CN-122026631-A - Box-type substation operation and maintenance management method and system based on digital twin

CN122026631ACN 122026631 ACN122026631 ACN 122026631ACN-122026631-A

Abstract

The invention relates to the technical field of operation and maintenance management of transformer substations, in particular to a box-type transformer substation operation and maintenance management method and system based on digital twinning. The method comprises the steps of initializing a particle swarm, optimizing and iterating the particle swarm by utilizing an improved particle swarm algorithm until a termination condition is met, obtaining a global optimal parameter set, and applying the global optimal parameter set to the digital twin model to realize operation and maintenance management of the transformer substation. The scheme of the invention can provide an operation and maintenance management method for predicting the equipment state and meeting the operation and maintenance management requirement of high reliability.

Inventors

MA HONGGE
YU GANG
YU JIALE
LIU SHAOHUA
ZHANG CHAN

Assignees

保定市子盛电气设备制造有限公司

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (10)

1. The box-type substation operation and maintenance management method based on digital twinning is characterized by comprising the following steps of: initializing a particle swarm, wherein each particle corresponds to a group of parameter sets of the box-type substation; Optimizing and iterating the particle swarm by utilizing the improved particle swarm algorithm until the termination condition is met, so as to obtain a global optimal parameter set; applying the global optimal parameter set to the digital twin model to realize operation and maintenance management of the transformer substation; The improved particle swarm algorithm comprises the steps of superposing a chaos disturbance term based on Lorentz distribution in particle updating speed in each iteration by taking the dynamic escape probability as a triggering condition; The dynamic escape probability is in positive correlation with a steady-state trap risk index at the current iteration, the steady-state trap risk index is in inverse relation with an aggregation degree index and a working condition excitation intensity negative correlation respectively, the aggregation degree index represents aggregation conditions from all particle positions of a particle swarm to a global optimal position at the current iteration, the working condition excitation intensity is in positive correlation with a pre-obtained variance of load current of the box-type transformer substation in a set time window, is in negative correlation with a mean value of the load current, and is in positive correlation with an absolute value of a change index of the top oil temperature of the transformer.
2. The digital twinning-based box-type substation operation and maintenance management method according to claim 1, wherein the aggregation index calculation method comprises the following steps: And calculating the root mean square of Euclidean distance between each particle position vector and the global optimal position vector in each iteration, and taking the root mean square as the aggregation index.
3. The digital twinning-based box-type substation operation and maintenance management method according to claim 1, wherein the working condition excitation intensity is as follows The calculation method of (1) is as follows: ; Wherein, the And Respectively the standard deviation and the average value of the load current in a set time window, wherein I is the load current, To set the index of the change of the top layer oil temperature of the transformer in the time window, To prevent the denominator from being zero a preset positive real number, To set the length of the time window.
4. The digital twinning-based box-type substation operation and maintenance management method according to claim 1, wherein the steady-state trap risk index The calculation method of (1) is as follows: ; Wherein, the For the purpose of normalizing the scale factor, Is the aggregation index at the t-th iteration, For the excitation intensity of the working condition, The weight factor is influenced for the working condition.
5. The digital twinning-based box-type substation operation and maintenance management method according to claim 1, wherein the dynamic escape probability The calculation method of (1) is as follows: ; Wherein, the Is the steady state trap risk index at the t-th iteration, Is a preset risk threshold constant.
6. The digital twinning-based box-type substation operation and maintenance management method according to claim 1, wherein the method for generating the chaotic disturbance term comprises the following steps: The random numbers uniformly distributed in the (-0.5, 0.5) interval are subjected to tangent function transformation.
7. The method for managing operation and maintenance of a box-type substation based on digital twinning according to claim 1 or 6, wherein the dynamic escape probability is used as a trigger condition, specifically, when the generated random number is smaller than the dynamic escape probability, the disturbance update is triggered.
8. The digital twinning-based box-type substation operation and maintenance management method according to claim 1, wherein the parameter set comprises at least one of a transformer equivalent circuit parameter, a thermal resistance parameter and a heat capacity parameter of a thermal path model, wherein the equivalent circuit parameter of the transformer comprises a winding direct current resistance and a leakage reactance, and the thermal path model parameter comprises a thermal resistance and a heat capacity.
9. The method for managing operation and maintenance of a box-type substation based on digital twinning according to claim 1, wherein after applying the obtained global optimum parameter set to the digital twinning model, further comprises: Acquiring an operation data set in a set time period, wherein each operation data in the operation data set at least comprises load voltage, load current and top-layer oil temperature of the transformer; the operation data set is used for verifying the prediction precision of the calibrated digital twin model, if the prediction precision meets the set requirement, the calibration is completed, and if the prediction precision does not meet the set requirement, the improved particle swarm optimization algorithm is triggered again.
10. Box-type substation operation and maintenance management system based on digital twin, characterized by comprising: A processor; A memory storing computer instructions for digital twinning-based box-type substation operation and maintenance management, which when executed by the processor, cause the system to perform the digital twinning-based box-type substation operation and maintenance management method according to any one of claims 1-9.

