable sub-interval refers to the safe output range divided from the adjustable interval based on the vibration zone parameters.

[0111] The combined adjustable sub-interval refers to the combined result obtained by adding the values ​​of the adjustable sub-intervals according to the power boundary. For example, if the adjustable sub-interval of Unit 1 is (C,D) and the adjustable sub-interval of Unit 2 is (E,F), then the combined adjustable sub-interval is (C+E,D+F).

[0112] For example, the server determines the vibration zone corresponding to the controlled unit based on the vibration zone parameters, and divides the adjustable interval according to the vibration zone of the controlled unit to obtain the adjustable sub-intervals corresponding to the controlled unit. If the adjustable interval of a certain unit is 20MW-60MW, and the vibration zone parameters show that the vibration zones are 30MW-35MW and 45MW-50MW, then three adjustable sub-intervals are divided: 20MW-30MW, 35MW-45MW, and 50MW-60MW. Next, the server combines the adjustable sub-intervals corresponding to each controlled unit according to preset combination rules to obtain multiple combined adjustable sub-intervals. Then, the server merges the multiple combined adjustable sub-intervals (overlapping or adjacent intervals are merged into continuous intervals) to obtain the combined adjustable sub-intervals after interval merging, which serves as the integrated adjustable interval of the controlled unit under the current head.

[0113] In this embodiment, by subdividing the adjustable range into more precise adjustable sub-ranges, and then combining and merging the sub-ranges of multiple units, the safe operation potential of each unit can be fully explored. The precise division of sub-ranges ensures the vibration safety of each sub-segment, and the combined processing covers all possible safety schemes for the coordinated operation of multiple units, providing a more reliable basis for the subsequent determination of the joint vibration zone.

[0114] In an exemplary embodiment, step S101 above, obtaining the vibration zone parameters and unit output range of the power plant's interconnected units under the current water head, specifically includes the following: obtaining the current water head information, current running time information, and current flow information of the power plant's interconnected units under the current water head; using the current water head information as the primary data and the current running time information and current flow information as auxiliary data, inputting them into multiple trained vibration zone parameter prediction models to obtain multiple predicted vibration zone parameters; and fusing the multiple predicted vibration zone parameters according to the model weights of each trained vibration zone parameter prediction model to obtain the vibration zone parameters.

[0115] Among them, the current head information is used to represent structured data with the current head as the core, including the specific value of the current head, the data acquisition time (such as "acquired at 10:05"), the acquisition sensor number (such as "sensor 1#"), the data reliability (such as "error ±0.1 meters"), and other information.

[0116] The current running time information refers to the continuous running time of the joint control unit under the current water head (e.g., "running for 24 hours").

[0117] The current flow information refers to the volume of water flowing through the unit per unit time under the current head.

[0118] Among them, the vibration zone parameter prediction model refers to a network model, such as a neural network model, that can use current head information, current running time information, and current flow information to predict vibration zone parameters.

[0119] Among them, the predicted vibration zone parameters refer to the predicted values ​​of the vibration zone parameters of the joint control unit under the current water head.

[0120] Among them, the model weights are used to represent the weight coefficients corresponding to the vibration zone parameter prediction model.

[0121] For example, in response to a command to predict vibration zone parameters of a power plant's controlled units under the current head, the server retrieves the current head information, current running time information, and current flow information of the power plant's controlled units from the database. Then, the server inputs the current head information, current running time information, and current flow information into a feature extraction model to obtain a first feature vector for the current head information, a second feature vector for the current running time information, and a third feature vector for the current flow information. Next, the server uses the first feature vector as primary data and the second and third feature vectors as auxiliary data, inputting them into multiple trained vibration zone parameter prediction models to obtain multiple predicted vibration zone parameters. Then, based on the prediction accuracy of each trained vibration zone parameter prediction model, the server determines the model weight of each trained vibration zone parameter prediction model, and performs fusion processing on the multiple predicted vibration zone parameters based on the model weights of each trained vibration zone parameter prediction model to obtain the vibration zone parameters.

[0122] In this embodiment, by using the current head information as the core influencing factor as the main data and supplementing it with auxiliary data, the advantages of multiple models are combined and the prediction results are fused according to the model weights. This avoids the one-sidedness of a single data dimension and the inherent bias of a single model. Furthermore, by strengthening the contribution of reliable models through weight allocation, parameters that are more in line with the actual vibration characteristics of the unit are obtained, which is conducive to improving the accuracy of determining vibration zone parameters.

