Equipment layout method and system for rapid adaptation of transition module for transformation

Abstract

The invention discloses an equipment layout method and system for rapid adaptation of an adapter module for transformation, and relates to the technical field of power system transformation, and the method comprises the steps: collecting equipment operation data, and carrying out the preprocessing; carrying out demand analysis according to the data, and constructing a transition module simulation model based on digital twinning; performing modular customization according to the simulation model, and configuring a self-learning module; and performing intelligent task scheduling to quickly adapt to equipment layout. According to the method, through data-driven analysis and optimization, the scientificity and efficiency of layout planning are remarkably improved. The digital twinborn simulation model and the optimization method based on the multi-element heuristic algorithm are adopted, the problem that layout optimization and scheduling in an existing transition module technology are not intelligent enough is effectively solved, and meanwhile the self-learning ability of modular configuration is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system transformation, and in particular to a method and system for quickly adapting a transition cabin for transformation. Background Art

[0002] With the continuous advancement of technology and the rapid update and iteration of secondary equipment, some old substations are still using early models of secondary equipment. These devices often face the embarrassing situation of no spare parts available after the manufacturer stops production or upgrades. Once the equipment fails, the lack of spare parts support will greatly increase the difficulty of maintenance, and may even cause the equipment to be shut down for a long time. This not only affects the normal operation and power supply reliability of the power grid, but also damages the economic benefits and social image of power grid companies. According to statistics, power outages caused by equipment failures can cause economic losses of millions to tens of millions of yuan each year.

[0003] Therefore, in the process of comprehensive automation transformation of substations, the problem of spare parts after equipment update and iteration must be fully considered. By adopting innovative technical solutions such as transition cabins and prefabricated warehouses, space can be provided for replacement and upgrading of secondary equipment that has been running beyond the expiration date without interfering with the normal operation of the power grid. At the same time, communication and cooperation with equipment manufacturers should be strengthened to ensure that the transformed equipment can operate stably for a long time and have sufficient spare parts to cope with various faults and challenges that may arise in the future. Existing substation transformation technology usually adopts a combination of manual experience and static planning, which has certain limitations. First, the equipment layout lacks dynamic optimization capabilities and often requires repeated debugging, resulting in a long construction period and high cost. Secondly, for modular temporary structures such as transition cabins, existing technologies are difficult to adapt to changes in demand in different scenarios, and cannot achieve efficient module division and adaptive adjustment. In addition, traditional methods have insufficient optimization in wiring planning and resource scheduling, and cable laying has more redundancy and it is difficult to effectively avoid electromagnetic interference. These deficiencies lead to a decrease in system operation reliability during the transformation process, and it is difficult to improve construction efficiency. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing technology leads to a decrease in system operation reliability during the transformation process and it is difficult to improve the construction efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for quickly adapting equipment layout of a transition cabin for transformation, comprising:

[0007] Collect equipment operation data and pre-process it;

[0008] Conduct demand analysis based on data and build a transition cabin simulation model based on digital twins;

[0009] Modular customization is carried out according to the simulation model, and self-learning modules are configured;

[0010] Perform intelligent task scheduling to quickly adapt equipment layout.

[0011] As a preferred solution of the equipment layout method for rapid adaptation of the transition cabin for transformation described in the present invention, wherein: the collecting of equipment operation data and preprocessing includes using an Internet of Things sensor and a data acquisition terminal to collect the equipment operation data in real time, performing automatic data cleaning and denoising on the collected data, and combining an autoencoder to filter out data abnormal values;

[0012] The formula for collecting device data sets using IoT sensors is:

[0013] D = {x1, x2, ..., x n}

[0014] Among them, x i Represents the i-th sampling point, encoding function:

[0015] f(x)=σ(Wx+b)

[0016] Decoding function:

[0017] g(h)=σ(W′h+b′)

[0018] in, Represents input data, represents the encoding weight matrix, represents the bias vector, σ(·) represents the activation function, represents the encoded latent variable, Decoding weight matrix, represents the decoding bias vector;

[0019] For each data point x i , the reconstruction result is g(f(x i )) Data denoising uses an autoencoder; define the encoding function f(x) = σ(Wx+b) and decoding function g(h) = σ(W′h+b′) of the autoencoder, and minimize the reconstruction error:

[0020]

[0021] Use a distributed database to store pre-processed equipment operation data.

