KR20240029604A - Optimal design system for heating and cooling system using big data and artificial intelligence and method therefor - Google Patents

Abstract

The present invention uses AI technology for energy usage and carbon emissions based on building information and facility information to output a combination of heating and cooling equipment that is subject to optimization. In addition, the present invention performs a deep learning algorithm using a neural network to determine sensor values of energy usage and carbon emissions, uses training data to learn the neural network, verifies the performance of the neural network with test data, and provides prediction results for sampling data. Notifies users so they can respond to hardware failures, data errors, and data changes.

Description

Optimal design system and method for cooling and heating system using big data and AI {OPTIMAL DESIGN SYSTEM FOR HEATING AND COOLING SYSTEM USING BIG DATA AND ARTIFICIAL INTELLIGENCE AND METHOD THEREFOR}

The present invention relates to an optimal design system and method for a cooling and heating system using big data and AI, and more specifically, to optimally design a cooling and heating system, improve the performance of analysis technology using big data and AI, and prevent system errors. It is about an optimal design system and method for cooling and heating systems using big data and AI that minimize and maximize system performance.

Conventional technologies related to the present invention include, for example, a building design and energy performance evaluation module, a life-cycle energy evaluation system for a building, and a processor for evaluating energy consumption and carbon dioxide emissions in the operation stage of a building. Patent Document 1 The building design and energy performance evaluation module allows users to easily select building components to design a building in a 3D environment and facilitates energy performance evaluation for each section of the designed building. In addition, Patent Document 2, the whole-life energy evaluation system and method of a building for saving energy by applying new and renewable energy, receives data from the user to calculate energy consumption and carbon dioxide emissions, and calculates each unit area in the actual quantity calculation table. Calculate energy consumption according to the volume output for each material, calculate energy consumption and carbon dioxide emissions when transporting materials, energy consumption and carbon dioxide emissions of construction machinery, and energy consumption and carbon dioxide emissions of pump cars when pouring concrete, and calculate the energy consumption and carbon dioxide emissions of building buildings according to user input. Zone the zone into an air-conditioned space or a non-air-conditioned space, and calculate the energy consumption and carbon dioxide emissions of air-conditioning and heating equipment, hot water supply load, and lighting equipment for each of the zoned air-conditioning space or non-air-conditioning space. In addition, Patent Document 3, the energy consumption and carbon dioxide emissions evaluation process at the operation stage of a building for the development of a program to evaluate energy consumption and carbon dioxide emissions over the entire life cycle of a building is the entire life cycle of a building: design stage, construction stage, operation/maintenance stage, and dismantlement/disposal. It can be applied to the environmental assessment program by establishing a process to calculate energy consumption and corresponding carbon dioxide emissions in the operation stage among the stages.

In the prior art, Patent Documents 1 to 3 have the problem of not solving the global warming problem because they do not apply analysis technology using big data and AI for energy performance evaluation and carbon emissions optimization.

Korean Patent Publication No. 10-2011-0129172 Building design and energy performance evaluation module Korean Patent Publication No. 10-2016-0056643 Life-cycle energy evaluation system and method for buildings to save energy by applying new and renewable energy Korea Patent Publication No. 10-2015-0032952 Energy consumption and carbon dioxide emissions evaluation process of the building operation stage for development of a building life cycle energy consumption and carbon dioxide emissions evaluation program

The purpose of the present invention is to provide a cooling and heating system optimal design system and method using big data and AI that outputs a combination of cooling and heating equipment to be optimized using AI technology for building information, facility information-based energy usage, and carbon emissions. do.

In addition, the present invention performs a deep learning algorithm using a neural network to determine sensor values of energy usage and carbon emissions, uses training data for neural network learning, and uses big data and AI to verify neural network performance with test data. Another purpose is to provide an optimal system design system and method.

In addition, the present invention provides a cooling and heating system optimal design system and method using big data and AI to respond to hardware failures, data errors, and data changes by notifying users of prediction results for sampling data. The purpose.

The optimal design system and method for a cooling and heating system using big data and AI of the present invention construct building energy big data including energy usage and carbon emissions corresponding to building information and cooling and heating equipment information by inputting virtual building information. an input unit (21); An analysis unit 22 that performs analysis logic using AI technology on optimization targets including the energy usage and carbon emissions to generate a combination of heating and cooling equipment that is the optimal facility system; and an output unit 23 that outputs a combination of the cooling and heating equipment including a turbo refrigerator, an absorption cold/heater, a gas boiler, a gas heat pump, a geothermal heat pump, and a pump, which is the optimal equipment system.

