An electrical installation and debugging system based on artificial intelligence

Abstract

The invention discloses an electrical installation and debugging system based on artificial intelligence, comprising an acquisition module, an intelligent training module, a simulation module and an intelligent debugging module; the acquisition module is used to acquire an original data set and an installation data set; the original data set and the installation data set both include environmental parameters, environmental images, electrical equipment parameters and electrical equipment images; the intelligent training module is used to train a neural network model on the original data set using machine learning technology to obtain the trained neural network model; the simulation module is used to establish a three-dimensional simulation model of the electrical equipment according to the environmental parameters, the environmental image and the neural network model; the intelligent debugging module is used to automatically debug the electrical equipment according to the three-dimensional simulation model and the neural network model, and verify the debugging result.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical installation and debugging, and in particular to an electrical installation and debugging system based on artificial intelligence. Background Art

[0002] In recent years, with the continuous development and progress of electrical technology and information technology, electrical automation technology has been widely used in my country's industrial field. When applied to electrical installation, it not only improves the efficiency and quality of electrical installation, but also saves labor costs to a certain extent, thereby helping enterprises improve their economic benefits.

[0003] At present, the Chinese invention patent with application number 202010796928.0 discloses a method and system for debugging the function of electrical equipment. Although the motion trajectory of the robot in the equipment to be debugged is edited, and interference detection of the robot is performed according to the motion trajectory to obtain the final motion trajectory, it can reduce the interference between devices when debugging the functions of the electrical equipment and improve the reliability and accuracy of the debugging. However, the electrical installation environment is not fully considered and debugged, which may lead to the problem of accelerated aging of subsequent electrical equipment. Moreover, the debugging of the installation of electrical equipment still requires the participation of staff in editing and debugging, and the staff needs to check and analyze possible problems, which consumes a lot of energy and time of the staff. Summary of the invention

[0004] The technical problem solved by the present invention is that in the prior art, the electrical installation environment is not fully considered and debugged, which may lead to the problem of accelerated aging of subsequent electrical equipment. In addition, the debugging of the installation of electrical equipment still requires the participation of staff in editing and debugging, and the staff is required to check and analyze possible problems, which consumes a lot of energy and time of the staff.

[0005] In order to solve the above technical problems, the present invention provides an electrical installation and debugging system based on artificial intelligence, including an acquisition module, an intelligent training module, a simulation module and an intelligent debugging module;

[0006] The acquisition module is used to acquire the original data set and the installation data set;

[0007] The original data set and the installation data set both include environmental parameters, environmental images, electrical equipment parameters and electrical equipment images;

[0008] The intelligent training module is used to train the neural network model on the original data set using machine learning technology to obtain the trained neural network model;

[0009] The simulation module is used to establish a three-dimensional simulation model of the electrical equipment according to the environmental parameters, the environmental image and the neural network model;

[0010] The intelligent debugging module is used to automatically debug the electrical equipment according to the three-dimensional simulation model and the neural network model, and verify the debugging results;

[0011] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0012] The acquisition module includes an environment acquisition unit and an electrical acquisition unit;

[0013] The environment acquisition unit is used to acquire environment parameters and environment images;

[0014] The environment acquisition unit divides the air field where the electrical equipment is located into a number of equal areas, installs a group of identical sensors in each area, and obtains environmental parameters, environmental images and sensor position parameters of each area;

[0015] The electrical acquisition unit is used to acquire electrical equipment parameters and electrical equipment images;

[0016] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0017] The intelligent training module includes a data processing unit, a model training unit and a model storage unit;

[0018] The processing unit is used to perform data preprocessing and data segmentation on the original data set, wherein the data preprocessing includes missing value processing, outlier processing, duplicate value processing and data conversion to obtain a data set;

[0019] The data segmentation refers to segmenting the data set into a training set and a test set, wherein the training set is used to establish a neural network model, and the test set is used to test and evaluate the neural network model;

