Power equipment state evaluation method, system and equipment for intelligent monitoring and storage medium

Abstract

The invention discloses a power equipment state evaluation method, system and device for intelligent monitoring and a storage medium, and belongs to the technical field of power equipment state evaluation, and the method comprises the steps: building a multi-physics field coupling calculation model based on the working characteristic parameters of power equipment, and simulating the behaviors of the power equipment in different working states; outputting an expected output value, comparing the expected output value with the physical field signal after time alignment, and calculating a deviation to obtain an initial prediction residual error; according to the initial prediction residual error, adjusting model parameters of the multi-physics coupling calculation model through an incremental correction algorithm, correcting the state estimation value of the power equipment, and updating the initial prediction residual error; based on the updated prediction residual error, analyzing an abnormal state of the power equipment through a residual error value, and extracting a fault feature; and identifying the fault type of the power equipment. According to the invention, through multi-physics field coupling calculation and an incremental correction algorithm, the accuracy and real-time performance of power equipment state evaluation are significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment status assessment, and in particular to a power equipment status assessment method, system, equipment and storage medium for intelligent monitoring. Background Art

[0002] Existing methods for power equipment status assessment and fault diagnosis mostly rely on the monitoring of a single physical field signal, for example, judging the health status of the equipment only by electrical signals (such as current, voltage) or temperature signals. However, these methods usually have several obvious shortcomings. First, a single physical field signal cannot fully reflect the complex operating status and internal faults of power equipment. For example, electrical signals cannot directly reflect the operating status of the equipment under conditions such as high temperature, stress or electromagnetic interference, and these factors may have a significant impact on the health status of the equipment in actual operation. Secondly, existing monitoring methods based on physical field signals are usually unable to respond to dynamic changes in the status of the equipment in real time, and it is difficult to provide effective early warning in the early stages of equipment failure. Therefore, traditional methods often miss the best time for maintenance, resulting in equipment downtime and increased maintenance costs.

[0003] When it comes to fault diagnosis, existing technologies primarily rely on historical data and models to identify fault modes, but these methods have limitations. Fault diagnosis methods based on historical data often rely on comparisons with the equipment's past operating data, which makes them incapable of adequately identifying new faults or previously unoccurred fault modes. Furthermore, existing methods often overlook the coupling between multiple physical fields. Single-field analysis cannot fully capture the true operating state of a device, especially when the device is simultaneously subject to multiple stresses, such as thermal, mechanical, and electromagnetic forces. Traditional methods suffer from poor accuracy and reliability.

[0004] Therefore, how to accurately evaluate the operating status of power equipment and promptly detect potential faults in a changing environment and complex working conditions has become an urgent problem to be solved in the field of power equipment monitoring and maintenance. Summary of the Invention

[0005] To solve the above technical problems, a power equipment status assessment method for intelligent monitoring is proposed, including: constructing a multi-physics field coupling calculation model based on the working characteristic parameters of the power equipment to simulate the behavior of the power equipment under different working conditions; inputting the time-aligned physical field signal into the multi-physics field coupling calculation model, outputting the expected output value, comparing the expected output value with the time-aligned physical field signal, calculating the deviation, and obtaining the initial prediction residual; according to the initial prediction residual, adjusting the model parameters of the multi-physics field coupling calculation model through an incremental correction algorithm, correcting the power equipment status estimation value, and updating the initial prediction residual; based on the updated prediction residual, analyzing the abnormal state of the power equipment through the residual value and extracting the fault characteristics; matching the fault characteristics with a predefined fault mode library to identify the fault type of the power equipment.

[0006] As a preferred solution of the method for evaluating the state of power equipment for intelligent monitoring described in the present invention, before constructing the multi-physical field coupling calculation model, it also includes arranging multiple sensors to collect physical field signals of the power equipment in real time and aligning the physical field signals in time points; the physical field signals include electrical signals, thermal signals, mechanical signals and electromagnetic signals.

[0007] As a preferred solution of the method for evaluating the state of power equipment for intelligent monitoring described in the present invention, the construction of a multi-physical field coupling calculation model includes: constructing an electrical model based on electrical signals to simulate current, voltage distribution and power transmission; constructing a thermal model based on thermal signals to simulate the temperature rise process inside the power equipment; constructing a mechanical model based on mechanical signals to simulate the stress distribution and mechanical response of the power equipment; constructing an electromagnetic model based on electromagnetic signals to simulate the influence of electromagnetic force by calculating the magnetic field generated by the current based on Maxwell's equations.

[0008] As a preferred solution of the method for evaluating the state of power equipment for intelligent monitoring described in the present invention, the construction of a multi-physical field coupling calculation model also includes setting boundary conditions of the electrical model, thermal model, mechanical model and electromagnetic model according to the working environment of the power equipment; in the electrical model, setting the voltage source boundary, defining the electrical connection method of the power equipment and the external power grid interface, setting the grounding boundary condition, specifying the restriction of the current flow path, and specifying the voltage application method; in the thermal model, setting the surface heat dissipation conditions in the heat conduction model, setting the external ambient temperature, defining the convection heat transfer method, and specifying the thermal conductivity and specific heat capacity of the material; in the mechanical model, setting the boundary conditions of the support point, external force application point, and mechanical connection point, and specifying the displacement restriction conditions; in the electromagnetic model, setting the magnetic permeability and magnetic field insulation conditions, and specifying the propagation rules of the magnetic field.

[0009] As a preferred solution of the method for evaluating the state of power equipment for intelligent monitoring described in the present invention, the construction of a multi-physical field coupling calculation model also includes: coupling the electrical model with the thermal model, adjusting the resistance value through mutual feedback of current and temperature, and calculating the impact of current on the heat and temperature of the power equipment; coupling the electrical model with the mechanical model, and calculating the impact of electromagnetic force on mechanical movement through the interaction between the magnetic field force caused by current and mechanical components; coupling the thermal model with the mechanical model, and simulating the impact of temperature on the mechanical properties of the power equipment through the changes in thermal expansion and stress caused by temperature changes; coupling the mechanical model with the electromagnetic model, and calculating the mechanical vibration caused by the magnetic field through the force of electromagnetic force density on mechanical components.

