A modular-based combined mobile ice melting control method and system

Abstract

The present invention relates to the field of information technology, and discloses a modular combined mobile de-icing control method and system. By analyzing the de-icing demand parameters of various transmission lines in the power grid, an accurate de-icing demand model is constructed, and a multi-objective optimization algorithm is used to quantify the voltage and current output data of the transmission lines to generate a preliminary equipment combination plan; by evaluating the performance decay trend of the preliminary equipment combination under various scenarios to update the equipment combination, a final equipment combination plan is obtained; the modular design method is used to construct a combined mobile de-icing system adaptable to various scenarios according to the final equipment combination, a preliminary control strategy is generated by using a fuzzy control algorithm, an adaptive learning mechanism is introduced to update the control parameters, and a multi-level system performance simulation platform is constructed to further optimize it, and a target control strategy is obtained to control the execution of the combined mobile de-icing system. This solution can adapt to various application scenarios and effectively improve the de-icing efficiency of transmission lines.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and particularly to a modular-based combined mobile ice melting control method and system. Background Art

[0002] At present, the DC ice melting technology is widely used in the de-icing work of power grids due to its simple operation and environmental friendliness. However, the ice melting operation is usually carried out in harsh environments such as high altitudes and low temperatures, which easily leads to the attenuation of the electrical and mechanical properties of equipment, resulting in a reduction in ice melting efficiency.

[0003] Therefore, how to improve the ice melting efficiency of transmission lines in high altitude and low temperature environments has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0004] The present invention provides a modular-based combined mobile ice melting control method and system to solve the problem of how to improve the ice melting efficiency of transmission lines in high altitude and low temperature environments.

[0005] To solve the above technical problem, in the first aspect of the present invention, a modular-based combined mobile ice melting control method is provided, including:

[0006] Obtaining the ice melting demand parameters of different transmission lines in the power grid to construct an ice melting demand model;

[0007] Based on the ice melting demand model, using a multi-objective optimization algorithm to quantify the voltage and current output data of the transmission line to generate a preliminary equipment combination;

[0008] Evaluating the performance attenuation trend of the preliminary equipment combination in multiple scenarios, obtaining an environmental adaptability correction parameter to update the preliminary equipment combination, and obtaining a final equipment combination;

[0009] According to the final equipment combination, using a modular design method to construct a combined mobile ice melting system, and generating a control strategy for the combined mobile ice melting system through a fuzzy control algorithm;

[0010] Based on the control strategy, introducing an adaptive learning mechanism to update the control parameters in the control strategy to obtain an updated control strategy;

[0011] Constructing a multi-level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimizing the updated control strategy according to the operation results to obtain a target control strategy to control the combined mobile ice melting system to execute.

[0012] As a preferred solution, the obtaining the ice melting demand parameters of different transmission lines in the power grid to construct an ice melting demand model includes:

[0013] Obtain the current density of the conductor and the voltage stability value of the ground wire, and compare them with a preset ice melting current threshold and a preset ice melting voltage threshold respectively, and quantify the high current density value of the conductor and the high voltage stability value of the ground wire according to the comparison results;

[0014] Construct an ice melting demand difference model based on the high current density value and the high voltage stability value, and generate ice melting optimization parameters through a machine learning algorithm based on the ice melting demand difference model;

[0015] Obtain the current, voltage, density, and ice melting amount data of the conductor and the ground wire, combine them with the ice melting optimization parameters to construct a multi-dimensional feature set, and construct an ice melting demand model based on the multi-dimensional feature set.

[0016] As one of the preferred solutions, the obtaining the current, voltage, density, and ice melting amount data of the conductor and the ground wire, combining them with the ice melting optimization parameters to construct a multi-dimensional feature set, and constructing an ice melting demand model based on the multi-dimensional feature set includes:

[0017] Obtain the current, voltage, density, and ice melting amount data of the conductor, and select the conductor-related data with the current reaching the first preset threshold from them;

[0018] Obtain the current, voltage, density, and ice melting amount data of the ground wire, and select the ground wire-related data with the voltage reaching the second preset threshold from them;

[0019] Combine the conductor-related data, the ground wire-related data, and the ice melting optimization parameters to form a multi-dimensional feature set to construct an ice melting demand model;

[0020] Based on the ice melting demand model, judge the matching of the ice melting amount of the conductor and the ice melting amount of the ground wire, and when the matching judgment passes, use a machine learning algorithm to train the ice melting demand model to obtain an optimized model parameter set;

[0021] Perform an expected verification on the final ice melting amount of the conductor and the final ice melting amount of the ground wire through the ice melting demand model configured with the optimized model parameter set, and output the ice melting demand model that passes the expected verification.

[0022] As one of the preferred solutions, the quantifying the voltage and current output data of the transmission line based on the ice melting demand model by using a multi-objective optimization algorithm to generate a preliminary equipment combination includes:

[0023] Construct an objective function based on the ice melting demand model, and solve the objective function by using a multi-objective optimization algorithm to obtain the voltage and current output data;

[0024] Configure the ice melting equipment according to the voltage and current output data under the constraints of the equipment capacity and heat dissipation capacity to generate the preliminary equipment combination.

[0025] As one of the preferred solutions, evaluating the performance decay trend of the preliminary equipment combination in multiple scenarios, obtaining the environmental adaptability correction parameters to update the preliminary equipment combination, and obtaining the final equipment combination, including:

[0026] Obtain the performance operation data of the preliminary equipment combination in each of the scenarios to characterize the performance decay trend, and process the performance operation data by using the regression analysis method to obtain the environmental adaptability correction parameters;

[0027] Adjust the equipment models and quantities in the preliminary equipment combination based on the environmental adaptability correction parameters to obtain the corrected equipment combination;

[0028] Obtain the voltage and current output range of the corrected equipment combination, and judge whether the corrected equipment combination meets the ice melting requirements of each of the scenarios by using the decision tree algorithm based on the voltage and current output range;

[0029] When the corrected equipment combination meets the ice melting requirements of each of the scenarios, obtain the performance operation data of the corrected equipment combination in each of the scenarios, and judge whether the corrected equipment combination meets the preset performance decay condition by using the clustering algorithm based on the performance operation data;

[0030] Output the corrected equipment combination that meets the preset performance decay condition as the final equipment combination.

[0031] As one of the preferred solutions, constructing a combined mobile ice melting system by using the modular design method according to the final equipment combination, including:

[0032] Conduct functional division on the final equipment combination according to each of the scenarios to obtain several functional modules;

[0033] Optimize the layout of each of the functional modules by using the shortest path algorithm and the heuristic search algorithm to obtain the installation positions of each of the functional modules;

[0034] Based on each of the installation positions, determine the topological structure of each of the functional modules by using the fault tree analysis method and the multi-attribute decision algorithm, and construct a combined mobile ice melting system according to the installation positions and topological structures of each of the functional modules.

[0035] As one of the preferred solutions, generating a control strategy for the combined mobile ice melting system by using the fuzzy control algorithm, including:

[0036] Taking the ice melting requirements and real-time environmental data of each of the scenarios as input variables, and taking the current mode or voltage mode of the topological structure in the combined mobile ice melting system as output variables;

[0037] Fuzzifying the input variables and the output variables to obtain fuzzy sets, and performing fuzzy inference on the fuzzy sets of the input variables and the fuzzy rule base through Mamdani inference to obtain the fuzzy sets of the output variables;

[0038] Defuzzifying the fuzzy sets of the output variables by the maximum membership degree method to obtain a control strategy;

[0039] Obtaining the real-time ice melting data of each of the scenarios under the control strategy to match with the ice melting requirements of each of the scenarios, and updating the topological structure when the matching is unsuccessful;

[0040] Judging whether the updated topological structure meets the preset performance decay condition through a clustering algorithm, and re-executing the control strategy generation step based on the topological structure that meets the preset performance decay condition until the real-time ice melting data of each of the scenarios in the final obtained control strategy matches the ice melting requirements of each of the scenarios, and outputting the finally obtained control strategy.

