KR102191493B1 - Method and apparatus for controlling design and construction process of electrical equipment - Google Patents

Abstract

Disclosed are a method and an apparatus for controlling a design and a construction process of electrical equipment, capable of increasing accuracy and efficiency. According to one embodiment, the method for controlling the design and the construction process of the electrical equipment based on artificial intelligence includes: storing a blueprint of a target space scanned by a designer for the design of electrical equipment; generating a first input signal based on the blueprint; inputting the first input signal to a pre-trained convolutional neural network in a blockchain network; acquiring a first output signal based on a result of the input; arranging recommended optimized electrical equipment in the stored blueprint according to a recommended design based on the first output signal; generating a correction input signal according to a value input by the designer to adjust required electrical equipment and a number of the required electrical equipment based on a result of the arrangement; arranging correction electrical equipment in the blueprint based on the recommended design and positional relation of equipment, in which the positional relation includes role overlapping prevention, a distance, and connection of electrical equipment, based on the correction input signal; generating a final correction input signal according to a final input of the designer based on the blueprint, which has been subject to the arrangement; determining a final position of the electrical equipment and generating a training signal based on the final correction input signal; and training the convolutional neural network based on the training signal.

Description

Control method and device for design and construction process of electrical equipment {METHOD AND APPARATUS FOR CONTROLLING DESIGN AND CONSTRUCTION PROCESS OF ELECTRICAL EQUIPMENT}

The following embodiments relate to a control method for the design and construction process of electrical equipment.

Electric equipment is a collective term for a facility that uses electricity through design and construction, and can be classified into lighting equipment, electric heating equipment, electric power equipment, transmission and distribution equipment, and power generation equipment. The design of electrical equipment can be accomplished through the process of planning, calculation, planning, drawing, purchase and construction.

The design and construction process of electrical equipment is being automated in many parts with the development of smart equipment. However, it is a reality that many of the errors occurring in the design and construction process are still being corrected by human hands. Therefore, a study of a system capable of self-learning and correcting process errors is required.

KR 200179740 Y1 KR 102038092 B1 KR 100872386 B1 KR 102002636 B1

The embodiments seek to increase accuracy and efficiency by applying deep learning technology to a method of controlling the design and construction process of electrical equipment.

The embodiments intend to provide continuous feedback using errors in design errors in a method of controlling the design and construction process of electrical equipment.

The embodiments aim to convert information into big data through a blockchain network and use enhanced security.

A method for controlling the design and construction process of an electrical facility according to an embodiment is a method of controlling the design and construction process of an electrical facility based on artificial intelligence, wherein the target space scanned by the designer for designing the electrical facility is Storing the blueprint; Generating a first input signal based on the blueprint; Inputting the first input signal to a pre-learned convolutional neural network in a blockchain network; Obtaining a first output signal based on the input result; Arranging a recommended optimized electrical installation in the stored schematic according to a recommended design based on the first output signal; Generating a correction input signal according to a value input by the designer to adjust the number of electrical equipment required by the designer based on the arrangement result; Based on the corrected input signal, the revised electrical equipment is placed in the blueprint based on the recommended design and the positional relationship of each facility-the positional relationship includes the role overlap prevention, distance and connection of the respective electrical equipments- Step to do; Generating a final modified input signal according to the final input of the designer based on the arranged blueprint; Generating a final position determination and learning signal of the electrical installation based on the final modified input signal; And training the convolutional neural network based on the learning signal.

According to an embodiment, the electrical installation includes: a lighting facility designed to install various types of light and a space area; A heat transfer facility that allows the heating element to generate heat through electric power; Electric power equipment for operating elevator and escalator facilities using electric motors; A transmission and distribution facility for transmitting and distributing AC 220V electricity so that the user of the target space can use it; And it may include a power generation facility that provides electricity to the target space through the individual power generation facility.

According to an embodiment, the block chain network includes blocks including a database including blueprints, type, number, and location information of electrical equipment, and the pre-learned convolutional neural network; Chains connecting each block in chronological order; And a private blockchain network including the network storage devices for storing the respective blocks and chains, wherein the network storage devices include a first network storage device including a producer producing the electrical equipment; A second network storage device including a designer using a method of controlling the design and construction process of the electrical equipment; A third network storage device including a manager managing a control method of the design and construction process of the electrical equipment; And a high-speed Internet connection network connecting each of the network storage devices.

According to an embodiment, the database includes blueprints of various spaces collected from big data; And electrical installations designed according to the location and number determined to correspond to the blueprints, and a combination of the electrical installations corresponding to the blueprints is at least two, and the electrical installations in the database Among the combinations of facilities, an optimized facility and combination may be initially presented, and a design closest to the modified input information and the final modified input information of the designer may be modified and presented again.