[0010] As a preferred solution of the method for power equipment status assessment for intelligent monitoring described in the present invention, the output expected output value includes discretizing the electrical model, thermal model, mechanical model and electromagnetic model, constructing a calculation grid for each physical field, and gridding the model of each physical field respectively; spatially discretizing the coupling model to obtain the node value of each physical field at the grid point, and applying the corresponding physical characteristics at each node; inputting the time-aligned physical field signal into the discretized multi-physical field coupling calculation model for numerical solution; discretizing the coupling model using finite element analysis, and obtaining the physical quantity at each node by applying the discretization method to the calculation nodes of the physical field grid; solving the discretized coupling model using a numerical solution method, calculating each physical field based on the discrete nodes and grids using a numerical integration method, gradually updating the state of the physical field through an iterative method, and calculating the calculation results of each physical field.

[0011] As a preferred solution of the method for power equipment status assessment oriented to intelligent monitoring described in the present invention, wherein: the updating of the initial prediction residual includes comparing the physical field signal after time alignment with the output value of the multi-physical field coupling calculation model node by node, and calculating the prediction residual of each node; mapping the residual value to the corresponding physical field model according to the size of each component in the residual vector and the characteristics of the physical field; calculating the correction increment according to the parameter sensitivity matrix of each physical field model, the sensitivity matrix represents the degree of influence of the parameter change in each physical field model on the model output result, and the correction increment is calculated through the residual The vector is multiplied by the sensitivity matrix and the preset step size factor to obtain the parameter correction amount of each physical field model; the correction increment is added to the parameters of the current physical field model to obtain the updated parameters, and the multi-physical field coupling calculation model is re-solved using the updated parameters; the updated residual obtained by re-solving is compared with the initial prediction residual, and the change amplitude of the residual is calculated; if the change amplitude of the residual is less than or equal to the preset convergence threshold, the iteration is stopped; if it is greater than the convergence threshold, the steps of calculating the correction increment and updating the parameters are returned, and the iteration is continued until the residual amplitude meets the convergence condition.

[0012] Another object of the present invention is to provide an electric power equipment status assessment system for intelligent monitoring. The present invention solves the problems of insufficient real-time performance and insufficient multi-physical field coupling computing capabilities of existing assessment systems. By adopting a multi-physical field coupling computing model and an incremental correction algorithm, dynamic updates and accurate estimation of electric power equipment status based on real-time physical field signals are realized. By accurately monitoring and diagnosing the status of electric power equipment, the operating efficiency of the equipment is improved, the downtime of faults is reduced, and the intelligence level of the system and the accuracy of fault prediction are enhanced. This ensures real-time monitoring of the equipment status and rapid fault warning while meeting the safety and stability requirements of the operation of the electric power equipment.

[0013] As a preferred solution of the power equipment status assessment system for intelligent monitoring described in the present invention, it is characterized by including: a simulation module, which is used to construct a multi-physical field coupling calculation model based on the working characteristic parameters of the power equipment to simulate the behavior of the power equipment under different working conditions; a prediction module, which is used to input the time-aligned physical field signal into the multi-physical field coupling calculation model, output the expected output value, compare the expected output value with the time-aligned physical field signal, calculate the deviation, and obtain the initial prediction residual; a correction module, which is used to adjust the model parameters of the multi-physical field coupling calculation model through an incremental correction algorithm according to the initial prediction residual, correct the power equipment status estimation value, and update the initial prediction residual; an analysis module, which is used to analyze the abnormal state of the power equipment through the residual value based on the updated prediction residual and extract fault characteristics; an evaluation module, which is used to match the fault characteristics with a predefined fault mode library to identify the fault type of the power equipment.

[0014] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a power equipment status assessment method for intelligent monitoring when executing the computer program.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a power equipment status assessment method for intelligent monitoring.

[0016] Beneficial effects of the present invention: The present invention significantly improves the accuracy and real-time performance of power equipment status assessment through multi-physics field coupling calculation and incremental correction algorithm. The incremental correction method can dynamically adjust model parameters according to real-time data, eliminate the lag of traditional methods, and improve the response speed of equipment status. At the same time, the fault diagnosis method based on residual analysis can predict faults in advance and issue timely warnings, reducing downtime and maintenance costs caused by equipment failures. Through automated monitoring and diagnosis, the present invention reduces dependence on manual intervention, optimizes the maintenance efficiency and economy of equipment, and enhances the reliability and service life of power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 An overall flow chart of a method for evaluating the state of power equipment for intelligent monitoring is provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0020] Example 1, with reference to Figure 1 , which is the first embodiment of the present invention, provides a method for evaluating the state of power equipment for intelligent monitoring, comprising:

[0021] Step 1: Deploy multiple sensors to collect physical field signals from power equipment in real time and align the physical field signals in time.

[0022] Specifically, physical field signals include electrical signals, thermal signals, mechanical signals, and electromagnetic signals.

[0023] Electrical signals include, but are not limited to, current, voltage, power, and frequency.

[0024] Thermal signals include, but are not limited to, temperature and heat flux.

[0025] Mechanical signals include, but are not limited to, vibration, stress, and acceleration.

[0026] Electromagnetic signals include but are not limited to magnetic field strength, magnetic flux density, magnetic field gradient, and electromagnetic force density.

[0027] It should be noted that time point alignment can be achieved through time synchronization protocols, GPS synchronization, NTP protocols, etc.

