A power distribution cabinet wiring method and an electronic device

Abstract

The application relates to the technical field of power distribution systems. The application discloses a power distribution cabinet wire layout method and an electronic device, which comprises the following steps: first, obtaining basic parameters including wire specifications, load operation, cabinet environment and structure; second, constructing a target layout scene model according to the parameters; third, analyzing the model to obtain corresponding layout safety levels; and finally, combining the target layout scene model and the safety levels to determine a first layout scheme with higher priority and a second layout scheme as a backup. The method realizes data-driven standardized layout design through multi-dimensional basic parameter modeling, avoids artificial experience bias, and checks hidden dangers such as electrical interference and insufficient heat dissipation in advance; the optimal first scheme and the backup second scheme system are constructed, risk assessment and early warning with safety operation processes are matched, and safety redundancy is strengthened; relying on sensor feedback and a reinforcement learning iterative model, the method adapts to working condition changes, and improves the design standardization, safety guarantee and whole life cycle reliability of the power distribution cabinet.

Description

Technical Field

[0001] This invention relates to the field of power distribution system technology, and in particular to a wiring method for a power distribution cabinet and an electronic device. Background Technology

[0002] The design of electrical distribution cabinet wiring often relies heavily on manual experience. Designers frequently plan routes based solely on basic current and voltage parameters, neglecting crucial factors such as ambient humidity, heat dissipation efficiency, and the rate of insulation aging. This can easily lead to problems like localized overheating and insulation damage after wiring. Furthermore, manual design lacks standardized processes, resulting in significant differences in judgment regarding wiring paths and fixture distribution among different personnel. This leads to poor wiring consistency even for cabinets of the same specifications, increasing the difficulty of troubleshooting during later maintenance and resulting in high rework and rectification costs.

[0003] While existing cabling technologies incorporate some simulation tools, they can mostly only generate a single cabling scheme and lack backup mechanisms. When actual operating conditions deviate from the design scenario, there are no mature alternatives for quick switching, requiring a restart of the design process and delaying fault handling. Furthermore, safety assessments are mostly qualitative judgments, failing to incorporate factors such as load density distribution and heat dissipation efficiency to build quantitative models, making it difficult to accurately identify potential risks. Warnings only indicate anomalies without specific operational guidance, resulting in insufficient practicality.

[0004] Traditional cabling designs are one-time, static designs that do not consider the full lifecycle needs of the distribution cabinet. During operation, load changes and equipment aging can render the original cabling scheme inadequate, but current technology cannot dynamically optimize the scheme based on real-time data. Even if some systems are equipped with sensors to collect operating parameters, these are only used for simple monitoring and are not linked to the cabling scheme to form a closed-loop iteration. Over long-term operation, the safety and reliability of the cabling gradually decline, requiring frequent downtime for maintenance and affecting the continuity of power supply. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention discloses a standardized, safe, and dynamic wiring method for electrical distribution cabinet wiring and an electronic device.

[0006] This invention discloses a wiring method for a power distribution cabinet, comprising:

[0007] Obtain the basic parameters related to the wiring of the distribution cabinet. The basic parameters should include at least the wire specifications, load operating parameters, cabinet environment parameters, and cabinet structural parameters.

[0008] Based on the basic parameters, construct a target wiring scenario model corresponding to the power distribution cabinet wiring.

[0009] Analyze the target cabling scenario model to determine the corresponding cabling security level.

[0010] Based on the target cabling scenario model and cabling security level, a first cabling scheme and a second cabling scheme corresponding to the target cabling scenario model are determined, wherein the first cabling scheme has a higher priority than the second cabling scheme.

[0011] Furthermore, the basic parameters also include wire insulation parameters, cabinet heat dissipation channel parameters, and equipment interface adaptation parameters;

[0012] The parameters for wire insulation include insulation layer material, insulation thickness, and insulation withstand voltage. The parameters for cabinet heat dissipation channels include channel location, ventilation volume, and heat dissipation efficiency. The parameters for equipment interface adaptation include interface type, pin spacing, and rated number of insertions and removals.

[0013] Furthermore, based on the basic parameters, a target wiring scenario model corresponding to the power distribution cabinet wiring is constructed, including:

[0014] The basic parameters are preprocessed to obtain the processed basic parameters. The preprocessing includes data cleaning, data transformation and data labeling.

[0015] When the basic parameter is the wire specification parameter, data cleaning includes checking for missing specification parameters. If missing values ​​are found, the median of the specification parameters of the same type of wire is used to fill them in.

[0016] Data transformation includes unifying parameters from different units to industry standard units, and data annotation includes feature labeling of key parameters;

[0017] The processed basic parameters are input into the preset engine, and the preset engine outputs the target wiring scene model.

[0018] The preset engine includes at least one of electrical simulation software, CAD electrical design software, or power distribution system simulation software;

[0019] The target cabling scenario model is simulated, and the first and second cabling schemes are adjusted based on the simulation results.

[0020] Furthermore, the target cabling scenario model is analyzed to determine the corresponding cabling security level, including:

[0021] Based on the basic parameters, safety impact factors are set, including load density distribution, ambient temperature and humidity fluctuations, insulation aging rate, and heat dissipation channel unobstructedness.

[0022] Based on security impact factors, a cabling security assessment model is constructed. The cabling security assessment model is constructed using logistic regression or random forest algorithms and trained and optimized using historical cabling security data.

[0023] The target cabling scenario model is analyzed based on the cabling security assessment model to obtain the corresponding cabling security level, which is then displayed on the interface. The cabling security level includes three levels: low risk, medium risk, and high risk.

[0024] Furthermore, based on the target cabling scenario model and cabling security level, the first cabling scheme and the second cabling scheme corresponding to the target cabling scenario model are determined, including:

[0025] The target wiring scenario model and wiring security level are input into the prediction model, and the prediction model outputs the first wiring scheme. The prediction model consists of a convolutional neural network, a generative adversarial network, and a reinforcement learning algorithm. It generates the optimal scheme by extracting scenario features and combining them with the security level.

[0026] The first wiring scheme includes at least one wiring stage and corresponding first execution information. One wiring stage corresponds to a set of first execution information, which includes wiring path, wire fixing point distribution and current distribution method.