[0020] The model training unit is used to establish a neural network model according to the training set and select the best neural network model according to the test set;

[0021] The model storage unit is used to store the neural network model and related parameters;

[0022] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0023] The simulation model module establishes a three-dimensional simulation model according to environmental parameters, environmental images, electrical equipment parameters, electrical equipment images, sensor position parameters and a neural network model. The process of establishing the three-dimensional simulation model is as follows:

[0024] Using sensors to obtain environmental parameters, the environmental parameters include air humidity, air circulation, and air corrosivity, comparing the air humidity, air circulation, and air corrosivity obtained by the sensors, and defining that the environment of the electrical equipment installation area meets the standards when the air humidity, air circulation, and air corrosivity are within expected ranges;

[0025] If the environment of the electrical equipment installation area does not meet the standards, reselect the installation area and make comparisons until the expected ranges of air humidity, air circulation and air corrosivity are met, obtain the area location parameters, and obtain the installation coordinates based on the location parameters;

[0026] In the qualified installation area, a three-dimensional simulation model is established based on the installation coordinates and the neural network model;

[0027] The area location parameters include location coordinate parameters;

[0028] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0029] The intelligent debugging module includes an intelligent analysis unit and an intelligent debugging unit;

[0030] The intelligent analysis unit is used to analyze the electrical installation according to the three-dimensional simulation model and the neural network model to obtain installation problems;

[0031] The intelligent debugging module is used to issue debugging instructions according to the installation problem and analyze and verify the debugging results again;

[0032] The installation problems include humid environment, insufficient environmental circulation, highly corrosive environment, incorrect installation of electrical equipment circuits, substandard electrical components and loose wiring;

[0033] The re-analysis and verification refers to re-analyzing the structure of the debugged electrical equipment using a three-dimensional simulation model and re-analyzing the function of the debugged electrical equipment using a neural network model to verify whether the installation tolerance of the electrical equipment is met. If the installation tolerance of the electrical equipment is met, the debugging is deemed to be completed and the debugging is ended;

[0034] If the installation tolerance of the electrical equipment is still not reached, the three-dimensional simulation model and the neural network model are used again to install and debug the electrical equipment, and this cycle is repeated until the debugged electrical equipment reaches the installation tolerance;

[0035] As a preferred solution of the electrical installation and debugging system based on artificial intelligence described in the present invention, wherein: the intelligent analysis unit includes an electrical structure analysis subunit and an electrical function analysis subunit;

[0036] The electrical structure analysis subunit is used to compare and analyze the electrical installation structure and position according to the three-dimensional simulation model, and issue debugging instructions according to the analysis results;

[0037] The electrical structure analysis subunit uses the parallax ranging method to establish three-dimensional spatial coordinates for the electrical equipment image, and obtains the installation position coordinates of the electrical equipment, compares and analyzes the electrical installation position with the position parameters of the three-dimensional simulation model, and calculates the error of the installation position. If the error is within the expected range, the electrical installation position is not debugged. If the error exceeds the expected range, the electrical installation position is accurately debugged.

[0038] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0039] The process of establishing three-dimensional space coordinates is as follows:

[0040] Place two sensors with exactly the same internal parameters in parallel to obtain images of electrical equipment on the same plane;

[0041] Coordinate systems are established for the two sensors, defined as C1 coordinate system and C2 coordinate system respectively. The coordinates of any spatial point P are (x1, y1, z1) in C1 and (x2, y2, z2) in C2 coordinate system. The coordinates of the image point in the left sensor are (u1, v1) and (u2, v2) in the right sensor. The focal length of the sensor is f, and the distance between the two sensors is d. The three-dimensional coordinates of the spatial point P are obtained by calculation. The calculation expression is:

[0042]

[0043] Wherein, X represents the horizontal coordinate of point P, Y represents the vertical coordinate of point P, and Z represents the vertical coordinate of point P;

