KR20240056405A - Fault diagnosis method of hvac system and device using the same - Google Patents

Abstract

The present invention is a method for diagnosing a fault in an HVAC system, comprising the steps of acquiring equipment settings of the HVAC system and sensor data of the equipment, using a steady-state prediction model that inputs at least one of the equipment settings or the sensor data. Thus, outputting a steady-state value for the parameter of the equipment, comparing the steady-state value for the parameter and a measured value for the parameter, and according to the result of comparing the steady-state value and the measured value, It is configured to include the step of determining whether the equipment or the sensor is malfunctioning.

Description

HVAC system fault diagnosis method and device using the same {FAULT DIAGNOSIS METHOD OF HVAC SYSTEM AND DEVICE USING THE SAME}

The present invention relates to a method for diagnosing a fault in an HVAC (Heating, Ventilating, and Air Conditioning) system and a device using the same.

Energy demand management for large-scale buildings such as buildings or small-scale buildings such as ordinary homes is emerging as a very important issue. Various researches are actively being conducted to reduce building energy consumption and manage buildings intelligently. Since the HVAC system accounts for a significant portion of the energy used by the building, the equipment included in the HVAC system can be said to be an important factor in improving the efficiency of the entire building.

As part of various studies, the Home Energy Management System (HEMS) and the Building Energy Management System (HEMS), which can manage or control various facilities such as electricity, air conditioning, crime prevention, and lighting, by applying information and communication technology to buildings. Building Energy Management System (BEMS) has been proposed, and the energy management system can efficiently control heating and cooling equipment, lighting equipment, and power equipment, thereby reducing unnecessary energy waste and operating building resources efficiently.

Meanwhile, although many control and energy management technologies for general air conditioning (Heating, Ventilation, and Air Conditioning, HVAC) systems have been developed, development of technology to diagnose and manage failures in air conditioning equipment systems is required. This is the situation. In addition, for efficient operation and management of air conditioning equipment systems, there is also a need for the development of technology for diagnosing the failure status of equipment such as water coolers and heaters and cooling towers using artificial intelligence models.

The technology behind the invention has been written to facilitate easier understanding of the invention. It should not be understood as an admission that matters described in the technology underlying the invention exist as prior art.

The monitoring system currently being used to optimally operate a building's air conditioning system does not have the ability to properly detect failures when defects such as malfunctions or performance deterioration of operating equipment occur, and as a result, prompt processing of failures and optimal operation are required. There is a problem that it is impossible to operate.

Accordingly, there is a need for a fault diagnosis method that can quickly detect a fault in a building's air conditioning system and operate it optimally.

As a result, the inventors of the present invention constructed a method for diagnosing failures in each equipment and/or sensor included in the building's air conditioning system by using a plurality of artificial intelligence models and a decision tree.

The problems of the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

In order to solve the problems described above, a method for diagnosing a fault in an HVAC system according to an embodiment of the present invention is provided. The method includes acquiring equipment setting values of the HVAC system and sensor data of the equipment, using a steady-state prediction model that inputs at least one of the equipment setting values or the sensor data to determine parameters of the equipment. outputting a steady-state value for the parameter, comparing the normal-state value for the parameter with a measured value for the parameter, and determining whether the equipment or the sensor is in trouble according to a result of comparing the normal-state value and the measured value. It is configured to include a step of determining whether or not.

According to a feature of the present invention, the sensor data may include at least one of inlet and outlet water temperature data measured by the sensor installed for each facility collected over a certain period of time or flow rate data for each facility.

According to another feature of the present invention, when the HVAC system performs a heating cycle, the equipment may include at least one of a hot and cold water dispenser or an air conditioner.

According to another feature of the present invention, the steady-state prediction model includes a first heating steady-state prediction model, and the first heating steady-state prediction model includes time, external temperature, set temperature of the cold and hot water machine, and return water of the cold and hot water machine. It is an artificial intelligence model that takes the temperature as an input and the temperature of the water supplied to the cold and hot water machine as an output, and may further include the step of determining whether the temperature of the water supplied to the cold and hot water machine is normal using the first heating normal state prediction model. there is.

According to another feature of the present invention, the steady-state prediction model includes a second heating steady-state prediction model for a specific zone, and the second heating steady-state prediction model includes the header supply water temperature of the cold and hot water machine, the It is an artificial intelligence model that inputs the set temperature of the cold and hot water machine, the indoor temperature of the specific area, the set temperature of the specific area, and the operation signal of the specific area, and outputs the opening rate of the valve corresponding to the specific area, When it is determined that the temperature of water supplied to the cold/hot water supply is not normal, determining whether the opening rate of the valve is normal using the second heating steady state prediction model, and determining whether the opening rate of the valve is normal, Alternatively, the step of determining whether the cold/hot water sensor is broken may be further included.

According to another feature of the present invention, the steady-state prediction model includes a third heating steady-state prediction model, and the third heating steady-state prediction model includes the set temperature of the cold and hot water machine, the return water temperature of the cold and hot water machine, and the cold and hot water machine. Using the supplied water temperature as an input and the fuel consumption of the cold/hot water machine as an output, determining whether the fuel consumption of the cold/hot water machine is normal using the third heating steady state prediction model, and the fuel consumption If it is determined that it is not normal, a step of determining that the cold and hot water machine is broken may be further included.

According to another feature of the present invention, when the HVAC system performs a cooling cycle, the equipment may include at least one of a water cooler, an air conditioner, or a cooling tower.

According to another feature of the present invention, the steady state prediction model includes a first cooling steady state prediction model, and the first cooling steady state prediction model includes time, external temperature, set temperature of the cold and hot water machine, and return water of the cold and hot water machine. It is an artificial intelligence model that takes the water temperature and the return water temperature of the cooling tower as inputs and the temperature of water supplied to the cold and hot water machine as an output, and uses the first cooling normal state prediction model to determine whether the temperature of water supplied to the cold and hot water machine is normal. A judgment step may be further included.

According to another feature of the present invention, the steady-state prediction model includes a second cooling steady-state prediction model, and the second cooling steady-state prediction model includes the time, the external temperature, the relative humidity, and at least one of the cold and hot water dispensers. It is an artificial intelligence model that takes the operating signal, the return water temperature of the cooling tower as input, and the supply water temperature of the cooling tower as output, and when the temperature of the water supplied to the cold and hot water machine is determined to be normal, the second cooling normal state is predicted. The method may further include determining whether the temperature of the supply water to the cooling tower is normal using a model and, if the temperature of the supply water to the cooling tower is determined to be abnormal, determining that the cooling tower sensor is out of order. there is.

When it is determined that the temperature of the water supplied to the cold and hot water machine is abnormal, determining whether the temperature of the water supplied to the cooling tower is normal using the second cooling normal state prediction model, and determining whether the temperature of the water supplied to the cooling tower is abnormal. If it is determined that the cooling tower is out of order, the step of determining that the cooling tower is out of order may be further included.

According to another feature of the present invention, the steady-state prediction model includes a third cooling steady-state prediction model for a specific zone, and the third cooling steady-state prediction model includes the header supply water temperature of the cold and hot water machine, It is an artificial intelligence model that inputs the set temperature of the water heater, the indoor temperature of the specific area, the set temperature of the specific area, and the operation signal of the specific area, and outputs the opening rate of the valve corresponding to the specific area. , when it is determined that the temperature of the cooling tower supply water is normal, determining whether the opening rate of the valve is normal using the third cooling steady state prediction model, and determining whether the opening rate of the valve is normal and the cold and hot water supply unit Alternatively, the step of determining whether the cold/hot water sensor is broken may be further included.