According to an embodiment, the convolutional neural network receives a first input signal encoded by the scanned blueprint in a form suitable for the convolutional neural network as an input, and based on the blueprint, the convolutional neural network uses the most similar blueprint in the database. Classify through the feature extraction neural network and the classification neural network, and based on the classification, output a first output signal including information on the type, number, and location of the corresponding electric equipment, and the designer for the design of the electric equipment It may be learned through the first learning signal generated from the final modified input signal containing the final determination of.

The apparatus according to the embodiment may be controlled by a computer program stored in a medium in order to execute the method of any one of the above-described methods in combination with hardware.

The embodiments may increase accuracy and efficiency by applying deep learning technology to a method of controlling the design and construction process of electrical equipment.

The embodiments may provide continuous feedback using an error of design error in a method of controlling the design and construction process of electrical equipment.

The embodiments can convert information into big data and use enhanced security through a blockchain network.

1 is a flow chart illustrating a method of controlling a design and construction process of an electric facility according to an embodiment.
2 is a view for explaining an electrical installation according to an embodiment.
3 is a diagram illustrating a block chain network according to an embodiment.
4 is a diagram for describing a database according to an embodiment.
5 is a diagram illustrating a convolutional neural network according to an embodiment.
6 is an exemplary diagram of a configuration of an apparatus according to an embodiment according to an embodiment.

Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the rights of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes to the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be changed in various forms and implemented. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical idea.

Although terms such as first or second may be used to describe various components, these terms should be interpreted only for the purpose of distinguishing one component from other components. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

When a component is referred to as being "connected" to another component, it is to be understood that it may be directly connected or connected to the other component, but other components may exist in the middle.

The terms used in the examples are used for illustrative purposes only and should not be interpreted as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present specification, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this application. Does not.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of the reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, when it is determined that a detailed description of related known technologies may unnecessarily obscure the subject matter of the embodiments, the detailed description thereof will be omitted.

The embodiments may be implemented in various types of products such as a personal computer, a laptop computer, a tablet computer, a smart phone, a television, a smart home appliance, an intelligent vehicle, a kiosk, and a wearable device.

1 is a flow chart illustrating a method of controlling a design and construction process of an electric facility according to an embodiment.

According to an embodiment, in the method of controlling the design and construction process of electrical equipment based on artificial intelligence, the control device (hereinafter, the control device) of the design and construction process of the electrical equipment is a designer for the design of the electrical equipment. The blueprint of the scanned target space may be stored (101). The control device is a control device for the design process of an electrical facility, and may be implemented as, for example, a software module, a hardware module, or a combination thereof.

According to an embodiment, the control device may be an electronic device including a communication function. For example, electronic devices include smart phones, tablet personal computers (PCs), mobile phones, video phones, e-book readers, desktop personal computers (desktop personal computers), and laptops. Laptop personal computer (PC), netbook computer, personal digital assistant (PDA), portable multimedia player (PMP), MP3 player, mobile medical device, camera, or wearable device (e.g.: Including at least one of a head-mounted-device (HMD) such as an electronic glasses, an electronic clothing, an electronic bracelet, an electronic necklace, an electronic appcessory, an electronic tattoo, a smart car, or a smartwatch. I can.

According to an embodiment, the electronic device may be a smart home appliance having a communication function. Smart home appliances, for example, include televisions, digital video disk (DVD) players, audio, refrigerators, air conditioners, vacuum cleaners, ovens, microwave ovens, washing machines, air purifiers, set-top boxes, and TVs. It may include at least one of a box (eg, Samsung HomeSyncTM, Apple TVTM, or Google TVTM), game consoles, electronic dictionary, electronic key, camcorder, or electronic frame.

According to an embodiment, the electronic device includes various medical devices (e.g., magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), computed tomography (CT)), an imager, an ultrasonic device, etc.), a navigation device, a GPS receiver ( global positioning system receiver), EDR (event data recorder), FDR (flight data recorder), automobile infotainment device, marine electronic equipment (e.g. marine navigation equipment and gyro compass, etc.), avionics, security It may include at least one of a device, a vehicle head unit, an industrial or domestic robot, an automatic teller's machine (ATM) of a financial institution, or a point of sales (POS) of a store.