[0123] In an exemplary embodiment, step S106 above, which updates the vibration zone parameters according to the changed head corresponding to the joint control unit, to obtain the updated vibration zone parameters, specifically includes the following: based on the changed head information corresponding to the joint control unit, querying the correspondence between the head information and the vibration zone parameters to obtain the target vibration zone parameters corresponding to the changed head information; obtaining the first weight corresponding to the target vibration zone parameters and the second weight corresponding to the vibration zone parameters; and performing fusion processing on the target vibration zone parameters and the vibration zone parameters according to the first weight and the second weight to obtain the updated vibration zone parameters.

[0124] Among them, the changed head information is used to represent structured data with the changed head as the core, including the specific value of the changed head, the data acquisition time, the acquisition sensor number, the data reliability and other information.

[0125] Among them, the target vibration zone parameters refer to the vibration zone parameters that match the changed head information.

[0126] The first weight refers to the weight coefficient corresponding to the target vibration zone parameter.

[0127] The second weight refers to the weighting coefficient corresponding to the vibration zone parameters.

[0128] For example, the server retrieves the correspondence between head information and vibration zone parameters from the database or the database, and based on the changed head information corresponding to the controlled unit, queries the correspondence between head information and vibration zone parameters to obtain the vibration zone parameters corresponding to the changed head information, which are used as the target vibration zone parameters. Then, the server obtains the first weight corresponding to the target vibration zone parameters and the second weight corresponding to the vibration zone parameters. Then, based on the first weight and the second weight, the target vibration zone parameters and the vibration zone parameters are summed to obtain the updated vibration zone parameters.

[0129] In this embodiment, by using historical mapping query and dual-weight dynamic fusion, we can avoid the deviation that may exist by relying solely on historical data, and prevent information loss caused by direct replacement. The resulting updated vibration zone parameters can more accurately adapt to the new head conditions, which is beneficial to improving the reliability of vibration zone parameter updates.

[0130] In an exemplary embodiment, obtaining the first weight corresponding to the target vibration zone parameter and the second weight corresponding to the vibration zone parameter specifically includes the following: obtaining the first initial weight corresponding to the target vibration zone parameter and the second initial weight corresponding to the vibration zone parameter; determining the head change based on the current head and the changed head; updating the first initial weight and the second initial weight based on the head change to obtain the first updated weight corresponding to the target vibration zone parameter and the second updated weight corresponding to the vibration zone parameter; obtaining the first weight corresponding to the target vibration zone parameter based on the first updated weight, and obtaining the second weight corresponding to the vibration zone parameter based on the second updated weight.

[0131] The first initial weight refers to the preset weight corresponding to the target vibration zone parameters.

[0132] The second initial weight refers to the preset weight corresponding to the vibration zone parameters.

[0133] The change in water head refers to the difference between the current water head and the changed water head.

[0134] The first updated weight refers to the first initial weight updated based on the change in water head.

[0135] The second updated weight refers to the second initial weight updated based on the change in water head.

[0136] For example, the server uses the historical weights corresponding to the target vibration zone parameters as the first initial weights corresponding to the target vibration zone parameters, and uses the historical weights corresponding to the vibration zone parameters as the second initial weights corresponding to the vibration zone parameters. Next, the server uses the absolute difference between the current water head and the changed water head as the water head change. Then, based on the difference between the water head change and the preset water head change, the server determines the adjustment coefficients corresponding to the first and second initial weights, and adjusts the first and second initial weights according to the adjustment coefficients to obtain the first updated weights corresponding to the target vibration zone parameters and the second updated weights corresponding to the vibration zone parameters. Finally, the server uses the first updated weights as the first weights corresponding to the target vibration zone parameters, and uses the second updated weights as the second weights corresponding to the vibration zone parameters.

[0137] In this embodiment, by dynamically adjusting the initial weights according to the magnitude of head changes, the final weights retain the basic reliability of historical data while responding in real time to the actual impact of changes in operating conditions, avoiding the rigidity of fixed weights. This allows the fusion result of the target parameters and the original parameters to better match the characteristics of the unit under the new head, improving the dynamic adaptability and accuracy of parameter updates in the vibration zone.