[0028] Step 2: Based on the operating characteristic parameters of the power equipment, a multi-physics field coupling calculation model is constructed to simulate the behavior of the power equipment under different operating conditions;

[0029] In step 2, an electrical model is constructed based on the electrical signals to simulate the current, voltage distribution, and power transmission, which is expressed as:

[0030] V=I·R(T)

[0031] R(T)=R0·(1+α e (T-T0))

[0032] P=I 2 ·R(T)

[0033] Where V represents voltage, I represents current, R(T) represents resistance, R0 represents resistance at reference temperature, and α e represents the temperature coefficient of resistance, T represents the current temperature, T0 represents the reference temperature, and P represents power.

[0034] A thermal model is constructed based on the thermal signal to simulate the temperature rise process inside the power equipment, which can be expressed as:

[0035]

[0036] Q=I 2 ·R(T)

[0037] in, Indicates the density of the material, c p represents specific heat capacity, T represents temperature, t represents time, k represents thermal conductivity, and Q represents internal heat source term.

[0038] A mechanical model is constructed based on the mechanical signal to simulate the stress distribution and mechanical response of the power equipment, which can be expressed as:

[0039] ∈=α m ΔT

[0040] σ=E·∈

[0041] Among them, ∈ represents strain, α m represents the coefficient of thermal expansion, ΔT represents the temperature change, σ represents the stress, and E represents the elastic modulus.

[0042] An electromagnetic model is constructed based on electromagnetic signals. The magnetic field generated by the current is calculated based on Maxwell's equations to simulate the influence of electromagnetic force, which can be expressed as:

[0043]

[0044] F=J×B

[0045] Among them, E represents the electric field, B represents the magnetic field, μ0 represents the vacuum magnetic permeability, J represents the current density, and F represents the electromagnetic force.

[0046] It should be noted that power is the rate at which electrical energy is converted into heat or other forms of energy, typically referring to the energy consumed when current passes through a resistor. Power describes the rate at which energy is consumed or converted during operation of an electrical device. Internal heat sources refer to the heat generated within the device due to current flowing through a resistor. Internal heat sources not only describe electrical energy loss but also serve as energy inputs in thermal models, acting as sources for heat conduction, convection, or radiation. The generation of internal heat sources is related to temperature changes and contributes to the temperature rise of the device. Power is the rate at which electrical energy is converted into heat or other forms of energy, typically referring to the energy consumed when current passes through a resistor. Power describes the rate at which energy is consumed or converted during operation of an electrical device. Internal heat sources refer to the heat generated within the device due to current flowing through a resistor. Internal heat sources not only describe electrical energy loss but also serve as energy inputs in thermal models, acting as sources for heat conduction, convection, or radiation. The generation of internal heat sources is related to temperature changes and contributes to the temperature rise of the device.

[0047] Electrical model, calculate the relationship between voltage, current and resistance, and obtain voltage V and power P.

[0048] The thermal model calculates the temperature distribution T based on the internal heat source term of the electrical model.

[0049] Mechanical model, calculates the stress distribution σ of mechanical components according to temperature changes.

[0050] Electromagnetic model, which calculates the electromagnetic force F based on the magnetic field generated by the current.

[0051] Set the boundary conditions of the electrical model, thermal model, mechanical model and electromagnetic model according to the working environment of the power equipment;

[0052] In the electrical model, set the voltage source boundaries, define the electrical connection method of the power equipment to the external grid interface, set the ground boundary conditions, specify the restrictions on the current flow path, and specify the voltage application method;

[0053] In the thermal model, set the surface heat dissipation conditions in the heat conduction model, set the external ambient temperature, define the convection heat transfer method, and specify the thermal conductivity and specific heat capacity of the material;

[0054] In the mechanical model, boundary conditions of support points, external force application points, and mechanical connection points are set, and displacement restriction conditions are specified;

[0055] In the electromagnetic model, the magnetic permeability and magnetic field insulation conditions are set, and the propagation rules of the magnetic field are specified.

[0056] The electrical model is coupled with the thermal model, and the resistance value is adjusted through the mutual feedback of current and temperature to calculate the impact of current on the heat and temperature of the power equipment;

[0057] The electrical model is coupled with the mechanical model, and the effect of electromagnetic force on mechanical motion is calculated through the interaction between the magnetic field force caused by the current and the mechanical components;

[0058] The thermal model is coupled with the mechanical model to simulate the effect of temperature on the mechanical properties of power equipment through the changes in thermal expansion and stress caused by temperature changes;

[0059] The mechanical model is coupled with the electromagnetic model, and the mechanical vibration caused by the magnetic field is calculated through the force exerted by the electromagnetic force density on the mechanical components.

[0060] It should be noted that the key physical processes in the coupling of the electrical and thermal models are the heat generated by current flowing through a resistor and the feedback effect of temperature on the resistor. The electrical model first generates power through current flowing through the resistor. This power is converted into heat and fed into the thermal model, which in turn affects the temperature distribution of the electrical equipment. When current flows through the resistor, power is lost due to the resistor. This loss is released as heat, becoming an internal heat source in the thermal model. The thermal model calculates the temperature change of the device based on this internal heat source and updates the internal temperature distribution. As the device temperature changes, the resistor value also changes. Because resistance is a function of temperature, an increase in temperature increases resistance, and this change affects the flow characteristics of the current. The current and voltage in the electrical model, in turn, affect heat generation, while the temperature change in the thermal model in turn affects the resistance value, which in turn affects the current. In this process, the feedback relationship between temperature and current must be repeatedly calculated in both models until equilibrium is reached.

[0061] The coupling between the electrical and mechanical models is achieved through the electromagnetic force exerted on mechanical components by the magnetic field generated by current. The magnetic field generated by current flowing through a conductor affects the stress distribution in the mechanical components. Specifically, when current flows through a conductor in the electrical model, it generates current density and a magnetic field. The interaction between the current density and the magnetic field produces an electromagnetic force. This electromagnetic force acts on various components in the mechanical model, causing stress changes in the mechanical components. The stress in the mechanical model is calculated based on the elastic modulus of the material. The greater the electromagnetic force, the greater the stress and deformation in the mechanical components. The magnetic field force generated by the current in the electrical model directly acts on the mechanical components, changing their deformation and stress, which in turn affects the output of the mechanical model. Based on the relationship between deformation and stress, the mechanical model further influences the current distribution and voltage characteristics in the electrical model. Therefore, the coupling between the electrical and mechanical models is not just a one-way process, but rather a complex interaction between current, magnetic field forces, and mechanical stress.