The steady state prediction model includes a fourth cooling steady state prediction model, and the fourth cooling steady state prediction model includes the set temperature of the cold and hot water machine, the return water temperature of the cold and hot water machine, the supply water temperature of the cold and hot water machine, and the cooling tower. Using the supplied water temperature as an input and the fuel consumption of the cold/hot water machine as an output, determining whether the fuel consumption of the cold/hot water machine is normal using the fourth cooling normal state prediction model, and the fuel consumption If it is determined that it is not normal, a step of determining that the cold and hot water machine is broken may be further included.

In order to solve the problems described above, a fault diagnosis device for an HVAC system according to another embodiment of the present invention is provided. The device may include a transceiver that receives facility settings of an HVAC system and sensor data of the facility, a memory, and a processor operably connected to the transceiver and the memory. The processor outputs steady-state values for the parameters of the equipment using a steady-state prediction model that inputs at least one of the equipment setting values or the sensor data, and outputs the steady-state values for the parameters and the steady-state values for the parameters. It may be configured to compare measured values for parameters and determine whether the equipment or the sensor is in trouble according to a result of comparing the normal state value and the measured value.

Specific details of other embodiments are included in the description and drawings.

The present invention can predict the steady-state values of various parameters of each facility by providing an artificial intelligence model for each facility of the building's HVAC system.

Accordingly, the present invention can perform fault diagnosis for each facility of a building's HVAC system.

Additionally, the present invention can more accurately diagnose failures by using a failure diagnosis method that combines an artificial intelligence model and a decision tree.

The effects according to the present invention are not limited to the details exemplified above, and further various effects are included within the present invention.

1 is a block diagram showing a fault diagnosis system for an HVAC system according to an embodiment of the present invention.
Figure 2 is a block diagram showing the configuration of a fault diagnosis device for an HVAC system according to an embodiment of the present invention.
Figure 3 is a block diagram showing the configuration of a fault diagnosis server for an HVAC system according to an embodiment of the present invention.
Figure 4 is a schematic flowchart of a method for diagnosing a fault in an HVAC system according to an embodiment of the present invention.
Figure 5 is a schematic diagram illustrating a decision tree in a heating cycle according to an embodiment of the present invention.
Figures 6 to 8 are exemplary diagrams showing a heating steady-state prediction model according to an embodiment of the present invention.
Figure 9 is a schematic diagram illustrating a decision tree in a cooling cycle according to an embodiment of the present invention.
10 to 13 are exemplary diagrams showing a cooling steady-state prediction model according to an embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms. The present embodiments only serve to ensure that the disclosure of the present invention is complete and are within the scope of common knowledge in the technical field to which the present invention pertains. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. In connection with the description of the drawings, similar reference numbers may be used for similar components.

In this document, expressions such as “have,” “may have,” “includes,” or “may include” refer to the existence of the corresponding feature (e.g., a numerical value, function, operation, or component such as a part). , and does not rule out the existence of additional features.

In this document, expressions such as “A or B,” “at least one of A or/and B,” or “one or more of A or/and B” may include all possible combinations of the items listed together. . For example, “A or B,” “at least one of A and B,” or “at least one of A or B” (1) includes at least one A, (2) includes at least one B, Or (3) it may refer to all cases including both at least one A and at least one B.

Expressions such as “first,” “second,” “first,” or “second,” used in this document can modify various components regardless of order and/or importance, and can refer to one component. It is only used to distinguish from other components and does not limit the components. For example, a first user device and a second user device may represent different user devices regardless of order or importance. For example, the first component may be renamed as the second component without departing from the scope of rights described in this document, and similarly, the second component may also be renamed as the first component.

A component (e.g., a first component) is “(operatively or communicatively) coupled with/to” another component (e.g., a second component). When referred to as being “connected to,” it should be understood that any component may be directly connected to the other component or may be connected through another component (e.g., a third component). On the other hand, when a component (e.g., a first component) is said to be “directly connected” or “directly connected” to another component (e.g., a second component), It may be understood that no other component (e.g., a third component) exists between other components.

As used in this document, the expression “configured to” depends on the situation, for example, “suitable for,” “having the capacity to.” ," can be used interchangeably with "designed to," "adapted to," "made to," or "capable of." The term “configured (or set to)” may not necessarily mean “specifically designed to” in hardware. Instead, in some contexts, the expression “a device configured to” may mean that the device is “capable of” working with other devices or components. For example, the phrase "processor configured (or set) to perform A, B, and C" refers to a processor dedicated to performing the operations (e.g., an embedded processor), or by executing one or more software programs stored on a memory device. , may refer to a general-purpose processor (e.g., CPU or application processor) capable of performing the corresponding operations.

Terms used in this document are merely used to describe specific embodiments and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions, unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by a person of ordinary skill in the technical field described in this document. Among the terms used in this document, terms defined in general dictionaries may be interpreted to have the same or similar meaning as the meaning they have in the context of related technology, and unless clearly defined in this document, have an ideal or excessively formal meaning. It is not interpreted as In some cases, even terms defined in this document cannot be interpreted to exclude embodiments of this document.

Each feature of the various embodiments of the present invention can be partially or fully combined or combined with each other, and as can be fully understood by those skilled in the art, various technical interconnections and operations are possible, and each embodiment may be implemented independently of each other. It may be possible to conduct them together due to a related relationship.

For clarity of interpretation of this specification, terms used in this specification will be defined below.

As used herein, the term Heating Ventilation and Air Conditioning (HVAC) system may also be referred to as an air conditioning system. The air conditioning system may be equipped with air handling units (AHU) for heating, ventilation, and air conditioning. The air conditioning equipment system is operated by automatic control equipment and may be equipped with heating and cooling equipment, heating coils, cooling coils, humidifiers, air filters, etc. When the automatic control equipment of the air conditioner is operated between the air conditioner and the indoor space, a blower and a fan are further provided in the duct, which is an air ventilation passage that circulates clean air or introduces outside air. The HVAC system maintains clean indoor air by maintaining the four major elements of air conditioning: temperature, humidity, airflow, and cleanliness.

The term 'prediction model' used in this specification may be a model learned to predict equipment parameters based on HVAC system equipment setting values and equipment sensor data input. Specifically, in this specification, the prediction model is learned to predict the steady-state values of parameters such as the supply water temperature of the water heater and/or cooling tower, the fuel consumption of the water cooler and the heater, and the opening rate of the valve corresponding to the specific area subject to cooling and heating. It could be a model. Here, the valve refers to a valve connected to a specific zone in an air handling unit (AHU).

In various embodiments, the prediction model may be a regression model that combines a Convolutional Neural Network (CNN) and a Long Short-Term Model (LSTM). According to an embodiment of the present disclosure, the prediction model may be a model using 1D CNN-LSTM. 1D CNN can effectively and efficiently extract local characteristics of time series input data, and LSTM enables prediction of various parameters of facilities included in the HVAC system based on time series data. According to an embodiment of the present disclosure, a prediction model may be provided for each facility, and when there are multiple air conditioners, cooling towers, or specific areas, the fault diagnosis device may be composed of a plurality of prediction models.

Hereinafter, the present invention will be described in detail by explaining preferred embodiments of the present invention with reference to the accompanying drawings.