In addition, the input unit 21 inputs virtual building information, such as architectural information (use, total floor area, number of floors, building height), cooling and heating equipment information (turbo refrigerator, absorption type cold and hot water heater, gas boiler, gas heat pump, geothermal heat pump, pump). It is characterized by constructing building energy big data that includes energy usage (electricity, gas, district heating, total usage) and carbon emissions (freezers, boilers, air conditioners, total carbon emissions) corresponding to ).

In addition, the standard for organizing carbon emissions information used by the analysis unit 22 is: ① carbon emissions by heating and cooling equipment (refrigerator, boiler, air conditioner, etc.) (tCO2eq/kW), which means carbon emissions compared to the unit rated facility capacity = (carbon during operation) Emissions (tCO2eq) + Embedded carbon emissions (tCO2eq)) ÷ Rated facility capacity (kW), ② Carbon emissions during operation (tCO2eq) Carbon emissions generated during facility operation = Primary energy consumption during rated operation (MWh) x Power carbon Emission coefficient (0.125 tc/MWh) The sum of emissions = (emissions generated in the production process of goods directly controlled by the producer (tCO2eq) + amount of raw materials used in the production process of equipment (kg) x raw material carbon emissions per unit mass (tCO2eq/kg)) do.

In addition, the analysis unit 22 divides the building information or heating and cooling equipment information into a virtual building information group and an optimization target group, and uses linear discriminant analysis (LDA), logistic regression (LR), and support vector machine ( It is characterized by applying six machine learning algorithms, including SVM), decision tree (DT), k-nearest neighbor (KNN), and random forest (RF).

In addition, the control unit 5 inputs virtual building information and provides architectural information (use, total floor area, number of floors, building height), cooling and heating equipment information (turbo refrigerator, absorption type cold and hot water heater, gas boiler, gas heat pump, geothermal heat pump, pump). Building energy data input step (S201) to construct building energy big data including energy usage (electricity, gas, district heating, total usage) and carbon emissions (freezer, boiler, air conditioner, total carbon emissions) corresponding to; A data analysis step (S202) in which analysis logic using AI technology is performed on optimization targets including energy usage and carbon emissions to create a combination of heating and cooling equipment that is the optimal facility system; and a cooling and heating equipment combination output step (S203) for outputting a combination of cooling and heating equipment including a turbo refrigerator, an absorption cold and hot water heater, a gas boiler, a gas heat pump, a geothermal heat pump and a pump, which is the optimal equipment system.

The present invention can have the effect of optimally designing a cooling and heating system by outputting a combination of cooling and heating equipment to be optimized using AI technology for energy usage and carbon emissions based on building information and equipment information.

In addition, the present invention performs a deep learning algorithm using a neural network to determine sensor values of energy usage and carbon emissions, uses training data to learn the neural network, and verifies the performance of the neural network with test data, thereby analyzing big data and AI. It can have the effect of increasing the performance of the technology.

In addition, the present invention can have the effect of minimizing system errors and maximizing system performance by notifying users of prediction results for sampling data so that users can respond to hardware failures, data errors, and data changes.

Figure 1 is a block diagram showing the configuration of the optimal design system for a cooling and heating system using big data and AI of the present invention.
Figure 2 is a block diagram showing the detailed configuration of the optimal cooling and heating system design system in Figure 1.
Figure 3 is an example diagram showing the operation of a neural network in the analysis unit of Figure 1.
Figure 4 is a flowchart showing the operation of the cooling and heating system optimal design method using big data and AI of the present invention.
Figure 5 is an example diagram illustrating a configuration for verifying data errors to explain the present invention.
Figure 6 is an example diagram illustrating the hardware resources, operating system, operation of the core control unit, and system authentication configuration that grants authority to execute the control unit operation to explain the present invention.

Hereinafter, with reference to the drawings, the optimal design system and method for a cooling and heating system using big data and AI according to an embodiment of the present invention will be described in detail. Below, descriptions of previously known matters are omitted or simplified to clarify the gist of the present invention. The components included in the description of the present invention operate individually or in combination.

Figure 1 is a block diagram showing the configuration of the optimal design system for a cooling and heating system using big data and AI of the present invention. Referring to Figure 1, the terminal 6 includes an input unit 21, an analysis unit 22, and an output unit ( 23).

The input unit 21 inputs virtual building information and builds building energy big data including energy usage and carbon emissions corresponding to building information and heating and cooling equipment information.