[0062] The coupling between the thermal and mechanical models is achieved through thermal expansion caused by temperature changes. The output of the thermal model is temperature, which directly affects the thermal expansion of the material, thereby causing deformation of the mechanical components. During device operation, temperature changes cause the internal materials to expand or contract, which in turn induces strain in the mechanical components. Based on the coefficient of thermal expansion, the strain caused by temperature changes can be calculated in the mechanical model, further affecting the stress distribution in the mechanical components. Specifically, temperature changes cause volume changes in the material, which in turn causes displacement and deformation of the mechanical components. This deformation affects the mechanical properties of the mechanical components through the stress-strain relationship. In the thermal model, temperature changes are fed back as input to the mechanical model, affecting the strain of the mechanical components. The mechanical model then calculates stress based on the strain, which in turn affects the structure and mechanical properties of the device. This coupling process directly affects the stress distribution and structural deformation of mechanical components through temperature-induced thermal expansion.

[0063] The coupling between the mechanical and electromagnetic models is primarily achieved through the deformation and vibration of mechanical components caused by electromagnetic forces. The current generated by the electrical model interacts with the magnetic field created by the conductors in the mechanical model, generating electromagnetic forces that in turn affect the stress and deformation of the mechanical components. Specifically, when current flows through the conductors in the electrical model, it generates a magnetic field perpendicular to the direction of the current. This magnetic field acts on the mechanical components through the interaction between the current and the magnetic field, generating electromagnetic forces. Electromagnetic forces are one of the main factors affecting the deformation of mechanical components, especially in components such as the iron core and rotor in power equipment, where they cause vibration and deformation. The mechanical model calculates the stress distribution based on these electromagnetic forces, which further influences the mechanical response and deformation of the mechanical components. This feedback effect not only adjusts the magnetic field strength and distribution in the electromagnetic model but also reacts to the motion and deformation of the mechanical components.

[0064] Furthermore, the electrical model is coupled with the thermal model. The power generated when the current flows through the resistor is input into the thermal model as heat. The temperature change feedback affects the resistor and then affects the current.

[0065] The electrical model is coupled with the mechanical model, and the magnetic field force generated by the current passing through the resistor acts on the mechanical components, affecting their stress distribution and thus the mechanical properties of the equipment.

[0066] The thermal model is coupled with the mechanical model, and the thermal expansion caused by temperature changes affects the strain and stress distribution of mechanical components, ultimately affecting the mechanical properties.

[0067] The mechanical model is coupled with the electromagnetic model, and the electromagnetic force acts on the mechanical components, changing their stress and deformation, thereby affecting the distribution of the electromagnetic field and the transmission of force.

[0068] Furthermore, the coupling between the electrical and thermal models is achieved through a feedback mechanism between the heat generated by current flowing through a resistor and the temperature. The power generated by current flowing through the resistor acts as an internal heat source and is input into the thermal model, affecting the device's temperature distribution. This temperature change, in turn, affects the resistance value, which in turn influences the current flow characteristics. This coupling allows the feedback relationship between the electrical and thermal models to be dynamically calculated, more accurately reflecting changes in the electrical performance of power equipment caused by temperature fluctuations during operation.

[0069] The coupling between the electrical and mechanical models is achieved through the magnetic field forces induced by current flow on mechanical components. The current density generated by current flowing through a conductor interacts with the magnetic field, generating electromagnetic forces. This electromagnetic force acts on the mechanical components, changing their stress distribution. The mechanical model calculates the stress and deformation of the components based on these stress changes. The current in the electrical model acts on the mechanical components through electromagnetic forces, changing their stresses and further influencing their deformation and mechanical response. This coupling accurately simulates the interplay between electrical and mechanical forces, enabling a more realistic representation of the actual operating conditions of the equipment.

[0070] The coupling between the thermal and mechanical models is achieved through the thermal expansion effect caused by temperature changes. Temperature changes in the thermal model cause the material to expand or contract, which in turn leads to deformation of the mechanical components. Specifically, the thermal expansion caused by temperature changes affects the strain in the mechanical components, which in turn affects the stress in the mechanical model. The relationship between strain and stress is described by the material's elastic modulus. This coupling allows the impact of temperature changes on the mechanical properties of mechanical components to be accurately reflected, thereby enhancing the accuracy and reliability of equipment condition assessment.

[0071] The coupling between the mechanical and electromagnetic models is achieved through the deformation of mechanical components caused by electromagnetic forces. The magnetic field generated by current flowing through the electrical model acts on the mechanical components, changing their stress and deformation. The mechanical model reflects the deformation of the mechanical components by calculating the relationship between stress and strain, while the electromagnetic force changes the stress distribution within the mechanical components. Changes in the strength and point of application of the electromagnetic force directly affect the stress state of the mechanical components, which in turn affects the calculation results of the mechanical model. This coupling ensures that the interactions between the electrical, thermal, and mechanical models are fully considered, thereby more accurately simulating the multi-physics coupled behavior of the device in actual operation.

[0072] By coupling these four physical fields, the limitations of traditional methods, which rely on independent analysis of each physical field, are overcome. This model provides a multi-physics feedback coupling model that more accurately and comprehensively describes the operating state of power equipment. Compared to existing technologies, this model not only considers the interactions between electrical, thermal, mechanical, and electromagnetic forces, but also reflects the feedback relationships between them in real time during equipment operation.