[0041] As one of the preferred solutions, based on the control strategy, an adaptive learning mechanism is introduced to update the control parameters in the control strategy to obtain an updated control strategy, including:

[0042] Obtaining the historical environmental data and the corresponding historical ice melting effect data of each of the scenarios to construct a mapping model through a reinforcement learning algorithm;

[0043] Updating the control strategy of the combined mobile ice melting system through the mapping model, and judging whether the control parameters in the updated control strategy meet the preset parameter threshold;

[0044] Adjusting the control strategy that meets the preset parameter threshold according to each functional module in the combined mobile ice melting system to obtain a multi-device collaborative control strategy;

[0045] Based on each of the scenarios, classifying the historical ice melting effect data by a clustering analysis algorithm to obtain multiple typical working conditions of icing degrees;

[0046] Segmenting each of the scenarios according to the multiple typical working conditions of icing degrees to adjust the multi-device collaborative control strategy to obtain a multi-device collaborative segmented control strategy as the updated control strategy for output.

[0047] As one of the preferred solutions, the method for constructing a multi - level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimize the updated control strategies according to the operation results to obtain a target control strategy for controlling the execution of the combined mobile de - icing system includes:

[0048] Construct a multi - level system performance simulation platform using virtualization technology; the multi - level system performance simulation platform includes a power equipment model layer, a power grid topology layer, and a control strategy layer;

[0049] Control the multi - level system performance simulation platform to run each of the scenarios and their corresponding multi - device collaborative segmented control strategies to collect real - time performance data;

[0050] Judge whether the real - time performance data reaches a preset performance threshold, and when the real - time performance data does not reach the preset performance threshold, optimize the functional modules and their topological structures to update the multi - device collaborative segmented control strategy;

[0051] Repeat the policy operation step and the performance judgment step based on the updated multi - device collaborative segmented control strategy until the updated real - time performance data reaches the preset performance threshold, and then output the finally obtained multi - device collaborative segmented control strategy as the target control strategy to control the execution of the combined mobile de - icing system.

[0052] The second aspect of the present invention provides a modular - based combined mobile de - icing control system, including:

[0053] A demand model construction module, configured to obtain the de - icing demand parameters of different transmission lines in the power grid to construct a de - icing demand model;

[0054] An equipment combination generation module, configured to quantify the voltage and current output data of the transmission lines based on the de - icing demand model using a multi - objective optimization algorithm to generate a preliminary equipment combination;

[0055] An equipment combination correction module, configured to evaluate the performance degradation trend of the preliminary equipment combination under multiple scenarios to obtain an environmental adaptability correction parameter to update the preliminary equipment combination to obtain a final equipment combination;

[0056] A control strategy generation module, configured to construct a combined mobile de - icing system according to the final equipment combination using a modular design method and generate a control strategy for the combined mobile de - icing system through a fuzzy control algorithm;

[0057] A control strategy update module, configured to introduce an adaptive learning mechanism based on the control strategy to update the control parameters in the control strategy to obtain an updated control strategy;

[0058] A control strategy execution module is used to build a multi-level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimize the updated control strategies according to the running results to obtain target control strategies for controlling the execution of the combined mobile de-icing system.

[0059] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0060] (1) By building an accurate de-icing demand model and optimizing the equipment combination, the de-icing demand of the transmission line can be more accurately matched, thereby improving the de-icing efficiency and accuracy; by evaluating the performance degradation trend of the equipment combination under various scenarios and making corrections accordingly, the environmental adaptability of the system is enhanced, enabling it to operate stably under different climate and geographical conditions;

[0061] (2) The introduction of the fuzzy control algorithm and the adaptive learning mechanism enables the control strategy to be adaptively adjusted according to real-time data and environmental changes, improving the response speed and stability of the system; through system performance simulation and optimization, potential problems can be discovered and solved in advance, reducing power outages and maintenance costs caused by equipment failures or improper control;

[0062] (3) By comprehensively applying a variety of advanced technologies and methods, the accurate matching and efficient management of the de-icing demand of the transmission lines in the power grid are realized, which helps to timely and effectively remove the ice on the transmission lines, prevent line breaks and power outages caused by icing, and is of great significance for improving the safety and stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0064] Figure 1 is a flowchart of a modular-based combined mobile de-icing control method provided by an embodiment of the present invention;

[0065] Figure 2 is a structural diagram of a modular-based combined mobile de-icing control system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0067] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0068] In the description of the present application, it should be noted that unless otherwise clearly defined and limited, the terms "mounted", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0069] In the description of the present application, it should be noted that unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0070] In one embodiment, as Figure 1 shown, the first aspect of the present invention provides a modular combined mobile ice melting control method, including:

[0071] S1. Obtain the ice melting demand parameters of different transmission lines in the power grid to construct an ice melting demand model. Since the core of the DC ice melting method in practical applications lies in simultaneously meeting the ice melting demands of different transmission lines in the power grid, that is, the conductors and ground wires, this requires the combined mobile ice melting system to have the output capabilities of high current and high voltage. However, high current and high voltage need to match the corresponding equipment capacity and heat dissipation capacity, and the improvement of equipment capacity and heat dissipation capacity will increase the volume and cost of the combined mobile ice melting system, which conflicts with the requirements of portability and economy for on-site operations. Moreover, there are differences in the ice melting demands of conductors and ground wires. The ice melting of conductors usually requires a higher current density, while due to the structural characteristics of ground wires, a higher voltage stability is required. This difference makes it difficult to optimize the two output modes simultaneously during system design and operation, easily resulting in performance waste. Based on this, the present invention obtains the high current density value required for conductors and the high voltage stability parameters required for ground wires according to the differences in the ice melting demands of conductors and ground wires in the power grid, to establish an ice melting demand model and coordinate the dynamic parameters of the demands of conductors and ground wires, ensuring efficient and safe ice melting operations.

[0072] In one embodiment, step S1 includes:

[0073] Obtain the current density of the conductor and the voltage stability value of the ground wire, and compare them with a preset ice melting current threshold and a preset ice melting voltage threshold respectively, and quantify the high current density value of the conductor and the high voltage stability value of the ground wire according to the comparison results;

[0074] Construct an ice melting demand difference model based on the high current density value and the high voltage stability value, and generate ice melting optimization parameters through a machine learning algorithm based on the ice melting demand difference model;

[0075] Obtain the current quantity, voltage value, density value, and ice melting quantity data of the conductor and the ground wire, combine them with the ice melting optimization parameters to construct a multi-dimensional feature set, and construct an ice melting demand model based on the multi-dimensional feature set.

[0076] Specifically, the present invention collects original data such as wire current density, ground wire voltage stability value, current quantity, voltage value, density value, etc. measured by professional measurement equipment, and cleans these data, such as removing outliers, normalizing, etc., to ensure data consistency; then compares the preprocessed current density and voltage stability value with a preset ice melting current threshold and a preset ice melting voltage threshold respectively. If the current density value is less than the preset ice melting current threshold, calculate the required high current density value (obtained by the sum of the preset ice melting current threshold and the dynamic compensation value, and the dynamic compensation value can be determined according to historical data), otherwise use the current density value as the required high current density value of the wire. Similarly, perform corresponding processing on the voltage stability value to obtain the required high voltage stability value of the ground wire; among them, the preset ice melting current threshold and the preset ice melting voltage threshold can be set according to industry standards or historical experience, and the two are used to judge whether the current transmission line is in a high ice melting demand state. The preset ice melting current threshold can be set to 2.5 amperes per square millimeter. For example, if the cross-sectional area of a certain wire is 200 square millimeters and the current density is 1.8 amperes per square millimeter, it needs to be increased to 3 amperes per square millimeter to meet the ice melting requirements; and the ground wire voltage stability reflects the safety and reliability of the ground wire during the ice melting process. The preset ice melting voltage threshold is usually between 1000 volts and 1200 volts. If the ground wire voltage stability is insufficient, it may lead to an unsatisfactory ice melting effect. Taking a certain ground wire as an example, the current voltage stability is 800 volts, and it needs to be increased to 1100 volts to ensure the ice melting effect.