[0022] As a preferred solution of the equipment layout method for rapid adaptation of the transition cabin for transformation described in the present invention, wherein: the demand analysis based on the data includes using the k-means clustering algorithm to classify the equipment into protection devices, measurement and control devices, and communication equipment types;

[0023] Use the Apriori algorithm to mine association rules and obtain the wiring dependency between devices;

[0024] Determine frequent item sets, split the device set into different combinations, and find out the device combinations that frequently appear in the wiring transaction data; these combinations reflect the stable and repeated connection relationships between devices; frequent item sets refer to device combinations that appear in the wiring data at a certain threshold number of times;

[0025] Based on frequent item sets, dependency rules between devices are generated. If the protection device and the measurement and control device frequently appear in the same wiring transaction, a rule is formed that the protection device should be directly connected to the measurement and control device.

[0026] Each rule consists of a precondition and a postcondition. The precondition is the dependent device, and the postcondition is the dependent device. "Protection device → measurement and control device" indicates that there is a wiring dependency between the protection device and the measurement and control device.

[0027] According to the importance index of the rule, the most important wiring rules are screened out, weakly related connections are filtered out, and only the dependencies that are valuable to the layout design are retained; if the number of times the connection between the protection device and the measurement and control device appears in the data is significantly greater than other connection relationships, this rule is preferentially included in the layout constraints;

[0028] According to the compatibility of communication protocols and physical interfaces, layout constraints are formed. The constraints will be used as input in subsequent layout optimization to guide the location of devices and the arrangement of connection paths.

[0029] As a preferred solution of the equipment layout method for rapid adaptation of the transition cabin for transformation described in the present invention, wherein: the construction of the transition cabin simulation model based on digital twin includes designing a digital twin model framework, including a physical layer, a data layer, a virtual model layer, and an interaction layer;

[0030] The physical layer includes real equipment and space environment; the data layer obtains real-time and historical operation data from sensors and historical records; the virtual model layer establishes a 3D model of the transition cabin and simulates the equipment layout; the interaction layer adopts real-time monitoring and feedback mechanism to support optimized decision-making.

[0031] As a preferred solution of the equipment layout method for rapid adaptation of the transition cabin for transformation described in the present invention, wherein: the modular customization according to the simulation model includes dividing the modules according to the functions, optimizing the module layout and performing modular configuration;

[0032] Wiring optimization formula to minimize wiring length:

[0033]

[0034] Among them, w ij represents the connection weight between device i and device j, d ij Indicates physical distance;

[0035] The functional division modules include: a remote control area module, a protection area module, a measurement and control area module, and a terminal connection area module; the module division objective function formula is expressed as:

[0036]

[0037] Among them, D ij Represents the physical distance between device i and device j, M i Represents the equipment set of the i-th module; among them, the remote control area module is arranged with communication equipment, the protection area module is arranged with main transformer protection equipment, the measurement and control module is arranged with line measurement and control equipment, and the terminal connection area module is used for signal conversion between devices.

[0038] As a preferred solution of the equipment layout method for rapid adaptation of the transition cabin for transformation described in the present invention, wherein: the configuration self-learning module includes using reinforcement learning to simulate the module placement sequence in a simulation environment to complete the layout with the optimal path;

[0039] It provides a human-computer interaction interface, where engineers can view optimization solutions and adjust module configurations in real time; and use augmented reality technology to visualize layouts and conduct scenario previews.