[0027] Furthermore, based on the target cabling scenario model, a second cabling scheme corresponding to the target cabling scenario model is determined, including:

[0028] Access the cabling case library; the cabling case library includes multiple preset cabling scenarios and corresponding security cabling solutions for each preset cabling scenario. The preset cabling scenarios are classified according to load type, cabinet structure and environmental conditions.

[0029] Based on the target cabling scenario model, the target cabling scenario model is divided into at least one cabling area;

[0030] By comparing at least one wiring area with multiple preset wiring scenarios, a target preset wiring scenario with a matching degree exceeding a preset threshold is determined.

[0031] The security wiring scheme corresponding to the target preset wiring scenario is determined as the second wiring scheme. The second wiring scheme includes at least one wiring stage and corresponding second execution information. One wiring stage corresponds to a set of second execution information.

[0032] Furthermore, the method also includes: using a sensor array to obtain operational feedback results corresponding to at least one executed action;

[0033] The sensor group includes a temperature sensor, a current sensor, and an insulation resistance sensor. The operational feedback results include the wire operating temperature, actual load current, and insulation resistance value. At least one execution action is a wiring-related action in the first execution information or the second execution information.

[0034] The reinforcement learning algorithm in the prediction model updates the neural network parameters in the prediction model based on the running feedback results, and obtains the updated prediction model. The reinforcement learning algorithm adopts the deep Q-network algorithm or the policy gradient algorithm.

[0035] Furthermore, the method also includes: monitoring whether the real-time operating parameters and wiring status data of the power distribution cabinet exceed the threshold;

[0036] Real-time operating parameters include real-time load current, cabinet internal temperature and humidity, and wiring status data includes wire joint temperature, insulation damage, and degree of looseness of fixing points.

[0037] The thresholds include a first threshold and a second threshold, which correspond to the real-time operating parameter threshold and the wiring status data threshold, respectively;

[0038] If the real-time operating parameters exceed the first threshold or the cabling status data exceeds the second threshold, an early warning message will be output. The early warning message is used to prompt the switch to the second cabling scheme.

[0039] The warning information includes detailed execution steps for the second cabling scheme, which is optimized based on historical secure cabling cases.

[0040] Furthermore, the first and second execution information also include wire harness binding spacing, insulation protection layer selection, and heat dissipation auxiliary structure configuration;

[0041] Wiring sequence includes main circuit wiring priority and control circuit wiring sequence; fixing force includes buckle tightening torque range and cable tie tightness standard; interface tightening torque includes terminal tightening torque value and re-inspection requirements.

[0042] The selection of the insulation protection layer is determined based on the ambient humidity and voltage level. The configuration of the heat dissipation auxiliary structure includes the installation position of the heat sink and the laying method of the thermal pad.

[0043] This invention discloses an electronic device comprising:

[0044] A touchscreen includes a touch sensor and a display screen.

[0045] One or more processors;

[0046] Memory;

[0047] The memory stores one or more computer programs, which include instructions that, when executed by the electronic device, cause the electronic device to perform the wiring method for the distribution cabinet as described in any one of claims 1 to 9.

[0048] The electronic device also includes a sensor interface connected to the processor for receiving data from temperature, current, and insulation resistance sensors.

[0049] The beneficial effects of this invention are:

[0050] Compared to traditional cabling methods that rely on manual experience, this approach comprehensively acquires multi-dimensional basic parameters such as wire specifications, load operation, and cabinet environment. Combined with data cleaning, standardization, and professional software modeling, it constructs a high-fidelity target cabling scenario model. This eliminates the subjective judgment bias of designers, allowing for the early identification of potential problems such as electrical interference and insufficient heat dissipation through simulation before physical cabling. This reduces later rectification costs and project delays, while ensuring a high degree of uniformity in parameter standards and safety thresholds across different batches and personnel, significantly improving the standardization and consistency of distribution cabinet design.

[0051] This method generates a globally optimal first cabling scheme through an AI prediction model, while simultaneously generating a second scheme based on case library matching and expert rules, forming a dual system of optimal design and backup protection. Combined with a security assessment model based on logistic regression / random forest, it can accurately classify low, medium, and high risk levels. When thresholds are exceeded in real time, the warning information not only prompts a switch to a different scheme but also includes safe operating procedures such as power outages and load transfers. This avoids potential risks associated with the first scheme and prevents situations where there are no procedures to follow during emergencies, building a solid security defense line from design and assessment to operation and maintenance, effectively reducing the probability of accidents such as short circuits and overheating.

[0052] By collecting operational feedback data from sensors such as temperature and current, and combining this data with reinforcement learning algorithms such as deep Q-networks, the predictive model parameters are continuously updated. This allows the cabling scheme to proactively adapt to changes in load, equipment aging, and other evolving operating conditions. Simultaneously, details such as auxiliary heat dissipation configurations and insulation protection selections can be dynamically adjusted based on ambient humidity and voltage levels. This ensures that the distribution cabinet maintains optimal heat dissipation and insulation performance throughout long-term operation, extending equipment lifespan and enhancing the long-term reliability and resilience of the power distribution system. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating a wiring method for a power distribution cabinet according to an embodiment of this application. Detailed Implementation

[0054] To enable those skilled in the art to better understand the present invention, the technical solutions in the specific embodiments of the present invention will be clearly and completely described below.

[0055] This invention discloses a wiring method for a power distribution cabinet, comprising:

[0056] Obtain the basic parameters related to the wiring of the distribution cabinet. The basic parameters should include at least the wire specifications, load operating parameters, cabinet environment parameters, and cabinet structural parameters.

[0057] Based on the basic parameters, construct a target wiring scenario model corresponding to the power distribution cabinet wiring.

[0058] Analyze the target cabling scenario model to determine the corresponding cabling security level.

[0059] Based on the target cabling scenario model and cabling security level, a first cabling scheme and a second cabling scheme corresponding to the target cabling scenario model are determined, wherein the first cabling scheme has a higher priority than the second cabling scheme.