1 is a block diagram showing a fault diagnosis system for an HVAC system according to an embodiment of the present invention.

Referring to FIG. 1, the failure diagnosis system of the HVAC system 1000 may be a system that can diagnose failures of various equipment(s) included in the HVAC system and/or sensor(s) provided in the equipment. The fault diagnosis system 1000 of the HVAC system may include an HVAC system 1000, a fault diagnosis device 100, and/or a fault diagnosis server 200.

The HVAC system 1000 may include a hot and cold water dispenser, a boiler, an air conditioner (or air conditioner), a cooling tower, and/or a specific area (or room).

The chiller may be an absorption type chiller or hotter. An absorption type cold/hot water machine is a facility that uses an absorbent. It is a facility that can cool and heat by using LNG, waste heat, etc. as a driving heat source instead of electric energy, using the principle that refrigerant vapor is absorbed by the vapor pressure difference of the refrigerant. According to an embodiment of the present disclosure, the HVAC system 1000 may include a plurality of cold and hot water dispensers.

An air handling unit (AHU) is a device for controlling indoor air. It is a device that intakes air, adjusts the intake air, and then expels it. The air conditioner can cool the air by exchanging heat with the cold water generated from the absorption type cold water heater, or it can heat the air by receiving hot water stored in a heat storage tank.

A cooling tower is a heat exchange device that cools the cooling water used in the condenser of the water heater by directly connecting it to outdoor air in order to reuse the cooling water. According to an embodiment of the present disclosure, HVAC system 1000 may include a plurality of cooling towers.

A specific area (or indoor zone) refers to a space within a building that is subject to cooling and heating. According to an embodiment of the present disclosure, the HVAC system 1000 may include a plurality of specific zones.

The fault diagnosis device 100 may be a device that receives facility setting values and/or sensor data from the HVAC system 1000 and determines whether a facility or sensor included in the HVAC system 1000 is broken. The fault diagnosis device 100 may include a smartphone, tablet PC (personal computer), laptop, and PC.

The facility set value may be the set temperature of the hot and cold water dispenser or the set temperature of a specific area. Here, the 'set temperature of the cold and hot water machine' means the set temperature of the water returned or supplied to the cold and hot water machine. For example, the set temperature of the returned water may be 12 degrees, and the set temperature of the supplied water may be 7 degrees. ‘Set temperature of a specific area’ refers to the set temperature of the room corresponding to a specific area. For example, the indoor temperature in specific area A may be set to 25 degrees, and the indoor temperature in specific area B may be set to 22 degrees, and the HVAC system 1000 may be driven so that the indoor temperature in each specific area is the set temperature. .

The fault diagnosis device 100 learns by using the data collected for each facility (e.g., time, external temperature, supply water temperature of the cold and hot water machine, return water temperature of the cold and hot water machine, and return water temperature of the cooling tower) as input to the steady-state prediction model. can do. Here, the return water temperature may mean the outlet water temperature from the corresponding facility. Data collected for each facility may be data acquired by sensors provided in each facility.

In various embodiments, the fault diagnosis device 100 may be configured to install or execute a web, mobile application, and/or program provided by the fault diagnosis server 200. The fault diagnosis server 200 may include a general-purpose computer, laptop, and/or data server capable of analysis.

So far, a fault diagnosis system for the HVAC system 1000 according to an embodiment of the present invention has been described. According to the present invention, the fault diagnosis system of the HVAC system 1000 operates a fault diagnosis method combining a steady-state prediction model and a decision tree differently during the heating cycle and the cooling cycle to diagnose the fault more accurately, thereby more accurately diagnosing the HVAC system. Faults in equipment included in (1000) can be diagnosed.

Hereinafter, the fault diagnosis device 100 will be described with reference to FIG. 2 .

Figure 2 is a block diagram showing the configuration of a fault diagnosis device for an HVAC system according to an embodiment of the present invention.

Referring to FIG. 2 , the fault diagnosis device 100 may include a memory interface 110, processor(s) 120, and peripheral interface 130. Various components within the fault diagnosis device 100 may be connected by one or more communication buses or signal lines.

The memory interface 110 is connected to the memory 150 and can transmit various data to the processor(s) 120. Here, the memory 150 is a flash memory type, hard disk type, multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, and cloud. , It may include at least one type of storage medium among the blockchain database.

In various embodiments, memory 150 may store a web/app application or program for diagnosing a malfunction of an HVAC system. In addition, the memory 150 stores inlet and outlet water temperature data measured by the sensor installed for each facility collected over a certain period of time or flow rate data for each facility (i.e., sensor data) and/or facility setting values and various parameter(s). Steady state prediction values, etc. can be stored.

In various embodiments, memory 150 includes operating system 151, communications module 152, graphical user interface module (GUI) 153, sensor processing module 154, telephony module 155, and application module 156. ) can be stored. Specifically, the operating system 151 may include instructions for processing basic system services and instructions for performing hardware tasks. The communication module 152 may communicate with at least one of one or more other devices, computers, and servers. The graphical user interface module (GUI) 153 can process a graphical user interface. Sensor processing module 154 may process sensor-related functions (e.g., processing voice input received through one or more microphones 192). The phone module 155 can process phone-related functions. Application module 156 may perform various functions of a user application, such as electronic messaging, web browsing, media processing, navigation, imaging, and other processing functions. In addition, the fault diagnosis device 100 may store one or more software applications 156-1 and 156-2 (eg, a fault diagnosis application for an HVAC system) associated with one type of service in the memory 150.

In various embodiments, memory 150 may store a digital assistant client module 157 (hereinafter referred to as DA client module), thereby storing various user data 158 and instructions for performing client-side functions of the digital assistant. (e.g. sensor data of each facility, setting value(s) of each facility, parameter(s) of each facility) can be saved.

Meanwhile, the DA client module 157 provides user voice input, text input, touch input, and/or gesture input through various user interfaces (e.g., I/O subsystem 140) provided in the fault diagnosis device 100. can be obtained.

Additionally, the DA client module 157 can output data in audiovisual and tactile forms. For example, the DA client module 157 may output data consisting of a combination of at least two or more of voice, sound, notification, text message, menu, graphics, video, animation, and vibration. In addition, the DA client module 157 can communicate with a digital assistant server (not shown) using the communication subsystem 180.

In various embodiments, the DA client module 157 may collect additional information about the surrounding environment of the fault diagnosis device 100 from various sensors, subsystems, and peripheral devices to construct a context associated with user input. there is. For example, the DA client module 157 may infer the user's intention by providing context information along with user input to the digital assistant server. Here, context information that may accompany the user input may include sensor information, for example, lighting, ambient noise, ambient temperature, images of the surrounding environment, video, etc. As another example, the context information may include the physical state of the fault diagnosis device 100 (e.g., device orientation, device location, device temperature, power level, speed, acceleration, motion pattern, cellular signal strength, etc.). As another example, the situation information may include information related to the software status of the fault diagnosis device 100 (e.g., processes running on the fault diagnosis device 100, installed programs, past and present network activity, background services, error logs, resource usage, etc.).

In various embodiments, memory 150 may include added or deleted instructions. Furthermore, the fault diagnosis device 100 may also include additional components other than those shown in FIG. 2 or may exclude some components.

