Method for vibration control of a power equipment of the pylon type and vibration control device for a power equipment of the pylon type

Abstract

The application discloses a vibration control method and device for a column type power equipment, and relates to the field of power equipment, which can reduce damage of the power equipment caused by earthquakes. The vibration control method for the column type power equipment comprises the following steps: acquiring ground acceleration, support structure strain and displacement of a position where the column type power equipment is located; inputting the ground acceleration into a preset physical information neural network model to obtain bottom stress and top acceleration of the column type power equipment; checking the bottom stress and the top acceleration through the support structure strain and the displacement to obtain checked stress prediction values and acceleration prediction values; determining control parameters of a vibration control module through the stress prediction values and the acceleration prediction values, and starting the vibration control module based on the control parameters to generate corresponding damping, and the damping generated by the vibration control module is consumed to respond to power of the column type power equipment.

Description

Technical Field

[0001] This application relates to the field of power equipment, and in particular to a vibration control method and a vibration control device for support-type power equipment. Background Technology

[0002] Current structural performance monitoring and early warning solutions require setting up monitoring nodes at key parts of the structure to collect response data from these key parts, and then using this data to determine the structure's performance status and issue early warnings. For example: Patent application CN119845361A discloses an intelligent system and method for monitoring and early warning deformation of steel space frame structures. This technical solution employs distributed monitoring nodes, flexibly deployed at key locations within the steel space frame structure, to collect deformation data in real time. Combined with advanced data acquisition and transmission equipment, it ensures efficient and accurate data transmission. The core data processing and analysis system utilizes deep learning algorithms such as convolutional neural networks to conduct in-depth analysis of the deformation data, identifying complex deformation patterns and potential risks.

[0003] Patent CN119442040B discloses a bridge structural health monitoring system based on intelligent sensor networks and deep learning. This technical solution, based on intelligent sensor networks and deep learning, includes: a data acquisition module for setting up multiple collection points on the bridge to acquire bridge structural monitoring data; a data monitoring module for matching and relating the bridge structural monitoring data, setting corresponding anomaly indicators, and acquiring anomaly-related data corresponding to the anomaly indicators; and a modal anomaly analysis module for identifying anomaly-related data, determining anomaly labels for the anomaly-related data, and clustering according to the anomaly labels to obtain anomaly classification results.

[0004] In the first approach, data acquisition points need to be placed at critical performance nodes of the structure. However, for pillar-type power facilities, their structural weak points (critical performance nodes) are usually located in areas where it is difficult to place measurement points. For example, for surge arresters, their critical performance lies in the stress at the root of the insulating porcelain bushing and the acceleration at the top; it is difficult to place strain gauges at the root of the bushing, and it is also difficult to place acceleration sensors at the top of the bushing. In the second approach mentioned above, the intelligent structural monitoring solution only includes two modules: monitoring and early warning. Although it can monitor equipment performance in real time and detect equipment damage when applied to power equipment, it cannot fundamentally solve the problem of equipment damage caused by excessive dynamic response of power equipment. Summary of the Invention

[0005] This application provides a vibration control method and a vibration control device for support-type power equipment, which can absorb the dynamic response of power equipment caused by earthquakes and reduce the damage to power equipment.

[0006] In a first aspect, this application provides a vibration control method for support-type power equipment, comprising: Acquire multi-source data on the location of support-type power equipment, including ground acceleration, strain of the supporting structure, and displacement; The ground acceleration is input into a preset physical information neural network model to obtain the bottom stress and top acceleration; The bottom stress and top acceleration are verified by the strain and displacement of the supporting structure to obtain the verified stress prediction value and acceleration prediction value. The control parameters of the vibration control module are determined by the predicted stress and acceleration values, and the vibration control module is started based on the control parameters to generate damping corresponding to the control parameters. The damping generated by the vibration control module consumes the dynamic response of the support-type power equipment.

[0007] In the vibration control method for support-type power equipment described above, data is collected from the support-type power equipment to obtain multi-source data on the location of the power equipment. This multi-source data is used to predict the stress and acceleration experienced by the power equipment, enabling real-time monitoring and facilitating the timely detection of any abnormalities. Furthermore, control parameters are calculated using the predicted stress and acceleration values. A damping force is generated by the vibration control module to absorb the dynamic response of the electronic equipment during an earthquake, thus addressing the problem of equipment damage caused by excessive dynamic response. This method not only provides timely monitoring of the equipment but also ensures the safety of the power equipment under seismic loads and extends its service life.