[0060] This method begins with the comprehensive acquisition of basic parameters related to the wiring of the distribution cabinet. In practice, the system collects structured and unstructured data from one or more data sources. Wire specifications can be obtained by querying an integrated wire and cable standard database, such as conductor cross-sectional area, material, and rated current. Load operating parameters may come from electrical design drawings or be imported from load calculation software via an interface, including expected current, voltage, power factor, and transient peak values ​​at startup for each circuit. Cabinet environmental parameters are defined using environmental simulation data installed inside the cabinet or during the design phase, such as ambient temperature range, relative humidity, and the presence of dust or corrosive gases. Cabinet structural parameters are extracted by parsing the 3D model of the distribution cabinet, obtaining the physical location and spatial dimensions of mounting plates, cable trays, rails, and components. Next, based on the above-aggregated basic parameters, the system constructs a target wiring scenario model. The construction of this model essentially creates a virtual digital twin of the distribution cabinet. This can be accomplished using existing computer-aided design engines or dedicated electrical system modeling software. For example, the system can input the acquired parameters into the application programming interface (API) of software such as AutoCAD Electrical, EPLAN, or Siemens NX, driving it to automatically generate a 3D model containing all electrical components, cabinet structure, and theoretical cable paths. This model not only includes physical geometric information but also embeds electrical semantic information, such as the electrical properties of components and their connection relationships. This makes the target wiring scenario model a comprehensive platform capable of static interference checks, dynamic electrical simulations, and thermodynamic analysis, creating conditions for in-depth quantitative analysis.

[0061] This invention analyzes the constructed target cabling scenario model to derive a quantified cabling safety level. This process is achieved through an embedded evaluation algorithm. This algorithm comprehensively considers multiple risk factors inherent in the model, such as calculating current density distribution based on load current and wire specifications, assessing hotspot risks based on ambient temperature and cabinet ventilation, and evaluating the compliance of clearances and creepage distances based on insulation parameters and voltage levels. Risk thresholds can be pre-set, or decision support algorithms such as fuzzy logic evaluation or analytic hierarchy process (AHP) can be used to aggregate multiple continuous risk indicators into a discrete safety level output, such as low risk, medium risk, or high risk. This level provides users with an intuitive and comprehensive understanding of the safety of the current cabling design.

[0062] This technical solution delivers significant benefits. It shifts the focus from reliance on human experience to a data-driven approach, reducing wiring defects caused by subjective errors in design through standardized parameter acquisition and model building. Before physical wiring implementation, this solution allows for proactive safety assessments of complex wiring schemes in a virtual space, identifying potential electrical, thermal, and structural interference risks in advance, effectively avoiding cost waste and project delays caused by later modifications. By generating multiple prioritized wiring schemes, it provides designers with optimized decision support, ensuring the final implementation achieves the best balance between safety, reliability, and economy, significantly improving the overall design quality and operational safety of the distribution cabinet.

[0063] As one implementation method, the basic parameters also include wire insulation parameters, cabinet heat dissipation channel parameters, and equipment interface adaptation parameters;

[0064] The parameters for wire insulation include insulation layer material, insulation thickness, and insulation withstand voltage. The parameters for cabinet heat dissipation channels include channel location, ventilation volume, and heat dissipation efficiency. The parameters for equipment interface adaptation include interface type, pin spacing, and rated number of insertions and removals.

[0065] The acquisition of wire insulation parameters is accomplished by integrating a material database with electrical standards. Based on the wire type, the system automatically retrieves the insulation material (e.g., PVC, XLPE, or silicone rubber) from the built-in or interconnected insulation material database, and obtains its standard insulation thickness and rated withstand voltage. This data is crucial for assessing the insulation aging rate and electrical safety margin of wires under specific operating conditions. The quantification of cabinet heat dissipation channel parameters is more complex, combining 3D model analysis with physical law calculations. The system identifies the location and dimensions of ventilation holes, fans, heat sinks, and other structures from the CAD assembly model of the distribution cabinet, and calculates the theoretical ventilation volume based on data such as opening area and fan power using fluid dynamics principles. Heat dissipation efficiency can be assigned by comparing with historical operating data or importing simulation results from computational fluid dynamics software, thus reflecting the actual heat dissipation capacity of the cabinet. The input of equipment interface adaptation parameters relies on an integrated component library. This library pre-stores interface standard information for various components such as circuit breakers, contactors, and terminal blocks, including their interface types (e.g., pin-type, screw-type); the precise millimeter spacing between pins; and mechanical durability indicators such as the rated number of mating cycles. This data ensures that the wiring scheme matches the physical interface.

[0066] Introducing these in-depth parameters provides more refined input to the analysis model, resulting in several significant benefits. By incorporating wire insulation parameters, the system can perform higher-level insulation coordination verification, ensuring that the insulation capacity of the selected wires not only meets the normal operating voltage but also withstands potential transient overvoltages or damp heat stress from the environment, fundamentally preventing short-circuit accidents caused by insulation failure. Integrated cabinet heat dissipation channel parameters enable dynamic thermal simulation of the model. The system can predict the temperature distribution in various areas within the cabinet, especially in areas with dense wiring bundles, under high load operation, proactively identifying potential overheating risks due to poor heat dissipation. This allows for risk mitigation during the wiring design phase by optimizing paths or adding heat dissipation measures, improving the long-term operational reliability of the system. Finally, the addition of device interface adaptation parameters incorporates the physical aspects of electrical connections, avoiding insufficient creepage distances due to excessively small pin spacing or premature mechanical failure of connectors due to mismatched mating and unmating cycles, ensuring the physical reliability and electrical safety of every connection point.

[0067] By constructing a panoramic parameter system encompassing electrical, thermal, and mechanical dimensions, the target cabling scenario model evolves from a simple geometric connection diagram into a high-fidelity digital twin capable of simulating complex interactions in the real physical world. This not only elevates the scientific nature of cabling design to a new level but also provides a solid data-driven foundation for manufacturing safe, stable, and durable distribution cabinet products through forward-looking risk insights.

[0068] As one implementation method, based on basic parameters, a target wiring scenario model corresponding to the power distribution cabinet wiring is constructed, including:

[0069] The basic parameters are preprocessed to obtain the processed basic parameters. The preprocessing includes data cleaning, data transformation and data labeling.

[0070] When the basic parameter is the wire specification parameter, data cleaning includes checking for missing specification parameters. If missing values ​​are found, the median of the specification parameters of the same type of wire is used to fill them in.