[0138] In an exemplary embodiment, the risk management method based on dynamic determination of the joint vibration zone of multiple units provided in this application further includes a training process for an adjustable interval prediction model, specifically including the following: obtaining the first vibration zone parameters and the first unit output range of the sample joint control unit of the sample power plant under the sample head, and the second vibration zone parameters and the second unit output range of the target joint control unit of the sample power plant under the sample head; based on the first vibration zone parameters and the second vibration zone parameters, obtaining the sample vibration zone parameters of the sample joint control unit under the sample head, and based on the first unit output range and the second unit output range, obtaining the sample... The output range of the control unit under the sample head is determined. The vibration zone parameters and output range of the control unit are input into the adjustable range prediction model to be trained to obtain the sample prediction probability of the control unit under each preset adjustable range. From each preset adjustable range, the preset adjustable range with the highest sample prediction probability is selected as the predicted adjustable range of the control unit under the sample head. The actual adjustable range of the control unit under the sample head is obtained. Based on the difference between the predicted adjustable range and the actual adjustable range, the adjustable range prediction model to be trained is iteratively trained to obtain the trained adjustable range prediction model.

[0139] Among them, the sample power plants refer to the power plants used to train the adjustable interval prediction model to be trained.

[0140] Among them, the sample joint control unit refers to the joint control unit that uses the sample power plant as the main training sample.

[0141] Among them, the sample head refers to the water level difference between the sample power plant and the sample control unit caused by the water flow.

[0142] Among them, the first vibration zone parameter refers to the vibration zone parameter of the sample control unit under the sample head.

[0143] The first unit's output range refers to the output range of the sample control unit under the sample head.

[0144] Among them, the target control unit is used to represent the control unit in the sample power plant whose similarity with the sample control unit is greater than the preset similarity.

[0145] Among them, the second vibration zone parameter refers to the vibration zone parameter of the target control unit under the sample head.

[0146] The output range of the second unit refers to the output range of the target control unit under the sample head.

[0147] Among them, the sample vibration zone parameters refer to the vibration zone parameters used to train the adjustable interval prediction model to be trained.

[0148] The sample unit output range refers to the unit output range used to train the adjustable range prediction model to be trained.

[0149] Among them, the sample prediction probability refers to the likelihood that the adjustable interval prediction model to be trained will correctly determine the preset adjustable interval.

[0150] The adjustable interval refers to the predicted value corresponding to the adjustable interval output by the adjustable interval prediction model to be trained.

[0151] The actual adjustable range refers to the true value corresponding to the adjustable range.

[0152] For example, the server identifies the sample control units of the sample power plant and obtains the first unit parameters (including unit hardware parameters, operating condition parameters, and vibration characteristic parameters) of the sample control units, and obtains the second unit parameters of the candidate control units in the sample power plant. Then, based on the first and second unit parameters, the server determines the similarity between the sample control units and the candidate control units. Next, the server selects control units from the candidate control units whose similarity is greater than a preset similarity as the target control units of the sample power plant. Then, the server obtains the first vibration zone parameters and the first unit output range of the sample control units under the sample head, as well as the second vibration zone parameters and the second unit output range of the target control units under the sample head. Finally, the server uses both the first and second vibration zone parameters as the sample vibration zone parameters of the sample control units under the sample head, and uses the first unit output range and the second unit output range as the sample vibration zone parameters. The output range is used as the sample unit output range of the sample control unit under the sample head. Next, the server inputs the sample vibration zone parameters and the sample unit output range into the adjustable range prediction model to be trained, obtaining the sample prediction probability of the sample control unit under each preset adjustable range. Then, the server selects the preset adjustable range with the highest sample prediction probability from each preset adjustable range as the predicted adjustable range of the sample control unit under the sample head. Next, the server obtains the actual adjustable range of the sample control unit under the sample head, obtains the loss value based on the difference between the predicted and actual adjustable ranges, and adjusts the model parameters of the adjustable range prediction model to be trained based on the loss value. Then, the server retrains the adjustable range prediction model with adjusted model parameters until the loss value obtained by the trained adjustable range prediction model is less than the loss value threshold, at which point training stops, and the trained adjustable range prediction model is taken as the completed adjustable range prediction model.

[0153] In this embodiment, by fusing the vibration zone parameters and output range of sample joint control units and similar target joint control units under the same head, the representativeness and richness of the training data are expanded. Furthermore, by continuously iterating and optimizing the model through the difference between the prediction and the actual adjustable range, the model can capture the operating characteristics of a single unit and absorb the common patterns of similar units, which is beneficial to improving the training quality of the adjustable range prediction model.