[0008] Secondly, this application provides a vibration control device for support-type power equipment, comprising: Monitoring module, vibration control module; The monitoring module is used to detect the acceleration and displacement of support-type power equipment; The vibration control module is used to determine control parameters based on the acceleration and displacement obtained by the monitoring module, and generate damping corresponding to the control parameters to consume the kinetic energy of the support-type power equipment. The monitoring module includes a broadband seismograph, an accelerometer, a strain gauge, and a displacement meter; The broadband seismograph and accelerometer are installed on the ground near the support structure of the power equipment to detect the triaxial and horizontal acceleration of the ground. The strain gauge and displacement meter are installed on the support structure of the power equipment to detect the strain and displacement of the support structure. The vibration control module is installed between the support structure of the pillar-type power equipment and the ground.

[0009] The vibration control module includes a magnetorheological damper and coil-type electrically controlled positive and negative stiffness springs. By adjusting the excitation coil current of the magnetorheological damper and the energized coil current of the coil-type electrically controlled positive and negative stiffness springs through control parameters, the magnetorheological damper and the coil-type damper generate corresponding damping, and the electrically controlled positive and negative stiffness springs generate corresponding stiffness.

[0010] Thirdly, this application also provides a vibration control device for support-type power equipment, comprising: The data acquisition module is used to acquire multi-source data on the location of the support structure power equipment, including ground acceleration, strain of the support structure, and displacement. The structural prediction module is used to input the ground acceleration into a preset physical information neural network model to obtain the bottom stress at the first performance weak point and the top acceleration at the second performance weak point of the support-type power equipment. The verification module is used to verify the bottom stress and top acceleration by means of the strain and displacement of the support structure, and to obtain the verified stress prediction value and acceleration prediction value. The control module is used to determine the control parameters of the vibration control module through the predicted stress value and the predicted acceleration value, and to start the vibration control module based on the control parameters to generate damping corresponding to the control parameters. The damping generated by the vibration control module consumes the dynamic response of the support-type power equipment.

[0011] Fourthly, this application provides an electronic device including a memory and one or more processors. The memory stores one or more computer programs, each including instructions that, when executed by the processor, cause the electronic device to perform a vibration control method for support-type power equipment as described in the first aspect.

[0012] Fifthly, this application provides a computer-readable storage medium storing instructions that, when executed on an electronic device, cause the electronic device to perform a vibration control method for support-type power equipment as described in the first aspect.

[0013] Sixthly, this application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the vibration control method for pillar-type power equipment as described in the first aspect.

[0014] It is understood that the beneficial effects achieved by the vibration control device, electronic device, computer-readable storage medium, and computer program product for the above-mentioned support-type power equipment can be referred to the beneficial effects in the first aspect, and will not be repeated here. Attached Figure Description

[0015] Figure 1 A schematic flowchart illustrating the vibration control method for support-type power equipment provided in this application embodiment; Figure 2 This is a structural schematic diagram of a pillar-type power equipment provided in an embodiment of this application; Figure 3 A schematic diagram of the vibration control module in the vibration control method for support-type power equipment provided in this application embodiment; Figure 4 A schematic diagram of the magnetorheological damper in the vibration control module provided in this application embodiment; Figure 5 A schematic diagram of the structure of the coil-type electrically controlled positive and negative stiffness springs in the vibration control module provided in the embodiments of this application; Figure 6 A schematic diagram of the structure of the vibration control device for support-type power equipment provided in the embodiments of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0016] To facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. For example, "first chip" and "second chip" are only used to distinguish different chips and do not limit their order. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" do not necessarily imply that they are different. It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. In the embodiments of this application, "at least one" means one or more, and "more than one" means two or more.

[0017] It should be noted that "at the time of..." in the embodiments of this application can be either at the instant when a certain situation occurs, or for a period of time after the occurrence of a certain situation. The embodiments of this application do not make specific limitations on this.

[0018] The implementation of this embodiment will now be described in detail with reference to the accompanying drawings.

[0019] This embodiment provides a vibration control method for support-type power equipment. For example, this vibration control method for support-type power equipment can be applied to various electronic devices such as computers (PCs), tablets, virtual reality / augmented reality devices, wearable devices, industrial computers, and vehicle-mounted systems; it can also be applied to servers, cloud computing, server clusters, etc. This embodiment does not impose any special limitations on it.

[0020] Figure 1 A schematic flowchart of the vibration control method for support-type power equipment provided in an embodiment of this application is shown.

[0021] like Figure 1 As shown, the vibration control method for this type of support-type power equipment may include the following steps: Step 101: Obtain multi-source data on the location of the support-type power equipment, including ground acceleration, strain of the support structure, and displacement.

[0022] Ground acceleration includes triaxial acceleration and horizontal acceleration. In this embodiment, a broadband seismograph and an acceleration sensor are installed on the ground near the support structure of the power equipment, strain gauges are installed on the support structure of the power equipment, and displacement gauges are installed below the support structure. The triaxial acceleration of the ground near the power equipment is obtained by the broadband seismograph, the horizontal acceleration of the power equipment is obtained by the acceleration sensor, the strain of the support structure is collected by the strain gauges, and the displacement of the support structure is obtained by the displacement gauges.