[0071] Data transformation includes unifying parameters from different units to industry standard units, and data annotation includes feature labeling of key parameters;

[0072] The processed basic parameters are input into the preset engine, and the preset engine outputs the target wiring scene model.

[0073] The preset engine includes at least one of electrical simulation software, CAD electrical design software, or power distribution system simulation software;

[0074] The target cabling scenario model is simulated, and the first and second cabling schemes are adjusted based on the simulation results.

[0075] Feature labeling is based on a predefined business rule base. For example, the system automatically determines whether a scenario is labeled as a high-humidity environment if the ambient humidity parameter is consistently higher than a set threshold, or as an overload risk if the ratio of load current to cable current carrying capacity exceeds the safety margin. These feature labels serve as metadata, providing crucial decision-making support for subsequent safety assessments and solution generation. The partitioning is automatically performed based on the spatial structure and electrical functional topology of the distribution cabinet's 3D model. The system utilizes region growing algorithms from image processing, using large components and key structural parts as core growth points, and combining this with the tightness of electrical connections, to aggregate physically continuous and functionally related components into an independent wiring area, such as dividing the main power supply area, motor drive circuit area, and control signal area.

[0076] Data cleaning begins with an automatic scan of the dataset using a rule engine or scripts to identify outliers such as null values ​​or values ​​significantly outside the reasonable range. When processing wire specifications, if critical information such as cross-sectional area or rated current is missing, the system initiates a data entry strategy. For example, it filters a dataset of wire specifications of the same material and voltage rating from a vast historical cable database and uses the median of their cross-sectional area for intelligent data entry, effectively avoiding model bias caused by missing data. Next, data transformation is performed. The system has a built-in unit conversion library that automatically identifies and standardizes the units for various parameters, such as converting wire gauge from AWG (American standard) to square millimeters and length from inches to millimeters, all conforming to industry standards and establishing a unified benchmark for subsequent calculations and modeling. Finally, data annotation is performed. The system uses natural language processing technology or predefined rules to label parameters with features. For example, it labels wires used in high-temperature environments with heat resistance characteristics and fixing points in high-vibration areas with anti-loosening requirements. These labels become important feature dimensions in subsequent model construction and safety assessment.

[0077] After preprocessing, the clean and standardized data is input into a pre-defined modeling engine. This engine is not a standalone tool, but a configurable integrated environment. Its core can be professional electrical computer-aided design software such as EPLAN, used to generate accurate 2D schematics and 3D cabinet layouts; simulation software such as ANSYS or Simulink, which directly builds models that can be used for physical field analysis; or power distribution system simulation software such as Siemens PSS. The system automatically maps the processed parameter set to the corresponding attributes of the engine through an application programming interface, driving the engine to automatically generate a high-fidelity target cabling scenario model that includes geometric, electrical, and material properties.

[0078] The final step in model building is closed-loop optimization. The system performs a series of simulations on this model. For example, it performs current load simulations to analyze voltage drop and power loss; computational fluid dynamics thermal simulations to predict temperature distribution and potential hot spots within the cabinet; and mechanical stress simulations to assess cable bundle vibration and wear. These simulations are based on real physical laws and mathematical models, and the resulting quantitative results, such as maximum temperature and maximum stress values, are compared with preset safety thresholds. Based on the comparison results, the system generates adjustment instructions, automatically or assisted by designers to refine the first and second wiring schemes, such as adjusting wire diameter to reduce temperature rise, replanning paths to avoid interference, or adding fixing points to suppress vibration.

[0079] By preprocessing data, the quality of input data is improved, ensuring the accuracy and reliability of the constructed digital model and achieving source control. Utilizing mature commercial or professional software as modeling engines maximizes the modeling advantages of these tools in their respective fields, guaranteeing the professional depth and engineering practicality of the model. Simulation enables virtual verification and iterative optimization of the design scheme. This allows hidden problems that traditionally can only be discovered during physical testing to be identified and resolved early in the design process, thereby minimizing later design changes and physical rework, significantly reducing development costs, shortening the design cycle, and ultimately ensuring the safety, reliability, and economy of the power distribution cabinet wiring scheme.

[0080] As one implementation method, the target cabling scenario model is analyzed to determine the cabling security level corresponding to the target cabling scenario model, including:

[0081] Based on the basic parameters, safety impact factors are set, including load density distribution, ambient temperature and humidity fluctuations, insulation aging rate, and heat dissipation channel unobstructedness.

[0082] Based on security impact factors, a cabling security assessment model is constructed. The cabling security assessment model is constructed using logistic regression or random forest algorithms and trained and optimized using historical cabling security data.

[0083] The target cabling scenario model is analyzed based on the cabling security assessment model to obtain the corresponding cabling security level, which is then displayed on the interface. The cabling security level includes three levels: low risk, medium risk, and high risk.

[0084] Based on the basic parameters acquired and preprocessed in the aforementioned steps, the system automatically sets a series of key safety influencing factors. For example, load density distribution is quantified by calculating the total current carried by the wires per unit volume and the heat dissipation; environmental temperature and humidity fluctuations are extracted from the cabinet's environmental parameters, including their range and extreme values; insulation aging rate is extrapolated by considering the heat resistance rating of the wire insulation material, ambient temperature, and withstand voltage; and the unobstructedness of heat dissipation channels is assessed based on the ventilation volume and heat dissipation efficiency indicators in the cabinet's heat dissipation channel parameters. The system utilizes these safety influencing factors to construct an intelligent cabling safety assessment model. This model relies on machine learning algorithms. In a specific implementation, a logistic regression algorithm can be used to construct a linear classifier. This algorithm can learn the weight relationships between each influencing factor and historical safety incidents, thereby making logical judgments about the risks of the new model. Another preferred implementation is to use a random forest algorithm. This algorithm, by constructing a large number of decision trees and performing ensemble learning, can more accurately capture the complex, nonlinear interactions between multiple influencing factors and effectively prevent overfitting. Regardless of the algorithm used, the security assessment model requires supervised learning training and optimization using a large amount of labeled historical cabling security data. This data includes successful cabling cases and various failure cases along with their corresponding risk factors. Through continuous iterative training, the model achieves extremely high prediction accuracy.