[0044] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0045] The intelligent debugging unit issues debugging instructions according to the installation problem, and collects the parameters and images of the electrical equipment after the debugging instructions are executed again, and compares and analyzes the parameters and images of the electrical equipment again using the three-dimensional simulation model and the neural network model to determine whether the electrical equipment after debugging is installed properly;

[0046] If the installation is unqualified, the electrical installation is debugged again according to the 3D simulation model and the neural network model until the electrical equipment is installed qualified after debugging;

[0047] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0048] The process of establishing the neural network model includes:

[0049] Extract features with information content and discriminative ability from the data set through feature engineering, select machine learning algorithms and neural network models according to the features and recognition targets, adjust the parameters of the neural network model using the training set, and evaluate the performance of the neural network model using the test set and cross-validation method, tune the neural network model, and obtain the best neural network model;

[0050] As a preferred solution of the artificial intelligence-based electrical installation and debugging system described in the present invention, wherein:

[0051] The electrical function analysis subunit is used to compare and analyze internal problems of the electrical installation according to the neural network model and issue debugging instructions;

[0052] The electrical function analysis subunit uses a neural network model to verify and analyze electrical equipment parameters and related functions of the electrical equipment. If the electrical equipment parameters are not within the expected range or the related functions of the electrical equipment cannot operate normally, the neural network model obtains installation problems and issues debugging instructions based on the installation problems.

[0053] The verification analysis refers to verifying whether the parameters of the electrical equipment are within the expected range and verifying whether the relevant functions of the electrical equipment can operate normally through the neural network model. If the parameters of the electrical equipment are not within the expected range, the neural network model is used to analyze the parameters of the electrical equipment and obtain installation problems; or if the functions of the electrical equipment cannot operate normally, the neural network model is used to analyze the operation status and parameters of the electrical equipment to obtain installation problems;

[0054] The electrical equipment parameters include voltage, current, resistance, power, capacitance and electrical equipment installation location parameters.

[0055] Beneficial effects of the present invention: The present invention collects environmental parameters and environmental images through sensors within each equivalent spatial range, analyzes the environmental parameters, obtains the air humidity, air circulation and air corrosivity of the installation environment, determines whether the air humidity, air circulation and air corrosivity are within the expected range, and adjusts the installation position for the installation environment where the environmental parameters are not within the expected range, thereby avoiding safety problems of electrical equipment caused by unqualified installation environment and slowing down the aging rate of electrical equipment to a certain extent.

[0056] By using data sets to establish three-dimensional simulation models and neural network models, the three-dimensional simulation model is used to automatically and accurately debug the circuit structure and installation position of the electrical installation. The neural network model is used to automatically debug functional problems that arise in the electrical installation. The debugging results are verified and readjusted multiple times, making the electrical installation debugging more accurate and efficient, saving a lot of manpower and material resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A basic flow chart of an artificial intelligence-based electrical installation and debugging system provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned objects, 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. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0059] Example 1, reference Figure 1 , as an embodiment of the present invention, provides an electrical installation and debugging system based on artificial intelligence, including an acquisition module, an intelligent training module, a simulation module and an intelligent debugging module;

[0060] The acquisition module is used to acquire the original data set and the installation data set;

[0061] The original data set and the installation data set both include environmental parameters, environmental images, electrical equipment parameters and electrical equipment images;

[0062] The intelligent training module is used to train the neural network model on the original data set using machine learning technology to obtain the trained neural network model;

[0063] The simulation module is used to establish a three-dimensional simulation model of the electrical equipment according to the environmental parameters, the environmental image and the neural network model;

[0064] The intelligent debugging module is used to automatically debug the electrical equipment according to the three-dimensional simulation model and the neural network model, and verify the debugging results;

[0065] The present invention automatically debugs electrical installations by establishing a three-dimensional simulation model and a neural network model, making the debugging of electrical equipment accurate and efficient, saving a lot of manpower and material resources, and determining whether the installation environment is suitable for electrical installation by analyzing environmental parameters, thereby avoiding invisible safety issues of electrical installations caused by the environment and slowing down the aging speed of electrical equipment to a certain extent;