[0154] In one exemplary embodiment, such as Figure 3 As shown, another risk management method based on the dynamic determination of vibration zones of multiple units is provided. Taking the application of this method to a server as an example, the specific steps include:

[0155] Step S301: Obtain the current head information, current running time information, and current flow information of the power plant's interconnected units under the current water head; use the current head information as the main data, and the current running time information and current flow information as auxiliary data, and input them into multiple trained vibration zone parameter prediction models to obtain multiple predicted vibration zone parameters.

[0156] Step S302: Based on the model weights of each trained vibration zone parameter prediction model, multiple predicted vibration zone parameters are fused to obtain the vibration zone parameters.

[0157] Step S303: Input the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0158] Step S304: Select the preset adjustable range with the highest predicted probability from each preset adjustable range, and use it as the adjustable range of the joint control unit under the current head.

[0159] Step S305: Based on the vibration zone parameters, the adjustable interval is divided to obtain the adjustable sub-intervals corresponding to the control unit.

[0160] Step S306: Combine the adjustable sub-intervals corresponding to each control unit to obtain multiple combined adjustable sub-intervals.

[0161] Step S307: Merge multiple combined adjustable sub-intervals to obtain the integrated adjustable interval of the joint control unit under the current head.

[0162] Step S308: Determine the combined vibration zone of the power plant based on the fusion adjustable range.

[0163] Step S309: When a change in the current water head is detected, based on the changed water head information of the corresponding unit, the correspondence between the water head information and the vibration zone parameters is queried to obtain the target vibration zone parameters corresponding to the changed water head information.

[0164] Step S310: Obtain the first initial weight corresponding to the target vibration zone parameters and the second initial weight corresponding to the vibration zone parameters.

[0165] Step S311: Based on the current water head and the changed water head, determine the change in water head. Based on the change in water head, update the first initial weight and the second initial weight to obtain the first updated weight corresponding to the target vibration zone parameters and the second updated weight corresponding to the vibration zone parameters.

[0166] Step S312: Based on the first updated weight, obtain the first weight corresponding to the target vibration zone parameter, and based on the second updated weight, obtain the second weight corresponding to the vibration zone parameter.

[0167] Step S313: Based on the first weight and the second weight, the target vibration zone parameters and the vibration zone parameters are fused to obtain the updated vibration zone parameters.

[0168] Step S314: The updated vibration zone parameters are used as the new vibration zone parameters, and the process jumps to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range. This continues until no change in the current head is detected. Then, based on the last obtained joint vibration zone, the risk handling instruction corresponding to the power plant is determined, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0169] In the aforementioned risk management method based on the dynamic determination of the joint vibration zone of multiple units, when managing the risks of a power plant, a robust and adjustable fusion range is obtained by using vibration and output data under the current head as a basis, followed by model prediction and fusion processing. The joint vibration zone determined accordingly can accurately reflect the safety boundary of the units. At the same time, by monitoring changes in head in real time and dynamically updating parameters and iteratively optimizing the joint vibration zone, it is ensured that the risk assessment always adapts to the latest operating conditions. Finally, risk management instructions are generated based on the joint vibration zone that best fits the current reality. This method avoids the lag error caused by fixed parameters and reduces the deviation of single data or models through multi-stage verification, enabling risk management to accurately match the actual safety requirements of the units and improving the accuracy of power plant risk management. Moreover, the entire process does not require manual intervention, avoiding the subjective factors and errors that can easily occur with manual experience-based processing, which leads to low accuracy in power plant risk management, further improving the accuracy of power plant risk management.

[0170] In one exemplary embodiment, to more clearly illustrate the risk handling method based on the dynamic determination of the joint vibration zone of multiple units provided in this application, the following specific embodiment will be used to describe the risk handling method based on the dynamic determination of the joint vibration zone of multiple units. In one embodiment, this application also provides another risk handling method based on the dynamic determination of the joint vibration zone of multiple units. Specifically, it includes the following:

[0171] Step 1: Obtain individual unit parameters: Collect the adjustable range (e.g., (C,D), (E,F)) and vibration zone parameters of each unit under the current head;

[0172] Step 2: Generate a candidate set of jointly adjustable ranges: Arrange and combine the adjustable ranges of all jointly controlled units:

[0173] If there are n generating units, each generating unit takes an adjustable sub-interval, and calculates the combination result of adding the sub-intervals pairwise (e.g., if generating unit 1 takes (C,D) and generating unit 2 takes (E,F), then the combination is (C+E,D+F)).