[0040] As a preferred solution of the equipment layout method for rapid adaptation of the transition cabin for transformation of the present invention, wherein: the intelligent task scheduling and rapid adaptation of the equipment layout includes generating a task priority queue according to the demand matrix, defining the demand matrix, defining the demand matrix Where m represents the number of tasks, n represents the number of devices, and t ij Represents the required priority value of device j to execute task i; task priority calculation, use the following weight to calculate the task priority P i :

[0041]

[0042] Among them, w j Represents the weight of device j, reflecting the importance of the device; all tasks are assigned a priority value P i Arrange in descending order to generate a task priority queue Q = {q1, q2, ..., q m};

[0043] Task classification: divide tasks into two categories: layout tasks install equipment and connect to the network, and debugging tasks verify equipment performance and operating conditions; give priority to the layout and debugging of key equipment, parallelize installation and debugging tasks, and reduce construction time;

[0044] Through the priority queue Q, tasks are assigned in sequence, with layout tasks given priority to ensure that key equipment is installed first; after the layout task is completed, the debugging task is immediately arranged;

[0045] Use the scheduling algorithm to generate a parallel task schedule, define A i Indicates the installation task, D i Represents the debugging task, at time t k The combination formula of the tasks performed on is expressed as:

[0046]

[0047] Target optimization, the goal is to minimize the total task completion time T total :

[0048]

[0049] in, is the completion time of the ith task;

[0050] The ant colony optimization algorithm is used to plan the wiring path, and the device connection path is defined as a graph G = (V, E), where V represents the device node set, E represents the edge set of the connecting cable, and d ij represents the length of the cable from device i to device j;

[0051] Path optimization goal is to find the shortest path L:

[0052]

[0053] Among them, P represents the complete path of the ant; the ant colony optimization algorithm is used to plan the wiring path, find the connection path with the shortest cable length, and optimize the cable distribution to reduce electromagnetic interference.

[0054] As a preferred solution of the equipment layout system for rapid adaptation of the transition cabin for transformation described in the present invention, it includes: a data acquisition and preprocessing module to realize real-time acquisition and preprocessing of equipment operation data; automatic cleaning and denoising, using an autoencoder to filter data outliers, and storing the preprocessed data in a distributed database;

[0055] The digital twin simulation module builds a digital twin simulation model of the transition cabin based on the collected equipment data; divides the equipment modules by function, and performs modular configuration and layout optimization; the physical layer, the real equipment environment; the data layer, the storage of real-time and historical operation data; the virtual model layer, the three-dimensional simulation model; the interaction layer, real-time monitoring and feedback support;

[0056] The self-learning module uses reinforcement learning to optimize module layout, provides a human-computer interaction interface, displays optimization solutions in real time, and supports engineers to make adjustments;

[0057] The intelligent task scheduling module generates task priority queues according to demand, schedules layout and debugging tasks; uses the ant colony optimization algorithm to optimize wiring paths, find the shortest cable path, and reduce electromagnetic interference.

[0058] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of a method for quickly adapting a transition cabin for transformation.

[0059] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for quickly adapting a transition cabin for transformation.

[0060] Beneficial effects of the invention: The equipment layout method for rapid adaptation of the transition cabin provided by the invention integrates the traditional equipment transformation method by using the Internet of Things and digital twin technology, and significantly improves the scientificity and efficiency of layout planning through data-driven analysis and optimization. The digital twin simulation model adopted by the invention and the optimization method based on the multivariate heuristic algorithm not only effectively solve the problem of insufficient intelligence in layout optimization and scheduling in the existing transition cabin technology, but also realizes the self-learning ability of modular configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0062] Figure 1 An overall flow chart of a method for quickly adapting equipment layout for a transition cabin for transformation provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0064] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a method for quickly adapting equipment layout for a transition cabin for transformation, comprising:

[0065] S1: Collect equipment operation data and perform preprocessing.

[0066] Furthermore, IoT sensors are used to collect device data sets D = {x1, x2, ..., x n}, where x i represents the i-th sampling point.