[0073] Step 3: Input the time-aligned physical field signal into the multi-physics field coupling calculation model, output the expected output value, compare the expected output value with the time-aligned physical field signal, calculate the deviation, and obtain the initial prediction residual;

[0074] In step 3, the electrical model, thermal model, mechanical model, and electromagnetic model are discretized to construct a computational grid for each physical field, and the model of each physical field is meshed separately;

[0075] Discretize the coupled model spatially, obtain the node value of each physical field at the grid point, and apply the corresponding physical properties at each node;

[0076] Input the time-aligned physical field signals into the discretized multi-physics field coupling calculation model for numerical solution;

[0077] Use finite element analysis to discretize the coupled model and obtain the physical quantity at each node by applying the discretization method to the computational nodes of the physical field grid;

[0078] The discretized coupling model is solved using a numerical solution method. Based on discrete nodes and grids, each physical field is calculated using a numerical integration method. The state of the physical field is gradually updated through an iterative method to obtain the calculation results of each physical field.

[0079] First, each physical field model (electrical, thermal, mechanical, and electromagnetic) is discretized to construct a computational grid for each physical field. This grid is created by dividing the physical space into a number of small units (grid nodes). Each physical field is segmented within its defined spatial region using an appropriate grid structure to ensure that each node represents the physical properties of the space. The fineness and precision of the grid division are crucial to the accuracy of the calculation results. Finer grids provide higher computational accuracy but also require more computing resources.

[0080] In practical applications, mesh selection is typically optimized based on the characteristics of the physical field and the requirements of the model. For example, for thermal models, a finer mesh might be used in areas with high temperature gradients, while a larger mesh might be used in areas with less temperature variation. Meshing for electrical and electromagnetic models requires consideration of the distribution of currents and magnetic fields, while the mesh for mechanical models is refined based on changes in stress and strain. Proper mesh selection ensures the simulation accuracy of each physical field and lays a solid foundation for subsequent numerical solutions.

[0081] After spatially discretizing the coupled model, each physical field model is divided into discrete nodes. Each node represents a spatial location at which the corresponding physical properties are applied. During this process, boundary conditions and initial conditions for each physical field must be applied to the mesh nodes. For example, the voltage, current, and resistance values ​​in the electrical model must be calculated at each mesh node and interact with other nodes in the thermal, mechanical, and electromagnetic models.

[0082] Furthermore, boundary conditions are crucial. In electrical models, these might involve limiting current flow or imposing voltage sources. In thermal models, they involve setting boundaries for heat flow or convection cooling. In mechanical models, these include limiting displacement and stress. In electromagnetic models, magnetic field boundary conditions are particularly important. These boundary conditions ensure that interactions between physical fields are properly transferred through discrete nodes.

[0083] Numerical solution is a key step in the discretization process. Using the finite element analysis method to discretize the coupling model is the core of realizing multi-physics field coupling calculations. The finite element method (FEM) converts the continuous changes of the physical field into a finite number of computational nodes in discrete units. Within each unit, the characteristics of the physical field (such as current density, electric field, temperature, stress, etc.) are approximated by basis functions and then solved by establishing a set of equations. Finite element analysis can handle complex geometries and boundary conditions and is applicable to a wide range of multi-physics field coupling problems.

[0084] During the numerical solution process, each discretized physical field must first be numerically integrated. This involves integrating the physical quantities within each cell to approximate its global behavior. For electrical models, numerical integration helps calculate current distribution; for thermal models, it helps calculate temperature fields; for mechanical models, it helps calculate stress distribution; and for electromagnetic models, it helps calculate the distribution of the magnetic field and the magnitude of the electromagnetic force. Through these integration operations, the behavior of the physical field can be accurately represented at each computational node.

[0085] During the numerical solution process, an iterative method is used to gradually update the state of each physical field. This method effectively handles nonlinear problems, gradually approaching the exact solution through repeated calculations. During each iteration, the calculation results of all physical fields (such as temperature, current, and stress) are updated based on the results of the previous round of calculations, thus achieving feedback correction between physical fields.

[0086] For example, when the electrical model is coupled with the thermal model, the calculated current and voltage will affect the resistance value through temperature feedback from the thermal model, thereby affecting the recalculation of the current. Similarly, temperature changes in the thermal model will affect the stress distribution in the mechanical model, and stress changes in the mechanical model will be fed back into the electromagnetic model, further affecting the magnetic field distribution. During each iteration, these feedback relationships gradually update the state of each physical field, ultimately solving for the true state of the device under different operating conditions.

[0087] Step 4: Based on the initial prediction residuals, the model parameters of the multi-physics field coupling calculation model are adjusted through an incremental correction algorithm to correct the power equipment state estimate and update the initial prediction residuals.

[0088] In step 4, the time-aligned physical field signals are compared with the output values ​​of the multi-physics field coupling calculation model node by node, and the prediction residual of each node is calculated;

[0089] According to the size of each component in the residual vector and the characteristics of the physical field, the residual value is mapped to the corresponding physical field model;

[0090] The correction increment is calculated based on the parameter sensitivity matrix of each physical field model. The sensitivity matrix represents the degree of influence of parameter changes in each physical field model on the model output results. The correction increment is obtained by multiplying the residual vector with the sensitivity matrix and then multiplying it with the preset step size factor to obtain the parameter correction amount of each physical field model.

[0091] Adding the correction increment to the parameters of the current physical field model to obtain updated parameters, and resolving the multi-physics field coupling calculation model using the updated parameters;

[0092] Compare the updated residuals obtained by resolving with the initial prediction residuals and calculate the magnitude of the residual change;

[0093] If the residual error is less than or equal to the preset convergence threshold, the iteration is stopped; if it is greater than the convergence threshold, the process returns to the step of calculating the correction increment and updating the parameters, and the iteration is continued until the residual error meets the convergence condition.

[0094] In a preferred embodiment of the present invention, the following can be achieved: Step 4.1: Construct a residual vector, obtain the time-aligned physical field signal value and the output result of the current multi-physics field coupling calculation model, and calculate the predicted residual value r of each node according to the node-to-node correspondence. i , and form the residual vector r t ,in:

[0095]

[0096] Among them, r t is the residual vector, which represents the residual of all nodes in the tth iteration; r i is the residual of the i-th node, which is equal to the signal s collected by the sensor i and the model predicted value y i The difference of s i is the time-aligned physical field signal of the i-th node; y i is the output value of the multi-physics field coupling calculation model of the i-th node; n is the total number of nodes, which means the number of nodes after spatial discretization.