[0066] The acquisition module includes an environment acquisition unit and an electrical acquisition unit;

[0067] The environment acquisition unit is used to acquire environment parameters and environment images;

[0068] The environment acquisition unit divides the air field where the electrical equipment is located into a number of equal areas, installs a group of identical sensors in each area, and obtains environmental parameters, environmental images and sensor position parameters of each area;

[0069] The electrical acquisition unit is used to acquire electrical equipment parameters and electrical equipment images;

[0070] The present invention collects environmental parameters and environmental images in different areas to provide data samples for selecting a suitable electrical installation environment, and collects electrical equipment parameters and electrical equipment images to provide data basis for accurate debugging of electrical equipment;

[0071] The intelligent training module includes a data processing unit, a model training unit and a model storage unit;

[0072] The processing unit is used to perform data preprocessing and data segmentation on the original data set, wherein the data preprocessing includes missing value processing, outlier processing, duplicate value processing and data conversion to obtain a data set;

[0073] The data segmentation refers to segmenting the data set into a training set and a test set, wherein the training set is used to establish a neural network model, and the test set is used to test and evaluate the neural network model;

[0074] The model training unit is used to establish a neural network model according to the training set and select the best neural network model according to the test set;

[0075] The model storage unit is used to store the neural network model and related parameters;

[0076] The missing value processing includes: using pandas.isnan() to determine whether there are null values ​​in the original data set, and when null values ​​are returned, using DataFrame.dropna() to remove the data containing null values ​​to avoid errors;

[0077] The outlier processing includes: using a determined threshold value to scan the data, identifying data that exceeds the threshold range, identifying these data as outliers, and using drop() to delete the outliers;

[0078] The duplicate value processing includes: using duplicate() to find duplicate data in the data set and define it as a duplicate value, using drop_dupliacate() to delete the duplicate value and retain the first or last one of the duplicate values;

[0079] The process of establishing the neural network model includes:

[0080] Extract features with information content and discriminative ability from the data set through feature engineering, select appropriate machine learning algorithms and neural network models according to the features and recognition targets, adjust the parameters of the neural network model using the training set, and evaluate the performance of the neural network model using the test set and cross-validation method, tune the neural network model, and obtain the best neural network model;

[0081] The feature engineering includes feature selection, feature extraction, feature transformation, feature dimension reduction, feature construction and feature expansion;

[0082] The feature selection and feature extraction are the processes of selecting a subset of features that are useful for the target task from the original data. Common feature selection methods include filtering, packaging, and embedding. The filtering method evaluates the importance of features based on statistical indicators or correlation analysis, and then selects features with high scores. The packaging method embeds the feature selection process into the model training and uses the model performance as the evaluation indicator of the feature subset. The embedding method regards feature selection as part of the model training and selects useful features through regularization techniques or decision trees.

[0083] The feature transformation is a process of mathematically transforming the original features to better meet the needs of the model. Common feature transformation methods include logarithmic transformation, power transformation, normalization, and standardization. These transformations can improve the distribution characteristics of features and reduce the correlation between features, thereby improving the performance of the model;

[0084] The feature dimensionality reduction is a process of converting a high-dimensional feature space into a low-dimensional feature space, aiming to reduce the dimension of the feature and retain as much information as possible. Common feature dimensionality reduction methods include principal component analysis (PCA) and linear discriminant analysis (LDA). These methods achieve data dimensionality reduction through projection or clustering techniques, thereby reducing computational complexity and improving the efficiency of model training.

[0085] The feature construction is a process of creating new features by combining, deriving or transforming original features to improve model performance, including creating new features by mathematical operations, text processing, time series analysis, etc.