[0174] Step 3: Merge candidate intervals: Merge all combination results (merge overlapping or adjacent intervals into continuous intervals) to obtain the plant-wide joint adjustable range;

[0175] Step 4: Determine the joint vibration zone: Calculate the continuous interval outside the joint adjustable range, which is the plant-wide joint vibration zone (non-adjustable risk area).

[0176] Step 5, Real-time Update and Verification: When the water head changes, the vibration zone of a single unit is updated by linear interpolation based on the vibration zone parameters under 10 preset water heads. Steps 2-4 are repeated to dynamically update the joint vibration zone and send it to the monitoring system for load distribution constraints.

[0177] In the above embodiments, when performing risk management for power plants, a robust and adjustable fusion range is obtained based on vibration and output data under the current head through model prediction and fusion processing. The combined vibration zone determined accordingly can accurately reflect the safety boundary of the unit. At the same time, by monitoring head changes in real time and dynamically updating parameters and iteratively optimizing the combined vibration zone, it is ensured that the risk assessment is always adapted to the latest operating conditions. Finally, risk management instructions are generated based on the combined vibration zone that best fits the current reality. This avoids the lag error caused by fixed parameters and reduces the deviation of single data or models through multi-stage verification, so that risk management can accurately match the actual safety requirements of the unit, which is conducive to improving the accuracy of power plant risk management. Moreover, the entire process does not require human intervention, avoiding the subjective factors and errors that are prone to occur when using manual experience, which leads to low accuracy in power plant risk management, further improving the accuracy of power plant risk management.

[0178] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0179] Based on the same inventive concept, this application also provides a risk management device for implementing the risk management method based on the dynamic determination of the joint vibration zone of multiple units as described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the risk management device based on the dynamic determination of the joint vibration zone of multiple units provided below can be found in the limitations of the risk management method based on the dynamic determination of the joint vibration zone of multiple units described above, and will not be repeated here.

[0180] In one exemplary embodiment, such as Figure 4 As shown, a risk management device based on the dynamic determination of vibration zones of multiple units is provided, including: a data acquisition module 401, a model prediction module 402, an interval screening module 403, an interval fusion module 404, a vibration zone determination module 405, a parameter update module 406, and a parameter processing module 407, wherein:

[0181] The data acquisition module 401 is used to acquire the vibration zone parameters and output range of the power plant's interconnected units under the current water head.

[0182] The model prediction module 402 is used to input the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range.

[0183] The interval filtering module 403 is used to filter out the preset adjustable interval with the highest predicted probability from each preset adjustable interval, and use it as the adjustable interval of the joint control unit under the current water head.

[0184] The interval fusion module 404 is used to perform fusion processing on the adjustable intervals to obtain the fused adjustable interval of the joint control unit under the current head.

[0185] The vibration zone determination module 405 is used to determine the combined vibration zone of the power plant based on the integrated adjustable range.

[0186] The parameter update module 406 is used to update the vibration zone parameters according to the changed water head of the control unit when a change in the current water head is detected, so as to obtain the updated vibration zone parameters.

[0187] The parameter processing module 407 is used to take the updated vibration zone parameters as the new vibration zone parameters, and jump to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable range prediction model to obtain the prediction probability of the joint control unit under each preset adjustable range. Until no change in the current head is detected, the risk handling instruction corresponding to the power plant is determined according to the last obtained joint vibration zone, and the corresponding risk handling is carried out on the power plant according to the risk handling instruction.

[0188] In an exemplary embodiment, the interval fusion module 404 is further configured to divide the adjustable interval according to the vibration zone parameters to obtain the adjustable sub-intervals corresponding to the joint control unit; combine the adjustable sub-intervals corresponding to each joint control unit to obtain multiple combined adjustable sub-intervals; and merge the multiple combined adjustable sub-intervals to obtain the fused adjustable interval of the joint control unit under the current head.

[0189] In an exemplary embodiment, the data acquisition module 401 is further configured to acquire the current head information, current running time information, and current flow information of the power plant's interconnected units under the current water head; use the current head information as the primary data and the current running time information and current flow information as auxiliary data, and input them into multiple trained vibration zone parameter prediction models to obtain multiple predicted vibration zone parameters; and perform fusion processing on the multiple predicted vibration zone parameters according to the model weights of each trained vibration zone parameter prediction model to obtain the vibration zone parameters.