[0067] Furthermore, data denoising uses an autoencoder, defining the encoding function f(x) = σ(Wx+b) and the decoding function g(h) = σ(W′h+b′) of the autoencoder, by minimizing the reconstruction error:

[0068]

[0069] Filter outliers x i , satisfying the conditions:

[0070] ||x i -g(f(x i ))||>∈

[0071] Where,∈ represents the threshold. Distributed storage, using a distributed database to store preprocessed data, the formula is expressed as:

[0072] D′={x i ||x i -g(f(x i ))||≤∈}

[0073] in, Represents input data, represents the encoding weight matrix, represents the bias vector, σ(·) represents the activation function, represents the encoded latent variable, Decoding weight matrix, Represents the decoding bias vector.

[0074] For each data point x i, the reconstruction result is g(f(x i )) Data denoising uses an autoencoder; define the encoding function f(x) = σ(Wx+b) and decoding function g(h) = σ(W′h+b′) of the autoencoder, and minimize the reconstruction error:

[0075]

[0076] Use a distributed database to store pre-processed equipment operation data.

[0077] It should be noted that the wiring history data of the equipment is collected, and each record represents the wiring relationship of a certain equipment group in actual operation. For example, the record may include the connection between certain protection devices and measurement and control devices and communication equipment. The transaction data set is constructed, and each transaction contains a group of equipment, indicating that these equipment have wiring associations in actual operation.

[0078] S2: Conduct demand analysis based on the data and build a transition cabin simulation model based on digital twins.

[0079] Furthermore, the demand analysis based on the data includes using a k-means clustering algorithm to classify the equipment into protection devices, measurement and control devices, and communication equipment types.

[0080] Randomly select k device feature vectors as cluster centers {μ1, μ2, ..., μ k}. Assign the device to the nearest cluster.

[0081] For each device x i ∈X, calculate the distance to each cluster center:

[0082] d(x i , μ j )=||x i -μ j || 2

[0083] x i Assign to the nearest cluster C j .

[0084]

[0085] Update the cluster centers and calculate the new center of each cluster:

[0086]

[0087] Repeat the steps until the center position converges (or the change is less than the threshold ∈). Clustering results {C1, C2, ..., C k}, each device is assigned to a specific category.

[0088] The Apriori algorithm is used to mine association rules and obtain the wiring dependency between devices.

[0089] Determine frequent item sets, split the device set into different combinations, and find out the device combinations that frequently appear in the wiring transaction data; these combinations reflect the stable and repeated connection relationships between devices; frequent item sets refer to device combinations that appear in the wiring data a certain number of times.

[0090] Based on frequent item sets, dependency rules between devices are generated. If the protection device and the measurement and control device frequently appear in the same wiring transaction, a rule is formed that the protection device should be directly connected to the measurement and control device.

[0091] Each rule consists of a precondition and a postcondition. The precondition is the dependent device, and the postcondition is the dependent device. "Protection device → measurement and control device" indicates that there is a wiring dependency between the protection device and the measurement and control device.

[0092] According to the importance index of the rules, the most important wiring rules are screened out, weakly related connections are filtered out, and only dependencies that are valuable to the layout design are retained; if the connection between the protection device and the measurement and control device appears significantly more times in the data than other connection relationships, this rule will be prioritized as a layout constraint.

[0093] According to the compatibility of communication protocols and physical interfaces, layout constraints are formed. The constraints will be used as input in subsequent layout optimization to guide the location of devices and the arrangement of connection paths.

[0094] The construction of the transition cabin simulation model based on digital twin includes designing a digital twin model framework, including a physical layer, a data layer, a virtual model layer, and an interaction layer.

[0095] The physical layer includes real equipment and space environment; the data layer obtains real-time and historical operation data from sensors and historical records; the virtual model layer establishes a 3D model of the transition cabin and simulates the equipment layout; the interaction layer adopts real-time monitoring and feedback mechanism to support optimized decision-making.

[0096] It should be noted that the virtual model layer accurately simulates the layout of the transition cabin equipment through 3D simulation, and combined with the real-time data of the physical layer, the rationality of the design scheme can be quickly verified. The interactive layer supports real-time monitoring and feedback, and engineers can dynamically adjust the layout scheme to avoid unforeseen problems caused by static design in the traditional layout process.

[0097] S3: Modular customization is performed according to the simulation model, and the self-learning module is configured.