[0097] Step 4.2: Map the residual to the model parameter space, according to the residual vector r t, according to the physical field type corresponding to each node, the residual is mapped to the parameters of the corresponding physical field model to form a joint parameter vector θ t ,in:

[0098]

[0099] Among them, θ t is the joint parameter vector at the tth iteration, which contains all the physical field model parameters to be adjusted; θ (e) is the parameter vector of the electrical model; θ (h) is the parameter vector of the thermal model; θ (m) is the parameter vector of the mechanical model; θ (em) is the parameter vector of the electromagnetic model.

[0100] Step 4.3: Calculate the parameter update increment according to the residual vector r t and sensitivity matrix J, calculate the update increment Δθ of each physical field model parameter t , the formula is:

[0101] Δθ t =η·E T ·r t

[0102] Where Δθ t is the parameter increment vector, which represents the parameter update amount of all physical field models in the tth iteration; η is the incremental step coefficient, which controls the amplitude of parameter update; E is the sensitivity matrix, which represents the partial derivative of each residual with respect to the physical field parameter; E T is the transpose of the sensitivity matrix; r t is the residual vector, which represents the residual of all nodes in the tth iteration.

[0103] Step 4.4: Perform parameter vector update by calculating the increment Δθ t , update the joint parameter vector and obtain the model parameter θ after the t+1th iteration t+1 :

[0104] θ t+1 =θ t +Δθ t

[0105] Among them, θ t+1 is the updated joint parameter vector; θ t is the joint parameter vector of the tth iteration; Δθ t Update increment for the parameter.

[0106] Step 4.5: Update the model output and update the updated parameters θ t+1Substitute into the multi-physics field coupling calculation model and recalculate the predicted output value y of all nodes t+1 , the formula is:

[0107] y t+1 =f(θ t+1 )

[0108] Where f(·) is the prediction function of the multi-physics field coupling calculation model, and the input is the updated parameter vector θ t+1 , the output is the predicted value of all nodes; y t+1 is the updated model output vector, which represents the predicted output of all nodes after the t+1th iteration.

[0109] Step 4.6: Update the residual and determine whether to terminate, output y according to the newly calculated model t+1 Compare with the original observation signal s and calculate the new residual vector r t+1 :

[0110] r t+1 =sy t+1

[0111] Compute the new residual norm:

[0112]

[0113] If the convergence condition is met:

[0114] ||r t+1 ||2≤∈ r

[0115] The iteration process is terminated; if the condition is not met, θ t+1 As the new parameter vector, return to steps 4.3 to 4.6 and continue iterating until the convergence criterion is reached.

[0116] Among them, ∈ r is the convergence threshold, which controls the maximum allowable value of the residual; is the residual of the i-th node in the t+1th iteration.

[0117] It should be noted that the sensitivity matrix E describes the dependence of each output on the model parameters in the multi-physics field coupling calculation model. Each element of the sensitivity matrix E ij It represents the rate of change of the output value of the i-th node to the j-th model parameter, that is:

[0118]

[0119] Among them, y i Represents the output value of the i-th node, which represents the predicted value of the node under the current physical field calculation; θ jIndicates the jth parameter; E ij The sensitivity of the ith node output to the jth parameter indicates the degree of influence of the parameter in the model calculation.

[0120] The incremental step size factor controls the magnitude of each parameter update. It determines the speed of parameter updates during each iteration. If the step size is too large, it may lead to excessive updates and cause model instability; while if the step size is too small, it may lead to slow convergence and even failure to achieve the desired accuracy.

[0121] The incremental step size coefficient is dynamically adjusted according to the change of the residual, ensuring that the parameters can be adjusted quickly when the error is large, and gradually fine-tuned when the error is small. The calculation formula for the adaptive step size is as follows:

[0122]

[0123] Among them, η t+1 is the step size coefficient for the t+1th iteration; r t is the residual vector of the tth iteration; r t+1 is the residual vector of the t+1th iteration; ||r t ||2 is the 2-norm of the residual vector.

[0124] Furthermore, the parameters of the multi-physics field coupling calculation model are iteratively optimized through an incremental correction algorithm, allowing the model to be fine-tuned according to the current prediction error (residual) in each iteration. This algorithm avoids large-scale model reconstruction and retraining of historical data, ensuring efficient use of computing resources. During each correction process, the model parameters gradually converge in the correct direction, gradually reducing the prediction error. This local parameter adjustment based on residual feedback can gradually correct the errors of each physical field model, providing an efficient and real-time model update method, especially for dynamic monitoring systems.

[0125] For example, during the state assessment of power equipment, problems such as temperature fluctuations and changes in mechanical stress caused by current changes may arise. Using an incremental correction algorithm, parameters such as resistance and inductance in the electrical model are fine-tuned based on the prediction error after each iteration. If deviations occur in the temperature and mechanical stress simulations, the thermal and mechanical models are adjusted accordingly. This local optimization continuously refines the model of each physical field, ultimately achieving globally accurate state prediction. The advantage of this approach is that it can accurately provide a state estimate for the device at every moment, without the need for complex and computationally intensive global optimization.

[0126] In practical applications, the incremental correction algorithm models the influence relationship of each parameter through the sensitivity matrix, feeds back each residual to the relevant model parameters, and generates a correction amount. The sensitivity matrix captures the influence of each residual component on each parameter. By multiplying the sensitivity matrix and the residual, the incremental correction algorithm accurately calculates the adjustment amount of each physical field parameter. For example, if the residual shows that the error of certain mechanical parameters in the mechanical model is large, the sensitivity matrix will emphasize the adjustment of the corresponding mechanical parameters (such as elastic modulus or stress-strain relationship) and make corrections through larger increments. Such corrections ensure that each physical model can more accurately reflect the true state of the equipment in the next iteration.