[0023] Broadband seismometers are deployed at seismic monitoring points near pillar-type power facilities to monitor ground motion acceleration. Preferably, a sampling rate of 100Hz-200Hz is used to collect ground motion acceleration in the X, Y, and Z directions, with a range covering ±2g (suitable for moderate to strong earthquake scenarios) and a data accuracy of 0.001g. It can capture the low-frequency long-period components and high-frequency pulse components of ground motion.

[0024] Accelerometers are deployed on the ground adjacent to the supporting power facilities to monitor the ground acceleration near the facilities. For example, a piezoelectric accelerometer with a sampling rate of 50Hz-100Hz, a range of ±5g, and a resolution of 0.0001g is used. It is fixed to the ground adjacent to the power equipment and ≤1m from the edge of the equipment foundation to collect horizontal ground acceleration data, which is then compared with broadband seismograph data to form a near-field to far-field ground motion comparison.

[0025] The support structure for column-type electronic equipment can be a reinforced concrete structure or a steel frame structure. For steel frame support structures, they can be directly placed at the steel supports. For reinforced concrete support structures, they can be embedded in the reinforcing bars inside the pier for monitoring the strain of the steel supports (reinforcing bars).

[0026] Step 102: Input the ground acceleration into the preset physical information neural network model to obtain the bottom stress at the first weak point and the top acceleration at the second weak point of the support-type power equipment.

[0027] Bottom stress refers to the stress at a pre-defined performance weakness (first performance weakness) of the support-type electrical equipment, which, for example, may be the bottom of the electrical equipment. Top acceleration refers to the acceleration at another pre-defined performance weakness (i.e., second performance weakness) of the support-type electrical equipment, which, for example, may be the top of the electrical equipment.

[0028] It is understood that the first and second performance weaknesses can be other locations on the power equipment, and this implementation does not impose any special limitations on them.

[0029] The physical information neural network model is a hybrid neural network architecture consisting of an LSTM and a physical constraint layer. The input layer includes four input features: detected triaxial acceleration and horizontal acceleration. The output layer provides two output metrics: bottom stress and top acceleration. The hidden layer comprises one LSTM layer and multiple fully connected neural network layers; the specific number of fully connected neural network layers should be determined based on the actual model training. The loss function uses a physical constraint function, with the constraint terms determined according to material mechanics and structural mechanics to ensure that the prediction results conform to physical laws and avoid unreasonable outputs caused by neural network overfitting.

[0030] A physical information neural network model is obtained by training the above model structure. The training process is as follows: Based on more than 100 sets of historical earthquake records, simulation data of the equipment is obtained through finite element analysis, including the data types of the input and output layers of the aforementioned model structure (input layer: 4 input features, output layer: 2 output indices), which serve as the model training dataset. The structural dynamics theoretical solution of the power equipment is used as the physical constraint function, and the errors between the predicted values ​​and the physical constraint function, and between the predicted values ​​and the true values ​​in the training data are calculated and used together as the loss function for model training. The dataset is divided into training, validation, and test sets in a 7:2:1 ratio. The model is trained using the training set data, and iterative training is performed using the Adam optimizer to continuously update the model's hyperparameters. After each hyperparameter update, the loss function is calculated using the validation set data, which serves as the evaluation criterion for the model's hyperparameters. When the root mean square value of the loss function on the validation set is ≤5%, model training stops, and the hyperparameters at this point are considered to be the optimal hyperparameters for the "LSTM + physical constraint layer" hybrid neural network model.

[0031] The trained model is used as a physical information neural network model, and then multi-source data of support-type power equipment is processed in real time based on this model. Specifically, four input features are input in real time: triaxial acceleration and horizontal acceleration. The model will automatically run calculations and output the aforementioned two output indicators, bottom stress and top acceleration, as preliminary prediction results.

[0032] Step 103: Verify the bottom stress and top acceleration by measuring the strain and displacement of the supporting structure, and obtain the verified predicted stress and acceleration values.

[0033] Specifically, the elastic modulus of the support structure of the pillar-type power equipment is obtained, and the stress calculation value is obtained by converting the strain of the support structure with the elastic modulus. If the deviation between the stress calculation value and the bottom stress output by the physical information neural network model is greater than a first preset threshold, the bottom stress calculation value and the bottom stress are weighted and fused to obtain a verified stress prediction value. If the deviation between the top acceleration and the displacement obtained by the displacement gauge exceeds a second preset threshold, the top acceleration is corrected to obtain an acceleration prediction value.