[0086] The feature expansion is to increase the number and diversity of features by introducing external data or domain knowledge;

[0087] The cross-validation method is an important method for evaluating model performance and selecting optimal model parameters. The original data set is divided into multiple subsets, and multiple training and validation are performed based on these subsets to obtain a more accurate neural network model, including a simple cross-validation method, a K-fold cross-validation method, a leave-one-out cross-validation method, a stratified cross-validation method, a repeated cross-validation method, a time series cross-validation method, and a nested cross-validation method;

[0088] The present invention processes and trains the original data set to obtain a neural network model, provides model dependence for automatic debugging of electrical equipment, makes electrical debugging more accurate and efficient, and saves a lot of manpower and material resources;

[0089] The simulation model module establishes a three-dimensional simulation model according to environmental parameters, environmental images, electrical equipment parameters, electrical equipment images, sensor position parameters and a neural network model. The process of establishing the three-dimensional simulation model is as follows:

[0090] Using sensors to obtain environmental parameters, the environmental parameters include air humidity, air circulation, and air corrosivity, comparing the air humidity, air circulation, and air corrosivity obtained by the sensors, and defining that the environment of the electrical equipment installation area meets the standards when the air humidity, air circulation, and air corrosivity are within expected ranges;

[0091] If the environment of the electrical equipment installation area does not meet the standards, reselect the installation area and make comparisons until the expected ranges of air humidity, air circulation and air corrosivity are met, obtain the area location parameters, and obtain the installation coordinates based on the location parameters;

[0092] In the qualified installation area, a three-dimensional simulation model is established based on the installation coordinates and the neural network model;

[0093] The area location parameters include location coordinate parameters;

[0094] In one embodiment, the expected range of air humidity is 20% to 70%, the expected range of air circulation is 2 to 20 m / s, and the expected range of air corrosivity is 0.001 to 0.005 mm / a;

[0095] The present invention establishes a three-dimensional simulation model through installation coordinates and a neural network model, provides a model reference for accurate debugging of electrical equipment, makes the debugging of the installation position more accurate, and can more intuitively discover structural problems of electrical installation;

[0096] The intelligent debugging module includes an intelligent analysis unit and an intelligent debugging unit;

[0097] The intelligent analysis unit is used to analyze the electrical installation according to the three-dimensional simulation model and the neural network model to obtain installation problems;

[0098] The intelligent debugging module is used to issue debugging instructions according to the installation problem and analyze and verify the debugging results again;

[0099] The re-analysis and verification refers to re-analyzing the structure of the debugged electrical equipment using a three-dimensional simulation model and re-analyzing the function of the debugged electrical equipment using a neural network model to verify whether the installation standards of the electrical equipment are met. If the installation standards of the electrical equipment are met, the debugging is deemed to be completed and the debugging is ended;

[0100] If the installation standard of the electrical equipment is still not met, the three-dimensional simulation model and the neural network model are used again to install and debug the electrical equipment, and this cycle is repeated until the debugged electrical equipment meets the installation standard;

[0101] The installation problems include humid environment, insufficient environmental circulation, highly corrosive environment, incorrect installation of electrical equipment circuits, substandard electrical components and loose wiring;

[0102] The present invention uses a three-dimensional simulation model and a neural network model to automatically debug electrical equipment, making electrical debugging more accurate and efficient, saving a lot of manpower and material resources, and further improving the accuracy of electrical debugging through repeated verification;

[0103] The intelligent analysis unit includes an electrical structure analysis subunit and an electrical function analysis subunit;

[0104] The electrical structure analysis subunit is used to compare and analyze the electrical installation structure and position according to the three-dimensional simulation model, and issue debugging instructions according to the analysis results;

[0105] The electrical structure analysis subunit uses the parallax ranging method to establish three-dimensional spatial coordinates for the electrical equipment image, and obtains the installation position coordinates of the electrical equipment, compares and analyzes the electrical installation position with the position parameters of the three-dimensional simulation model, and calculates the error of the installation position. If the error is within the expected range, the electrical installation position is not debugged. If the error exceeds the expected range, the electrical installation position is accurately debugged.