[0077] Then, use the high current density value and the high voltage stability value as input parameters to establish a mathematical relationship (difference index) to describe the demand difference between the two, and then obtain an ice melting demand difference model to reflect the mismatch degree of the two demands, and use the ice melting demand difference model to drive parameter optimization. Input the difference index output by the ice melting demand difference model and environmental parameters (temperature, humidity, ice cover thickness, etc.) into a machine learning model trained with historical ice melting data (high current density value, high voltage stability value, ice melting effect, etc.) and environmental parameters as training data and using supervised learning (such as random forest, XGBoost) to output the optimized current of the wire and the optimized voltage of the ground wire, that is, the ice melting optimization parameters.

[0078] Finally, use the ice melting optimization parameters to combine the original data such as the current quantity, voltage value, density value, and ice melting quantity data of different transmission lines to construct a multi-dimensional feature set, and design a regression model (such as multiple linear regression, support vector regression) based on the multi-dimensional feature set to establish a relationship model between the ice melting quantity and the ice melting optimization parameters, that is, the ice melting demand model.

[0079] By quantifying the current density and voltage stability values and combining the ice melting optimization parameters generated by machine learning algorithms, the present invention can more accurately identify the ice melting requirements and their differences of different transmission lines, thereby improving the efficiency of ice melting operations; the accurate ice melting requirement model helps to avoid unnecessary ice melting operations, thus saving power resources and operating costs; this solution integrates multiple links such as data measurement, machine learning algorithms and model construction, providing strong support for the intelligent management of the power grid.

[0080] In one embodiment, obtaining the current quantity, voltage value, density value and ice melting quantity data of the wire and the ground wire, combining them with the ice melting optimization parameters to construct a multi-dimensional feature set, and constructing an ice melting requirement model based on the multi-dimensional feature set includes:

[0081] Obtaining the current quantity, voltage value, density value and ice melting quantity data of the wire, and selecting the wire-related data with the current quantity reaching the first preset threshold from them;

[0082] Obtaining the current quantity, voltage value, density value and ice melting quantity data of the ground wire, and selecting the ground wire-related data with the voltage quantity reaching the second preset threshold from them;

[0083] Combining the wire-related data, the ground wire-related data and the ice melting optimization parameters to form a multi-dimensional feature set for constructing an ice melting requirement model;

[0084] Based on the ice melting requirement model, making a matching judgment on the ice melting quantity of the wire and the ice melting quantity of the ground wire, and when the matching judgment passes, using a machine learning algorithm to train the ice melting requirement model to obtain an optimized model parameter set;

[0085] Performing an expected verification on the final ice melting quantity of the wire and the final ice melting quantity of the ground wire through the ice melting requirement model configured with the optimized model parameter set, and outputting the ice melting requirement model that passes the expected verification.

[0086] Specifically, data such as the current, voltage value, density value, and ice melting amount associated with the wire passing time are obtained, and the wire-associated data with the current reaching the first preset threshold is selected from them, that is, the relevant data with the wire ice melting amount meeting the requirements is determined. Similarly, the ground wire-associated data with the voltage reaching the second preset threshold needs to be selected from the data such as the current, voltage value, density value, stability parameter, and ice melting amount associated with the ground wire passing time. The selected data are the relevant data with the ground wire ice melting amount meeting the requirements. The selected wire-associated data, ground wire-associated data, and ice melting optimization parameters are combined to form a multi-dimensional feature set to construct an ice melting demand model. This model is used to describe the relationship between ice melting data (ice melting thickness, ice melting time, etc.) and the optimized current of the wire and the optimized voltage of the ground wire. Taking a certain line as an example, the wire ice melting amount is positively correlated with the current, and the ground wire ice melting amount has an exponential relationship with the voltage stability. The ice melting demand model can be constructed based on these relationships.

[0087] Then, based on the ice melting demand model, information such as the high current density and current of the wire and information such as the high voltage stability and required voltage value of the ground wire are obtained, and the ice melting amounts of the two are calculated respectively. It is judged whether the ice melting amounts of the two match (that is, whether the difference in the ice melting amounts of the wire and the ground wire is within the allowable error range). Since the determination of the ice melting amount needs to meet the requirements of both the wire and the ground wire at the same time, for example, the wire ice melting thickness reaches 0.5 cm, the ground wire ice melting thickness reaches 0.4 cm, and the matching degree is more than 90%, it indicates that the parameter setting of the ice melting demand model is reasonable and the model can be used; otherwise, it returns to the ice melting optimization parameter generation step to recalculate until the matching judgment passes, and then the regression analysis method in the machine learning algorithm is used to train the ice melting demand model to obtain an optimized model parameter set.

[0088] Finally, through the ice melting demand model configured with the optimized model parameter set, the final ice melting amount of the wire and the final ice melting amount of the ground wire are obtained, and it is judged whether the ice melting effects of the two reach the expectation (ice melting thickness, ice melting time, energy consumption, etc.). When the expected effect is achieved, the ice melting demand model parameters are determined to complete the establishment and verification of the model. If not, the model parameters are adjusted and the expected effect judgment is performed again until the expected effect is achieved. In addition, in practical applications, factors such as environmental temperature and ice layer thickness need to be considered in the verification process of the ice melting demand model. For example, in an environment of minus 10 degrees Celsius, the ice thickness on the surface of a certain line wire is 1 cm, and the required ice melting time calculated by the model is 30 minutes, and the actual ice melting effect is consistent with the expectation, which proves that the model has good practicability.

[0089] By collecting and processing multi-dimensional feature data and combining machine learning algorithms, the ice melting demand model constructed by the present invention can more accurately predict the ice melting amount of conductors and ground wires; based on the prediction results of the ice melting demand model, a more reasonable ice melting strategy can be formulated to reduce the energy consumption and time cost during the ice melting process; by optimizing the ice melting process, the risk of power system failures caused by ice melting can be reduced, and the stability and reliability of the power system can be improved.

[0090] S2. Based on the ice melting demand model, use a multi-objective optimization algorithm to quantify the voltage and current output data of the transmission line to generate a preliminary equipment combination.

[0091] In one embodiment, step S2 includes:

[0092] Construct an objective function based on the ice melting demand model, and use a multi-objective optimization algorithm to solve the objective function to obtain voltage and current output data.

[0093] Under the constraints of equipment capacity and heat dissipation capacity, configure ice melting equipment according to the voltage and current output data to generate the preliminary equipment combination.

[0094] Specifically, the present invention constructs an objective function based on the ice melting demand model. For example, under the premise of simultaneously satisfying the conductor current density and the ground wire voltage stability, maximize the ice melting efficiency, the shortest ice melting time, minimize the ice melting power consumption and cost, etc., and use the safety threshold (current and voltage upper limits) as the constraint condition, and use the particle swarm optimization algorithm or genetic algorithm to solve the objective function: by setting the parameters of the algorithm, such as the population size, the number of iterations, etc., and performing initialization operations, execute the particle swarm optimization algorithm, and obtain a set of non-dominated solutions (Pareto optimal solutions) through iterative search. These solutions perform well on multiple objective functions; select a set of solutions that meet the actual requirements from the non-dominated solution set as the optimization result of the voltage and current output data to balance the large current and high voltage output; then, under the constraints of equipment capacity and heat dissipation capacity, configure ice melting equipment according to the voltage and current output data to obtain a preliminary equipment combination. For example, in a certain ice melting scenario, the equipment capacity limit is 1000 kVA, and the heat dissipation capacity is 60 watts per minute. The optimal output combination calculated by the particle swarm optimization algorithm is: current 600 amperes, voltage 1100 volts. This combination not only meets the ice melting demand but also does not exceed the equipment limit. Then, according to the optimal output combination, consider factors such as the reliability and economy of the equipment, determine the parameters such as the number and model of the equipment, and configure the equipment to form a preliminary equipment combination plan, providing a basis for subsequent implementation.