[0127] The incremental step size factor controls the magnitude of each update, ensuring that the model does not oscillate or become unstable due to overcorrection. Excessively large step sizes can lead to over-adjustment and loss of stability, while too small a step size can result in slow convergence. By dynamically adjusting the step size, the incremental correction algorithm can adaptively control the update speed based on the size of the residual, ensuring that each correction is made within a reasonable range, ultimately achieving fast and stable convergence.

[0128] In practical applications, for example, in power equipment fault diagnosis, the electrical model may need to accurately simulate current distribution and power transmission, while the thermal model must accurately simulate the temperature rise process within the equipment. If current changes lead to temperature changes, an incremental correction algorithm gradually adjusts the relevant parameters of the electrical and thermal models based on the predicted error in each model output to prevent the temperature simulation error from increasing. This method can update the status of each model in real time, ensuring that the error between the predicted value and the actual value remains within an acceptable range.

[0129] After each correction, the new prediction results are compared again with the time-aligned physical field signals, and new residuals are calculated and fed into the next iteration. This iterative process not only corrects the parameters but also ensures that the model gradually converges with each iteration until it reaches the preset convergence criteria, ensuring that the model can ultimately accurately predict the state of the power equipment. This convergence process ensures that the model's prediction accuracy continues to improve with each optimization, avoiding inaccurate equipment state estimates during fault diagnosis.

[0130] Step 5: Based on the updated prediction residual, analyze the abnormal state of the power equipment through the residual value and extract the fault characteristics;

[0131] In step 5, the residual values ​​of each physical field are first compared node by node, and the residual of each node is calculated. The residual size and trend of each residual are then analyzed. Aggregating and analyzing these residual values ​​can identify whether the device is operating normally and whether there are any faults or anomalies. In practice, if the residuals of certain nodes exceed a predetermined threshold, this indicates a potential fault at these nodes, indicating possible equipment overload, abnormal temperature rise, or excessive mechanical stress.

[0132] On this basis, feature extraction methods are used to extract fault-related feature information from the residual values ​​of each physical field. These features usually include but are not limited to:

[0133] Electrical fault characteristics: By analyzing electrical residuals, such as current and voltage fluctuations, it is possible to determine whether the equipment is overloaded or has poor electrical contact.

[0134] Thermal fault characteristics: Analyze whether the equipment has overheated or has abnormal temperature rise by analyzing the changes in temperature residuals, and then infer possible cooling system failure or overload.

[0135] Mechanical failure characteristics: Based on the residuals of stress and vibration, analyze whether the mechanical components of the equipment are damaged, worn, or mechanically overloaded.

[0136] Electromagnetic fault characteristics: By analyzing the electromagnetic force density and magnetic field residual, it is inferred whether the equipment has electromagnetic interference or mechanical deformation caused by excessive electromagnetic force.

[0137] Step 6: Match the fault signature with the predefined fault mode library to identify the fault type of the power equipment.

[0138] In step 6, the extracted fault features are compared with the features of each fault mode in the fault mode library. Each fault mode in the fault mode library describes the typical characteristic values ​​associated with a certain equipment failure, such as current fluctuation, temperature rise rate, vibration amplitude, etc. By comparing with the fault modes in the library, the similarity between the fault features and the mode can be calculated. Common similarity calculation methods include:

[0139] Euclidean distance: Calculates the distance between the extracted fault features and each fault mode. The smaller the distance, the higher the matching degree.

[0140] Cosine similarity: Calculate the angle between the extracted fault feature and each fault feature in the fault pattern library. The smaller the angle, the more similar the features are.

[0141] Through similarity calculation, the fault mode closest to the current device status is matched and the specific fault type is identified. For example, if residual analysis reveals large current fluctuations and abnormally high temperature, this may indicate an overload fault mode. Abnormal vibration frequency and significant stress changes may indicate a mechanical fault mode. Matched fault types can include overload, insulation damage, equipment aging, mechanical wear, and more.

[0142] Finally, the identified fault type is output as a diagnostic result, providing real-time alerts and recommended troubleshooting solutions to maintenance personnel. This process utilizes a predefined fault pattern library and automated fault diagnosis through intelligent matching technology, significantly improving the efficiency of power equipment fault detection and management.

[0143] Example 2 is the second embodiment of the present invention, which is different from the previous embodiment in that:

[0144] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0145] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0146] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0147] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0148] Embodiment 3, the third embodiment of the present invention, provides a power equipment status assessment system for intelligent monitoring, including.

[0149] The simulation module is used to build a multi-physics field coupling calculation model based on the operating characteristic parameters of the power equipment to simulate the behavior of the power equipment under different working conditions;

[0150] A prediction module is used to input the time-aligned physical field signals into the multi-physics field coupling calculation model, output the expected output value, compare the expected output value with the time-aligned physical field signals, calculate the deviation, and obtain the initial prediction residual;

[0151] A correction module is used to adjust the model parameters of the multi-physics field coupling calculation model through an incremental correction algorithm based on the initial prediction residual, correct the power equipment state estimation value, and update the initial prediction residual;

[0152] An analysis module is used to analyze abnormal states of power equipment and extract fault features based on the updated prediction residuals through residual values;

[0153] The evaluation module is used to match the fault characteristics with the predefined fault mode library to identify the fault type of the power equipment.

[0154] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating the state of power equipment for intelligent monitoring, characterized by: include, Based on the operating characteristic parameters of power equipment, a multi-physics field coupling calculation model is constructed to simulate the behavior of power equipment under different working conditions; Input the time-aligned physical field signal into the multi-physics field coupling calculation model, output the expected output value, compare the expected output value with the time-aligned physical field signal, calculate the deviation, and obtain the initial prediction residual; Based on the initial prediction residuals, the model parameters of the multi-physics field coupling calculation model are adjusted through an incremental correction algorithm to correct the power equipment state estimate and update the initial prediction residuals. Based on the updated prediction residuals, the abnormal state of the power equipment is analyzed through the residual values ​​and the fault characteristics are extracted; Match the fault signature with the predefined fault mode library to identify the fault type of the power equipment.