[0106] In one embodiment, the expected range of error is 0.01 to 0.1 mm;

[0107] The parallax ranging method refers to using two cameras with the same internal parameters to record different angles of the same object and establish the three-dimensional spatial coordinates of the object through stereo calibration;

[0108] Stereo calibration is to determine the mapping between the 2D camera image and the 3D real scene. The basic principle is to calculate the internal and external parameters of the camera model based on the known points in the world coordinate system and the image coordinate system. The internal parameters of the binocular camera calibration include the camera's internal parameter matrix K and the distortion coefficient matrix D. The internal parameters are mainly determined by the type and manufacturing process of the camera, and the calibration can be obtained through the single-target calibration method. The external parameters of the calibration include the rotation matrix R, the translation matrix T, the intrinsic matrix E and the fundamental matrix F. The external parameters can describe the relative relationship between the two camera coordinate systems and can be obtained through the binocular calibration method;

[0109] The present invention analyzes the electrical structure by establishing a three-dimensional simulation model and three-dimensional space coordinates, provides accurate position coordinates and model references for electrical installation and debugging, and improves the accuracy of electrical installation and debugging;

[0110] The process of establishing three-dimensional space coordinates is as follows:

[0111] Place two sensors with exactly the same internal parameters in parallel to obtain images of electrical equipment on the same plane;

[0112] Coordinate systems are established for the two sensors, defined as C1 coordinate system and C2 coordinate system respectively. The coordinates of any spatial point P are (x1, y1, z1) in C1 and (x2, y2, z2) in C2 coordinate system. The coordinates of the image point in the left sensor are (u1, v1) and (u2, v2) in the right sensor. The focal length of the sensor is f, and the distance between the two sensors is d. The three-dimensional coordinates of the spatial point P are obtained by calculation. The calculation expression is:

[0113]

[0114] Wherein, X represents the horizontal coordinate of point P, Y represents the vertical coordinate of point P, and Z represents the vertical coordinate of point P;

[0115] The present invention obtains the installation position coordinates of the electrical equipment by establishing three-dimensional space coordinates, provides accurate coordinate parameters for electrical equipment debugging, and improves the accuracy of electrical installation and debugging;

[0116] The intelligent debugging unit issues debugging instructions according to the installation problem, and collects the parameters and images of the electrical equipment after the debugging instructions are executed again, and compares and analyzes the parameters and images of the electrical equipment again using the three-dimensional simulation model and the neural network model to determine whether the electrical equipment after debugging is installed properly;

[0117] If the installation is unqualified, the electrical installation is debugged again according to the 3D simulation model and the neural network model, and this cycle is repeated until the debugged electrical equipment is installed to a qualified standard;

[0118] Determining whether the electrical equipment after debugging is installed properly means analyzing the installation structure and installation position of the electrical equipment again through the electrical structure analysis subunit, and analyzing the basic functions and related electrical parameters of the electrical equipment through the electrical function analysis subunit to determine whether the difference is within the expected range;

[0119] The present invention debugs the installation results of electrical equipment multiple times and checks potential problems in electrical installation multiple times, thereby improving the safety and reliability of electrical installation and making the installation of electrical equipment more accurate and reliable.

[0120] The electrical function analysis subunit is used to compare and analyze internal problems of the electrical installation according to the neural network model and issue debugging instructions;

[0121] The electrical function analysis subunit uses a neural network model to verify and analyze electrical equipment parameters and related functions of the electrical equipment. If the electrical equipment parameters are not within the expected range or the related functions of the electrical equipment cannot operate normally, the neural network model obtains installation problems and issues debugging instructions based on the installation problems.