[0095] The voltage and current output data obtained by the multi-objective optimization algorithm of the present invention can more accurately meet the ice melting requirements, thereby improving the ice melting efficiency; the optimized equipment combination scheme can reduce the operation cost of the equipment while ensuring the ice melting effect; the reasonable equipment combination and voltage and current output data configuration help to enhance the stability of the power system and reduce the impact on the grid operation caused by the ice melting operation.

[0096] S3. Evaluate the performance attenuation trend of the preliminary equipment combination in multiple scenarios, obtain the environmental adaptability correction parameters to update the preliminary equipment combination, and obtain the final equipment combination;

[0097] In one embodiment, step S3 includes:

[0098] Obtain the performance operation data of the preliminary equipment combination in each of the scenarios to characterize the performance attenuation trend, and use the regression analysis method to process the performance operation data to obtain the environmental adaptability correction parameters;

[0099] Adjust the equipment models and quantities in the preliminary equipment combination based on the environmental adaptability correction parameters to obtain a corrected equipment combination;

[0100] Obtain the voltage and current output range of the corrected equipment combination, and based on the voltage and current output range, use the decision tree algorithm to determine whether the corrected equipment combination meets the ice melting requirements of each of the scenarios;

[0101] When the corrected equipment combination meets the ice melting requirements of each of the scenarios, obtain the performance operation data of the corrected equipment combination in each of the scenarios, and based on the performance operation data, use the clustering algorithm to determine whether the corrected equipment combination meets the preset performance attenuation conditions;

[0102] Output the corrected equipment combination that meets the preset performance attenuation conditions as the final equipment combination.

[0103] Specifically, in application scenarios such as high altitude and low temperature environments, it will cause equipment performance attenuation. For a certain ice melting equipment in an environment with an altitude of 3,000 meters, the output current will decrease by 15%, and the voltage stability will decrease by 10%. Based on this, the present invention conducts simulation operation tests on the preliminary equipment combination in multiple preset scenarios (such as different temperature, humidity, wind speed and other environmental conditions), records the changes of its performance parameters (such as power output, efficiency, failure rate, etc.) over time to characterize the performance attenuation trend, and uses the regression analysis method to process the collected performance operation data to identify the correlation between equipment performance attenuation and environmental factors (such as temperature, humidity), so as to calculate the environmental adaptability correction parameters to reflect the performance change law and attenuation trend of the equipment in different environments.

[0104] Next, based on the environmental adaptability correction parameters obtained from the regression analysis, adjust the equipment models and quantities in the preliminary equipment combination, that is, adjust the equipment capacity and redundancy design to optimize the performance of the preliminary equipment combination in different environments, form a corrected equipment combination, and obtain the voltage and current output range of the corrected equipment combination (such as current 400 - 700 A, voltage 800 - 1200 V). Construct a decision tree node to determine whether the corrected equipment combination can meet the ice melting requirements of each scenario. Input the equipment voltage and current data (such as current 380 A at low temperature), traverse the decision tree to determine whether the requirements are met. Since the current 380 A is lower than the lower limit (400 A), it is determined that the equipment does not meet the range standard and does not meet the ice melting requirements of the scenario (such as current 500 A at low temperature). Return to the multi-objective optimization step, recalculate after adjusting the constraints until the equipment voltage and current data obtained after adjustment not only meet the voltage and current output range but also meet the ice melting requirements of the scenario, then the iteration ends. The decision tree algorithm can quickly and accurately evaluate whether the equipment performance meets the requirements by integrating historical data and expert experience. If not, return to the preliminary equipment selection stage to recalculate the optimal output combination. Among them, the selection of specific equipment during correction should include main transformers, switchgear, control systems, etc. For each type of equipment, environmental adaptability needs to be considered. For example, in an ice melting project for a transmission line in a mountainous area, originally an 800 kVA equipment was planned to be used, and after considering environmental correction, it was upgraded to 1000 kVA and two standby equipment were added to ensure that the ice melting requirements can still be met under extreme weather conditions.

[0105] Then, on the basis that the corrected equipment combination meets the ice melting requirements, further obtain its performance operation data simulated in each scenario, and use the K-means or hierarchical clustering algorithm to determine whether the corrected equipment combination meets the preset performance decay conditions. The clustering algorithm can identify the laws of equipment performance decay and can divide the equipment performance data into different categories according to environmental conditions (such as altitude, temperature). By comparing the performance data categories of the corrected equipment combination with the preset performance decay conditions, determine whether it meets the requirements. If not, correct the corrected equipment combination again. For example, the performance of a certain type of equipment decays significantly in areas above 3000 meters and is classified as the "high decay class". Analyze the decay laws of various types of equipment and determine that it is not within the preset performance decay conditions (such as decay ≤ 5%). Then, when optimizing the selection for the high decay class environment, special designed equipment (such as enhanced insulation, enhanced heat dissipation) can be considered according to the specific scenario, or special equipment can be used in plateau areas, so that the performance decay of the corrected equipment combination in high altitude environments is controlled within 5% and can meet the ice melting requirements in extreme environments.

[0106] Finally, the corrected equipment combination that meets the preset performance degradation conditions is output as the final equipment combination, which means that this equipment combination has good environmental adaptability and stable performance in various scenarios. In addition, during the optimization process, electrical parameters, environmental adaptability, and equipment reliability also need to be considered simultaneously to ensure the stable operation of the combined mobile de-icing system under various working conditions.

[0107] Through the introduction of regression analysis method and environmental adaptability correction parameters, the present invention can significantly improve the adaptability and stability of the equipment combination in different environments, ensuring that it can still maintain good performance under various harsh conditions; based on the adjustment of equipment models and quantities according to performance operation data, it can optimize resource allocation, avoid excessive or insufficient equipment investment, and reduce operation costs; using the decision tree algorithm to quickly judge the de-icing ability of the equipment combination can ensure a rapid response to de-icing requirements in case of emergencies and improve the emergency handling efficiency; through the judgment of performance degradation conditions by the clustering algorithm, it can screen out equipment combinations with stable performance and slow attenuation, enhancing the reliability and durability of the overall system; by establishing a scientific equipment selection system, it can significantly improve the de-icing efficiency and reduce equipment failure rates; through steps such as data collection, analysis, verification, and optimization, this solution realizes the precise adjustment and optimization of the preliminary equipment combination, and finally obtains the final equipment combination that meets the performance requirements in various scenarios.

[0108] S4. According to the final equipment combination, adopt the modular design method to construct a combined mobile de-icing system, and generate a control strategy for the combined mobile de-icing system through the fuzzy control algorithm;

[0109] In one embodiment, the adopting the modular design method to construct a combined mobile de-icing system according to the final equipment combination includes:

[0110] Conduct functional division on the final equipment combination according to each of the scenarios to obtain several functional modules;

[0111] Adopt the shortest path algorithm and heuristic search algorithm to optimize the layout of each of the functional modules to obtain the setting positions of each of the functional modules;

[0112] Based on each of the setting positions, determine the topological structure of each of the functional modules through the fault tree analysis method and multi-attribute decision algorithm, and construct a combined mobile de-icing system according to the setting positions and topological structures of each of the functional modules.

[0113] Specifically, the present invention carefully divides the functional requirements of the final equipment combination according to each scenario, decomposes the equipment combination into several functional modules with specific functions, such as an energy supply module, an ice melting execution module, a monitoring and feedback module, etc.; after determining the functional modules, the shortest path algorithm (such as Dijkstra algorithm, Floyd-Warshall algorithm, etc.) is used to analyze the connection paths between the functional modules to minimize energy transmission loss and response time, and combined with a heuristic search algorithm (such as genetic algorithm, ant colony algorithm, etc.) to further optimize the layout of each functional module, considering actual space limitations, mutual interference between devices, etc., to obtain the optimal installation positions and connection methods of each functional module; based on the installation positions of each functional module, the fault tree analysis method is used to analyze the possible fault modes and their impacts on the system, identify key functional modules and potential risk points, and combined with a multi-attribute decision-making algorithm (such as TOPSIS, AHP, etc.) to comprehensively consider multiple dimensions such as the performance, cost, and reliability of the functional modules, determine the optimal topological structure between each functional module, and ensure the efficient, stable, and reliable operation of the system; finally, according to the installation positions and topological structures of each functional module, using the modular design concept, each functional module is assembled and integrated according to a predetermined plan to construct a combined mobile ice melting system applicable to multiple scenarios.