The processor(s) 120 can control the overall operation of the fault diagnosis device 100 and run an application or program stored in the memory 150 to display steady state prediction model results and a decision tree and display the results of the steady-state prediction model and the decision tree for each facility or device. Various commands can be executed to implement a user interface that can display whether a sensor corresponding to a facility is broken or check the prediction results provided through the steady-state prediction model (i.e., the output of the steady-state prediction model). .

The processor(s) 120 may correspond to a computing device such as a Central Processing Unit (CPU) or an Application Processor (AP). In addition, the processor(s) 120 is implemented in the form of an integrated chip (IC) such as a System on Chip (SoC) that integrates various computing devices that perform machine learning, such as a Neural Processing Unit (NPU). It can be.

In various embodiments, the processor(s) 120 displays a target region in the medical image through a user interface screen or divides the target region through a medical image segmentation application or program provided by the medical image segmentation device 300. You can make a request and display the results accordingly.

In various embodiments, the processor(s) 120 may output steady-state values for parameters of the facility using a steady-state prediction model that inputs at least one of the acquired facility setting values and sensor data of the facility. there is. Processor(s) 120 may compare the steady-state value for the parameter and the measured value for the parameter. The processor(s) 120 may determine whether the equipment or the sensor is in trouble according to a comparison result between the normal state value and the measured value.

The peripheral interface 130 is connected to various sensors, subsystems, and peripheral devices and can provide data so that the fault diagnosis device 100 can perform various functions. Here, what function the fault diagnosis device 100 performs may be understood as being performed by the processor(s) 120.

The peripheral interface 130 may receive data from the motion sensor 160, the light sensor (light sensor) 161, and the proximity sensor 162, and through this, the fault diagnosis device 100 detects orientation, light, and It can perform proximity detection functions, etc. For another example, the peripheral interface 130 may receive data from other sensors 163 (positioning system-GPS receiver, temperature sensor, biometric sensor), and through this, the fault diagnosis device 100 may receive data from other sensors 163. Functions related to fields 163 can be performed.

In various embodiments, the fault diagnosis device 100 may include a camera subsystem 170 connected to the peripheral interface 130 and an optical sensor 171 connected thereto, through which the fault diagnosis device 100 may take a photo. and video clip recording.

In various embodiments, the fault diagnosis device 100 may include a communication subsystem 180 connected to the peripheral interface 130. The communication subsystem 180 consists of one or more wired/wireless networks and may include various communication ports, radio frequency transceivers, and optical transceivers.

In various embodiments, the fault diagnosis device 100 includes an audio subsystem 190 connected to a peripheral interface 130, which includes one or more speakers 191 and one or more microphones 192. By including, the fault diagnosis device 100 can perform voice-activated functions, such as voice recognition, voice duplication, digital recording, and phone functions.

In various embodiments, the fault diagnosis device 100 may include an I/O subsystem 140 connected to a peripheral interface 130. For example, the I/O subsystem 140 may control the touch screen 143 included in the fault diagnosis device 100 through the touch screen controller 141.

For example, the touch screen controller 141 uses any one of a plurality of touch sensing technologies such as capacitive, resistive, infrared, surface acoustic wave technology, proximity sensor array, etc. to detect the user's touch and movement or touch. and cessation of movement can be detected. As another example, the I/O subsystem 140 may control other input/control devices 144 included in the fault diagnosis device 100 through other input controller(s) 142. As an example, other input controller(s) 142 may control one or more buttons, rocker switches, thumb-wheels, infrared ports, USB ports, and pointer devices such as a stylus.

So far, the fault diagnosis device 100 according to an embodiment of the present invention has been described. According to the present invention, the steady-state values of various parameters of each facility can be predicted using the fault diagnosis device 100 equipped with an artificial intelligence model for each facility of the building's HVAC system.

Hereinafter, the fault diagnosis server 300 will be described with reference to FIG. 3.

Figure 3 is a block diagram showing the configuration of a fault diagnosis server for an HVAC system according to an embodiment of the present invention. Below, description is made with reference to FIG. 1 .

Referring to FIG. 3, the fault diagnosis device 300 may include a communication interface 310, a memory 320, an I/O interface 330, and a processor 340, and each component may include one or more communication buses or They can communicate with each other through signal lines.

Referring to FIGS. 1 and 3 , the communication interface 310 can be connected to the fault diagnosis device 100 through a wired/wireless communication network to exchange data. The communication interface 310 may be referred to as a transceiver. For example, the communication interface 310 may receive temperature data of inlet and outlet water collected over a certain period of time and measured by sensors installed for each facility or flow rate data for each facility (i.e., sensor data) from the failure diagnosis device 100. You can. For another example, the communication interface 310 may transmit a result predicted through a steady-state prediction model to the failure diagnosis device 100 and may provide a user interface screen to visually display the result.

Meanwhile, the communication interface 310 that enables transmission and reception of such data includes a wired communication port 311 and a wireless circuit 312, where the wired communication port 311 is one or more wired interfaces, for example, Ethernet , Universal Serial Bus (USB), Firewire, etc. Additionally, the wireless circuit 312 can transmit and receive data with an external device through RF signals or optical signals. Additionally, wireless communications may use at least one of a plurality of communication standards, protocols and technologies, such as GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol.

The memory 320 can store various data used in the fault diagnosis server 300. For example, the memory 320 contains information about various facilities included in the HVAC system (e.g., hot and cold water dispenser, cooling tower, air conditioner), parameter information of the HVAC system (e.g., time, external temperature), and parameter information for each facility (e.g. (temperature of supply water to cold/hot water machine, return water temperature of cold/hot water machine, indoor temperature of specific area, opening rate of valve of specific area, supply water temperature of cooling tower, return water temperature of cooling tower), learned to predict the normal state of parameters for each facility. Steady-state prediction models can be saved.

In various embodiments, memory 320 may include volatile or non-volatile recording media capable of storing various data, instructions, and information. For example, the memory 320 may be a flash memory type, hard disk type, multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage storage. , cloud, or blockchain database may include at least one type of storage medium.

In various embodiments, memory 320 may store configuration of at least one of operating system 321, communication module 322, user interface module 323, and one or more applications 324.

Operating system 321 (e.g., embedded operating system such as LINUX, UNIX, MAC OS, WINDOWS, VxWorks, etc.) is a variety of software for controlling and managing common system tasks (e.g., memory management, storage device control, power management, etc.) It may contain components and drivers and may support communication between various hardware, firmware, and software components.

The communication module 323 may support communication with other devices through the communication interface 310. The communication module 320 may include various software components for processing data received by the wired communication port 311 or the wireless circuit 312 of the communication interface 310.

The user interface module 323 may receive a user's request or input from a keyboard, touch screen, keyboard, mouse, microphone, etc. through the I/O interface 330 and provide a user interface on the display.

Applications 324 may include programs or modules configured to be executed by one or more processors 340 . Here, applications for medical image classification and segmentation can be implemented on a server farm.

The I/O interface 330 may connect at least one of input/output devices (not shown) of the fault diagnosis server 300, such as a display, keyboard, touch screen, and microphone, to the user interface module 323. The I/O interface 330 may receive user input (eg, voice input, keyboard input, touch input, etc.) together with the user interface module 323 and process commands according to the received input.

The processor 340 is connected to the communication interface 310, memory 320, and I/O interface 330 to control the overall operation of the fault diagnosis server 300, and an application or program stored in the memory 320. Through this, you can learn a prediction model and execute various commands to output steady-state values for facility parameters when inputting time series data related to the facility, such as HVAC system facility setting values and facility sensor data.