The analysis unit 22 performs analysis logic using AI technology on optimization targets including energy usage and carbon emissions to create a combination of heating and cooling equipment that is the optimal facility system.

The output unit 23 outputs a combination of cooling and heating equipment including a turbo refrigerator, absorption type cold/hot water heater, gas boiler, gas heat pump, geothermal heat pump, and pump, which is the optimal facility system.

Figure 2 is a block diagram showing the detailed configuration of the optimal design system for the cooling and heating system in Figure 1. Referring to Figure 2, the terminal 6 includes an input unit 21, an analysis unit 22, and an output unit 23.

The input unit 21 inputs virtual building information and generates information corresponding to architectural information (use, total floor area, number of floors, building height) and cooling and heating equipment information (turbo freezer, absorption type cold and hot water heater, gas boiler, gas heat pump, geothermal heat pump, pump). Build building energy big data including energy usage (electricity, gas, district heating, total usage) and carbon emissions (freezers, boilers, air conditioners, total carbon emissions).

The analysis unit 22 performs analysis logic using AI technology on optimization targets including energy usage and carbon emissions to create a combination of heating and cooling equipment that is the optimal facility system.

The standard for organizing carbon emissions information used by the analysis department (22) is: ① Carbon emissions by heating and cooling equipment (refrigerator, boiler, air conditioner, etc.) (tCO2eq/kW), meaning carbon emissions compared to rated facility capacity in units = (Carbon emissions during operation (tCO2eq) ) + Embedded carbon emissions (tCO2eq)) ÷ Rated facility capacity (kW), ② Carbon emissions during operation (tCO2eq) Carbon emissions generated during facility operation = Primary energy consumption during rated operation (MWh) x Power carbon emission factor ( 0.125 tc/MWh) = (emissions generated in the production process of goods directly controlled by the producer (tCO2eq) + amount of raw materials used in the production process of equipment (kg) x raw material carbon emissions per unit mass (tCO2eq/kg)).

The output unit 23 outputs a combination of cooling and heating equipment including a turbo refrigerator, absorption type cold/hot water heater, gas boiler, gas heat pump, geothermal heat pump, and pump, which is the optimal facility system.

Figure 3 is an example diagram showing the operation of a neural network in the analysis unit of Figure 1.

Neural network learning selects a model through feature selection and algorithm selection (32) from the time series data (31) collected from the input unit (21), and repeats trial and error (35) through the learning (33) and performance verification (34) processes. ) and repeat model selection (36). After performance verification (34) is completed, the artificial intelligence model (37) is selected.

The control unit 5 performs a deep learning algorithm using a neural network to determine sensor values, uses training data to learn the neural network, and verifies the neural network performance with test data.

The analysis unit 22 divides the building information or heating and cooling equipment information into a virtual building information group and an optimization target group, and uses linear discriminant analysis (LDA), logistic regression (LR), support vector machine (SVM), and decision making for optimization comparison between groups. Six machine learning algorithms are applied, including tree (DT), k-nearest neighbor (KNN), and random forest (RF).

The analysis unit 22 uses optimization targets including building information including use, total floor area, number of floors, building height, energy usage, and carbon emissions as parameters, and linear discriminant analysis (LDA) uses a new input set for each class. The probability of belonging to is estimated and predicted. The class that obtains the highest probability is the output class and prediction is performed. Logistic regression (LR) is the probability of two possible classification problems.

Support vector machines (SVMs) find hyperplane decision boundaries that best split examples into two classes. The segmentation is made smooth using margins, which may cause some points to be misclassified. Decision trees (DTs) involve growing a tree to classify examples in a training data set. A tree can be thought of as dividing the training data set. Here, the example progresses along the tree's decision points until it reaches a leaf of the tree and is assigned a class label. k-Nearest Neighbor (KNN) stores all available data and classifies new data points based on similarity. That is, when new data appears, it can be easily classified into well-sweet categories using k-nearest neighbors (KNN). Lastly, Random Forest (RF) consists of many decision trees for the final output, and is considered a very accurate and powerful method due to the large number of decision trees participating in the process.

Figure 4 is a flow chart showing the operation of the cooling and heating system optimal design method using big data and AI of the present invention. Referring to Figure 4, the control unit 5 performs the building energy data input step (S201) and the data analysis step (S202). , perform the cooling and heating equipment combination output step (S203).