[0114] The modular design method can be flexibly adjusted according to the scale and application scenarios of the combined mobile ice melting system. Taking the transmission lines in a certain alpine mountainous area as an example, it is necessary to de-ice five transmission lines with different voltage levels. The final equipment combination uses three high-power devices and two standby devices to construct a combined mobile ice melting system. The shortest connection distance between each device is calculated through the Dijkstra algorithm (taking the device position coordinates and connection path weights, such as cable length and loss as inputs, and the shortest connection path between each functional module as the output) and the ant colony algorithm (taking the device position, path weight, number of ants, and number of iterations as inputs, and the global optimal layout plan, such as device position and connection method as the output) to obtain the installation position and connection method to arrange the devices near the line intersection nodes to reduce cable loss. Then, the fault tree analysis method (taking the fault modes of the functional modules, such as power module power failure and control module communication interruption as inputs, and system reliability evaluation and key fault paths as outputs) and the TOPSIS algorithm (taking the topological structure candidate scheme and evaluation indicators such as reliability, cost, and scalability as inputs, and the optimal topological structure as the output) are used to determine that the devices are connected in a ring topology structure, which can achieve bidirectional power supply ability and improve system reliability.

[0115] The modular design adopted by the present invention enables the system to flexibly adjust the configuration and layout of functional modules according to the requirements of different scenarios, which is easy to expand and upgrade, and reduces the costs of system maintenance and update; through the optimized layout of the shortest path algorithm and the heuristic search algorithm, the energy transmission loss and response time are reduced, and the overall performance of the system is improved; the fault tree analysis method can identify potential risk points of the system, and the multi-attribute decision-making algorithm comprehensively considers multiple dimensions to ensure that the system has high reliability at the design stage; through functional division and modular design, the system can flexibly meet the requirements of multiple ice melting scenarios, and improves the versatility and practicability of the system; this solution realizes the precise construction and optimization of the combined mobile ice melting system by combining the modular design method with advanced methods such as the shortest path algorithm, the heuristic search algorithm, the fault tree analysis method and the multi-attribute decision-making algorithm, and improves the performance, reliability and flexibility of the system.

[0116] In one embodiment, generating a control strategy for the combined mobile ice melting system through a fuzzy control algorithm includes:

[0117] Using the ice melting requirements and real-time environmental data of each of the scenarios as input variables, and using the current mode or voltage mode of the topological structure in the combined mobile ice melting system as output variables;

[0118] Fuzzifying the input variables and the output variables to obtain fuzzy sets, and performing fuzzy inference on the fuzzy sets of the input variables and the fuzzy rule base through Mamdani inference to obtain the fuzzy sets of the output variables;

[0119] Defuzzifying the fuzzy sets of the output variables by using the maximum membership degree method to obtain a control strategy;

[0120] Obtaining the real-time ice melting data of each of the scenarios under the control strategy to match with the ice melting requirements of each of the scenarios, and updating the topological structure when the matching is unsuccessful;

[0121] Judging whether the updated topological structure meets the preset performance decay condition through a clustering algorithm, and re-executing the control strategy generation step based on the topological structure that meets the preset performance decay condition until the real-time ice melting data of each of the scenarios in the simulation run of the finally obtained control strategy matches the ice melting requirements of each of the scenarios, and outputting the finally obtained control strategy.

[0122] Specifically, the present invention uses the ice melting requirements of each scenario and real-time environmental data (such as temperature, humidity, wind speed, ice layer thickness, etc.) as input variables, and uses the current mode or voltage mode of the topology structure in the combined mobile ice melting system (used to control the operation of the ice melting equipment) as output variables. The input and output variables are fuzzified to obtain corresponding fuzzy sets. For example, the ice thickness can be divided into fuzzy sets such as "low", "medium", "high", etc., and the real-time temperature data can be divided into fuzzy sets such as "extremely low", "moderate", "high", etc. The output variables are fuzzified into "constant voltage priority, hybrid mode, constant current priority", etc. Among them, the fuzzy set describes the degree to which a variable belongs to a certain fuzzy concept by defining a membership function. Then, a fuzzy rule base is constructed, which contains a series of rules based on expert experience and historical data, used to describe the relationship between the input variables and the output variables. For example, IF ice thickness = high AND temperature = extremely low THEN output = constant current mode (600 A); IF ice thickness = medium AND wind speed = high THEN output = hybrid mode (500 A + 900 V), etc. Then, the Mamdani inference method is used to match and infer the fuzzy sets of the input variables with the rules in the fuzzy rule base to obtain the fuzzy set of the output variables, that is, the set of possible current modes or voltage modes, and the maximum membership degree method or other defuzzification methods are used to defuzzify it to obtain the control strategy. Among them, the control strategy of the fuzzy control algorithm can be dynamically adjusted based on the ice thickness of the wire and meteorological conditions. For example, in a certain ice melting scenario, when the ice thickness is less than five millimeters, a constant voltage mode is used to output 800 volts, and when the ice thickness reaches one centimeter, it is switched to a constant current mode to output 500 amperes of current.

[0123] Then, the real-time ice melting data of each scenario under the corresponding control strategy is obtained and matched with the ice melting requirements of each scenario. If the match is unsuccessful (that is, the real-time ice melting data does not meet the ice melting requirements), the topology structure is updated, which can be achieved by adding equipment or adjusting the connection method, etc. (such as upgrading from a single loop network to a double loop network), and the layout and parameters are recalculated to improve the ice melting effect. The ice melting requirements of the wire and the ground wire are derived from the real-time monitoring of the scenario. For example, the on-line monitoring device installed on a certain transmission line shows that the ice thickness of the wire is 8 millimeters and the ice thickness of the ground wire is 6 millimeters. Based on these data, the system determines that an ice melting current of 500 amperes is required. Through calculation, it is found that the maximum output current under the existing topology structure is 400 amperes, which cannot meet the ice melting requirements, and the system solution needs to be re-optimized. The updated topology structure adopts a double loop network design and adds a device with a power of 1200 kVA. Under the new solution, the maximum output current of the system can reach 600 amperes, meeting the ice melting requirements, indicating that the newly obtained system and control strategy are successfully matched with the scenario requirements.

[0124] To verify the feasibility of the solution, the present invention uses a clustering algorithm to determine whether the updated topological structure meets the preset performance decay condition, and adopts a density-based clustering analysis algorithm to classify the historical de-icing data according to environmental parameters such as air temperature and wind speed. The analysis results in a certain transmission line de-icing scenario show that under similar meteorological conditions, the de-icing success rate of the updated topological structure exceeds 95%, reaching the preset performance threshold. The finally determined combined mobile de-icing system consists of four main devices and two standby devices, adopts a double-ring network topological structure, and the control strategy automatically selects a constant voltage or constant current mode according to the ice thickness. The voltage output range is 600 to 1000 volts, and the current output range is 300 to 600 amperes. The system reserves a secondary expansion interface, and devices can be added or the topological structure can be adjusted according to future requirements. If the updated topological structure does not meet the preset performance decay condition, the control strategy generation steps are re-executed, including fuzzification, fuzzy inference, and defuzzification, until a new control strategy is obtained; the above process is repeated until the real-time de-icing data of each scenario can completely match the de-icing requirements of each scenario when the finally obtained control strategy is simulated and run. When a control strategy that meets the de-icing requirements of all scenarios is found, it is output as the final control strategy.