[0034] The elastic modulus of the supporting structure can be determined based on its physical parameters, such as material parameters and geometric parameters. For example, if the deviation between the strain of the supporting structure acquired by the strain gauge, multiplied by the elastic modulus of the structural material, and the bottom stress of the equipment box is greater than 8%, and the bottom stress predicted by the neural network is greater than 8%, then a weighted fusion correction is used. If the displacement of the vibration control module acquired by the displacement gauge exceeds the static normal range (±5mm), then the predicted value of the top acceleration is corrected. The first preset threshold and the second preset threshold are determined according to the actual situation, and this embodiment is not limited to this.

[0035] Step 104: Determine the control parameters of the vibration control module based on the predicted stress and acceleration values, and start the vibration control module based on the control parameters to generate damping corresponding to the control parameters. The damping generated by the vibration control module consumes the dynamic response of the support-type power equipment.

[0036] This implementation also includes: determining whether there are structural performance deficiencies in the support-type power equipment using predicted stress and acceleration values; issuing an early warning if structural performance deficiencies are found in the support-type power equipment; and activating the vibration control module in the event of structural performance deficiencies.

[0037] The structural performance level is determined based on the predicted stress value and the predicted acceleration value. The structural performance level is divided into undamaged, potential damage risk, and damaged. When the structural performance level is potential damage risk or damaged, it is determined that the support-type power equipment has insufficient structural performance.

[0038] The relationship between the predicted stress and acceleration values ​​and their respective threshold ranges is used to comprehensively determine whether structural performance has deteriorated to a threshold. The thresholds for predicted stress and acceleration values ​​can be set separately based on the actual situation of performance weaknesses. For example, if one parameter (out of two) is greater than 80% of the threshold and the other is less than 80%, it is considered a "potential risk of failure"; if either corrective predicted response (out of two) is greater than 100% of the threshold, it is considered "already failed"; if both corrective predicted responses (out of two) are greater than 90% of the threshold but less than 100%, it is considered "already failed"; if both corrective predicted responses (out of two) are less than 80% of the threshold, it is considered "not failed". If structural performance is determined to be "potential risk of failure" or "already failed", the structural performance is considered insufficient, and the early warning module is activated; otherwise, it is not activated.

[0039] The early warning module mainly includes local audible and visual alarms and an IoT control center. The local audible and visual alarms are deployed around pillar-type power facilities. When the performance judgment submodule in the intelligent decision-making module determines that the performance of the power facility has deteriorated to a threshold, it will issue an audible and visual alarm. The IoT control center connects to the power facility's central control center, reports the performance status of the power equipment, and automatically cuts off power.

[0040] Similarly, when structural performance is insufficient, the vibration control module is activated for control. Specifically, when the structural performance of support-type power equipment is insufficient, the state equation and quadratic performance evaluation function between the predicted stress value, predicted acceleration value and control parameters are obtained; the linear quadratic optimal control algorithm is used to solve the state equation and determine the optimal parameters that minimize the quadratic performance evaluation function.

[0041] In this embodiment, the vibration control module includes a magnetorheological damper and a coil-type electrically controlled positive and negative stiffness spring. The control parameters include the excitation coil current of the magnetorheological damper and the energized coil current of the coil-type electrically controlled positive and negative stiffness spring.

[0042] Linear quadratic optimal control is an optimal control method for linear systems. Its core is to find a control input sequence that minimizes a predefined quadratic performance evaluation function while satisfying the linear dynamic constraints of the system.

[0043] The current I2 of the spring's energized coil includes its direction. Control parameters include the excitation coil current I1 of the magnetorheological damper and the energized coil current I2 of the coil-type electrically controlled positive and negative stiffness springs. Additionally, they include the damping coefficient C of the magnetorheological damper and the stiffness K (including direction) of the coil-type electrically controlled positive and negative stiffness springs. The optimal parameters of the vibration control module are calculated using a linear quadratic optimal control method, with the following steps: Step 1: Define the state equation of the device and determine the quadratic performance evaluation function.

[0044] Step 2: Linear quadratic optimal control theory, under the condition of ensuring asymptotic stability of the dynamic system, aims to minimize energy to achieve vibration control design. This requires solving for the optimal control force that minimizes the quadratic performance evaluation function. The solution for the optimal control force is the positive definite solution of the Riccati equation.

[0045] Step 3: Using the optimal control force obtained from the solution and the displacement of the vibration control module measured by the displacement gauge (8), calculate the optimal parameters required for the vibration control module based on the force-displacement relationship of the device.

[0046] Specifically, the early warning methods and vibration control methods are shown in Table 1: Table 1: Early Warning and Vibration Control Methods Corresponding to Different Structural Performance Levels

[0047] After determining the control parameters of the vibration control module, the control commands for the spring and damper can be executed via control commands, including the following procedures: Command transmission: The optimal parameters are transmitted to the controller of the vibration control module via the MQTT-SN encryption protocol. CRC check is used during transmission to ensure command integrity.