[0085] The system inputs the values ​​of various security impact factors parsed from the target cabling scenario model into this well-trained cabling security assessment model. After internal calculations, the model outputs a comprehensive and intuitive cabling security level, such as low risk, medium risk, or high risk. This level is displayed clearly on the system's graphical interface in real time, usually presented with different colors or prominent symbols, providing designers with a clear overview of the security situation.

[0086] This system shifts safety assessments from relying on expert qualitative judgments to data-driven quantitative analysis, resulting in more objective and standardized assessments that eliminate human uncertainty. By introducing mature machine learning algorithms such as logistic regression and random forests, the system can not only assess current static risks but also uncover potential and hidden complex risks, achieving deep insights and predictive warnings regarding cabling security. The complex model analysis results are visualized in a concise risk level format, improving human-computer interaction efficiency and enabling designers to quickly grasp core issues. This provides a direct and reliable basis for prioritizing high-risk items in subsequent decisions, thereby comprehensively improving the inherent safety level of distribution cabinet design.

[0087] As one implementation method, based on the target cabling scenario model and the cabling security level, a first cabling scheme and a second cabling scheme corresponding to the target cabling scenario model are determined, including:

[0088] The target wiring scenario model and wiring security level are input into the prediction model, and the prediction model outputs the first wiring scheme. The prediction model consists of a convolutional neural network, a generative adversarial network, and a reinforcement learning algorithm. It generates the optimal scheme by extracting scenario features and combining them with the security level.

[0089] The first wiring scheme includes at least one wiring stage and corresponding first execution information. One wiring stage corresponds to a set of first execution information, which includes wiring path, wire fixing point distribution and current distribution method.

[0090] The convolutional neural network (CNN) first acts as a feature extractor, transforming the structured information of the target wiring scene model into a high-dimensional feature vector. The generator in the generative adversarial network (GAN) receives this feature vector along with the wiring security level encoding, and is responsible for generating initial, diverse wiring scheme prototypes. Reinforcement learning then intervenes, running the initial schemes in a simulated environment and using electrical performance, thermodynamic indicators, and security as reward signals. It iteratively optimizes the schemes using methods such as deep Q-networks or policy gradients, while simultaneously providing feedback to adjust the generator's parameters. The action sequence output by the reinforcement learning policy network is decoded into an executable first wiring scheme. Simultaneously, the entire prediction model, as a whole, periodically retrains the GAN generator using these optimization results and corresponding scene features, continuously improving the quality of its initial generated schemes.

[0091] The system takes a target wiring scenario model containing detailed geometric and electrical information, along with its quantified wiring safety level, as input data and transmits it to the prediction model. This prediction model is a complex hybrid artificial intelligence system whose architecture deeply integrates multiple advanced machine learning algorithms. A convolutional neural network (CNN) is used for deep feature learning on the target wiring scenario model. It can intelligently identify key structural features in the model, such as the spatial layout of components, the direction of cable trays, and the distribution of free areas, much like image processing. A generative adversarial network (GAN) is then involved. Based on the features extracted by the CNN and the input safety level constraints, its internal generator and discriminator engage in a game of mutual competition, continuously iterating and creating a new, optimized prototype of a wiring scheme that conforms to both physical constraints and safety requirements. Reinforcement learning algorithms inject decision-making optimization capabilities into the scheme. It simulates the wiring environment as a dynamic environment, learning and ultimately determining the optimal wiring strategy through continuous trial and error and receiving feedback from the virtual environment.

[0092] Through the aforementioned collaborative working mechanism, the prediction model ultimately outputs a structured and executable first wiring scheme. This scheme is not a simple instruction, but a detailed plan broken down into multiple logically coherent wiring stages. Each wiring stage corresponds to a set of meticulous first execution information. This set of information is the fundamental guarantee of the scheme's feasibility. It clearly specifies the specific three-dimensional spatial path that the wires should follow within that stage, effectively avoiding interference with components; it precisely indicates the distribution and spacing of wire fixing points, ensuring the stability and neatness of the wire bundle and reducing vibration stress; it also plans the current distribution method in different parallel paths, achieving electrical load balance and preventing local overload.

[0093] By integrating three major artificial intelligence technologies—convolutional neural networks, generative adversarial networks, and reinforcement learning—it achieves end-to-end automated design from scenario analysis to solution generation, producing globally optimized cabling solutions that transcend the limitations of traditional human experience. The generated first cabling solution possesses highly structured and refined characteristics; its phased execution information makes complex cabling tasks clear, easy to construct and manage, and improves design efficiency and construction accuracy. This solution not only satisfies basic connectivity functions but also achieves optimization in deeper dimensions such as path optimization, fixed reliability, and current balanced distribution, fundamentally improving the engineering quality, long-term operational safety, and maintenance convenience of distribution cabinet cabling.

[0094] As one implementation method, based on the target cabling scenario model, a second cabling scheme corresponding to the target cabling scenario model is determined, including:

[0095] Access the cabling case library; the cabling case library includes multiple preset cabling scenarios and corresponding security cabling solutions for each preset cabling scenario. The preset cabling scenarios are classified according to load type, cabinet structure and environmental conditions.

[0096] Based on the target cabling scenario model, the target cabling scenario model is divided into at least one cabling area;

[0097] By comparing at least one wiring area with multiple preset wiring scenarios, a target preset wiring scenario with a matching degree exceeding a preset threshold is determined.

[0098] The security wiring scheme corresponding to the target preset wiring scenario is determined as the second wiring scheme. The second wiring scheme includes at least one wiring stage and corresponding second execution information. One wiring stage corresponds to a set of second execution information.

[0099] If the matching degree between all preset wiring scenarios and wiring areas does not exceed the preset threshold, the system automatically triggers the built-in expert rule base: based on the load type, voltage level and environmental parameters of the target scenario, extract the core safety constraints, and generate a simplified second wiring scheme. The scheme includes basic wiring paths, key fixed points and minimum insulation protection standards, ensuring that there are still safe and feasible alternative schemes when there are no matching cases, avoiding being at a loss in an emergency.