[0125] Due to the characteristics of the fuzzy control algorithm of the present invention that can handle uncertainty and fuzziness, the system can better adapt to various complex and changeable de-icing scenarios; by continuously iterating and updating the control strategy, the performance of the system can be gradually optimized to ensure that the real-time de-icing data meets the de-icing requirements; the fuzzy control algorithm avoids the complex mathematical models and precise calculations in traditional control methods, reducing the complexity and implementation difficulty of the system; by using the clustering algorithm to judge the performance decay of the topological structure and updating it when necessary, the system can be ensured to maintain stable performance during long-term operation; this solution generates a control strategy for the combined mobile de-icing system through the fuzzy control algorithm, realizing precise control and optimization of complex de-icing scenarios, and improving the adaptability, robustness, and flexibility of the system.

[0126] S5. Based on the control strategy, introduce an adaptive learning mechanism to update the control parameters in the control strategy to obtain an updated control strategy;

[0127] In one embodiment, step S5 includes:

[0128] Obtain the historical environmental data and corresponding historical de-icing effect data of each scenario to construct a mapping model through a reinforcement learning algorithm;

[0129] Update the control strategy of the combined mobile de-icing system through the mapping model, and judge whether the control parameters in the updated control strategy meet the preset parameter threshold;

[0130] Adjust the control strategy that meets the preset parameter thresholds according to each functional module in the combined mobile de-icing system to obtain a multi-device collaborative control strategy;

[0131] Based on each of the scenarios, use the clustering analysis algorithm to classify the historical de-icing effect data to obtain multiple typical working conditions of icing degrees;

[0132] Segment each of the scenarios according to the multiple typical working conditions of icing degrees to adjust the multi-device collaborative control strategy, and obtain a multi-device collaborative segmented control strategy as the updated control strategy for output.

[0133] Specifically, the control strategy in the topological structure requires real-time environmental data as input, and the adaptive learning mechanism establishes a mapping relationship between environmental parameters and de-icing effects based on historical data. Then, the present invention obtains the historical environmental data (such as temperature, humidity, wind speed, ice layer thickness, etc.) and corresponding historical de-icing effect data (such as de-icing speed, de-icing efficiency, time, energy consumption, etc.) of each scenario, and performs cleaning, denoising, and standardization processing on these data to ensure the quality and consistency of the data; then uses reinforcement learning algorithms (such as Q-learning, deep Q-network DQN, policy gradient method, etc.) to construct the correlation relationship between the input (environmental data and current control parameters) and the output (de-icing effect prediction data). Under the goal of minimizing the de-icing time and not exceeding the voltage and current safety thresholds, the gradient descent method or Bayesian optimization method is used to iteratively update the control parameters, so that the reinforcement learning algorithm learns how to adjust the control parameters according to environmental data to maximize the de-icing effect through continuous trial and error and iterative optimization, and then obtains the mapping model. Taking a mountainous area line as an example, the present invention analyzes its de-icing records within one year and finds that when the temperature is minus eight degrees and the wind speed is three meters per second, de-icing is carried out with a current of five hundred amperes, and it takes about forty minutes to complete the de-icing process. The system can establish a correlation model based on these data to predict the de-icing time and current intensity required under different environmental conditions.

[0134] Then, update the control strategy of the combined mobile de-icing system through the mapping model to obtain new control parameters, and judge whether the updated control parameters meet the preset parameter thresholds (such as ice thickness reduction rate < 1 mm / min, etc.) to ensure the rationality and feasibility of the control strategy. The threshold setting of the control parameters is based on the safe current-carrying capacity of the wire and the de-icing efficiency. Still taking the mountainous area line as an example, the safe current-carrying capacity of a certain type of wire is eight hundred amperes. Considering the safety margin, the upper limit of the de-icing current is set to six hundred amperes. When the predicted de-icing time exceeds sixty minutes, the system judges that the control parameters do not meet the requirements and needs to be recalculated. After calculation based on the mapping model, the system obtains a de-icing current of five hundred and fifty amperes, and the de-icing time is shortened to thirty-five minutes.

[0135] According to each functional module in the combined mobile de-icing system (such as heating equipment, cooling equipment, sensors, etc.), adjust the control strategy that meets the preset parameter thresholds to achieve collaborative work among multiple devices, obtain a multi-device collaborative control strategy considering the mutual influence and restriction among devices to ensure the optimal performance of the overall system; the optimized system operation plan needs to consider the coordinated cooperation of multiple de-icing devices. Taking a double-circuit transmission line as an example, when two de-icing devices work simultaneously, Device 1 outputs 800 volts in a constant voltage mode, and Device 2 outputs 400 amperes in a constant current mode. By obtaining the de-icing effect data of the two lines through an on-line monitoring device, it is found that the de-icing speed of Device 2 is faster, and the system automatically switches Device 1 to the constant current mode as well.

[0136] And use clustering analysis algorithms (such as K-means, hierarchical clustering, etc.) to classify the historical de-icing effect data according to environmental characteristics (temperature, wind speed, ice thickness) to obtain typical working conditions of various icing degrees. Segment each scenario according to the typical working conditions of various icing degrees to formulate different control strategies for different icing degrees, and then adjust the multi-device collaborative control strategy to obtain a multi-device collaborative segmented control strategy as the updated control strategy output for use in the combined mobile de-icing system, and better adapt to scenarios of different icing degrees. Since the clustering analysis method can classify historical de-icing data according to environmental characteristics and evaluate the applicable range of the control strategy, taking the de-icing records in a certain area within one year as an example, using the density-based clustering algorithm to analyze the de-icing data within one year, it is found that the icing degree in this scenario can be divided into three types of typical working conditions: slight icing, moderate icing, and severe icing. The success rate of the updated control strategy in the slight icing working condition reaches 98%, and the success rate in the severe icing working condition is 92%. Based on this, segmented control can be carried out on the updated control strategy, and the de-icing mode and parameters can be automatically selected according to the icing degree. Exemplarily, the multi-device collaborative segmented control strategy includes: when the ice thickness is less than 5 mm, output 700 volts in a constant voltage mode; when the ice thickness is between 5 and 10 mm, output 400 to 500 amperes in a constant current mode; when the ice thickness exceeds 10 mm, use time-division control, first break the ice with high-voltage oscillation, and then melt the ice with a large current.

[0137] The present invention constructs a mapping model through a reinforcement learning algorithm, which can more accurately adjust control parameters according to environmental data, improving the control accuracy of the ice melting effect; the adaptive learning mechanism can continuously update the control strategy based on historical data, enabling the system to better adapt to different environments and ice melting requirements; the multi-device collaborative control strategy can reasonably allocate the working states of each functional module, achieving optimal configuration and efficient utilization of resources; through clustering analysis and segmented control strategies, the system can formulate different control strategies for scenarios with different icing degrees, improving the robustness and stability of the system; this solution updates the control parameters in the control strategy by introducing an adaptive learning mechanism, achieving precise control and optimization of the combined mobile ice melting system, and improving the adaptability, robustness, and energy efficiency ratio of the system.

[0138] S6. Construct a multi-level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimize the updated control strategies according to the operation results to obtain a target control strategy for controlling the combined mobile ice melting system to execute;

[0139] In one embodiment, step S6 includes:

[0140] Construct a multi-level system performance simulation platform using virtualization technology; the multi-level system performance simulation platform includes a power equipment model layer, a power grid topology layer, and a control strategy layer;

[0141] Control the multi-level system performance simulation platform to run each of the scenarios and their corresponding multi-device collaborative segmented control strategies to collect real-time performance data;

[0142] Judge whether the real-time performance data reaches a preset performance threshold, and when the real-time performance data does not reach the preset performance threshold, optimize the functional module and its topology structure to update the multi-device collaborative segmented control strategy;

[0143] Repeat the strategy operation step and the performance judgment step based on the updated multi-device collaborative segmented control strategy until the updated real-time performance data reaches the preset performance threshold, and then output the finally obtained multi-device collaborative segmented control strategy as the target control strategy to control the combined mobile ice melting system to execute.