[0122] The verification analysis refers to verifying whether the parameters of the electrical equipment are within the expected range and verifying whether the relevant functions of the electrical equipment can operate normally through the neural network model. If the parameters of the electrical equipment are not within the expected range, the neural network model is used to analyze the parameters of the electrical equipment and obtain installation problems; or if the functions of the electrical equipment cannot operate normally, the neural network model is used to analyze the operation status and parameters of the electrical equipment to obtain installation problems;

[0123] The electrical equipment parameters include voltage, current, resistance, power, capacitance and electrical equipment installation location parameters;

[0124] The present invention verifies and analyzes relevant functions of electrical equipment through a neural network model and automatically obtains installation problems. It not only eliminates and solves installation problems of electrical equipment from multiple aspects, but also automatically analyzes problems and debugs equipment, effectively improving the efficiency of electrical installation and debugging and saving a lot of manpower and material resources.

[0125] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] 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. An electrical installation and debugging system based on artificial intelligence, characterized in that: It includes acquisition module, intelligent training module, simulation module and intelligent debugging module; The acquisition module is used to acquire the original data set and the installation data set; The original data set and the installation data set both include environmental parameters, environmental images, electrical equipment parameters and electrical equipment images; The intelligent training module is used to train the neural network model on the original data set using machine learning technology to obtain the trained neural network model; The simulation module is used to establish a three-dimensional simulation model of the electrical equipment according to the environmental parameters, the environmental image and the neural network model; The intelligent debugging module is used to automatically debug the electrical equipment according to the three-dimensional simulation model and the neural network model, and verify the debugging results; The intelligent debugging module includes an intelligent analysis unit and an intelligent debugging unit; The intelligent analysis unit is used to analyze the electrical installation according to the three-dimensional simulation model and the neural network model to obtain installation problems; The intelligent debugging module is used to issue debugging instructions according to the installation problem and analyze and verify the debugging results again; The re-analysis and verification includes re-analyzing the structure of the debugged electrical equipment using a three-dimensional simulation model, and re-analyzing the function of the debugged electrical equipment using a neural network model to verify whether the installation tolerance of the electrical equipment is met. If the installation tolerance of the electrical equipment is met, the debugging is deemed to be completed and the debugging is ended; If the installation tolerance of the electrical equipment is still not reached, the three-dimensional simulation model and the neural network model are used again to install and debug the electrical equipment, and this cycle is repeated until the debugged electrical equipment reaches the installation tolerance; The installation problems include humid environment, insufficient environmental circulation, highly corrosive environment, incorrect installation of electrical equipment circuits, substandard electrical components and loose wiring; The intelligent analysis unit includes an electrical structure analysis subunit and an electrical function analysis subunit; The electrical structure analysis subunit is used to compare and analyze the electrical installation structure and position according to the three-dimensional simulation model, and issue debugging instructions according to the analysis results; The electrical structure analysis subunit uses the parallax ranging method to establish three-dimensional spatial coordinates for the electrical equipment image, and obtains the installation position coordinates of the electrical equipment, compares and analyzes the electrical installation position with the position parameters of the three-dimensional simulation model, and calculates the error of the installation position. If the error is within the expected range, the electrical installation position is not debugged. If the error exceeds the expected range, the electrical installation position is accurately debugged. The process of establishing three-dimensional space coordinates is as follows: Place two sensors with exactly the same internal parameters in parallel to obtain images of electrical equipment on the same plane; Coordinate systems are established for the two sensors, defined as C1 coordinate system and C2 coordinate system respectively. The coordinates of any spatial point P are (x1, y1, z1) in C1 and (x2, y2, z2) in C2 coordinate system. The coordinates of the image point in the left sensor are (u1, v1) and (u2, v2) in the right sensor. The focal length of the sensor is f, and the distance between the two sensors is d. The three-dimensional coordinates of the spatial point P are obtained by calculation. The calculation expression is: ； Wherein, X represents the horizontal coordinate of point P, Y represents the vertical coordinate of point P, and Z represents the vertical coordinate of point P; The intelligent debugging unit issues debugging instructions according to the installation problem, and collects the parameters and images of the electrical equipment after the debugging instructions are executed again, and compares and analyzes the parameters and images of the electrical equipment again using the three-dimensional simulation model and the neural network model to determine whether the electrical equipment after debugging is installed properly; If the installation is unqualified, the electrical installation is debugged again according to the 3D simulation model and the neural network model until the electrical equipment is installed qualified after debugging; The electrical function analysis subunit is used to compare and analyze internal problems of the electrical installation according to the neural network model and issue debugging instructions; The electrical function analysis subunit is used to compare and analyze internal problems of the electrical installation according to the neural network model and issue debugging instructions; The electrical function analysis subunit uses a neural network model to verify and analyze electrical equipment parameters and related functions of the electrical equipment. If the electrical equipment parameters are not within the expected range or the related functions of the electrical equipment cannot operate normally, the neural network model obtains installation problems and issues debugging instructions based on the installation problems. The verification analysis includes verifying whether the electrical equipment parameters are within the expected range and verifying whether the relevant functions of the electrical equipment can operate normally through a neural network model. If the electrical equipment parameters are not within the expected range, the neural network model is used to analyze the electrical equipment parameters and obtain installation problems; or if the electrical equipment functions cannot operate normally, the neural network model is used to analyze the operating conditions and electrical equipment parameters of the electrical equipment to obtain installation problems.