According to one embodiment, the electronic device is a piece of furniture or building/structure including a communication function, an electronic board, an electronic signature receiving device, a projector, or various measurement devices. It may include at least one of devices (eg, water, electricity, gas, or radio wave measurement devices). The electronic device according to an embodiment may be a combination of one or more of the aforementioned various devices. In addition, the electronic device according to an embodiment may be a flexible device. In addition, it is obvious to those skilled in the art that the electronic device according to the embodiment is not limited to the above-described devices. The term user used in various embodiments may refer to a person using an electronic device or a device (eg, an artificial intelligence electronic device) using an electronic device.

An electronic device according to an embodiment includes a processor, a memory, a user interface, and a communication interface, and may be connected to other electronic devices through a network. The communication interface may transmit and receive data to and from other electronic devices within a predetermined distance through wired, wireless network, or wired serial communication. The network enables wired and wireless communication between an electronic device and various entities according to an embodiment. The electronic device can communicate with various entities through the network, and the network can use standard communication technologies and/or protocols. In this case, the network includes, but is not limited to, the Internet, a local area network (LAN), a wireless local area network (LAN), a wide area network (WAN), a personal area network (PAN), and the like, It can be understood by those of ordinary skill in the field of communication technology that it may be another type of network capable of transmitting and receiving information.

According to an embodiment, the target space is a detached house, apartment house, type 1 neighborhood living facility, type 2 neighborhood living facility, cultural and assembly facility, religious facility, sales facility, transportation facility, medical facility, educational research facility, Elderly people's facilities, training facilities, sports facilities, business facilities, lodging facilities, amusement facilities, factories, warehouse facilities, hazardous materials storage and treatment facilities, automobile related facilities, animal and plant related facilities, excrement and waste disposal facilities, correctional and military facilities, It may be any one of a broadcasting communication facility, a power generation facility, a cemetery-related facility, a tourist rest facility, and a funeral home, but is not limited thereto.

According to an embodiment, the design diagram of the target space may include a plan view, a cross-sectional view, an elevation view, a side view, a rear view, etc., but is not limited thereto. The design drawing in the design of electrical equipment and the control method of the construction process may be two-dimensional or three-dimensional. The blueprint can be input to the control device through a scan, but in some cases, the blueprint can be drawn using a design program. Design drawings through the design program can be automatically entered into the control device without having to go through a scan.

According to an embodiment, the control device may generate a first input signal based on the blueprint (102). The control device may input the first input signal to the previously learned convolutional neural network in the blockchain network (103).

According to an embodiment, the control device may encode the scanned blueprint to generate an input signal in a form suitable for a convolutional neural network in a blockchain network. A detailed description of the generation of the first input signal will be described later with reference to FIG. 5.

The convolutional neural network according to an embodiment may be designed to determine the most similar blueprint among blueprints in a database based on the blueprint scanned in real time, and to determine electrical equipment corresponding thereto. This convolutional neural network is composed of a feature extraction neural network and a classification neural network, and the feature extraction neural network proceeds by sequentially stacking a convolutional layer and a pooling layer for input signals. The convolutional layer includes a convolution operation, a convolution filter, and an activation function. The calculation of the convolution filter is adjusted according to the size of the matrix of the target input, but a 9X9 matrix is generally used. The activation function generally uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The pooling layer is a layer that reduces the size of the input matrix, and uses a method of extracting a representative value by grouping pixels in a specific area. In general, an average value or a maximum value is often used for the operation of the pooling layer, but the present invention is not limited thereto. This operation is performed using a square matrix, typically a 9X9 matrix. The convolutional layer and the pooling layer are alternately repeated until the corresponding input is small enough while maintaining the difference.

According to one embodiment, the classification neural network has a hidden layer and an output layer. In a convolutional neural network for the control method of the design and construction process of electrical facilities, there are generally three or more hidden layers, and each hidden layer has 100 nodes, but it can be set to more or less depending on the case. The activation function of the hidden layer uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The number of output layer nodes of a convolutional neural network can be a total of 10. The output layer activation function of the classification neural network uses the softmax function. The softmax function is a representative function of one-hot encoding, which makes the sum of all output nodes total 1, the output of the output node with the largest value as 1, and the output of the remaining output nodes as 0. . It is possible to select only one of the 10 outputs through the softmax function.

The blockchain network according to an embodiment is composed of blocks that store a database and a chain that connects them in chronological order, and the database can store data such as blueprints, types, number and location information of electrical equipment. . The stored database is managed as big data, and the blockchain network can help keep the information in this database safe and make it available only to limited users. A description of the blockchain network and the convolutional neural network will be described later with reference to FIGS. 3, 4 and 5.

According to an embodiment, the control device may acquire the first output signal based on the input result (104). Based on the first output signal, the control device may place the recommended optimized electrical equipment in the stored design according to the recommended design (105).