The processor 340 may correspond to a computing device such as a Central Processing Unit (CPU) or an Application Processor (AP). Additionally, the processor 340 may be implemented in the form of an integrated chip (IC) such as a system on chip (SoC) in which various computing devices are integrated. Alternatively, the processor 340 may include a module for calculating an artificial neural network model, such as a Neural Processing Unit (NPU).

Hereinafter, with reference to FIG. 4 , a method of the processor of the failure diagnosis device 100 (or the failure diagnosis server 300) to diagnose a failure of the HVAC system will be described.

Figure 4 is a schematic flowchart of a method for diagnosing a fault in an HVAC system according to an embodiment of the present invention.

Referring to FIG. 4, the fault diagnosis device (or transceiver of the fault diagnosis device) may acquire facility setting values of the HVAC system and sensor data of the facility (S402).

The equipment settings of the HVAC system and the sensor data of the equipment may be time series data over a certain period of time. The sensor data of a facility may include at least one of inlet and outlet water temperature data measured by the sensor installed for each facility collected over a certain period of time or flow rate data for each facility.

The fault diagnosis device (or processor of the fault diagnosis device) may output steady-state values for equipment parameters using a steady-state prediction model that inputs at least one of equipment setting values or sensor data (S404). .

Here, parameters are variables representing specific characteristics of the HVAC system and may refer to parameters for each facility. For example, the parameters may include the supply water temperature of the cold and hot water machine, the return water temperature of the cold and hot water machine, the indoor temperature of a specific area, the opening rate of the valve of the specific area, the supply water temperature of the cooling tower, the return water temperature of the cooling tower, etc.

According to one embodiment of the present invention, when the HVAC system performs a heating cycle, the equipment may use at least one of a cold and hot water machine or an air conditioner.

When the HVAC system is performing a heating cycle, the steady-state prediction model may include a first heating steady-state prediction model. The first heating steady-state prediction model may be an artificial intelligence model that uses time, external temperature, set temperature of the cold and hot water machine, and return water temperature of the cold and hot water machine as inputs, and outputs the temperature of water supplied to the cold and hot water machine.

When the HVAC system performs a heating cycle, the steady-state prediction model may include a second heating steady-state prediction model for a specific zone. The second heating steady-state prediction model uses the header supply water temperature of the cold and hot water machine, the set temperature of the cold and hot water machine, the indoor temperature of a specific zone, the set temperature of a specific zone, and the operating signal of a specific zone as input, and the opening degree of the valve corresponding to the specific zone. It may be an artificial intelligence model with rate as output.

When the HVAC system is performing a heating cycle, the steady-state prediction model may include a third heating steady-state prediction model. The third heating steady-state prediction model may be an artificial intelligence model that uses the set temperature of the cold and hot water machine, the return water temperature of the cold and hot water machine, and the supply water temperature of the cold and hot water machine as inputs, and the fuel consumption of the cold and hot water machine as an output.

According to another embodiment of the present invention, when the HVAC system performs a cooling cycle, the equipment may use at least one of a water cooler, an air conditioner, or a cooling tower.

When the HVAC system is performing a cooling cycle, the steady-state prediction model may include a first cooling steady-state prediction model. The first cooling steady-state prediction model may be an artificial intelligence model that uses time, external temperature, set temperature of the cold and hot water machine, return water temperature of the cold and hot water machine, and return water temperature of the cooling tower as inputs, and outputs the temperature of water supplied to the cold and hot water machine.

When the HVAC system is performing a cooling cycle, the steady-state prediction model may include a second cooling steady-state prediction model. The second cooling steady-state prediction model is an artificial intelligence model that uses time, the external temperature, relative humidity, an operation signal of at least one cold/hot water dispenser, and the return water temperature of the cooling tower as inputs, and uses the temperature of the supply water of the cooling tower as an output. It could be a model.

When the HVAC system performs a cooling cycle, the steady-state prediction model may include a third cooling steady-state prediction model for a specific zone. The third cooling steady-state prediction model takes as input the header supply water temperature of the cold/hot water machine, the set temperature of the cold/hot water machine, the indoor temperature of the specific zone, the set temperature of the specific zone, and the operation signal of the specific zone, It may be an artificial intelligence model that outputs the opening rate of the valve corresponding to the zone.

When the HVAC system performs a cooling cycle, the steady-state prediction model may include a fourth cooling steady-state prediction model. The fourth cooling steady-state prediction model uses the set temperature of the cold and hot water machine, the return water temperature of the cold and hot water machine, the supply water temperature of the cold and hot water machine, and the supply water temperature of the cooling tower as inputs, and the fuel consumption of the cold and hot water machine as output. It could be an artificial intelligence model.

In an embodiment, the first cooling steady-state prediction model, the second cooling steady-state prediction model, and the third cooling steady-state prediction model included in the steady-state prediction model may each output steady-state values for the parameters of the equipment. The parameter values of each facility output from the prediction model may mean steady-state values. For example, “temperature of water supplied to the cold and hot water machine” as the output of the prediction model may mean the steady-state value of the temperature of water supplied to the cold and hot water machine.

Likewise in other embodiments, the first heating steady-state prediction model, the second heating steady-state prediction model, the third heating steady-state prediction model, and the third heating steady-state prediction model included in the steady-state prediction model are each related to the parameters of the equipment. The steady state value can be output.

The fault diagnosis device (or processor of the fault diagnosis device) may compare the normal state value for the parameter and the measured value for the parameter (S406).

As an example, if the first cooling steady-state prediction model that outputs the steady-state value of the temperature of the water supplied to the cold and hot water machine outputs “100 degrees”, it can be compared with the measured value of the actual temperature of the water supplied to the cold and hot water machine.

The fault diagnosis device (or the processor of the fault diagnosis device) may determine whether the equipment or sensor is faulty according to the comparison result between the normal state value and the measured value (S408).

The comparison result can be determined as whether the equipment or parameters are normal according to established criteria. The criteria for determining whether a comparison result is normal or abnormal can be determined in various ways. In addition, the standard for determining whether the comparison result is normal or abnormal may be set differently for each facility or parameter. For example, if the difference between the steady-state value for the temperature of the water supplied to the cold and hot water machine and the measured value for the temperature of the water supplied to the cold and hot water machine is 3 or less in absolute value, it is normal, and if the difference is 3 or more in absolute value, it may be judged to be abnormal. . This example is only an example, and the comparison method or standard does not limit the scope of the technical idea of the present invention.

When the HVAC system performs a heating cycle, the fault diagnosis device (or a processor of the fault diagnosis device) may determine whether the water temperature supplied to the cold/hot water machine is normal using the first heating normal state prediction model.

If it is determined that the water temperature supplied to the cold/hot water machine is not normal, the failure diagnosis device (or the processor of the failure diagnosis device) may determine whether the opening rate of the valve is normal using the second heating normal state prediction model. Additionally, the failure diagnosis device (or the processor of the failure diagnosis device) may determine whether the cold/hot water dispenser or the cold/hot water sensor sensor is broken depending on whether the valve opening rate is normal.

When the HVAC system performs a heating cycle, a fault diagnosis device (or a processor of the fault diagnosis device) may determine whether the fuel consumption of the cold/hot water dispenser is normal using a third heating normal state prediction model. If it is determined that the fuel consumption is not normal, the fault diagnosis device (or the processor of the fault diagnosis device) may determine that the cold/hot water machine is broken.