2. The method for evaluating the state of power equipment for intelligent monitoring according to claim 1, characterized in that: Before constructing the multi-physics field coupling calculation model, it also includes: Deploy multiple sensors to collect physical field signals from power equipment in real time and align the physical field signals in time; The physical field signals include electrical signals, thermal signals, mechanical signals and electromagnetic signals.

3. The method for evaluating the state of power equipment for intelligent monitoring according to claim 2, characterized in that: The construction of the multi-physics field coupling calculation model includes: Build electrical models based on electrical signals to simulate current, voltage distribution, and power transmission; Build a thermal model based on thermal signals to simulate the temperature rise process inside the power equipment; Build mechanical models based on mechanical signals to simulate the stress distribution and mechanical response of power equipment; An electromagnetic model is constructed based on electromagnetic signals, and the influence of electromagnetic force is simulated by calculating the magnetic field generated by the current based on Maxwell's equations.

4. The method for evaluating the state of power equipment for intelligent monitoring according to claim 3, wherein: The construction of the multi-physics field coupling calculation model also includes: Set the boundary conditions of the electrical model, thermal model, mechanical model and electromagnetic model according to the working environment of the power equipment; In the electrical model, set the voltage source boundaries, define the electrical connection method of the power equipment to the external grid interface, set the ground boundary conditions, specify the restrictions on the current flow path, and specify the voltage application method; In the thermal model, set the surface heat dissipation conditions in the heat conduction model, set the external ambient temperature, define the convection heat transfer method, and specify the thermal conductivity and specific heat capacity of the material; In the mechanical model, boundary conditions of support points, external force application points, and mechanical connection points are set, and displacement restriction conditions are specified; In the electromagnetic model, the magnetic permeability and magnetic field insulation conditions are set, and the propagation rules of the magnetic field are specified.

5. The method for evaluating the state of power equipment for intelligent monitoring according to claim 4, characterized in that: The construction of the multi-physics field coupling calculation model also includes: The electrical model is coupled with the thermal model, and the resistance value is adjusted through the mutual feedback of current and temperature to calculate the impact of current on the heat and temperature of the power equipment; The electrical model is coupled with the mechanical model, and the effect of electromagnetic force on mechanical motion is calculated through the interaction between the magnetic field force caused by the current and the mechanical components; The thermal model is coupled with the mechanical model to simulate the effect of temperature on the mechanical properties of power equipment through the changes in thermal expansion and stress caused by temperature changes; The mechanical model is coupled with the electromagnetic model, and the mechanical vibration caused by the magnetic field is calculated through the force exerted by the electromagnetic force density on the mechanical components.

6. The method for evaluating the state of power equipment for intelligent monitoring according to claim 5, characterized in that: The output expected output value includes: Discretize the electrical model, thermal model, mechanical model, and electromagnetic model, construct the computational grid for each physical field, and mesh the model for each physical field separately; Discretize the coupled model spatially, obtain the node value of each physical field at the grid point, and apply the corresponding physical properties at each node; Input the time-aligned physical field signals into the discretized multi-physics field coupling calculation model for numerical solution; Use finite element analysis to discretize the coupled model and obtain the physical quantity at each node by applying the discretization method to the computational nodes of the physical field grid; The discretized coupling model is solved using a numerical solution method. Based on discrete nodes and grids, each physical field is calculated using a numerical integration method. The state of the physical field is gradually updated through an iterative method to obtain the calculation results of each physical field.

7. The method for evaluating the state of power equipment for intelligent monitoring according to claim 6, characterized in that: The updating of the initial prediction residual includes, Compare the time-aligned physical field signals with the output values ​​of the multi-physics field coupling calculation model node by node, and calculate the prediction residual of each node; According to the size of each component in the residual vector and the characteristics of the physical field, the residual value is mapped to the corresponding physical field model; The correction increment is calculated based on the parameter sensitivity matrix of each physical field model. The sensitivity matrix represents the degree of influence of parameter changes in each physical field model on the model output results. The correction increment is obtained by multiplying the residual vector with the sensitivity matrix and then multiplying it with the preset step size factor to obtain the parameter correction amount of each physical field model. Adding the correction increment to the parameters of the current physical field model to obtain updated parameters, and resolving the multi-physics field coupling calculation model using the updated parameters; Compare the updated residuals obtained by resolving with the initial prediction residuals and calculate the magnitude of the residual change; If the residual error is less than or equal to the preset convergence threshold, the iteration is stopped; if it is greater than the convergence threshold, the process returns to the step of calculating the correction increment and updating the parameters, and the iteration is continued until the residual error meets the convergence condition.

8. A power equipment status assessment system for intelligent monitoring, applying the power equipment status assessment method for intelligent monitoring according to any one of claims 1 to 7, characterized in that: include: The simulation module is used to build a multi-physics field coupling calculation model based on the operating characteristic parameters of the power equipment to simulate the behavior of the power equipment under different working conditions; A prediction module is used to input the time-aligned physical field signals into the multi-physics field coupling calculation model, output the expected output value, compare the expected output value with the time-aligned physical field signals, calculate the deviation, and obtain the initial prediction residual; A correction module is used to adjust the model parameters of the multi-physics field coupling calculation model through an incremental correction algorithm based on the initial prediction residual, correct the power equipment state estimation value, and update the initial prediction residual; An analysis module is used to analyze abnormal states of power equipment and extract fault features based on the updated prediction residuals through residual values; The evaluation module is used to match the fault characteristics with the predefined fault mode library to identify the fault type of the power equipment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the processor implements the steps of a method for evaluating the state of power equipment oriented to intelligent monitoring according to any one of claims 1 to 7.

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

Images