The building energy data input step (S201) inputs virtual building information to include architectural information (use, total floor area, number of floors, building height), cooling and heating equipment information (turbo freezer, absorption type cold and hot water heater, gas boiler, gas heat pump, geothermal heat pump, pump). Build building energy big data that includes energy usage (electricity, gas, district heating, total usage) and carbon emissions (freezers, boilers, air conditioners, total carbon emissions) corresponding to ).

The data analysis step (S202) performs analysis logic using AI technology on optimization targets including energy usage and carbon emissions to create a combination of heating and cooling equipment that is the optimal facility system.

The cooling and heating equipment combination output step (S203) outputs the cooling and heating equipment combination including the turbo refrigerator, absorption type cold and hot water heater, gas boiler, gas heat pump, geothermal heat pump, and pump, which is the optimal facility system.

Figure 5 is an example diagram illustrating a configuration for verifying data errors to explain the present invention.

Referring to FIG. 5, the control unit 5 stores sampling data, calculates a probability distribution by accumulating the number of occurrences for each size of the sampling data over a certain period of time, calculates a probability distribution for another period of time, and calculates the two probabilities. By calculating the distribution difference, area difference, and difference distance accumulation (S101), sampling circuit abnormalities, data errors, and data changes can be predicted and responded to (S102). The control unit 5 notifies the user of the prediction result so that the user can respond, or the control unit 5 can respond to hardware failure, data error, or data change.

Sampling data includes architectural information including use, total floor area, number of floors, and building height; Equipment information including turbo chillers, absorption chillers and hot water heaters, gas boilers, gas heat pumps, geothermal heat pumps and pumps; Energy usage, including electricity, gas, district heating and total consumption; Carbon emissions, including refrigerators, boilers, air conditioners, and total carbon emissions;

FIG. 6 is an exemplary diagram illustrating hardware resources, operating system, operation of the core control unit, and system authentication configuration for granting authority to execute control unit operations for illustrating the present invention. Referring to FIG. 6, the present invention is a processor (1). ), memory (2), input/output device (3), operating system (4), and control unit (5).

The processor (1) is a CPU (Central Processing Unit), GPU (Graphic Processing Unit), FPGA (Field Programmable Gate Array), and NPU (Neural Processing Unit), and the operating system (4) and control unit (5) mounted on the memory (2) ) executes the execution code.

Memory (2) includes permanent mass storage devices such as random access memory (RAM), read only memory (ROM), disk drives, solid state drives (SSD), flash memory, etc. can do.

The input/output device 3 is an input device, such as a camera, keyboard, microphone, mouse, etc. including an audio sensor and/or image sensor, and an output device such as a display, speaker, haptic feedback device, etc. May include devices.

The operating system 4 may include Windows, Linux, IOS, virtual machines, web browsers, and interpreters, and supports tasks, threads, timer execution, scheduling, resource management, graphics, font processing, communication, etc.

The control unit 5 determines the state based on sensor, key, touch, and mouse input of the input/output device 3 with the support of the operating system 4 and performs operations according to the determined state. The control unit 5 performs job scheduling by timers and threads using parallel execution routines.

The control unit 5 determines the state using the sensor value of the input/output device 3 and performs an algorithm according to the determined state.

Referring to Figure 6, the system authentication configuration includes a terminal 6 including a control unit 5, and an authentication server 7.

The terminal 6 duplicates the data channel, receives the key value and biometric information of the terminal 6, and requests user authentication through the first data channel to the authentication server 7, and the terminal 6 receives the generated kit value. It is displayed on the display and transmitted to the authentication server (7).

The terminal 6 inputs the kit value displayed on the display of the terminal 6 and transmits it along with the user information to the authentication server 7 through the second data channel. The terminal 6 requests the authentication server 7 to authenticate the system mounted on the terminal 6 using the kit value and user information. The kit value of the terminal 6 can be generated from computer-specific information, such as the CPU manufacturing number and the Ethernet chip number. The terminal 6 can obtain user information through face recognition using a camera, voice recognition using a microphone, and handwriting recognition using a display, and use it for authentication.

The authentication server 7 receives the kit value from the terminal 6, receives the kit value and user information from the terminal 6 through a duplicated data channel, compares the kit value and the user information of the terminal 6, and By matching, authentication for use of the system of the terminal 6 is processed. The authentication server 7 transmits the authentication result to the terminal 6 to authorize the user's use of the system. Due to the dual data channels of the terminal 6, kit value loss can be minimized.

The authentication server 7 performs history analysis of user information and compares and determines consistency and changes in user information over time. In history analysis, if user information shows consistency, the user's use is permitted; if it shows changes, the user's use is not permitted. By allowing users to use the system when user information shows consistency, security is strengthened to prevent users with altered user information from accessing the system.