[0144] Specifically, the present invention uses virtualization technologies (such as VMware, Hyper-V, etc.) to construct a system performance simulation platform with multiple levels, including: Power equipment model layer: It contains simulation models of various power equipment, such as generators, transformers, etc. These models can simulate the operating characteristics and behaviors of actual equipment; Power grid topology layer: It constructs the topology of the combined mobile ice melting system, including the connection relationships and transmission paths between various power equipment; Control strategy layer: It realizes the simulation of various control strategies, that is, embeds fuzzy control, adaptive learning algorithms, and multi-device collaborative segmented control strategies to guide the operation of the power equipment model and the power grid topology layer, and supports dynamic parameter adjustment.

[0145] Then, on this simulation platform, various actual operating scenarios are simulated, such as different weather conditions, load changes, etc.; among them, the scenario parameter settings cover multiple dimensions, such as the preset temperature from minus five degrees to zero degrees, relative humidity from 85% to 90%, and wind speed from 3 to 5 m / s in the spring ice melting condition. For each scenario, the corresponding multi-device collaborative segmented control strategy is applied, and real-time performance data of the simulation is collected, such as conductor temperature, ice melting current, and bus voltage.

[0146] A series of performance thresholds can be set, such as voltage fluctuation range, current overload rate, energy consumption upper limit, etc. to evaluate whether the system performance meets the requirements. By comparing the ice melting effect achieved by the real-time performance data with the preset performance thresholds, it is judged whether the system performance meets the standards. If the real-time performance data does not reach the preset performance thresholds, it indicates that there are problems with the current control strategy or system structure, and the functional modules and power grid topology are optimized, such as adjusting equipment parameters and optimizing the power grid structure.

[0147] The optimized functional modules and topology are used to re-run the simulation platform, and the real-time performance data of the new simulation is collected. It is judged again whether the real-time performance data reaches the preset performance thresholds. If it still does not meet the standards, continue to optimize and repeat the above steps until the real-time performance data reaches the preset performance thresholds, indicating that the current control strategy is excellent enough to meet the system performance requirements, and the finally obtained multi-device collaborative segmented control strategy is output as the target control strategy to be executed in the corresponding actual scenario.

[0148] Through the construction and operation of a multi-level system performance simulation platform, the present invention can comprehensively simulate the operation scenarios and performance of an actual system, thereby discovering potential problems and optimizing them to improve system performance; by continuously iteratively optimizing functional modules, topological structures, and control strategies, the stability and reliability of the system can be enhanced, and the probability of faults can be reduced; performing control and optimization on the simulation platform can avoid the time and cost waste caused by trial and error and debugging in the actual system, and reduce the operation and maintenance costs; by verifying and optimizing the multi-device collaborative segmented control strategy through the simulation platform, the effectiveness and accuracy of the control strategy in actual operation can be ensured.

[0149] In the embodiment of the present application, based on the problem of how to improve the ice melting efficiency of transmission lines in high altitude and low temperature environments, a modular-based combined mobile ice melting control method is designed. It establishes an ice melting demand model according to the differences in ice melting demands of different transmission lines, uses a multi-objective optimization algorithm to calculate the optimal large current and high voltage output combinations, and selects appropriate devices by correcting parameters according to environmental adaptability; based on these devices, a modular design method is used to construct the topological structure of the combined mobile ice melting system, and a control strategy based on a fuzzy control algorithm is designed to dynamically adjust the large current and high voltage output modes to balance the ice melting demands of the conductor and the ground wire; an adaptive learning mechanism is introduced based on the control strategy to optimize its control parameters and improve the system operation efficiency; the performance of the control strategy after system simulation optimization in different scenarios is verified through a simulation platform to adjust the device selection and topological design to generate a target control strategy and execute it. The present invention solves the technical problems of ice melting of transmission lines in multiple scenarios such as high altitude and low temperature environments, realizes the intelligence and high efficiency of the ice melting process, and effectively improves the safety and reliability of power grid operation.

[0150] It should be noted that although the steps in the above flowchart are sequentially shown according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders.

[0151] In another embodiment, as Figure 2 shown, the second aspect of the present invention provides a modular-based combined mobile ice melting control system, including:

[0152] A demand model construction module 10, configured to obtain ice melting demand parameters of different transmission lines in the power grid to construct an ice melting demand model;

[0153] A device combination generation module 20, configured to quantify the voltage and current output data of the transmission line by using a multi-objective optimization algorithm based on the ice melting demand model to generate a preliminary device combination;

[0154] The device combination correction module 30 is used to evaluate the performance decay trend of the preliminary device combination in multiple scenarios, obtain the environmental adaptability correction parameters to update the preliminary device combination, and obtain the final device combination;

[0155] The control strategy generation module 40 is used to construct a combined mobile de-icing system according to the final device combination by using the modular design method, and generate a control strategy for the combined mobile de-icing system through a fuzzy control algorithm;

[0156] The control strategy update module 50 is used to update the control parameters in the control strategy by introducing an adaptive learning mechanism based on the control strategy, and obtain the updated control strategy;

[0157] The control strategy execution module 60 is used to construct a multi-level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimize the updated control strategy according to the operation results to obtain the target control strategy to control the execution of the combined mobile de-icing system.

[0158] It should be noted that each module in the above-mentioned modular-based combined mobile de-icing control system can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules. For the specific limitations of a modular-based combined mobile de-icing control system, refer to the limitations of a modular-based combined mobile de-icing control method in the above text. The two have the same functions and effects, and will not be elaborated here.

[0159] In summary, the present invention relates to the field of information technology, and discloses a modular-based combined mobile de-icing control method and system. It collects and analyzes the de-icing demand parameters of various transmission lines in the power grid to construct an accurate de-icing demand model, and uses a multi-objective optimization algorithm to quantify the voltage and current output data of the transmission line, thereby generating a preliminary device combination plan; it updates the device combination by evaluating the performance decay trend of the preliminary device combination in multiple scenarios to obtain the final device combination plan; uses the modular design method to construct a combined mobile de-icing system adapted to multiple scenarios according to the final device combination, and uses a fuzzy control algorithm to generate a preliminary control strategy. After introducing an adaptive learning mechanism to update the control parameters therein, a multi-level system performance simulation platform is constructed to further optimize it, and the target control strategy is obtained to control the execution of the combined mobile de-icing system. This solution can adapt to various application scenarios and effectively improve the de-icing efficiency of transmission lines.

[0160] Each embodiment in this specification is described in a progressive manner. For the parts that are the same or similar in each embodiment, reference can be made to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference can be made to the corresponding part of the method embodiment for relevant content. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0161] The above embodiments only represent several preferred implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the technical principle of the present invention, several improvements and substitutions can be made, and these improvements and substitutions should also be regarded as within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the protection scope of the claimed rights.

Claims

1. A modular-based combined mobile ice melting control method, characterized in that Including: Obtaining the ice melting demand parameters of different transmission lines in the power grid to construct an ice melting demand model; Based on the ice melting demand model, using a multi-objective optimization algorithm to quantify the voltage and current output data of the transmission line to generate a preliminary equipment combination; Evaluating the performance decay trend of the preliminary equipment combination under multiple scenarios, obtaining an environmental adaptability correction parameter to update the preliminary equipment combination, and obtaining a final equipment combination; According to the final equipment combination, using a modular design method to construct a combined mobile ice melting system, and generating a control strategy for the combined mobile ice melting system through a fuzzy control algorithm; Based on the control strategy, introducing an adaptive learning mechanism to update the control parameters in the control strategy to obtain an updated control strategy; Constructing a multi-level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimizing the updated control strategy according to the operation results to obtain a target control strategy to control the execution of the combined mobile ice melting system.