According to an embodiment, the convolutional neural network may have 10 outputs, each of which may include type, number, and location information of electrical equipment based on a scanned design. The control device may locate each electrical installation in the scanned design drawing based on the type, number and location information of the electrical installation in the first output signal. The type, number, and location information of the electrical equipment may be determined as a first priority combination among recommended combinations, and this may be referred to as a recommended design. The scanned blueprint may be a blueprint stored in the form of a soft copy in the control device based on the color information of the existing hardcopy blueprint.

According to an embodiment, the control device may generate a correction input signal according to a value input to adjust the number of electrical equipment and electrical equipment required by the designer based on the arrangement result (106). Based on the correction input signal, the control device may place the corrected electrical equipment in the design drawing based on the recommended design and the positional relationship of each equipment (107).

According to an embodiment, a designer or a user of a method for controlling the design and construction process of an electrical facility may input a type of electrical facility selected from a recommended design and a matter deemed to require modification in water into the control device. This input can be used to generate a crystal input signal. The corrected input signal can be used to select the most similar design among other designs previously included in the first output signal. After selecting the most similar design, the type of electrical equipment modified according to the information contained in the corrected input signal. And it is possible to create new location information according to the number. The control device can locate the revised electrical installation in the blueprint based on the newly created location information. In this case, if there is a type and number of electrical installations that were not included in the existing first output signal, the positional relationship of each electrical installation is affected. It can be placed within the blueprint based on it.

The positional relationship according to an embodiment may include prevention of overlapping roles of electrical equipment, distance, and connection. In order to prevent overlapping of roles of electric equipment, the roles of electric equipment are similar or identical, so that the location of electric equipment can be adjusted by comparing the increase in user convenience and efficiency reduction obtained by positioning it in a nearby location. The distance between the electrical installations may mean a distance at which each electrical installation can be optimized based on role overlap prevention. Each distance may include a linear distance and a distance taking into account an actual moving line. The connection of electrical installations refers to the respective connection relationship of the electrical installations, and can be considered so as to exhibit an optimized function with the least possible connection complexity. Information on each location relationship may exist in a database within the blockchain network, and may be included in the first output signal together.

According to an embodiment, the control device may generate a final correction input signal according to a final input of a designer based on the arranged blueprint (108). The control device may generate a final position determination and learning signal of the electrical installation based on the final modified input signal (109). The control device may train the convolutional neural network based on the learning signal (110).

According to an embodiment, a designer may review a corrected design diagram according to a correction input signal, and then input correction and confirmation details for this. The input of corrections and confirmations can be used to generate the final correction input signal. If the designer does not input correction and confirmation details, the control device can generate a learning signal based on the previously modified design, and this learning signal is used in a direction to increase the confidence level of the convolutional neural network for the first output signal. I can. The final modification input of the designer is based on 1 hour after generation of the first output signal of the convolutional neural network, but may be more or less than that in some cases. The control device can increase accuracy and efficiency by applying deep learning technology to a method of controlling the design and construction process of electrical equipment.

2 is a view for explaining an electrical installation according to an embodiment.

Referring to Figure 2, the electrical installation is a lighting fixture 201 designed to install various types of light and the width of the space; A heat transfer facility 202 that allows the heating element to generate heat through electric power; A power facility 203 for operating an elevator and escalator facility using an electric motor; A transmission and distribution facility 204 for transmitting and distributing AC 220V electricity so that users of the target space can use it; And a power generation facility 205 that provides electricity to the target space through individual power generation facilities.

The lighting facility 201 according to an embodiment is a facility composed of a lighting fixture, a flashing dimming system, a power system, and a wiring, and may mean a facility that serves to illuminate a space by converting an electric signal into light. Types of the lighting equipment 201 may be classified into office lighting, factory lighting, hospital lighting, stage lighting, flood lighting, road lighting, etc., but are not limited thereto.

The heat transfer facility 202 according to an embodiment heats using electric power, and can be classified into a nichrome wire heating method using resistance heating, a high frequency heating using an AC frequency, etc., but is not limited thereto. The heat transfer facility 202 may be divided into a direct type or an indirect type according to a method of generating heat in the heating element.

The electric power facility 203 according to an embodiment may mean that an electric motor is used and various facilities are operated, such as a fan, a refrigerator gas compressor, a pump motor, etc., to a motor of an escalator and an elevator, and others. It may include an industrial electric motor. Among them, the power facility 203 of an escalator and an elevator is a facility mainly used in a control method of a design and construction process of an electrical facility, and may exhibit a high power usage rate in the entire electrical facility.