The terminal 6, which is a means of authenticating the use of the system, does not connect directly to the system, but forms a bypass route through the authentication server 7, so that the network that makes up the Internet network is composed of an internal network and an external network, and the IP address setting process There is an advantage that the authentication process using the terminal 6 is performed smoothly in this cumbersome time. At this time, the system is mounted on the terminal 6, the terminal 6 becomes an authentication terminal means, and the authentication server 7 becomes an authentication server means.

The cloud (12) is a modularization of the container (7) with the support of the operating system (4) that manages the processor (1), memory (2), input/output device (3), and communication unit (6), and the web (8) and DB ( 9), provides the services of the protocol 10 and library 11, and the control unit 5 executes a cloud application using the services of the container 7. A standard software package, called a container (7), bundles an application's code with associated configuration files, libraries (11), and dependencies needed to run the app.

The cloud 12 integrates control of multiple terminals 6, stores sensor values received from the terminal 6, monitors them over time, processes operation errors of the terminal 6, and sends error messages to other terminals. Notifies the terminal 6, and performs switching control on the terminal 6 that is the control target.

The present invention is not limited to the specific preferred embodiments described above, and various modifications can be made by anyone skilled in the art without departing from the gist of the invention as claimed in the claims. Of course, such changes are within the scope of the claims.

1: processor
2: memory
3: Input/output device
4: Operating system
5: Control unit
6: Terminal
7: Authentication server
8: web
9: DB
11: Library
12: Cloud
14: Container
16: Department of Communications
21: input unit
22: analysis department
23: output unit
31: Time series data
32: Feature point selection/algorithm selection
33: Learning
34: Performance verification
35: Repeated trial and error
36: selection
37: AI model

Claims (5)

An input unit 21 that inputs virtual building information to construct building energy big data including energy usage and carbon emissions corresponding to building information and heating and cooling equipment information;
An analysis unit 22 that performs analysis logic using AI technology on optimization targets including the energy usage and carbon emissions to generate a combination of heating and cooling equipment that is the optimal facility system; and
Big data and Optimal design system and method for cooling and heating systems using AI.
According to claim 1,
The input unit 21 is,
By entering virtual building information, energy usage (electricity, An optimal design system for cooling and heating systems using big data and AI, which is characterized by building building energy big data including gas, district heating, total consumption) and carbon emissions (freezers, boilers, air conditioners, total carbon emissions), and That way.
According to claim 1,
The standard for organizing carbon emissions information used by the analysis unit 22 is: ① Carbon emissions by heating and cooling equipment (refrigerator, boiler, air conditioner, etc.) (tCO2eq/kW), meaning carbon emissions compared to rated facility capacity in units = (carbon emissions during operation ( tCO2eq) + embodied carbon emissions (tCO2eq)) ÷ rated facility capacity (kW), ② carbon emissions during operation (tCO2eq) carbon emissions generated during facility operation = primary energy consumption during rated operation (MWh) x power carbon emission factor (0.125 tc/MWh) Characterized by the sum = (emissions generated during the production process of goods directly controlled by the producer (tCO2eq) + amount of raw materials used in the production process of equipment (kg) x raw material carbon emissions per unit mass (tCO2eq/kg)) Optimal design system and method for cooling and heating systems using big data and AI.
According to claim 1,
The analysis unit 22,
Building information or air conditioning equipment information is divided into a virtual building information group and an optimization target group, and optimization comparison between groups is performed using linear discriminant analysis (LDA), logistic regression (LR), support vector machine (SVM), decision tree (DT), k -A cooling and heating system optimal design system and method using big data and AI, characterized by applying six machine learning algorithms such as nearest neighbor (KNN) and random forest (RF).
According to claim 1,
The control unit 5,
By entering virtual building information, energy usage (electricity, Building energy data input step (S201) to construct building energy big data including gas, district heating, total consumption) and carbon emissions (refrigerator, boiler, air conditioner, total carbon emissions);
A data analysis step (S202) in which analysis logic using AI technology is performed on optimization targets including energy usage and carbon emissions to create a combination of heating and cooling equipment that is the optimal facility system; and
A cooling and heating equipment combination output step (S203) for outputting a combination of cooling and heating equipment including a turbo refrigerator, an absorption cold and hot water heater, a gas boiler, a gas heat pump, a geothermal heat pump and a pump, which is the optimal equipment system. Optimal design system and method for cooling and heating systems using data and AI.