2. An electrical installation and debugging system based on artificial intelligence as claimed in claim 1, characterized in that: The acquisition module includes an environment acquisition unit and an electrical acquisition unit; The environment acquisition unit is used to acquire environment parameters and environment images; The environment acquisition unit divides the air field where the electrical equipment is located into a number of equal areas, installs a group of identical sensors in each area, and obtains the environment parameters, environment images and location parameters of the sensors in each area; The electrical acquisition unit is used to acquire electrical equipment parameters and electrical equipment images.

3. An electrical installation and debugging system based on artificial intelligence as claimed in claim 1, characterized in that: The intelligent training module includes a data processing unit, a model training unit and a model storage unit; The processing unit is used to perform data preprocessing and data segmentation on the original data set, wherein the data preprocessing includes missing value processing, outlier processing, duplicate value processing and data conversion to obtain a data set; The data segmentation refers to segmenting the data set into a training set and a test set, wherein the training set is used to establish a neural network model, and the test set is used to test and evaluate the neural network model; The model training unit is used to establish a neural network model according to the training set and select the best neural network model according to the test set; The model storage unit is used to store the neural network model and related parameters.

4. An electrical installation and debugging system based on artificial intelligence as claimed in claim 1, characterized in that: The simulation model module establishes a three-dimensional simulation model according to environmental parameters, environmental images, electrical equipment parameters, electrical equipment images, sensor position parameters and a neural network model. The process of establishing the three-dimensional simulation model is as follows: Using sensors to obtain environmental parameters, the environmental parameters include air humidity, air circulation, and air corrosivity, comparing the air humidity, air circulation, and air corrosivity obtained by the sensors, and defining that the environment of the electrical equipment installation area meets the standards when the air humidity, air circulation, and air corrosivity are within expected ranges; If the environment of the electrical equipment installation area does not meet the standards, reselect the installation area and make comparisons until the expected ranges of air humidity, air circulation and air corrosivity are met, obtain the area location parameters, and obtain the installation coordinates based on the location parameters; In the qualified installation area, a three-dimensional simulation model is established based on the installation coordinates and the neural network model; The area location parameters include location coordinate parameters.

5. An electrical installation and debugging system based on artificial intelligence as claimed in claim 3, characterized in that: The process of establishing the neural network model includes: Through feature engineering, features with information content and discriminative ability are extracted from the data set. Machine learning algorithms and neural network models are selected according to the features and recognition targets. The training set is used to adjust the parameters of the neural network model. The test set and cross-validation method are used to evaluate the performance of the neural network model. The neural network model is tuned to obtain the best neural network model.

Images