[0098] Furthermore, the modular customization according to the simulation model includes dividing the modules according to functions, optimizing the module layout and performing modular configuration.

[0099] Wiring optimization formula to minimize wiring length:

[0100]

[0101] Among them, w ij represents the connection weight between device i and device j, d ij Indicates physical distance.

[0102] The functional division modules include: a remote control area module, a protection area module, a measurement and control area module, and a terminal connection area module; the module division objective function formula is expressed as:

[0103]

[0104] Among them, D ij Represents the physical distance between device i and device j, M i Represents the equipment set of the i-th module; among them, the remote control area module is arranged with communication equipment, the protection area module is arranged with main transformer protection equipment, the measurement and control module is arranged with line measurement and control equipment, and the terminal connection area module is used for signal conversion between devices.

[0105] The configuration self-learning module includes using reinforcement learning to simulate the module placement sequence in a simulation environment to complete the layout with an optimal path.

[0106] It provides a human-computer interaction interface, where engineers can view optimization solutions and adjust module configurations in real time; and use augmented reality technology to visualize layouts and conduct scenario previews.

[0107] It should be noted that modules divided by function (such as remote control area, protection area, etc.) make the equipment layout more logical and standardized, reducing interference and operational complexity. By simulating the layout optimization path in the simulation environment through reinforcement learning, the module position can be automatically adjusted to achieve the global optimal effect and avoid the uncertainty of manual experience design.

[0108] S4: Perform intelligent task scheduling to quickly adapt device layout.

[0109] Furthermore, intelligent task scheduling to quickly adapt to device layout includes generating task priority queues based on the demand matrix. Demand matrix definition: Defining the demand matrix Where m represents the number of tasks, n represents the number of devices, and t ij Represents the required priority value of device j to execute task i; task priority calculation, use the following weight to calculate the task priority P i :

[0110]

[0111] Among them, wj Represents the weight of device j, reflecting the importance of the device; all tasks are assigned a priority value P i Arrange in descending order to generate a task priority queue Q = {q1, q2, ..., q m}.

[0112] Task classification, divides tasks into two categories: layout tasks install equipment and connect to the network, and debugging tasks verify equipment performance and operating status. The priority calculation formula is expressed as:

[0113]

[0114] Prioritize the layout and commissioning of key equipment, parallelize installation and commissioning tasks, and reduce construction time.

[0115] Tasks are assigned in sequence through the priority queue Q, with layout tasks given priority to ensure that key equipment is installed first; after the layout task is completed, the debugging task is immediately arranged.

[0116] Task parallelization: Use the scheduling algorithm to generate a parallel task schedule and define A i Indicates the installation task, D i Represents the debugging task, at time t k The combination formula of the tasks performed on is expressed as:

[0117]

[0118] Target optimization, the goal is to minimize the total task completion time T total :

[0119]

[0120] in, is the completion time of the ith task.

[0121] The ant colony optimization algorithm is used to plan the wiring path, and the device connection path is defined as a graph G = (V, E), where V represents the device node set, E represents the edge set of the connecting cable, and d ij Represents the length of the cable from device i to device j.

[0122] Pheromone initialization, initialize the pheromone value τ for each edge (i, j) ∈ E ij (0):

[0123]

[0124] Path selection probability, the probability that ant k chooses node j from node i

[0125]

[0126] Among them, α represents the pheromone importance factor, β represents the inspiration factor, and η ij represents the heuristic value of the edge, N i Represents the set of reachable neighbor nodes of node i.

[0127] Pheromone volatilization and renewal:

[0128] τ ij (t+1)=(1-p)τ ij (t)+Δτ ij (t)

[0129] Where ρ represents the pheromone volatilization rate.

[0130]

[0131] Among them, L k represents the path length of the kth ant; the path optimization goal is to find the shortest path L:

[0132]

[0133] Among them, P represents the complete path of the ant; the ant colony optimization algorithm is used to plan the wiring path, find the connection path with the shortest cable length, and optimize the cable distribution to reduce electromagnetic interference.