The transmission and distribution facility 204 according to an embodiment is a generic term for transmission that sends electricity provided from the power generation facility 205 to a target space and a distribution facility that distributes it, and may be a facility including an electric wire connecting electricity inside and outside the target space. have. Basically, it can serve as a way to provide electricity to the lighting equipment 201, the electric heating equipment 202 and the electric power equipment 203, and in the target space, 220V AC electricity, which is a form that can be used mainly by users, can be distributed. I can.

The power generation facility 205 according to an embodiment may be regarded as a generic name including all existing power generation facilities such as hydroelectric power plants, thermal power plants, and nuclear power plants to renewable energy generation facilities such as wind power generation and solar power generation. Electrical equipment in the method and device for controlling the design and construction process of electrical equipment is mainly limited to the target space to provide electricity and is equipment that can generate power in the target space, and most of them can include solar power facilities. However, it is not limited to this.

3 is a diagram illustrating a block chain network according to an embodiment.

Referring to FIG. 3, the block chain network includes blocks 301 including a database including blueprints, type, number and location information of electrical equipment, and a pre-learned convolutional neural network; Chains 302 connecting each block 301 in chronological order; And a first 310, a second 320, and a third network storage device 330 for storing each block chain.

According to an embodiment, the block 301 of the block chain network may include a database including blueprints, type, number, and location information of electrical equipment, and a pre-learned convolutional neural network that handles the data. Each block 301 is generally connected in chronological order, and accordingly, new blocks 301 may be produced every 10 minutes. The contents of the already generated block 301 are stored in all network storage devices, and have a structure that cannot be changed unless a majority of the contents are changed within time. For example, if a block chain network with a total of 3 network storage devices has one block 301 for each network storage device, if the contents of two or more blocks 301 cannot be changed within a limited time, Each block 301 may change the value of the block 301 having contents different from the majority through verification to be the same as the majority. Accordingly, high security can be maintained, and since the number of network storage devices actually participating in the blockchain network can reach tens to hundreds of thousands of devices, higher security can be exhibited.

Chains 302 according to an embodiment may be configured with a hash value. The chains 302 allow the blocks 301 to be consecutive in chronological order, and in this case, each block 301 may be connected using a hash value. The block 301 may store a database, a hash value of the database, a previous header, and a header of the current block. Here, since the header of the current block functions as the previous header in the next block, the blocks 301 can be organically connected. In addition, if the content of the block changes even a little, the hash value is transformed into a completely different form, which effectively prevents attempts to change the content of the database. Since the header of the current block becomes the hash value of the total sum including the database, the hash value of the database, and the previous header, any attempt to compromise security by effectively modifying the database and the hash value becomes difficult. This is because the moment the database and the hash value are modified, the contents of the header also change, and accordingly, the previous header that enters the next block also changes, and accordingly, the header of the block also changes and the previous header of the next block may be changed again. That is, all subsequent blocks 301 must be hacked. Therefore, the security of the blockchain can be increased with the chain 302 through the hash value. The control device can convert information into big data through a blockchain network and use enhanced security.

According to an embodiment, the network storage devices include: a first network storage device 310 including a producer producing electrical equipment; A second network storage device 320 including a designer using a method for controlling the design and construction process of electrical equipment; A third network storage device 330 including a manager managing a control method of designing and constructing electrical equipment; And a high-speed Internet connection network 303 connecting each of the network storage devices. The number of network storage devices classified as first, second, and third may be determined according to the number of practitioners, the number of users, and the number of storage devices included.

According to an embodiment, the first network storage device 310 may include a producer who produces electrical equipment, and the producer may be one or more. The number of first network storage devices 310 may be determined according to the number of storage devices used by each company. Producers who produce the electrical equipment of the first network storage device 310 can update information on the type of electrical equipment based on the database of the blockchain network and the convolutional neural network, and the electrical equipment according to the need for design. Can be maintained or developed.

According to an embodiment, the second network storage device 320 may include a designer who uses a method of controlling the design and construction process of electrical equipment. The number of the second network storage devices 320 may be determined according to the number of companies and users who design them in the design and construction process of electrical equipment. The designer of the second network storage device 320 may also be referred to as an actual user (hereinafter, referred to as a user) who uses the method and device for controlling the design and construction process of electrical equipment. Users of the control device for the design and construction process of the electrical equipment of the second network storage device 320 may facilitate learning of the convolutional neural network by manually inputting information on errors occurring during actual use.

According to an embodiment, the third network storage device 330 may include a manager who manages a method of controlling design and construction processes of electrical equipment. The administrator of the third network storage device 330 may directly modify the electrical equipment design and construction process control method according to the request of the producer and the designer, and may manually learn the convolutional neural network if necessary.