[0048] Magnetorheological damper adjustment: The controller outputs current to the excitation coil (13) according to the value of I1: When the current increases, the magnetic field strength increases, the viscosity of the magnetorheological fluid (16) increases, and the damping coefficient C increases linearly.

[0049] Coil-type electronically controlled positive and negative stiffness spring adjustment: The controller outputs current to three energized coils according to the value and direction of I2 (18): If I2 is positive, the current of the middle coil and the two side coils is in the same direction, which is negative stiffness; if I2 is negative, the current of the middle coil and the two side coils is opposite, which is positive stiffness; the magnitude of the current is proportional to the absolute value of the stiffness.

[0050] After the vibration control module is started, the monitoring module transmits the displacement data of the vibration control module to the intelligent decision module every 100ms. The linear quadratic optimal control theory is used to calculate the device parameters required by the vibration control module and determine the current required to adjust the parameters.

[0051] The functions of vibration control include: Direct protection of equipment safety: Vibration control measures can reduce stress at weak points, preventing cracks in the supporting structure and breakage at connection points; reduce the acceleration at the top of the equipment box, preventing the top structure (sensors, wiring terminals) from loosening or falling off; limit the displacement of vibration control devices, preventing excessive deformation of the vibration isolation supports from causing the equipment to tilt or overturn.

[0052] Ensuring the stability of the power grid system: Vibration control reduces the probability of equipment porcelain bushing breakage and insulation structure damage, preventing power grid faults such as line tripping and substation power outages caused by equipment short circuits; when vibration control cannot control the response of weak points (such as stress ≥ threshold), the early warning module promptly triggers power outage, disconnecting only the line where the faulty equipment is located, narrowing the power outage area, and achieving "precise power outage".

[0053] Improved seismic adaptability: Adjustable damping and positive and negative stiffness are adapted to short-period and long-period earthquakes, solving the problem of poor adaptability of traditional fixed-parameter vibration control.

[0054] Extending equipment lifespan: Vibration control reduces seismic fatigue damage to equipment, thus extending its seismic service life.

[0055] This embodiment also provides a vibration control device for support-type power equipment, used to implement the above-mentioned vibration control method for support-type power equipment. The device specifically includes: a monitoring module and a vibration control module. The monitoring module is used to detect the acceleration and displacement of the support structure of the power equipment; the vibration control module is used to determine control parameters based on the acceleration and displacement obtained by the monitoring module, and generate damping corresponding to the control parameters to consume the kinetic energy of the support structure of the power equipment; the monitoring module includes a broadband seismograph, an accelerometer, a strain gauge, and a displacement meter; the broadband seismograph and the accelerometer are installed on the ground near the support structure of the power equipment to detect the triaxial acceleration and horizontal acceleration of the ground, and the strain gauge and displacement meter are installed on the support structure of the power equipment to detect the strain and displacement of the support structure; the vibration control module is installed between the support structure of the power equipment and the ground.

[0056] The monitoring module mainly includes a broadband seismograph, strain gauges, displacement gauges, and accelerometers. The layout scheme of the monitoring module in the support-type power equipment is as follows: Figure 2 As shown. A typical pillar-type power equipment includes a top structure (1), an insulation structure (2), an equipment box (3), and a support structure (4), with the support structure (4) connected to the ground. After a vibration control module (5) is installed on the pillar-type power equipment, the support structure (4) is connected to the vibration control module (5), and the vibration control module (5) is connected to the ground.

[0057] A broadband seismograph (6) is placed at a seismic monitoring point near a pillar-type power facility to monitor ground motion acceleration. The preferred sampling rate is 100Hz-200Hz. It collects ground motion acceleration in the X, Y, and Z directions, with a range of ±2g (suitable for moderate to strong earthquake scenarios). The data accuracy is 0.001g, and it can capture the low-frequency long-period components and high-frequency pulse components of ground motion.

[0058] Strain gauges (9) are arranged on the support structure (4) of the power facility. For steel frame support structures, they can be directly arranged at the steel support. For reinforced concrete support structures, they can be embedded in the steel bars inside the support pier to monitor the strain of the steel support (steel bars). High-precision foil strain gauges with a range of ±3000με and a sensitivity coefficient of 2.0±1% are preferred. For steel support structures, surface bonding is adopted, and for reinforced concrete support structures, pre-embedded arrangement is adopted to collect the axial and bending strain of the support structure in real time.

[0059] Accelerometer (7) should be placed on the ground adjacent to the support-type power facilities to monitor the acceleration of the support-type power facilities near the ground; a piezoelectric accelerometer with a sampling rate of 50Hz-100Hz, a range of ±5g, and a resolution of 0.0001g should be used. It should be fixed on the ground adjacent to the power equipment and ≤1m away from the edge of the equipment foundation to collect the horizontal acceleration of the ground and form a “near field-far field” ground motion comparison with the broadband seismograph data.