As another example, when the HVAC system performs a cooling cycle, the fault diagnosis device (or the processor of the fault diagnosis device) may determine whether the temperature of water supplied to the cold/hot water machine is normal using the first cooling normal state prediction model.

When it is determined that the temperature of the water supplied to the cold and hot water machine is normal, the failure diagnosis device (or the processor of the failure diagnosis device) may determine whether the temperature of the water supplied to the cooling tower is normal using the second cooling normal state prediction model. there is. When it is determined that the temperature of the supply water to the cooling tower is abnormal, the failure diagnosis device (or the processor of the failure diagnosis device) may determine that the cooling tower sensor is malfunctioning.

When the HVAC system performs a cooling cycle, when it is determined that the water temperature supplied to the cold/hot water unit is abnormal, the fault diagnosis device (or the processor of the fault diagnosis device) uses a second cooling normal state prediction model to supply the water to the cooling tower. You can determine whether the water temperature is normal.

If the temperature of the water supplied to the cooling tower is determined to be abnormal, the failure diagnosis device (or the processor of the failure diagnosis device) may determine that the cooling tower is in trouble.

When the HVAC system performs a cooling cycle, when the cooling tower supply water temperature is determined to be normal, the fault diagnosis device (or the processor of the fault diagnosis device) uses a third cooling steady-state prediction model to determine the opening rate of the valve. You can determine whether it is normal or not. At this time, the failure diagnosis device (or the processor of the failure diagnosis device) may determine whether the cold or hot water machine or the cold or hot water sensor sensor is broken depending on whether the valve opening rate is normal.

When the HVAC system performs a cooling cycle, the fault diagnosis device (or the processor of the fault diagnosis device) may determine whether the fuel consumption of the water cooler or hotter is normal using the fourth cooling normal state prediction model. If the fuel consumption is determined to be abnormal, the fault diagnosis device (or the processor of the fault diagnosis device) may determine that the cold/hot water heater is broken.

In various embodiments, the failure diagnosis device according to an embodiment of the present invention is provided with prediction models corresponding to equipment (or equipment parameters), so that the steady-state prediction model includes a plurality of prediction models, and the steady-state prediction model includes a plurality of prediction models. By operating the prediction model based on different decision trees for the heating cycle and the cooling cycle, failures in equipment included in the HVAC system can be diagnosed.

Figure 5 is a schematic diagram illustrating a decision tree in a heating cycle according to an embodiment of the present invention.

5, a decision tree used to determine equipment failure when an HVAC system is performing a heating cycle is shown.

A decision tree may also be referred to as a decision tree model. The decision tree model is a model that uses a decision tree to classify data according to specific criteria (or questions).

The decision tree model can divide the variable area into two for each branch. In a decision tree, a square box containing a question or correct answer can be defined as a node. The node containing the first classification standard (i.e. the first question) is defined as the root node, the node in the main part of the tree structure is defined as the internal node, and the last node is defined as the terminal node or leaf node. can do.

According to the decision tree of the heating cycle of FIG. 5, the decision tree may include two root nodes 502 and 506.

When the first root node 502 branches out, it can be determined whether the temperature of the water supplied to the cold and hot water machine is normal using the first heating steady state prediction model. The first root node 502 may be a node whose classification criteria is whether the water temperature supplied to the cold or hot water machine is normal (Is the chiller supply water temperature normal?).

As a result of the judgment, if the temperature of the water supplied to the cold and hot water machine is determined to be normal, it may be determined that all facilities are not malfunctioning. On the other hand, if it is determined that the temperature of the water supplied to the cold/hot water machine is not normal, it can be moved to the middle node 504 to determine whether the classification criteria of the middle node 504 are satisfied. The middle node 504 may be a node whose classification criteria is whether the opening rate of the temperature control valve (TCV) is normal (is the TCV open rate normal?).

When the middle node 504 branches out, it can be determined whether the opening rate of the temperature control valve is normal using the second heating steady state prediction model. As a result of the determination, if the opening rate of the temperature control valve is determined to be normal, it may be determined that the chiller supply water sensor is malfunctioning. On the other hand, if it is determined that the opening rate of the temperature control valve is not normal, it may be determined that the cold and hot water machine is broken.

In another embodiment, when the second root node 506 branches out, it may be determined whether the fuel consumption of the cold/hot water dispenser is normal using the third heating normal state prediction model. The second root node 506 may be a node that uses whether the colder/hoter fuel consumption is normal (is the chiller fuel consumption normal?) as a classification criterion.

As a result of the determination, if the fuel consumption of the cold/hot water machine is determined to be abnormal, it may be determined that the cold/hot water machine is broken.

The first to third heating steady-state prediction models used to determine whether the classification criteria of each node are satisfied will be described later with reference to FIGS. 6 to 8 below.

Figures 6 to 8 are exemplary diagrams showing steady-state heating prediction models according to an embodiment of the present invention.

Figure 6 shows a first heating steady-state prediction model, Figure 7 shows a second heating steady-state prediction model, and Figure 8 shows a third heating steady-state prediction model.

Referring to FIGS. 6 to 8 , the first to third heating steady state prediction models may include a Convolutional Neural Network (CNN) that performs a convolution operation with one-dimensional (1D) data. CNN according to an embodiment of the present invention may use ReLU (Rectified Linear Unit) as an activation function.

Additionally, the output data of CNN can be input to LSTM (Long Short-Term Model) through a flatten layer. The platen layer refers to a layer that flattens input data into one-dimensional data.

Referring to FIG. 6, the first heating steady-state prediction model inputs time, outside temperature, Chiller Set Temperature of the cold and hot water machine, and/or Chiller Return Temperature of the cold and hot water machine. You can do this. The first heating steady-state prediction model can predict and output the steady-state value of the water supply temperature (Chiller Supply Temperature) of the cold and hot water machine.

Referring to FIG. 7, the second heating steady state prediction model includes the header supply temperature of the cold and hot water machine (Header Supply Temperature), the set temperature of the cold and hot water machine (Chiller Set Temperature), the indoor temperature of a specific area (Return Air Temperature, R.A Temperature), The set temperature of a specific zone (Zone Set Temperature) and/or the operation signal of the specific zone (Zone Operation Sign) can be input. Here, the header refers to a facility that serves to equalize the pressure and concentration of the supply fluid, and hot and cold water is distributed from the header to each cold and hot water supply. In another embodiment, the second heating steady state prediction model may additionally input other time series data, such as time and outside temperature. The second heating steady-state prediction model can predict and output the steady-state value of the opening rate of the valve.

In various embodiments, when the building's HVAC system heats a plurality of specific zones (e.g., four), the heating steady-state prediction model may include a second heating steady-state prediction model as many as the number of specific zones (e.g., four). 4) may be included.

Referring to FIG. 8, the third heating steady state prediction model inputs the set temperature of the cold and hot water machine (Chiller Set Temperature), the return water temperature of the cold and hot water machine (Chiller Return Temperature), and/or the supply water temperature of the cold and hot water machine (Chiller Supply Temperature). can do. In another embodiment, the third heating steady state prediction model may additionally input other time series data such as time and outside temperature. The third heating steady-state prediction model can predict and output the steady-state value of fuel consumption of the cold and hot water machine.

Figure 9 is a schematic diagram illustrating a decision tree in a cooling cycle according to an embodiment of the present invention.