[0100] This cabling case library is a structured database storing numerous pre-defined cabling scenarios and their corresponding, practically proven, safe cabling solutions. These pre-defined scenarios are not randomly compiled but systematically categorized and indexed according to key dimensions such as load type (e.g., motor drive, lighting distribution), cabinet structure (e.g., compact, modular), and environmental conditions (e.g., high temperature and humidity, explosion-proof). The system intelligently divides the current target cabling scenario model into regions. This is typically done by analyzing the model's three-dimensional spatial structure and electrical connections. For example, spatial segmentation algorithms are used to divide the entire cabinet into at least one logically and physically independent cabling region, such as a main circuit area, a control circuit area, and a signal line area. Then, the system initiates an efficient matching retrieval process, comparing the feature vectors of each divided cabling region with the features of numerous pre-defined cabling scenarios in the case library. This process typically employs distance-based or deep learning matching algorithms to calculate the matching degree between the two based on key features such as load, structure, and environment, and filters out target pre-defined cabling scenarios with matching degrees exceeding a preset threshold. The system then identifies the safe cabling solutions corresponding to these verified target pre-defined cabling scenarios as the secondary cabling solution for the current region.

[0101] The resulting second cabling scheme is also a detailed and executable plan. It is broken down into several ordered cabling phases, each associated with a clear set of second execution information. This information provides guidance for the specific operations of that phase, such as the cable routing paths to be followed in the control loop area, the recommended locations and spacing of clamp fixing points, and the specific handling methods for grounding shielded wires. This information is derived from successful practical experience, ensuring the feasibility and reliability of the scheme.

[0102] Applying case studies and intelligent matching technology to electrical design allows for the systematic reuse of valuable historical experience and successful practices, improving the efficiency and starting point of design work. The second cabling solution, as a validated alternative, provides crucial redundancy for design decisions. When an innovative first cabling solution is too aggressive and introduces uncertainty, this robust and reliable second solution effectively reduces the overall risk of project implementation. The structured and phased execution information provided by this solution effectively ensures the standardization and quality consistency of the final cabling project, inheriting best practices.

[0103] As one implementation method, the method further includes: using a sensor array to acquire operational feedback results corresponding to at least one executed action;

[0104] The sensor group includes a temperature sensor, a current sensor, and an insulation resistance sensor. The operational feedback results include the wire operating temperature, actual load current, and insulation resistance value. At least one execution action is a wiring-related action in the first execution information or the second execution information.

[0105] The reinforcement learning algorithm in the prediction model updates the neural network parameters in the prediction model based on the running feedback results, and obtains the updated prediction model. The reinforcement learning algorithm adopts the deep Q-network algorithm or the policy gradient algorithm.

[0106] The sensor array typically consists of high-precision temperature sensors, current sensors, and insulation resistance sensors, strategically installed at critical circuit nodes, areas with dense wire connections, and various locations within the cabinet. Once wiring is completed and power is supplied according to the first or second wiring scheme, these sensors begin to collect physical quantities directly related to the wiring operation in real time, generating operational feedback results. These results primarily include the actual operating temperature of the wires, the actual load current of each circuit, and the insulation resistance value of the cable insulation layer. This data is transmitted to the central processing system via wired or wireless communication modules.

[0107] After obtaining the operational feedback results, the system inputs them into the reinforcement learning algorithm module in the prediction model. This algorithm treats the actual operating environment of the distribution cabinet as a dynamic testing ground. Taking the deep Q-network algorithm as an example, it defines different wiring scheme characteristics and operating states as states, possible scheme adjustments as actions, and operational feedback results as rewards. By continuously analyzing the relationship between states, actions, and rewards, the algorithm calculates the optimal policy function, which then guides the updating of parameters of components such as convolutional neural networks in the prediction model. Another policy gradient algorithm directly learns a parameterized policy and adjusts the neural network parameters by estimating the gradient of the reward, enabling the model to output wiring scheme characteristics that have historically received good operational feedback with a higher probability. Through this continuous iterative learning, the prediction model can continuously evolve, resulting in a more capable updated prediction model.

[0108] It successfully transforms one-off offline design into an online learning and optimization process throughout the entire product lifecycle, enabling cabling solutions to proactively adapt to changes in load, equipment aging, and other real-world operating conditions. Model updates based on real-world operational data significantly improve the reliability and accuracy of the predictive model's output, making the generated cabling solutions increasingly realistic and effectively mitigating potential risks associated with purely theoretical designs. This closed-loop system endows the distribution cabinet with intelligent evolution capabilities, not only extending its lifespan but also achieving a leap from static safety to dynamic safety, laying the core technological foundation for building truly intelligent and robust power distribution systems.

[0109] As one implementation method, the method further includes: monitoring whether the real-time operating parameters and wiring status data of the power distribution cabinet exceed the threshold;

[0110] Real-time operating parameters include real-time load current, cabinet internal temperature and humidity, and wiring status data includes wire joint temperature, insulation damage, and degree of looseness of fixing points.

[0111] The thresholds include a first threshold and a second threshold, which correspond to the real-time operating parameter threshold and the wiring status data threshold, respectively;

[0112] If the real-time operating parameters exceed the first threshold or the cabling status data exceeds the second threshold, an early warning message will be output. The early warning message is used to prompt the switch to the second cabling scheme.

[0113] The warning information includes detailed execution steps for the second cabling scheme, which is optimized based on historical secure cabling cases.

[0114] Before switching, a safety procedure must be followed. First, a load transfer command is issued through the system to switch the target circuit load to the backup circuit. The power supply is disconnected in the order of disconnecting the control circuit first and then the main circuit, and a maintenance sign is hung. Insulating gloves and tools must be worn during construction. The insulation resistance must be measured before operation at critical points. Early warning information is embedded throughout the process to avoid safety accidents caused by live work or failure to transfer the load.

[0115] The first and second cabling schemes differ in their application scenarios and purposes within the system. The first cabling scheme, as the primary design generated by an advanced predictive model, aims to achieve the globally optimal solution under specific constraints and is mainly used in the initial planning and design phase of the distribution cabinet. The second cabling scheme, as an alternative based on historical success stories, prioritizes its proven reliability and security. It is primarily applied in two scenarios: first, during the design review phase, as a supplement and verification reference to the first scheme; and second, during the operation and maintenance phase, providing on-site personnel with a clear, reliable, and immediately executable emergency repair or modification guideline when the monitoring system issues an early warning. This division of labor clearly defines the leading role of the first scheme and the supporting role of the second scheme, together forming a complete decision support system.