[0060] A displacement gauge (8) is positioned between the transition layer (20) of the vibration control module (5) below the power facility support structure (4) and the support frame (22) on the ground to monitor the overall deformation of the vibration control module relative to the ground. It should be noted that... Figure 2 The specific location of the monitoring module should be determined according to the actual environment of the equipment. The figure is only one example. A laser displacement sensor is used, with a measurement range of 0-500mm, an accuracy of ±0.1mm, and a sampling rate of 10Hz-50Hz. It is fixed to the ground by a bracket (22). The laser emitter is aligned with the reflective target on the side of the vibration isolation conversion layer (20) to collect the horizontal displacement of the vibration control module in real time.

[0061] A schematic diagram of the vibration control module is shown below. Figure 3 As shown, it mainly includes: a seismic isolation transfer layer (20), seismic isolation bearings (21), a magnetorheological damper, and coil-type electrically controlled positive and negative stiffness springs. The seismic isolation transfer layer (20) is generally a reinforced concrete slab, connected to the power facility support structure at the top and to the ground at the bottom through the seismic isolation bearings (20). The seismic isolation bearings (20) mainly include laminated rubber bearings, lead-core rubber bearings, friction pendulum bearings, and elastic sliding plate bearings, which are arranged between the power equipment support structure and the ground to isolate seismic forces. The magnetorheological damper is connected between the seismic isolation transfer layer (20) and the ground. It utilizes the property that the viscosity of the magnetorheological fluid changes with the magnetic field strength to achieve the damping behavior of a variable damping coefficient, which is beneficial to the energy dissipation of the seismic isolation layer. Its schematic diagram is shown in the figure. Figure 4As shown. The magnetorheological damper mainly consists of an outer cylinder (12), an excitation coil (13), a piston (14), a piston rod (15), a magnetorheological fluid (16), and an erbium ring (17). The erbium ring (17) is the main connecting component of the magnetorheological damper. The left erbium ring (17) is hinged to the ground, and the right erbium ring (17) is hinged to the vibration isolation conversion layer (20). The piston (14) is fixed on the piston rod (15), and the piston (14) and piston rod (15) move horizontally inside the outer cylinder (12). When the vibration isolation conversion layer (20) and the upper electrical equipment move horizontally relative to the ground, the horizontal movement of the piston (14) inside the outer cylinder (12) causes the magnetorheological fluid (16) to flow through the gap between the piston (14) and the outer cylinder (12) to generate damping. The excitation coil (13) is fixed on the outer cylinder (12). When current flows through the excitation coil (13), a magnetic field is generated, and the physical properties of the magnetorheological fluid (16) change accordingly, with increased viscosity and damping coefficient. The damping coefficient of the magnetorheological damper increases with the increase of magnetic field strength (current strength). Therefore, the optimal control parameter submodule in the intelligent decision module can control the magnetic field strength generated by the excitation coil (13) by adjusting the current strength, thereby regulating the damping coefficient of the magnetorheological damper. The coil-type electrically controlled positive and negative stiffness springs are connected between the vibration isolation conversion layer (20) and the ground. By utilizing the property that the magnetic poles and magnetic force of the energized coil (19) change with the direction and strength of the current, positive and negative stiffness behaviors are realized, and the stiffness of the vibration isolation layer is flexibly controlled, which is conducive to realizing broadband vibration control. Its schematic diagram is shown below. Figure 5As shown. The coil-type electrically controlled positive and negative stiffness spring is mainly composed of three energized coils (18) and three bases (19). Each energized coil (18) is fixed on the base (19) and arranged horizontally. The lower end of the base (19) of the two energized coils (18) is connected to the ground, and the upper end of the base (19) of the middle energized coil (18) is connected to the vibration isolation conversion layer (20). When the vibration isolation conversion layer (20) and the upper electrical equipment move horizontally relative to the ground, the middle energized coil (18) will move horizontally between the two energized coils (18). When the current direction of the middle energized coil (18) is the same as the current direction of the two energized coils (18), the right side of the left energized coil (18) is the N (S) pole, the left side of the middle energized coil (18) is the S (N) pole, the right side of the middle energized coil (18) is the N (S) pole, and the left side of the right energized coil (18) is the S (N) pole. At this time, the middle energized coil (18) and the two side energized coils (18) are opposite magnetic poles facing each other, exhibiting negative stiffness. When the current direction of the middle energized coil (18) is opposite to the current direction of the two side energized coils (18), the middle energized coil (18) and the two side energized coils (18) are opposite magnetic poles facing each other, exhibiting positive stiffness. The magnetic field strength of the energized coil (18) increases with the increase of the current intensity, that is, the stiffness of the coil-type electrically controlled positive and negative stiffness spring increases with the increase of the current intensity. Therefore, the optimal control parameter submodule in the intelligent decision module can control the magnitude and nature (positive stiffness or negative stiffness) of the stiffness of the coil-type electrically controlled positive and negative stiffness spring by adjusting the current intensity and current direction in the three energized coils (18).