The high-speed Internet connection network 303 according to an embodiment generally refers to an Internet connection network exhibiting a speed of 10 Mb/s or more, and is a connection network including wired, wireless, optical cable technology, etc., and is a local area network (LAN) or a wireless LAN (Wireless LAN). Local Area Network), Wide Area Network (WAN), Personal Area Network (PAN), and the like, but are not limited thereto.

4 is a diagram for describing a database according to an embodiment.

Referring to FIG. 4, the database includes design drawings 401 of various spaces collected from big data; And electrical installations 402 that determine the location and number to correspond to the blueprints 401 and are designed accordingly.

According to one embodiment, the database in the blockchain network can store values that were initially manually input by the administrator by the administrator, and these initial input values include blueprints of various spaces collected online based on big data. (401) may be included. The blueprints 401 may acquire only information including information on the purpose and area of the space. The initial input value may also include information on the type, number, and location of electrical installations 402 corresponding to these blueprints 401, which values are known to those of ordinary skill in electrical installation design. I can. The type, number, and location information of each electric equipment 402 are input by electric equipment design experts, and a ranking may be determined based on a standard from the maximum recommendation through values input by at least 100 experts. Except for the initial input, the database input may be updated through the learning process of the convolutional neural network.

According to an embodiment, a blueprint that is most similar to a blueprint input through a convolutional neural network is searched among the blueprints 401 in a database, and information on the type, number, and location of electrical equipment corresponding to the similar blueprint can be obtained. . The type, number, and location information of the electrical equipment corresponding to the blueprint may be recommended based on a ranking among values stored in the database, and these values may be included in the first output signal. The combination of electrical installations 402 corresponding to the blueprints 401 may be at least two or more.

According to an embodiment, the electrical installations 402 may initially present an optimized facility and a combination among the combinations of the electrical installations 402 in the database, and are closest to the designer's corrected input information and the final modified input information. The design can be revised and presented again. The combination of the type and number of electrical equipment initially presented may be based on a ranking derived from values input by experts, and this ranking may be modified through learning of a convolutional neural network. The correction input information and the final correction input information of the designer can be induced to select the closest combination among the combinations of the next order included in the first output signal, and in some cases, the correction values not included in the combination are based on the positional relationship. Can be automatically entered. The designer's corrected input information and the last modified input information can be used to train a convolutional neural network as a future learning signal.

5 is a diagram illustrating a convolutional neural network according to an embodiment.

Referring to FIG. 5, blocks in the blockchain network may include a pre-learned convolutional neural network 510 and a database, and take a first input signal 501 as an input and output a first output signal 502. And learning through the learning signal 503.

According to an embodiment, the first input signal 501 that is input to the convolutional neural network 510 may encode the scanned design diagram in a form suitable for the convolutional neural network. The first input signal 501 may encode a value obtained by digitizing color information of each pixel of the scanned blueprint to suit the convolutional neural network again. The color information may include RGB information, brightness, and saturation for each pixel. The first input signal 501 provides the information so that the blueprint of the target space can be distinguished from the background based on the respective values of the color information so that the boundary of the blueprint can be clearly defined. Color information included in the first input signal 501 may be compared with blueprints in the database through the convolutional neural network 510.

According to an embodiment, the convolutional neural network 510 may classify the most similar blueprint in the database through the feature extraction neural network and the classification neural network of the convolutional neural network based on the blueprint in the first input signal. The feature extraction neural network proceeds by sequentially stacking the convolutional layer and the pooling layer on the input signal. The convolutional layer includes a convolution operation, a convolution filter, and an activation function. The calculation of the convolution filter is adjusted according to the size of the matrix of the target input, but a 9X9 matrix is generally used. The activation function generally uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The pooling layer is a layer that reduces the size of the input matrix, and uses a method of extracting a representative value by grouping pixels in a specific area. In general, an average value or a maximum value is often used for the operation of the pooling layer, but the present invention is not limited thereto. This operation is performed using a square matrix, typically a 9X9 matrix. The convolutional layer and the pooling layer may alternately repeat until the corresponding input is sufficiently small while maintaining the difference. The classification neural network has a hidden layer and an output layer. In the convolutional neural network 510 for a method of controlling the design and construction process of an electrical facility, there are generally three or more hidden layers, and 100 nodes of each hidden layer are designated, but in some cases, more or less may be determined. The activation function of the hidden layer uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The number of output layer nodes of the convolutional neural network 510 may be a total of 10. The output layer activation function of the classification neural network uses the softmax function. The softmax function is a representative function of one-hot encoding, which makes the sum of all output nodes total 1, the output of the output node with the largest value as 1, and the output of the remaining output nodes as 0. . It may be possible to select only one of the 10 outputs through the softmax function. The ten outputs show the most similar blueprints in the database, and various information about them can be stored in the database.