[0134] It should be noted that based on the task priority queue and scheduling algorithm, the parallel processing of installation tasks and debugging tasks is realized, which significantly shortens the construction time. Compared with the traditional linear task execution method, it can save more than 30% of time. The use of ant colony optimization algorithm in wiring path planning reduces the total length of cables through global optimal search, while reducing the risk of electromagnetic interference.

[0135] Example 2 is an embodiment of the present invention, which provides a method for quickly adapting equipment layout in a transition cabin for transformation. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0136] First, the test preparation and implementation details. The test selected an old 110kV substation that has been in operation for 15 years. The secondary equipment has aging problems and needs to be fully transformed. Since the entire station cannot be shut down during the operation of the equipment, the transition cabin based on digital twin technology is used for rapid adaptation of equipment layout.

[0137] In preparation for the experiment, multiple sets of IoT sensors were deployed on key equipment in the substation to collect real-time operating data (including current, voltage, temperature, vibration, etc.).

[0138] Equipped with data acquisition terminals and edge computing gateways, the collected data is transmitted to the distributed database (Cassandra) in real time.

[0139] Data collection and preprocessing: Data collection lasted for 7 days, with key parameters recorded once a second. The total amount of data was about 100GB. 5% of duplicate or missing data was removed through automated cleaning tools. The autoencoder model was used to screen the data for outliers, identifying and removing about 1.5% of abnormal data points.

[0140] Demand analysis and layout constraint formation, using the Apriori algorithm to analyze the wiring dependencies between devices, it was found that the connection frequency between protection equipment and measurement and control equipment is 85%, and the frequency between communication equipment and measurement and control equipment is 75%. Based on the results, equipment layout constraints are generated, including wiring length between devices, interface compatibility, and heat dissipation requirements.

[0141] A digital twin model of the transition cabin was established using 3D modeling tools, including the physical layer (equipment model and space environment), data layer (real-time collection and historical records), virtual model layer (layout simulation) and interaction layer (real-time monitoring and feedback). Equipment placement and wiring schemes were simulated in the simulation model to ensure that the heat dissipation efficiency reached more than 90%.

[0142] The transition cabin was divided into four modules: telecontrol area, protection area, measurement and control area, and terminal connection area. A task priority queue was generated, with communication equipment (telecontrol area module) installed first, followed by protection equipment (protection area module), and finally measurement and control equipment. The wiring path was planned to optimize the total cable length from 680 meters in the initial plan to 520 meters. The installation and commissioning tasks were parallelized to shorten the construction period from the expected 10 days to 7 days.

[0143] Table 1 Experimental data comparison table

[0144]

[0145]

[0146] It can be seen from the experimental data that the present invention has significant advantages in optimizing the layout of transition cabin equipment, which is mainly reflected in the following aspects: The present invention adopts the ant colony optimization algorithm, which significantly reduces the total wiring length (from 680 meters to 520 meters), effectively reducing material costs and construction difficulties. Compared with the existing manual path planning method, its optimization effect is improved by 23.53%. In the digital twin simulation environment, the module placement order is optimized through the reinforcement learning algorithm, so that the heat dissipation efficiency is increased from 78% to 92%. This improvement not only reduces the risk of equipment failure, but also extends the service life of the equipment.

[0147] Data cleaning efficiency and accuracy: The present invention combines the autoencoder to screen outliers in the data, making the data cleaning efficiency reach 95%, which is 11.76% higher than that of traditional cleaning tools. Efficient data preprocessing provides reliable data support for subsequent demand analysis and layout optimization.

[0148] Embodiment 3, the following is an embodiment of the present invention, which provides a system for quickly adapting equipment layout for a transition cabin for transformation, including:

[0149] The data acquisition and preprocessing module realizes the real-time acquisition and preprocessing of equipment operation data; automatic cleaning and denoising, using autoencoders to filter outliers in the data, and storing the preprocessed data in a distributed database.