[0190] In an exemplary embodiment, the parameter update module 406 is further configured to query the correspondence between the head information and the vibration zone parameters based on the changed head information corresponding to the joint control unit, and obtain the target vibration zone parameters corresponding to the changed head information; obtain the first weight corresponding to the target vibration zone parameters and the second weight corresponding to the vibration zone parameters; and perform fusion processing on the target vibration zone parameters and the vibration zone parameters according to the first weight and the second weight to obtain the updated vibration zone parameters.

[0191] In an exemplary embodiment, the parameter update module 406 is further configured to obtain a first initial weight corresponding to the target vibration zone parameter and a second initial weight corresponding to the vibration zone parameter; determine the head change based on the current head and the changed head; update the first initial weight and the second initial weight based on the head change to obtain a first updated weight corresponding to the target vibration zone parameter and a second updated weight corresponding to the vibration zone parameter; obtain a first weight corresponding to the target vibration zone parameter based on the first updated weight, and obtain a second weight corresponding to the vibration zone parameter based on the second updated weight.

[0192] In an exemplary embodiment, the risk management device based on the dynamic determination of the joint vibration zone of multiple units further includes a model training module, used to obtain the first vibration zone parameters and the first unit output range of the sample joint control unit of the sample power plant under the sample head, and the second vibration zone parameters and the second unit output range of the target joint control unit of the sample power plant under the sample head; the target joint control unit is used to represent the joint control unit in the sample power plant with a similarity greater than a preset similarity to the sample joint control unit; based on the first vibration zone parameters and the second vibration zone parameters, the sample vibration zone parameters of the sample joint control unit under the sample head are obtained, and the second vibration zone parameters and the second unit output range of the target joint control unit are obtained based on the first unit output range and the second unit output range. The output range of the two units is obtained, and the output range of the sample unit under the sample head is obtained. The sample vibration zone parameters and the output range of the sample unit are input into the adjustable interval prediction model to be trained to obtain the sample prediction probability of the sample unit under each preset adjustable interval. From each preset adjustable interval, the preset adjustable interval with the highest sample prediction probability is selected as the predicted adjustable interval of the sample unit under the sample head. The actual adjustable interval of the sample unit under the sample head is obtained. Based on the difference between the predicted adjustable interval and the actual adjustable interval, the adjustable interval prediction model to be trained is iteratively trained to obtain the trained adjustable interval prediction model.

[0193] The various modules in the aforementioned risk management device based on the dynamic determination of vibration zones of multiple units can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0194] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores data such as vibration zone parameters and unit output range. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a risk management method based on the dynamic determination of the vibration zone of multiple units.

[0195] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0196] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0197] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0198] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0199] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0200] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0201] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A risk processing method based on multi-unit joint vibration zone dynamic determination, characterized in that, The method comprises: obtaining vibration zone parameters and unit output range of a joint control unit of a power plant under a current water head; inputting the vibration zone parameters and the unit output range into a trained adjustable interval prediction model to obtain prediction probabilities of the joint control unit under each preset adjustable interval; from the preset adjustable intervals, selecting a preset adjustable interval with the maximum prediction probability as an adjustable interval of the joint control unit under the current water head; performing fusion processing on the adjustable interval to obtain a fusion adjustable interval of the joint control unit under the current water head; determining a joint vibration zone of the power plant according to the fusion adjustable interval; in a case where a change in the current water head is detected, updating the vibration zone parameters according to a changed water head corresponding to the joint control unit to obtain updated vibration zone parameters; taking the updated vibration zone parameters as new vibration zone parameters, and jumping to the step of inputting the vibration zone parameters and the unit output range into the trained adjustable interval prediction model to obtain the prediction probabilities of the joint control unit under each preset adjustable interval until no change in the current water head is detected, then determining a risk processing instruction corresponding to the power plant according to the last determined joint vibration zone, and performing corresponding risk processing on the power plant according to the risk processing instruction.

2. The method of claim 1, wherein, The fusion processing on the adjustable interval to obtain the fusion adjustable interval of the joint control unit under the current water head comprises: performing division processing on the adjustable interval according to the vibration zone parameters to obtain adjustable subintervals corresponding to the joint control unit; respectively combining the adjustable subintervals corresponding to the joint control unit to obtain a plurality of combined adjustable subintervals; performing interval merging on the plurality of combined adjustable subintervals to obtain the fusion adjustable interval of the joint control unit under the current water head.