[0062] The monitoring module establishes a data synchronization and preprocessing mechanism. Each monitoring device achieves time synchronization via a GPS timing module, with a synchronization accuracy of ≤1ms. The collected raw data is preprocessed by an edge computing gateway; Kalman filtering is used to eliminate electromagnetic interference noise; and data exceeding the reasonable range is identified and replaced based on the 3σ criterion. The preprocessed data is transmitted in real-time to the intelligent decision-making module's database via 5G / industrial Ethernet, with a transmission latency of ≤100ms, meeting the real-time control requirements of earthquake response.

[0063] by Figure 2Taking the power facility shown as an example, in this embodiment, the weak points are first preset and the characteristics are defined. The preset core weak points and performance thresholds include the following: The weak point (10) at the bottom of the equipment box is the connection between the insulation structure (2) and the equipment box (3), which bears bending and shear stress, and the maximum allowable stress is taken as 80% of the yield strength (which can be adjusted according to the actual material yield strength of the equipment). The weak point (11) at the top of the equipment box is the connection between the equipment box (3) and the top structure (1), which mainly bears vibration acceleration; the equipment withstand acceleration threshold is set to 2.5g (based on the seismic test data of the equipment at the factory, which can be adjusted as needed); the stress at the root of the insulating porcelain bushing is indirectly related to the stress at the bottom of the equipment box, and the maximum allowable strain at the root of the porcelain bushing is preset according to the mechanical properties of the material.

[0064] Furthermore, this embodiment also provides a vibration control device for support-type power equipment, which can be used to execute the above-described vibration control method for support-type power equipment. For example... Figure 6 As shown, the vibration control device 400 for the support-type power equipment specifically includes: a data acquisition module 401, used to acquire multi-source data of the location of the support-type power equipment, including ground acceleration, support structure strain, and displacement; a structure prediction module 402, used to input the ground acceleration into a preset physical information neural network model to obtain the bottom stress at the first performance weak point and the top acceleration at the second performance weak point of the support-type power equipment; a verification module 403, used to verify the bottom stress and top acceleration through the support structure strain and displacement to obtain the verified stress prediction value and acceleration prediction value; and a control module 404, used to determine the control parameters of the vibration control module through the stress prediction value and acceleration prediction value, and to start the vibration control module based on the control parameters to generate damping corresponding to the control parameters, thereby consuming the dynamic response of the support-type power equipment through the damping generated by the vibration control module.

[0065] The specific details of each module or unit in the vibration control device of the aforementioned support-type power equipment have been described in detail in the corresponding vibration control method for support-type power equipment, so they will not be repeated here.

[0066] This application also provides an electronic device. Figure 7 A schematic diagram of the structure of an electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 7 The electronic device 600 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0067] like Figure 7As shown, the electronic device 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 602 or a program loaded from a storage section 608 into a random access memory (RAM) 603. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0068] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0069] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined in the embodiments of this application.

[0070] For example, when the computer program is executed by the central processing unit (CPU) 601, it can perform the following: acquire multi-source data on the location of the support-type power equipment, including ground acceleration, support structure strain, and displacement; input the ground acceleration into a preset physical information neural network model to obtain bottom stress and top acceleration; verify the bottom stress and top acceleration using the support structure strain and displacement to obtain verified stress prediction values ​​and acceleration prediction values; determine the control parameters of the vibration control module using the stress prediction values ​​and acceleration prediction values, and start the vibration control module based on the control parameters to generate damping corresponding to the control parameters, and consume the dynamic response of the support-type power equipment through the damping generated by the vibration control module.

[0071] It should be noted that the computer-readable medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0073] The units described in the embodiments of this disclosure can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the unit itself.

[0074] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which include instructions that, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0075] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0076] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A vibration control method for support-type power equipment, characterized in that, include: Acquire multi-source data on the location of support-type power equipment, including ground acceleration, strain of the supporting structure, and displacement; The ground acceleration is input into a preset physical information neural network model to obtain the bottom stress at the first performance weakness point and the top acceleration at the second performance weakness point of the support-type power equipment. The bottom stress and top acceleration are verified by the strain and displacement of the supporting structure to obtain the verified stress prediction value and acceleration prediction value. The control parameters of the vibration control module are determined by the predicted stress and acceleration values, and the vibration control module is started based on the control parameters to generate damping corresponding to the control parameters. The damping generated by the vibration control module consumes the dynamic response of the support-type power equipment.