According to an embodiment, the first output signal 502 that is an output of the convolutional neural network 510 may include information on the type, number, and location of electrical equipment corresponding thereto based on the classification of the convolutional neural network. The first output signal 502 may show a combination of the type, number and location information of the electrical installation, where the classification of the combination may generally be based on information stored on a database. The number of data stored in the database may increase or decrease according to the learning process of the convolutional neural network 510, and accordingly, the number of output nodes may be changed to 10 or more or less.

According to an embodiment, the learning signal 503 for learning of the convolutional neural network 510 may be generated from a final modified input signal including a designer's final decision on the design of an electrical facility. The designer may manually input information to be corrected based on the determination of the necessity of generating the learning signal, and through this, the database information may be strengthened or weakened according to the type of the learning signal 503.

The learning signal 503 according to an embodiment is created based on an error between a correct answer and an output value, and in some cases, an SGD using delta, a batch method, or a method following a backpropagation algorithm may be used. By this learning signal, the convolutional neural network 510 performs learning by modifying an existing weight, and in some cases, momentum can be used. The cost function can be used to calculate the error, and the cross entropy function can be used as the cost function.

According to an embodiment, the convolutional neural network 510 may learn to determine the most similar blueprint in the database based on the learning signal 503 and modify the type, number, and location information of the corresponding electrical equipment. . The pre-learned convolutional neural network 510 has three or more hidden layers, and each hidden layer may have 50 or more hidden nodes. The activation function of each hidden node may use a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The function of the output node can use a softmax function using one-hot encoding technique. For output, only one classification is selected according to the One-hot encoding technique, and commands can be executed from the selected classification.

According to an embodiment, the database may store information as big data, and may be continuously updated through a high-speed Internet connection network connected to a blockchain network.

The control device according to an embodiment may continuously provide feedback using an error of design error in a method of controlling the design and construction process of electrical equipment.

6 is an exemplary diagram of a configuration of an apparatus according to an embodiment.

The device 1201 according to an embodiment includes a processor 1202 and a memory 1203. The device 1201 according to an embodiment may be the above-described server or terminal. The processor may include at least one of the devices described above with reference to FIGS. 1 to 5, or may perform at least one of the methods described above with reference to FIGS. 1 to 5. The memory 1203 may store information related to the above-described method or a program in which the above-described method is implemented. The memory 1203 may be a volatile memory or a nonvolatile memory.

According to an embodiment, the processor 1202 may execute a program and control the device 1201. The code of a program executed by the processor 1202 may be stored in the memory 1203. The device 1201 is connected to an external device (for example, a personal computer or a network) through an input/output device (not shown), and may exchange data.

The embodiments described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices, methods, and components described in the embodiments include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, such as one or more general purpose computers or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of the program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to behave as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

As described above, although the embodiments have been described by the limited drawings, a person of ordinary skill in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order from the described method, and/or components such as a system, structure, device, circuit, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Therefore, other implementations, other embodiments and claims and equivalents fall within the scope of the following claims.

Claims (5)