According to the decision tree of the heating cycle of FIG. 5, the decision tree may include two root nodes 902, 910. The third root node 902 may be a node whose classification criteria is whether the water temperature supplied to the cold or hot water machine is normal (Is the chiller supply water temperature normal?).

When the third root node 902 branches out, it can be determined whether the temperature of the water supplied to the cold/hot water machine is normal using the first cooling normal state prediction model.

As a result of the determination, if it is determined that the temperature of the water supplied to the cold and hot water machine is normal, it can be moved to the first middle node 904 to determine whether the classification criteria of the first middle node 904 are satisfied. The first middle node 904 may be a node whose classification criteria is whether the cooling tower supply water temperature is normal (Is the cooling tower supply water temperature normal?).

When the first intermediate node 904 branches out, it can be determined whether the temperature of the supply water to the cooling tower is normal using the second cooling steady state prediction model. As a result of the judgment, if the temperature of the supply water to the cooling tower is determined to be normal, it may be determined that all facilities are not malfunctioning. On the other hand, if the temperature of the supply water to the cooling tower is determined to be abnormal, it may be determined that the cooling tower water sensor is malfunctioning.

When the third root node 902 branches out, if it is determined that the water temperature supplied to the cold and hot water machine is not normal as a result of judgment using the first cooling normal state prediction model, it moves to the second middle node 906 and moves to the second middle node. It can be determined whether the classification criteria of (906) are satisfied. The second middle node 906 may be a node whose classification criteria is whether the cooling tower supply water temperature is normal (Is the cooling tower supply water temperature normal?).

When the second intermediate node 906 branches out, it can be determined whether the temperature of the supply water to the cooling tower is normal using the second cooling steady state prediction model. As a result of the judgment, if the temperature of the water supplied to the cooling tower is determined to be abnormal, it may be determined that the cooling tower is out of order. On the other hand, if it is determined that the temperature of the water supplied to the cooling tower is normal, it can be moved to the third intermediate node 908 to determine whether the classification criteria of the third intermediate node 908 are satisfied. The third intermediate node 908 may be a node whose classification criteria is whether the opening rate of the temperature control valve is normal (is the TCV open rate normal?).

When the third intermediate node 908 branches out, it can be determined whether the opening rate of the temperature control valve is normal using the third cooling normal state prediction model. As a result of the determination, if the opening rate of the temperature control valve is determined to be normal, it may be determined that the chiller supply water sensor is malfunctioning. On the other hand, if the opening rate of the temperature control valve is determined to be abnormal, it may be determined that the cold and hot water dispenser (Chiller) is malfunctioning.

In another embodiment, when the fourth root node 910 branches out, it may be determined whether the fuel consumption of the water cooler or hotter is normal using the fourth cooling normal state prediction model. The fourth root node 910 may be a node that uses whether the colder/hoter fuel consumption is normal (is the chiller fuel consumption normal?) as a classification criterion.

As a result of the determination, if the fuel consumption of the cold/hot water machine is determined to be abnormal, it may be determined that the cold/hot water machine is broken.

The first to fourth cooling steady-state prediction models used to determine whether the classification criteria of each node are satisfied are described later with reference to FIGS. 10 to 13 below.

10 to 13 are exemplary diagrams showing a cooling steady-state prediction model according to an embodiment of the present invention.

FIG. 10 shows a first cooling steady-state prediction model, FIG. 11 shows a second cooling steady-state prediction model, FIG. 12 shows a third cooling steady-state prediction model, and FIG. 13 shows a fourth cooling steady-state prediction model.

Referring to FIGS. 10 to 13 , the first to fourth cooling steady-state prediction models may include a Convolutional Neural Network (CNN) that performs a convolution operation with 1-dimensional (1D) data. CNN according to an embodiment of the present invention may use ReLU (Rectified Linear Unit) as an activation function.

Additionally, the output data of CNN can be input to LSTM (Long Short-Term Model) through a flatten layer. The platen layer refers to a layer that flattens input data into one-dimensional data.

Referring to FIG. 10, the first cooling steady state prediction model includes time, outside temperature, Chiller Set Temperature of the cold and hot water machine, Chiller Return Temperature of the cold and hot water machine, and/or cooling tower. Cooling Tower Return Temperature can be input. In another embodiment, the first cooling steady-state prediction model may additionally input other time series data, such as the temperature of supply water to the cooling tower. The first cooling steady-state prediction model can predict and output the steady-state value of the water supply temperature (Chiller Supply Temperature) of the cold and hot water machine.

Referring to FIG. 11, the second cooling steady-state prediction model includes time, outside temperature, relative humidity, operation signals 1 and 2 of the cold and hot water machine (Chiller 1 sign, chiller 2 sign), Cooling Tower Return Temperature can be entered. The second cooling steady state prediction model can predict and output the steady state value of the cooling tower supply temperature.

In various embodiments, when the HVAC system of a building includes a plurality of water coolers and/or cooling towers, the cooling steady-state prediction model may include a plurality of second cooling steady-state prediction models. For example, if a building's HVAC system includes two water coolers (1 and 2) and two cooling towers (A and B), the cooling steady-state prediction model includes two primary cooling steady-state prediction models (first cooling and Steady state prediction models 1-1, 1-2) and two second cooling steady state prediction models (second cooling steady state prediction models 2-1, 2-2) may be included.

As an example, when water cooler 1 and cooling tower B operate at a specific time t, and water cooler 2 and cooling tower A do not operate, the first cooling steady-state prediction model 1-1 and the second cooling steady-state prediction model 2-2 operate. I do it.

At this time, the operation signal (chiller 1 sign) of water cooler 1 in the first cooling steady state prediction model 1-1 may be 1, and the operation signal (chiller 2 sign) of water heater 2 may be 0. That is, when there are two or more cold and hot water machines, the operation signal of the cold and hot water machines shows a value of 1 sign for the cold and hot water machines that are operating, and a value of 0 sign for the cold and hot water machines that are not in operation. The number of hot and cold water dispensers and/or cooling towers may have different values, and this does not limit the scope of rights according to the technical idea of the present invention.

Referring to FIG. 12, the third cooling steady state prediction model includes the header supply temperature of the cold and hot water machine (Header Supply Temperature), the set temperature of the cold and hot water machine (Chiller Set Temperature), the indoor temperature of a specific area (Return Air Temperature, R.A Temperature), The set temperature of a specific zone (Zone Set Temperature) and/or the operation signal of the specific zone (Zone Operation Sign) can be input. In another embodiment, the third cooling steady state prediction model may additionally input other time series data such as time and outside temperature. The third cooling steady state prediction model can predict and output the steady state value of the opening rate of the valve.

In various embodiments, when there are a plurality of specific zones (e.g., four) that the building's HVAC system cools, the cooling steady-state prediction model includes a third cooling steady-state prediction model as many as the number of specific zones (e.g., 4) may be included.

Referring to FIG. 13, the fourth cooling steady state prediction model is the set temperature of the cold and hot water machine (Chiller Set Temperature), the return water temperature of the cold and hot water machine (Chiller Return Temperature), the supply water temperature of the cold and hot water machine (Chiller Supply Temperature), and/or the cooling tower. Cooling Tower Return Temperature can be input. In another embodiment, the fourth cooling steady state prediction model includes other time series data such as Time, Outside Temperature, Chiller Operation Sign, and Cooling Tower Supply Temperature. Additional information may be entered. The fourth cooling steady-state prediction model can predict and output the steady-state value of the fuel consumption of the cold and hot water machine.