Description

Box-type substation operation and maintenance management method and system based on digital twin Technical Field The invention relates to the technical field of operation and maintenance management of transformer substations. More particularly, the invention relates to a box-type substation operation and maintenance management method and system based on digital twinning. Background The box-type transformer substation is used as a key node of a power distribution network, the inside of the box-type transformer substation comprises core equipment such as a transformer, a high-low voltage switch cabinet and the like, the equipment is influenced by thermal stress, electric stress and environmental factors in long-term operation, and physical parameters (such as winding direct current resistance, insulating layer heat conductivity coefficient, contact resistance and the like) of the equipment can generate nonlinear drift. In order to maintain high fidelity of the digital twin model, the prior art often employs Particle Swarm Optimization (PSO) algorithms and uses real-time monitoring data to reverse calibrate the model parameters. However, the parameters to be identified of the box-type substation are numerous, and a high-dimensional and multimodal complex solution space is formed. In the optimizing process of the traditional PSO algorithm, particles tend to be gathered near a certain local extreme point in advance due to lack of population diversity, so that 'premature convergence' is caused. Such a locally optimal solution may appear to have a small numerical fit error at the current time, but its corresponding combination of physical parameters tends to deviate from the true physical state (e.g., masking the true heat source anomalies by erroneous thermal conductivity). Once the box transformer operating condition changes (such as abrupt load change or diurnal temperature difference change), a digital twin model based on the local optimal parameter is quickly disabled, the equipment state cannot be accurately predicted, and the operation and maintenance management requirement of high reliability is difficult to meet. Therefore, there is a need for an operation and maintenance management method that can accurately predict the state of equipment and meet the requirements of operation and maintenance management with high reliability. Disclosure of Invention The invention aims to provide an operation and maintenance management method and system for a box-type substation based on digital twinning, which are used for solving the problem that the state of equipment cannot be accurately predicted in the prior art and meeting the operation and maintenance management requirement of high reliability. In a first aspect, the invention provides a digital twinning-based box-type substation operation and maintenance management method, which comprises the following steps: initializing a particle swarm, wherein each particle corresponds to a group of parameter sets of the box-type substation; Optimizing and iterating the particle swarm by utilizing the improved particle swarm algorithm until the termination condition is met, so as to obtain a global optimal parameter set; applying the global optimal parameter set to the digital twin model to realize operation and maintenance management of the transformer substation; The improved particle swarm algorithm comprises the steps of superposing a chaos disturbance term based on Lorentz distribution in particle updating speed in each iteration by taking the dynamic escape probability as a triggering condition; The dynamic escape probability is in positive correlation with a steady-state trap risk index at the current iteration, the steady-state trap risk index is in negative correlation with an aggregation degree index and a working condition excitation intensity respectively, the aggregation degree index represents aggregation conditions from all particle positions of a particle swarm to a global optimal position at the current iteration, the working condition excitation intensity is in positive correlation with a variance of load current of a box-type transformer substation in a preset time window, is in negative correlation with a mean value of the load current, and is in positive correlation with an absolute value of a change index of the top oil temperature of a transformer. According to the scheme, the steady-state trap risk index and the dynamic escape probability are introduced, so that the searching strategy of the algorithm is tightly coupled with the actual working conditions (such as load fluctuation and oil temperature change) of the physical system. Compared with the traditional algorithm relying only on mathematical convergence, the method can identify the pseudo-convergence state caused by insufficient excitation of working conditions (data depletion), and force particles to jump out of local extremum through a Lorentz chaotic disturbance mechanism, so that the physica