[0150] The digital twin simulation module builds a digital twin simulation model of the transition cabin based on the collected equipment data; divides the equipment modules by function, and performs modular configuration and layout optimization; physical layer, real equipment environment; data layer, storage of real-time and historical operation data; virtual model layer, three-dimensional simulation model; interaction layer, real-time monitoring and feedback support.

[0151] The self-learning module uses reinforcement learning to optimize module layout, provides a human-computer interaction interface, displays optimization solutions in real time, and supports engineers to make adjustments.

[0152] The intelligent task scheduling module generates task priority queues according to demand, schedules layout and debugging tasks; uses the ant colony optimization algorithm to optimize wiring paths, find the shortest cable path, and reduce electromagnetic interference.

[0153] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0154] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0155] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0156] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0157] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for quickly adapting equipment layout for a transition cabin for transformation, characterized in that: include: Collect equipment operation data and pre-process it; Conduct demand analysis based on data and build a transition cabin simulation model based on digital twins; Modular customization is carried out according to the simulation model, and self-learning modules are configured; Perform intelligent task scheduling to quickly adapt equipment layout.

2. The equipment layout method for rapid adaptation of the transition cabin for transformation according to claim 1 is characterized in that: The collecting and preprocessing of the equipment operation data includes using IoT sensors and data acquisition terminals to collect the equipment operation data in real time, automatically cleaning and denoising the collected data, and filtering data outliers in combination with an autoencoder; The formula for collecting device data sets using IoT sensors is: D={x1,x2,…,x n } Among them, x i Represents the i-th sampling point, encoding function: f(x)=σ(Wx+b) Decoding function: g(h)=σ(W′h+b′) in, Represents input data, represents the encoding weight matrix, represents the bias vector, σ(·) represents the activation function, represents the encoded latent variable, Decoding weight matrix, represents the decoding bias vector; For each data point x i , the reconstruction result is g(f(x i )) Data denoising uses an autoencoder; define the encoding function f(x) = σ(Wx+b) and decoding function g(h) = σ(W′h+b′) of the autoencoder, and minimize the reconstruction error: Use a distributed database to store pre-processed equipment operation data.

3. The equipment layout method for rapid adaptation of the transition cabin for transformation according to claim 2 is characterized in that: The demand analysis based on the data includes using a k-means clustering algorithm to classify the equipment into protection devices, measurement and control devices, and communication equipment types; Use the Apriori algorithm to mine association rules and obtain the wiring dependency between devices; Determine frequent item sets, split the device set into different combinations, and find out the device combinations that frequently appear in the wiring transaction data; these combinations reflect the stable and repeated connection relationships between devices; frequent item sets refer to device combinations that appear in the wiring data a certain number of times; Based on frequent item sets, dependency rules between devices are generated. If the protection device and the measurement and control device frequently appear in the same wiring transaction, a rule is formed that the protection device should be directly connected to the measurement and control device. Each rule consists of a precondition and a postcondition. The precondition is the dependent device, and the postcondition is the dependent device. "Protection device → measurement and control device" indicates that there is a wiring dependency between the protection device and the measurement and control device. According to the importance index of the rules, the most important routing rules are selected, weakly related connections are filtered out, and only the dependencies that are valuable to the layout design are retained; If the number of times the connection between the protection device and the measurement and control device appears in the data is significantly greater than other connection relationships, this rule should be included in the layout constraints first; According to the compatibility of communication protocols and physical interfaces, layout constraints are formed. The constraints will be used as input in subsequent layout optimization to guide the location of devices and the arrangement of connection paths.

4. The equipment layout method for rapid adaptation of the transition cabin for transformation as claimed in claim 3 is characterized by: The construction of the transition cabin simulation model based on digital twins includes designing a digital twin model framework, including a physical layer, a data layer, a virtual model layer, and an interaction layer; The physical layer includes real equipment and spatial environment; The data layer obtains real-time and historical operating data from sensors and historical records; the virtual model layer builds a 3D model of the transition cabin and performs equipment layout simulation; The interaction layer adopts real-time monitoring and feedback mechanisms to support optimized decision-making.