2. The vibration control method for support-type power equipment according to claim 1, characterized in that, A broadband seismograph and an accelerometer are installed on the ground near the support structure of the power equipment. Strain gauges are installed on the support structure of the power equipment, and displacement gauges are installed below the support structure. The acquisition of multi-source data on the location of pillar-type power equipment includes: The triaxial acceleration of the ground near the support-type power equipment is obtained by a broadband seismograph, and the horizontal acceleration of the support-type power equipment is obtained by an acceleration sensor. The strain of the supporting structure is collected by strain gauges, and the displacement is obtained by displacement meters.

3. The vibration control method for support-type power equipment according to claim 1, characterized in that, Also includes: Determine whether there are structural performance deficiencies in support-type power equipment by using stress prediction values ​​and acceleration prediction values; Early warnings are issued when there are structural performance deficiencies in pillar-type power equipment.

4. The vibration control method for support-type power equipment according to claim 2, characterized in that, The process of verifying the bottom stress and top acceleration by measuring the strain and displacement of the supporting structure to obtain the verified predicted stress and acceleration values ​​includes: The elastic modulus of the support structure of the column-type power equipment is obtained, and the stress calculation value is obtained by converting the strain of the support structure with the elastic modulus. If the deviation between the calculated stress value and the bottom stress output by the physical information neural network model is greater than a first preset threshold, then the calculated bottom stress value and the bottom stress are weighted and fused to obtain a verified stress prediction value. If the deviation between the top acceleration and the displacement obtained by the displacement meter exceeds a second preset threshold, the top acceleration is corrected to obtain a predicted acceleration value.

5. The vibration control method for support-type power equipment according to claim 3, characterized in that, The method of determining whether there are structural performance deficiencies in support-type power equipment through stress prediction values ​​and acceleration prediction values ​​includes: The structural performance level is determined based on the predicted stress and the predicted acceleration, and the structural performance level is divided into undamaged, potential damage risk, and damaged. When the structural performance level is at potential risk of failure or has already failed, it is determined that the pillar-type power equipment has insufficient structural performance.

6. The vibration control method for support-type power equipment according to claim 3, characterized in that, The process of determining the control parameters of the vibration control module using the predicted stress and acceleration values ​​includes: In cases where the structural performance of pillar-type power equipment is insufficient, the state equation and quadratic performance evaluation function between the predicted stress value, the predicted acceleration value and the control parameters are obtained. The state equations are solved using a linear quadratic optimal control algorithm to determine the optimal parameters that minimize the quadratic performance evaluation function.

7. The vibration control method for support-type power equipment according to claim 1, characterized in that, The vibration control module includes a magnetorheological damper and coil-type electrically controlled positive and negative stiffness springs. The control parameters include the excitation coil current of the magnetorheological damper and the energized coil current of the coil-type electrically controlled positive and negative stiffness springs.

8. A vibration control device for support-type power equipment, characterized in that, include: Monitoring module, vibration control module; The monitoring module is used to detect the acceleration and displacement of support-type power equipment; The vibration control module is used to determine control parameters based on the acceleration and displacement obtained by the monitoring module, and generate damping corresponding to the control parameters to consume the kinetic energy of the support-type power equipment. The monitoring module includes a broadband seismograph, an accelerometer, a strain gauge, and a displacement meter; The broadband seismograph and accelerometer are installed on the ground near the support structure of the power equipment to detect the triaxial and horizontal acceleration of the ground. The strain gauge and displacement meter are installed on the support structure of the power equipment to detect the strain and displacement of the support structure. The vibration control module is installed between the support structure of the pillar-type power equipment and the ground.

9. The vibration control device for support-type power equipment according to claim 8, characterized in that, The vibration control module includes a magnetorheological damper and coil-type electrically controlled positive and negative stiffness springs. By adjusting the excitation coil current of the magnetorheological damper and the energizing coil current of the coil-type electrically controlled positive and negative stiffness springs through control parameters, the magnetorheological damper and the coil-type damper generate corresponding damping, and the electrically controlled positive and negative stiffness springs generate corresponding stiffness.

10. A vibration control device for support-type power equipment, characterized in that, include: The data acquisition module is used to acquire multi-source data on the location of the support structure power equipment, including ground acceleration, strain of the support structure, and displacement. The structural prediction module is used to input the ground acceleration into a preset physical information neural network model to obtain the bottom stress at the first performance weak point and the top acceleration at the second performance weak point of the support-type power equipment. The verification module is used to verify the bottom stress and top acceleration by means of the strain and displacement of the support structure, and to obtain the verified stress prediction value and acceleration prediction value. The control module is used to determine the control parameters of the vibration control module through the predicted stress value and the predicted acceleration value, and to start the vibration control module based on the control parameters to generate damping corresponding to the control parameters. The damping generated by the vibration control module consumes the dynamic response of the support-type power equipment.

Images