3. The method of claim 1, wherein, The obtaining of the vibration zone parameters and the unit output range of the joint control unit of the power plant under the current water head comprises: obtaining current water head information, current running time information and current flow information of the joint control unit of the power plant under the current water head; inputting the current water head information as main data and the current running time information and the current flow information as auxiliary data into a plurality of trained vibration zone parameter prediction models to obtain a plurality of predicted vibration zone parameters; performing fusion processing on the plurality of predicted vibration zone parameters according to model weights of each trained vibration zone parameter prediction model to obtain the vibration zone parameters.

4. The method of claim 1, wherein, The updating of the vibration zone parameters according to the changed water head corresponding to the joint control unit to obtain the updated vibration zone parameters comprises: querying a corresponding relationship between water head information and vibration zone parameters based on changed water head information of the changed water head corresponding to the joint control unit to obtain target vibration zone parameters corresponding to the changed water head information; obtaining a first weight corresponding to the target vibration zone parameters and a second weight corresponding to the vibration zone parameters; The target vibration zone parameter and the vibration zone parameter are fused according to the first weight and the second weight, to obtain the updated vibration zone parameter.

5. The method of claim 4, wherein, The first weight corresponding to the target vibration zone parameter and the second weight corresponding to the vibration zone parameter are obtained by: The first initial weight corresponding to the target vibration zone parameter and the second initial weight corresponding to the vibration zone parameter are obtained; According to the current water head and the changed water head, a water head change amount is determined, and the first initial weight and the second initial weight are updated according to the water head change amount, to obtain the first updated weight corresponding to the target vibration zone parameter and the second updated weight corresponding to the vibration zone parameter; The first weight corresponding to the target vibration zone parameter is obtained based on the first updated weight, and the second weight corresponding to the vibration zone parameter is obtained based on the second updated weight.

6. The method according to any one of claims 1 to 5, characterized in that, The trained adjustable interval prediction model is trained by the following method: Obtain the first vibration zone parameter and the first unit output range of the sample unit in the sample power plant under the sample water head, and the second vibration zone parameter and the second unit output range of the target unit in the sample power plant under the sample water head; the target unit is used to represent the unit in the sample power plant, and the similarity between the sample unit and the target unit is greater than the preset similarity; Based on the first vibration zone parameter and the second vibration zone parameter, the sample vibration zone parameter of the sample unit under the sample water head is obtained, and based on the first unit output range and the second unit output range, the sample unit output range of the sample unit under the sample water head is obtained; The sample vibration zone parameter and the sample unit output range are input into the adjustable interval prediction model to be trained, to obtain the sample prediction probability of the sample unit under each preset adjustable interval; From each preset adjustable interval, the preset adjustable interval with the maximum sample prediction probability is selected as the predicted adjustable interval of the sample unit under the sample water head; Obtain the actual adjustable interval of the sample unit under the sample water head, and iteratively train the adjustable interval prediction model to be trained according to the difference between the predicted adjustable interval and the actual adjustable interval, to obtain the trained adjustable interval prediction model.

7. A risk processing device based on multi-unit joint vibration zone dynamic determination, characterized in that, The device comprises: The data acquisition module is configured to acquire the vibration zone parameter and the unit output range of the unit in the power plant under the current water head; The model prediction module is configured to input the vibration zone parameter and the unit output range into the trained adjustable interval prediction model to obtain the prediction probability of the unit under each preset adjustable interval; The interval screening module is configured to select the preset adjustable interval with the maximum prediction probability from each preset adjustable interval as the adjustable interval of the unit under the current water head; The interval fusion module is configured to fuse the adjustable interval to obtain the fused adjustable interval of the unit under the current water head; A vibration region determination module is configured to determine a joint vibration region of the power plant according to the fused adjustable interval; A parameter updating module is configured to, in a case where it is detected that the current water head changes, update the vibration region parameter according to a changed water head corresponding to the joint control unit, to obtain an updated vibration region parameter; A risk processing module is configured to take the updated vibration region parameter as a new vibration region parameter, and jump to the step of inputting the vibration region parameter and the unit output range into the trained adjustable interval prediction model to obtain the prediction probability of the joint control unit in each preset adjustable interval until it is detected that the current water head does not change, and then determine a risk processing instruction corresponding to the power plant according to the last obtained joint vibration region, and perform corresponding risk processing on the power plant according to the risk processing instruction.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images