5. The equipment layout method for rapid adaptation of the transition cabin for transformation according to claim 4 is characterized in that: The modular customization according to the simulation model includes dividing the modules according to their functions, optimizing the module layout and performing modular configuration; Wiring optimization formula to minimize wiring length: Among them, w ij represents the connection weight between device i and device j, d ij Indicates physical distance; The functional division modules include: a remote control area module, a protection area module, a measurement and control area module, and a terminal connection area module; the module division objective function formula is expressed as: Among them, D ij Represents the physical distance between device i and device j, M i Represents the equipment set of the i-th module; among them, the remote control area module is arranged with communication equipment, the protection area module is arranged with main transformer protection equipment, the measurement and control module is arranged with line measurement and control equipment, and the terminal connection area module is used for signal conversion between devices.

6. The equipment layout method for rapid adaptation of the transition cabin for transformation according to claim 5 is characterized in that: The configuration self-learning module includes using reinforcement learning to simulate the module placement sequence in a simulation environment to complete the layout with an optimal path; It provides a human-computer interaction interface, where engineers can view optimization solutions and adjust module configurations in real time; and use augmented reality technology to visualize layouts and conduct scenario previews.

7. The equipment layout method for rapid adaptation of the transition cabin for transformation according to claim 6 is characterized in that: The intelligent task scheduling and rapid adaptation of the equipment layout includes generating a task priority queue according to the demand matrix, defining the demand matrix, and defining the demand matrix. Where m represents the number of tasks, n represents the number of devices, and t ij Represents the required priority value of device j to execute task i; task priority calculation, use the following weight to calculate the task priority P i : Among them, w j Represents the weight of device j, reflecting the importance of the device; all tasks are assigned a priority value P i Arrange in descending order to generate a task priority queue Q = {q1, q2, ..., q m }; Task classification: divide tasks into two categories: layout tasks install equipment and connect to the network, and debugging tasks verify equipment performance and operating conditions; give priority to the layout and debugging of key equipment, parallelize installation and debugging tasks, and reduce construction time; Through the priority queue Q, tasks are assigned in sequence, with layout tasks given priority to ensure that key equipment is installed first; after the layout task is completed, the debugging task is immediately arranged; Use the scheduling algorithm to generate a parallel task schedule, define A i Indicates installation task, D i Represents the debugging task, at time t k The combination formula of the tasks performed on is expressed as: Target optimization, the goal is to minimize the total task completion time T total : in, is the completion time of the ith task; The ant colony optimization algorithm is used to plan the wiring path, and the device connection path is defined as a graph G = (V, E), where V represents the device node set, E represents the edge set of the connecting cable, and d ij represents the length of the cable from device i to device j; Path optimization goal is to find the shortest path L: Among them, P represents the complete path of the ant; the ant colony optimization algorithm is used to plan the wiring path, find the connection path with the shortest cable length, and optimize the cable distribution to reduce electromagnetic interference.

8. A system using the equipment layout method for rapid adaptation of the transition tank for transformation as claimed in any one of claims 1 to 7, characterized in that: The data collection and preprocessing module realizes the real-time collection and preprocessing of equipment operation data; automatic cleaning and denoising, using the autoencoder to filter outliers in the data, and storing the preprocessed data in a distributed database; The digital twin simulation module builds a digital twin simulation model of the transition cabin based on the collected equipment data; Divide equipment modules by function, and perform modular configuration and layout optimization; Physical layer, real device environment; Data layer, storage of real-time and historical operation data; virtual model layer, 3D simulation model; interaction layer, real-time monitoring and feedback support; The self-learning module uses reinforcement learning to optimize module layout, provides a human-computer interaction interface, displays optimization solutions in real time, and supports engineers to make adjustments; The intelligent task scheduling module generates task priority queues according to demand, schedules layout and debugging tasks; uses the ant colony optimization algorithm to optimize wiring paths, find the shortest cable path, and reduce electromagnetic interference.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the equipment layout method for rapid adaptation of the transition cabin for transformation described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the equipment layout method for rapid adaptation of a transition cabin for reconstruction described in any one of claims 1 to 7 are implemented.

Images