[0116] The system continuously collects two types of key data through various sensors deployed inside the cabinet: first, real-time operating parameters, including real-time load current of the main circuit and branch circuits, temperature and ambient humidity in different areas inside the cabinet; second, physical wiring status data, which is obtained through more professional detection methods, such as using infrared thermometers to monitor the temperature of wire joints, using online partial discharge detection to analyze the trend of insulation damage, and using vibration sensors and image recognition technology to help determine the degree of looseness of cable fixing points.

[0117] For acquiring wiring status data, the system employs a hierarchical monitoring strategy. For wire joint temperature, real-time monitoring is achieved through the deployment of temperature sensors. Insulation damage and loosening of fasteners are primarily addressed through periodic or on-demand maintenance inspections. For example, the system can integrate image recognition-based inspection analysis functions, comparing historical and current cabinet images to identify obvious insulation damage or fastener displacement. Simultaneously, the system can plan maintenance cycles, prompting personnel to perform quantitative testing using an insulation resistance tester or to manually check the tightness of fasteners by touch. This strategy, combining continuous real-time monitoring with periodic inspections, significantly improves the feasibility and cost-effectiveness of project implementation while ensuring the effectiveness of system early warnings.

[0118] The system has two preset safety thresholds: the first threshold targets real-time operating parameters, such as 115% of the rated current or the maximum permissible ambient temperature; the second threshold targets wiring status data, such as connector temperatures exceeding the heat resistance rating of insulation materials or fixed point displacement exceeding safe limits. These thresholds are set based on a combination of industry standards, equipment specifications, and historical operating data. The monitoring system continuously compares the collected real-time data with the corresponding thresholds. Once any real-time operating parameter exceeds the first threshold, or any wiring status data exceeds the second threshold, the system will immediately trigger an early warning process.

[0119] At this point, the system doesn't just issue a simple alarm; it outputs a structured warning message. The core function of this message is to prompt operators to switch to the second cabling solution for intervention. More importantly, the warning message directly includes detailed execution steps for this second cabling solution. This solution comes from the cabling case library mentioned earlier; it's a reliable, practice-tested solution obtained by matching and optimizing historical safe cabling cases based on the current fault characteristics. It provides complete guidance from power outage, cable removal and replacement to re-causing according to safety standards.

[0120] It represents a fundamental shift from reactive maintenance to proactive early warning. By continuously monitoring key parameters, it can issue timely alerts before serious faults such as complete insulation breakdown or burnt-out connections occur, preventing the accident from escalating. It integrates early warning with solutions, directly providing on-site personnel with a proven, immediately operable second wiring plan as emergency guidance, significantly shortening fault response and handling time and reducing decision-making delays caused by insufficient personnel experience. This mechanism enhances the resilience and reliability of distribution cabinet operation, ensuring the continuity and stability of the power supply system through intelligent status awareness and contingency plan preparation.

[0121] As one implementation method, the first execution information and the second execution information also include wire harness binding spacing, insulation protection layer selection, and heat dissipation auxiliary structure configuration;

[0122] Wiring sequence includes main circuit wiring priority and control circuit wiring sequence; fixing force includes buckle tightening torque range and cable tie tightness standard; interface tightening torque includes terminal tightening torque value and re-inspection requirements.

[0123] The selection of the insulation protection layer is determined based on the ambient humidity and voltage level. The configuration of the heat dissipation auxiliary structure includes the installation position of the heat sink and the laying method of the thermal pad.

[0124] In a refined embodiment of the present invention, the executability of the first and second routing schemes is further enhanced and guaranteed, which is reflected in the significant enrichment and specification of the first and second execution information. When generating routing schemes, the system automatically generates these crucial micro-operational guidelines through its built-in engineering rule base and optimization algorithm.

[0125] In terms of implementation, the system precisely sets these execution information based on its stored electrical engineering specifications, mechanical assembly standards, and best practices extracted from historical successful cases. For example, the determination of the wire harness binding spacing is based on a comprehensive calculation of electromagnetic interference suppression, heat dissipation and ventilation requirements, and mechanical vibration characteristics. The system will call the corresponding algorithm model to output the optimal binding spacing for different wire diameters. The selection of the insulation protection layer is a logical decision-making process. Based on the environmental humidity parameters and circuit voltage levels already included in the target wiring scenario model, the system automatically queries the insulation material database to match the type of protection layer with the corresponding moisture resistance and voltage resistance. The configuration of the heat dissipation auxiliary structure is deeply integrated with the thermodynamic simulation results. Based on the temperature field distribution obtained from the previous analysis, the system will automatically specify the installation position of the heat sink and the laying method and thickness of the thermal pad to ensure effective heat dissipation in hot areas.

[0126] Regarding wiring sequence, the system strictly stipulates that the main circuit takes precedence over the control circuit. This is based on considerations of power path reliability and electromagnetic compatibility, and decision rules ensure the shortest possible high-current path and minimize interference. For securing torque, the system extracts specific values ​​from a standard parts library, clearly defining the required tightening torque range for different specifications of clips and the binding tightness standards for different types of cable ties. These values ​​are directly related to the long-term mechanical stability of the cables. For interface tightening torque, the system not only provides precise torque values ​​for the terminals but also includes clear re-inspection requirements based on the importance level of the connection point, thereby eliminating the risk of poor contact at the process level.

[0127] By quantifying every detail, including binding, insulation, and heat dissipation, the arbitrariness and uncertainty inherent in traditional wiring operations, which rely on individual worker experience, are eliminated. This ensures a high degree of consistency and reliability in the results of work done by different personnel and in different batches. This extreme standardization not only prevents macroscopic failures caused by microscopic errors such as incorrect insulation selection or insufficient tightening torque from the source, greatly improving the product's intrinsic quality and long-term operational safety, but also standardizes and makes the entire wiring process traceable, setting a new benchmark for the manufacturing and maintenance of distribution cabinets.