2. The modular-based combined mobile ice melting control method according to claim 1, wherein The obtaining the ice melting demand parameters of different transmission lines in the power grid to construct an ice melting demand model includes: Obtaining the current density of the conductor and the voltage stability value of the ground wire, respectively comparing them with a preset ice melting current threshold and a preset ice melting voltage threshold, and quantifying the high current density value of the conductor and the high voltage stability value of the ground wire according to the comparison results; Constructing an ice melting demand difference model based on the high current density value and the high voltage stability value, and generating an ice melting optimization parameter through a machine learning algorithm based on the ice melting demand difference model; Obtaining the current amount, voltage value, density value and ice melting amount data of the conductor and the ground wire, combining them with the ice melting optimization parameter to construct a multi-dimensional feature set, and constructing an ice melting demand model based on the multi-dimensional feature set.

3. The modular combined mobile ice melting control method according to claim 2, wherein The obtaining the current amount, voltage value, density value and ice melting amount data of the conductor and the ground wire, combining them with the ice melting optimization parameter to construct a multi-dimensional feature set, and constructing an ice melting demand model based on the multi-dimensional feature set includes: Obtaining the current amount, voltage value, density value and ice melting amount data of the conductor, and selecting the conductor association data with the current amount reaching a first preset threshold from them; Obtaining the current amount, voltage value, density value and ice melting amount data of the ground wire, and selecting the ground wire association data with the voltage amount reaching a second preset threshold from them; Combining the conductor association data, the ground wire association data and the ice melting optimization parameter to form a multi-dimensional feature set to construct an ice melting demand model; Based on the ice melting demand model, making a matching judgment on the ice melting amount of the conductor and the ice melting amount of the ground wire, and when the matching judgment passes, using a machine learning algorithm to train the ice melting demand model to obtain an optimized model parameter set; Performing an expected verification on the final ice melting amount of the conductor and the final ice melting amount of the ground wire through the ice melting demand model configured with the optimized model parameter set, and outputting the ice melting demand model passing the expected verification.

4. A modular-based combined mobile ice melting control method according to claim 1, characterized in that The based on the ice melting demand model, using a multi-objective optimization algorithm to quantify the voltage and current output data of the transmission line to generate a preliminary equipment combination includes: Construct an objective function based on the ice melting demand model, and use a multi-objective optimization algorithm to solve the objective function to obtain voltage and current output data; Under the constraints of equipment capacity and heat dissipation capacity, configure ice melting equipment according to the voltage and current output data to generate the preliminary equipment combination.

5. A modular-based combined mobile ice melting control method according to claim 1, characterized in that, Evaluating the performance degradation trend of the preliminary equipment combination in multiple scenarios, and obtaining an environmental adaptability correction parameter to update the preliminary equipment combination to obtain the final equipment combination, including: Obtain the performance operation data of the preliminary equipment combination in each scenario to characterize the performance degradation trend, and use regression analysis to process the performance operation data to obtain the environmental adaptability correction parameter; Adjust the equipment model and quantity in the preliminary equipment combination based on the environmental adaptability correction parameter to obtain a corrected equipment combination; Obtain the voltage and current output range of the corrected equipment combination, and use a decision tree algorithm based on the voltage and current output range to determine whether the corrected equipment combination meets the ice melting requirements of each scenario; When the corrected equipment combination meets the ice melting requirements of each scenario, obtain the performance operation data of the corrected equipment combination in each scenario, and use a clustering algorithm based on the performance operation data to determine whether the corrected equipment combination meets the preset performance degradation condition; Output the corrected equipment combination that meets the preset performance degradation condition as the final equipment combination.

6. The modular-based combined mobile ice melting control method according to claim 1, characterized in that, According to the final equipment combination, use a modular design method to construct a combined mobile ice melting system, including: Conduct functional division on the final equipment combination according to each scenario to obtain several functional modules; Use the shortest path algorithm and heuristic search algorithm to optimize the layout of each functional module to obtain the installation positions of each functional module; Based on each installation position, determine the topological structure of each functional module through fault tree analysis and multi-attribute decision-making algorithm, and construct a combined mobile ice melting system according to the installation positions and topological structures of each functional module.

7. A modular-based combined mobile ice melting control method according to claim 6, characterized in that Generate a control strategy for the combined mobile ice melting system through a fuzzy control algorithm, including: Use the ice melting requirements and real-time environmental data of each scenario as input variables, and use the current mode or voltage mode of the topological structure in the combined mobile ice melting system as output variables; Fuzzify the input variables and the output variables to obtain fuzzy sets, and perform fuzzy inference on the fuzzy sets of the input variables and the fuzzy rule base through Mamdani inference to obtain the fuzzy set of the output variables; Use the maximum membership degree method to defuzzify the fuzzy set of the output variables to obtain a control strategy; Obtain the real-time ice melting data of each scenario under the control strategy to match the ice melting requirements of each scenario, and update the topological structure when the matching is unsuccessful; Determine whether the updated topological structure meets the preset performance decay condition through a clustering algorithm, and re-execute the control strategy generation step based on the topological structure that meets the preset performance decay condition until the real-time ice melting data of each of the scenarios during the simulation run of the finally obtained control strategy matches the ice melting requirements of each of the scenarios, and output the finally obtained control strategy.

8. A modular-based combined mobile ice melting control method according to claim 6, characterized in that, Based on the control strategy, introduce an adaptive learning mechanism to update the control parameters in the control strategy to obtain an updated control strategy, including: Obtain the historical environmental data and the corresponding historical ice melting effect data of each of the scenarios to construct a mapping model through a reinforcement learning algorithm; Update the control strategy of the combined mobile ice melting system through the mapping model, and determine whether the control parameters in the updated control strategy meet the preset parameter threshold; According to each functional module in the combined mobile ice melting system, adjust the control strategy that meets the preset parameter threshold to obtain a multi-device collaborative control strategy; Based on each of the scenarios, use a clustering analysis algorithm to classify the historical ice melting effect data to obtain multiple typical working conditions of icing degrees; Segment each of the scenarios according to the multiple typical working conditions of icing degrees to adjust the multi-device collaborative control strategy to obtain a multi-device collaborative segmented control strategy as the updated control strategy for output.

9. A modular combined mobile ice melting control method according to claim 8, characterized in that Construct a multi-level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimize the updated control strategy according to the operation results to obtain a target control strategy to control the combined mobile ice melting system to execute, including: Use virtualization technology to construct a multi-level system performance simulation platform; the multi-level system performance simulation platform includes a power equipment model layer, a power grid topology layer, and a control strategy layer; Control the multi-level system performance simulation platform to run each of the scenarios and their corresponding multi-device collaborative segmented control strategies to collect real-time performance data; Determine whether the real-time performance data reaches the preset performance threshold, and when the real-time performance data does not reach the preset performance threshold, optimize the functional module and its topological structure to update the multi-device collaborative segmented control strategy; Repeat the strategy operation step and the performance judgment step based on the updated multi-device collaborative segmented control strategy until the updated real-time performance data reaches the preset performance threshold, and output the finally obtained multi-device collaborative segmented control strategy as the target control strategy to control the combined mobile ice melting system to execute.

10. A modular combined mobile ice melting control system, characterized in that, Including: A demand model construction module, configured to obtain ice melting demand parameters of different transmission lines in the power grid to construct an ice melting demand model; An equipment combination generation module, configured to quantify the voltage and current output data of the transmission line by using a multi-objective optimization algorithm based on the ice melting demand model to generate a preliminary equipment combination; An equipment combination correction module, configured to evaluate the performance decay trend of the preliminary equipment combination in multiple scenarios, obtain an environmental adaptability correction parameter to update the preliminary equipment combination, and obtain a final equipment combination; A control strategy generation module, which is used to construct a combined mobile de-icing system by using a modular design method according to the final device combination, and generate a control strategy for the combined mobile de-icing system through a fuzzy control algorithm; A control strategy update module, which is used to introduce an adaptive learning mechanism based on the control strategy to update the control parameters in the control strategy, and obtain an updated control strategy; A control strategy execution module, which is used to build a multi-level system performance simulation platform to run each of the scenarios and their corresponding updated control strategies, and optimize the updated control strategy according to the operation results to obtain a target control strategy for controlling the execution of the combined mobile de-icing system.

Images