In the method of controlling the design and construction process of electrical equipment based on artificial intelligence,
Storing the blueprint of the target space scanned by the designer;
Generating a first input signal in which the color information for each pixel is encoded into a numerical value based on color information for each pixel of the blueprint-the color information includes RGB information, brightness, and saturation;
Inputting the first input signal to a pre-learned convolutional neural network in a blockchain network;
Obtaining a first output signal based on the input result;
Obtaining a recommended electrical installation and a recommended design based on the first output signal;
Arranging the recommended electrical installation in the stored schematic based on the recommended design;
Generating a correction input signal according to a value input by the designer to adjust the type and number of electrical installations based on a result of the arrangement in the blueprint;
Obtaining a modified electrical installation based on the modified input signal;
Placing the modified electrical installation in the blueprint based on the recommended design and the positional relationship of the modified electrical installation;
Generating a final modified input signal according to a final input of the designer based on the blueprint;
Determining a final location of the modified electrical installation and generating a learning signal based on the final modified input signal; And
Training the convolutional neural network based on the learning signal
Including,
The blockchain network is
Blocks including blueprints, a database including information on types, numbers, and locations of electrical equipment, and the pre-learned convolutional neural network;
Chains connecting each block in chronological order; And
Network storage devices that store each block and chain
It is a private blockchain network that includes,
The network storage devices
A first network storage device including a producer producing the electrical equipment;
A second network storage device including a designer using a method of controlling the design and construction process of the electrical equipment;
A third network storage device including a manager managing a control method of the design and construction process of the electrical equipment; And
Internet connection network connecting each network storage device
Including,
The database is
Blueprints of various spaces collected from big data; And
Electrical installations designed according to the location and number determined to correspond to the blueprints
Including,
The combination of the electrical equipment corresponding to the blueprints is at least two or more,
The electrical installations are
Comprising ranked combinations for the electrical installations in the database,
Include the combinations ranked in the first output signal,
Designating a first priority combination among the ranked combinations as the recommended electrical installation and the recommended design,
The positional relationship of the modified electrical installation
Preventing overlapping of roles determined through a determination of a control device performing a mutual comparison based on data in the database on increasing convenience and reducing efficiency obtained as the roles of each electrical facility are similar or identical and are located nearby;
A distance determined through determination of the control device based on data in the database about a linear distance of an electric facility and an expected movement line of a user, based on positions of the electric facility to which the role overlap prevention is applied; And
Connection determined by the control device based on data in the database on the connection complexity and function optimization of the electrical equipment connected through wires and wiring
Including,
The convolutional neural network is
Based on the color information included for each pixel in the first input signal, the blueprint is separated from the background to recognize only the blueprint,
Perform a convolution operation and a pooling operation on the first input signal using a convolutional layer and a pooling layer,
Using a classification neural network including a plurality of hidden layers and an output layer, a square matrix whose matrix size is reduced from that of the first input signal by the pooling operation is 1 Determine the similar blueprint most similar to the blueprint among the blueprints in the database by im-,
On the basis of the blueprints in the database, the type, number, and location information of electrical installations, obtain the type, number, and location information of the recommended electrical installations corresponding to the similar blueprints,
Based on the type, number, and location information of the recommended electrical equipment, a recommended design for locating the recommended electrical equipment in the blueprint is generated, and information on the recommended electrical equipment and the recommended design is transmitted to the first output signal. Including,
Pre-learned based on the type, number, and location information of the blueprints in the database and electrical equipment designed to correspond to the blueprints
Based on the final modification input of the designer, learning is continuously performed,
When the modified electrical equipment is placed in the blueprint and the final modified input signal is not input within 1 hour, learning is performed through a learning signal automatically generated based on the blueprint generated modified from the modified input signal,
Placing the modified electrical installation in the blueprint,
Using information contained in the modified input signal used to select the most similar design among designs included in the first output signal, newly generating location information suitable for the type and number of the modified electrical equipment; And
Arrange the modified electrical equipment in the blueprint based on the newly created position, and if there is a type and number of electrical installations not included in the first output signal, arrange in the blueprint based on the positional relationship of the modified electrical installations It includes the step of,
The blueprints in the database are
It is obtained including only information on the purpose and extent of use of the space,
Type, number, and location information of electrical equipment corresponding to the blueprints in the database
Ranked based on the maximum recommendation through the values entered through multiple electrical installation design experts,
The type, number, and location information of electrical equipment corresponding to the similar blueprint is
Among the values stored in the database, it is recommended based on a predetermined ranking through a value input through the experts,
Among the combinations of the above electric facilities, the combination of the type and number of electric facilities initially presented
It is designated according to a predetermined ranking through the values entered through the experts,
The ranking determined through the values entered through the above experts is
It is modified through the learning of the convolutional neural network,
The designer's correction input information and final correction input information
Induced to select the closest combination among combinations of difference orders included in the first output signal, or if not included in the combinations, correction values are automatically input based on a positional relationship,
There are a total of 10 output nodes of the output layer of the convolutional neural network, and 10 most similar designs in the database are output through the 10 output nodes,
The convolutional neural network is
Using the softmax function of the classification neural network, the sum of the 10 output nodes is made a total of 1, the output of the output node having the largest value among the output nodes is set to 1, and the output of the remaining output nodes is By setting it as 0, processing so that only one of the 10 outputs is selected
Control method for the design and construction process of electrical equipment.
The method of claim 1,
The electric equipment, the recommended electric equipment, and the modified electric equipment
Lighting equipment designed to install various types of lamps based on the area of the target space;
A heat transfer facility that allows the heating element to generate heat through electric power;
Electric power equipment for operating elevator and escalator facilities using electric motors;
A transmission and distribution facility for transmitting and distributing AC 220V electricity so that the user in the target space can use it; And
Power generation facility that provides electricity to the target space through individual power generation facilities
Including
Control method for the design and construction process of electrical equipment.
delete delete delete

Images