[0128] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for wiring electrical cables in a distribution cabinet, characterized in that, include: Obtain the basic parameters related to the wiring of the distribution cabinet. The basic parameters should include at least the wire specifications, load operating parameters, cabinet environment parameters, and cabinet structural parameters. Based on the basic parameters, construct a target wiring scenario model corresponding to the power distribution cabinet wiring. Analyze the target cabling scenario model to determine the corresponding cabling security level. Based on the target cabling scenario model and cabling security level, a first cabling scheme and a second cabling scheme corresponding to the target cabling scenario model are determined, wherein the first cabling scheme has a higher priority than the second cabling scheme.

2. The wiring method for a power distribution cabinet according to claim 1, characterized in that: Basic parameters also include wire insulation parameters, cabinet heat dissipation channel parameters, and equipment interface adaptation parameters; The parameters for wire insulation include insulation layer material, insulation thickness, and insulation withstand voltage. The parameters for cabinet heat dissipation channels include channel location, ventilation volume, and heat dissipation efficiency. The parameters for equipment interface adaptation include interface type, pin spacing, and rated number of insertions and removals.

3. The wiring method for a power distribution cabinet according to claim 1, characterized in that: Based on the basic parameters, a target wiring scenario model corresponding to the power distribution cabinet wiring is constructed, including: The basic parameters are preprocessed to obtain the processed basic parameters. The preprocessing includes data cleaning, data transformation and data labeling. When the basic parameter is the wire specification parameter, data cleaning includes checking for missing specification parameters. If missing values ​​are found, the median of the specification parameters of the same type of wire is used to fill them in. Data transformation includes unifying parameters from different units to industry standard units, and data annotation includes feature labeling of key parameters; The processed basic parameters are input into the preset engine, and the preset engine outputs the target wiring scene model. The preset engine includes at least one of electrical simulation software, CAD electrical design software, or power distribution system simulation software; The target cabling scenario model is simulated, and the first and second cabling schemes are adjusted based on the simulation results.

4. The wiring method for a power distribution cabinet according to claim 1, characterized in that: Analyze the target cabling scenario model to determine the corresponding cabling security level, including: Based on the basic parameters, safety impact factors are set, including load density distribution, ambient temperature and humidity fluctuations, insulation aging rate, and heat dissipation channel unobstructedness. Based on security impact factors, a cabling security assessment model is constructed. The cabling security assessment model is constructed using logistic regression or random forest algorithms and trained and optimized using historical cabling security data. The target cabling scenario model is analyzed based on the cabling security assessment model to obtain the corresponding cabling security level, which is then displayed on the interface. The cabling security level includes three levels: low risk, medium risk, and high risk.

5. The wiring method for a power distribution cabinet according to claim 1, characterized in that: Based on the target cabling scenario model and cabling security level, determine the first cabling scheme and the second cabling scheme corresponding to the target cabling scenario model, including: The target wiring scenario model and wiring security level are input into the prediction model, and the prediction model outputs the first wiring scheme. The prediction model consists of a convolutional neural network, a generative adversarial network, and a reinforcement learning algorithm. It generates the optimal scheme by extracting scenario features and combining them with the security level. The first wiring scheme includes at least one wiring stage and corresponding first execution information. One wiring stage corresponds to a set of first execution information, which includes wiring path, wire fixing point distribution and current distribution method.

6. The wiring method for a power distribution cabinet according to claim 5, characterized in that: Based on the target cabling scenario model, determine the second cabling scheme corresponding to the target cabling scenario model, including: Access the cabling case library; the cabling case library includes multiple preset cabling scenarios and corresponding security cabling solutions for each preset cabling scenario. The preset cabling scenarios are classified according to load type, cabinet structure and environmental conditions. Based on the target cabling scenario model, the target cabling scenario model is divided into at least one cabling area; By comparing at least one wiring area with multiple preset wiring scenarios, a target preset wiring scenario with a matching degree exceeding a preset threshold is determined. The security wiring scheme corresponding to the target preset wiring scenario is determined as the second wiring scheme. The second wiring scheme includes at least one wiring stage and corresponding second execution information. One wiring stage corresponds to a set of second execution information.

7. The wiring method for a power distribution cabinet according to claim 5, characterized in that: The method also includes: using a sensor array to obtain operational feedback results corresponding to at least one executed action; The sensor group includes a temperature sensor, a current sensor, and an insulation resistance sensor. The operational feedback results include the wire operating temperature, actual load current, and insulation resistance value. At least one execution action is a wiring-related action in the first execution information or the second execution information. The reinforcement learning algorithm in the prediction model updates the neural network parameters in the prediction model based on the running feedback results, and obtains the updated prediction model. The reinforcement learning algorithm adopts the deep Q-network algorithm or the policy gradient algorithm.

8. The wiring method for a power distribution cabinet according to claim 1, characterized in that: The method also includes: monitoring whether the real-time operating parameters and wiring status data of the power distribution cabinet exceed the threshold; Real-time operating parameters include real-time load current, cabinet internal temperature and humidity, and wiring status data includes wire joint temperature, insulation damage, and degree of looseness of fixing points. The thresholds include a first threshold and a second threshold, which correspond to the real-time operating parameter threshold and the wiring status data threshold, respectively; If the real-time operating parameters exceed the first threshold or the cabling status data exceeds the second threshold, an early warning message will be output. The early warning message is used to prompt the switch to the second cabling scheme. The warning information includes detailed execution steps for the second cabling scheme, which is optimized based on historical secure cabling cases.

9. A wiring method for a power distribution cabinet according to claim 6, characterized in that: The first and second execution information also include wire harness binding spacing, insulation protection layer selection, and heat dissipation auxiliary structure configuration; Wiring sequence includes main circuit wiring priority and control circuit wiring sequence; fixing force includes buckle tightening torque range and cable tie tightness standard; interface tightening torque includes terminal tightening torque value and re-inspection requirements. The selection of the insulation protection layer is determined based on the ambient humidity and voltage level. The configuration of the heat dissipation auxiliary structure includes the installation position of the heat sink and the laying method of the thermal pad.

10. An electronic device, characterized in that, include: A touchscreen includes a touch sensor and a display screen; One or more processors; Memory; The memory stores one or more computer programs, which include instructions that, when executed by the electronic device, cause the electronic device to perform the wiring method for the distribution cabinet as described in any one of claims 1 to 9. The electronic device also includes a sensor interface connected to the processor for receiving data from temperature, current, and insulation resistance sensors.

Images