Although embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and may be modified and implemented in various ways without departing from the technical spirit of the present invention. there is. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. The scope of protection of the present invention should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of the present invention.

1000: HVAC system
100: Fault diagnosis device
110: memory interface 120: processor(s)
130: peripheral interface 140: I/O subsystem
141: Touch screen controller 142: Other input controller
143: touch screen
144: Other input control devices
150: Memory 151: Operating system
152: Communication module 153: GUI module
154: sensor processing module 155: phone module
156: Applications
156-1, 156-2: Application
157: Digital assistant client module
158: User data
160: motion sensor 161: light sensor
162: Proximity sensor 163: Other sensors
170: Camera subsystem 171: Optical sensor
180: Communication subsystem
190: Audio subsystem
191: Speaker 192: Microphone
300: Fault diagnosis server
310: communication interface
311: wired communication port 312: wireless circuit
320: memory
321: operating system 322: communication module
323: User interface module 324: Application
330: I/O interface 340: Processor

Claims (13)

A method performed by a processor of a fault diagnosis device of an HVAC system, comprising:
Obtaining equipment setting values of the HVAC system and sensor data of the equipment;
outputting steady-state values for parameters of the equipment using a steady-state prediction model that inputs at least one of the equipment setting values or the sensor data;
comparing the steady-state value for the parameter with a measured value for the parameter; and
Including, determining whether the equipment or the sensor is broken according to a comparison result between the normal state value and the measured value.
How to diagnose faults in HVAC systems.
According to paragraph 1,
The sensor data includes at least one of inlet and outlet water temperature data measured by the sensor installed for each facility collected over a certain period of time or flow rate data for each facility,
How to diagnose faults in HVAC systems. According to paragraph 2,
When the HVAC system performs a heating cycle,
The equipment includes at least one of a cold and hot water machine or an air conditioner,
How to diagnose faults in HVAC systems.
According to paragraph 3,
The steady-state prediction model includes a first heating steady-state prediction model,
The first heating steady-state prediction model is an artificial intelligence model that inputs time, external temperature, set temperature of the cold and hot water machine, and return water temperature of the cold and hot water machine, and outputs the temperature of water supplied to the cold and hot water machine,
Further comprising: determining whether the temperature of water supplied to the cold and hot water machine is normal using the first heating normal state prediction model,
How to diagnose faults in HVAC systems.
According to clause 4,
The steady-state prediction model includes a second heating steady-state prediction model for a specific zone,
The second heating steady-state prediction model takes as input the header supply water temperature of the cold/hot water machine, the set temperature of the cold/hot water machine, the indoor temperature of the specific zone, the set temperature of the specific zone, and the operation signal of the specific zone, and the specific zone. It is an artificial intelligence model that outputs the opening rate of the valve corresponding to the zone,
When it is determined that the water temperature supplied to the cold/hot water machine is not normal, determining whether the opening rate of the valve is normal using the second heating normal state prediction model; and
Further comprising: determining whether the cold or hot water machine or the cold or hot water sensor sensor is broken depending on whether the valve opening rate is normal,
How to diagnose faults in HVAC systems.
According to clause 5,
The steady-state prediction model includes a third heating steady-state prediction model,
The third heating steady-state prediction model is an artificial intelligence model that takes the set temperature of the cold and hot water machine, the return water temperature of the cold and hot water machine, and the supply water temperature of the cold and hot water machine as inputs, and uses the fuel consumption of the cold and hot water machine as an output,
determining whether the fuel consumption of the cold/hot water machine is normal using the third heating normal state prediction model; and
Further comprising, when it is determined that the fuel consumption is not normal, determining that the cold and hot water machine is broken.
How to diagnose faults in HVAC systems.
According to paragraph 2,
When the HVAC system performs a cooling cycle,
The equipment includes at least one of a hot and cold water dispenser, an air conditioner, or a cooling tower.
How to diagnose faults in HVAC systems.
In clause 7,
The steady-state prediction model includes a first cooling steady-state prediction model,
The first cooling steady-state prediction model uses time, external temperature, set temperature of the cold and hot water machine, return water temperature of the cold and hot water machine, and return water temperature of the cooling tower as inputs, and outputs the temperature of water supplied to the cold and hot water machine. It's a model,
Further comprising: determining whether the temperature of water supplied to the cold/hot water machine is normal using the first cooling normal state prediction model,
How to diagnose faults in HVAC systems.
According to clause 8,
The steady-state prediction model includes a second cooling steady-state prediction model,
The second cooling steady-state prediction model takes the time, the external temperature, the relative humidity, an operation signal of at least one cold/hot water dispenser, and the return water temperature of the cooling tower as inputs, and the supply water temperature of the cooling tower as an output. It is an artificial intelligence model,
When it is determined that the temperature of the water supplied to the cold/hot water dispenser is normal, determining whether the temperature of the water supplied to the cooling tower is normal using the second cooling steady state prediction model; and
Further comprising: determining that the cooling tower sensor is in failure when the temperature of the supply water to the cooling tower is determined to be abnormal,
How to diagnose faults in HVAC systems.
According to clause 9,
When it is determined that the temperature of the water supplied to the cold/hot water dispenser is abnormal, determining whether the temperature of the water supplied to the cooling tower is normal using the second cooling normal state prediction model; and
Further comprising: determining that the cooling tower is out of order when the temperature of the supply water to the cooling tower is determined to be abnormal,
How to diagnose faults in HVAC systems.
According to clause 10,
The steady-state prediction model includes a third cooling steady-state prediction model for a specific zone,
The third cooling steady-state prediction model receives as input the header supply water temperature of the cold/hot water machine, the set temperature of the cold/hot water machine, the indoor temperature of the specific zone, the set temperature of the specific zone, and the operation signal of the specific zone, It is an artificial intelligence model that outputs the opening rate of the valve corresponding to a specific area,
When it is determined that the supply water temperature of the cooling tower is normal, determining whether the opening rate of the valve is normal using the third cooling steady state prediction model; and
Further comprising: determining whether the cold or hot water machine or the cold or hot water sensor sensor is broken depending on whether the valve opening rate is normal,
How to diagnose faults in HVAC systems.
According to clause 11,
The steady-state prediction model includes a fourth cooling steady-state prediction model,
The fourth cooling steady state prediction model inputs the set temperature of the cold/hot water machine, the return water temperature of the cold/hot water machine, the supply water temperature of the cold/hot water machine, and the supply water temperature of the cooling tower, and outputs the fuel consumption of the cold/hot water machine. It is an artificial intelligence model that uses
determining whether the fuel consumption of the cold/hot water machine is normal using the fourth cooling normal state prediction model; and
Further comprising, when it is determined that the fuel consumption is not normal, determining that the cold and hot water machine is broken.
How to diagnose faults in HVAC systems.
A transceiver that receives equipment settings of the HVAC system and sensor data of the equipment;
Memory; and
a processor operably connected to the transceiver and the memory; Including,
The processor,
Outputs steady-state values for the parameters of the equipment using a steady-state prediction model that inputs at least one of the equipment setting values or the sensor data, and outputs the steady-state values for the parameters and measured values for the parameters. and configured to determine whether the equipment or the sensor is in trouble according to the comparison result of the normal state value and the measured value,
Fault diagnosis device for HVAC systems.

Images