KR102264390B1 - Air dome autonomous driving system according to iot intelligent control - Google Patents

Abstract

The present invention relates to an air dome autonomous driving system, which may comprise: an input device for receiving external force data acting on the outside of the air dome and receiving monitoring data from an Internet of things (IoT) sensor disposed inside the air dome; a process device for performing autonomous driving control based on weather forecast information, the monitoring data, and autonomous driving learning data stored in a database; and an output device including an air conditioning system operating based on the autonomous driving control.

Description

Air dome autonomous driving system through IOT intelligent control {AIR DOME AUTONOMOUS DRIVING SYSTEM ACCORDING TO IOT INTELLIGENT CONTROL}

The present invention relates to an air dome autonomous driving system through IOT intelligent control, and more particularly, based on the data measured and learned data from each IOT sensor according to the internal state of the air dome changed from the external force, the normal driving state or external force It relates to an air dome autonomous driving system through IOT intelligent control that operates autonomously to become a state that can respond to

Because the air dome maintains its shape with internal air pressure and efficiently manages indoor air quality due to its structural characteristics, the system consists of a technology that can control and automatically operate not only the structural parts of membrane materials and cables, but also the entire facility and system. This is the most important structure.

In the air dome, the initial countermeasure for autonomous driving from heavy snow, typhoons, and earthquakes is to increase the internal pressure through autonomous driving. It is a technology to build a snowmelting device and network system that prevents ponding due to the load of snow accumulated on the upper part of the air dome when heavy snow falls outside and removes the accumulated snow. It is also a technology that makes the internal pressure safe through autonomous driving so that the air dome does not shake too much when a strong external typhoon blows

The technology of Korean Patent Registration No. 10-2004-0010378 was designed as a method to increase the pressure inside the air dome by measuring it with an external anemometer or a snow sensor, and also divided into two stages without a specific control method, and the wind speed is 10m/s, 20m/s The snow cover suggests a technology designed only for the general system configuration divided into 30mm and 50mm, but the air dome already has a lot of measurement errors because the internal pressure fan operates by the sensor measured after a typhoon has struck. there is a situation.

The present invention provides an air dome autonomous driving system and method through IOT intelligent control.

The present invention provides the control of the air dome through smart control using the Internet of Things (IOT) rather than manual control through experience, according to the state of the inside of the air dome changed from external force, the measured data and the learned data from each IOT sensor. To provide a system and method for autonomous driving of an air dome through IOT intelligent control that autonomously controls the air dome to be in a normal driving state or a state that can respond to external forces as a standard.

An air dome autonomous driving system according to an embodiment of the present invention includes: an input device for receiving external force data acting on the outside of the air dome and monitoring data from an Internet of Things (IOT) sensor disposed inside the air dome; a process device for performing autonomous driving control based on weather forecast information, the monitoring data, and autonomous driving learning data stored in a database; and an output device including an air conditioning system operating based on the autonomous driving control; may include.

In an autonomous driving method executed in an air dome autonomous driving system according to an embodiment of the present invention, the method comprising: receiving external force data acting on the outside of the air dome and monitoring data from an IoT sensor disposed inside the air dome; performing autonomous driving control based on weather forecast information, the monitoring data, and external force data learned in a database; and operating an air conditioning system based on the autonomous driving control.

In the present invention, as the overshoot of the existing PID control occurs, a time delay occurs in reaching the objective function. Therefore, the MPC controller is used to suppress the occurrence of overshoot through prediction in advance, and to reach the objective function according to the natural increase/decrease. use

According to the present invention, the state of the air dome (internal pressure change, air quality change, safety problem change, etc.) due to external external force (heavy snow, typhoon, earthquake, air pollution, etc.) is measured through a sensor network linked to each object. Autonomous driving is possible based on the acquired data and the learned data.

According to the present invention, it is possible to more safely and efficiently maintain the air dome, which requires sensitive driving, by learning the stored data as well as the recorded data while driving.

1 is a diagram illustrating Architecture Inflation & HVAC of data of an air dome autonomous driving system through IOT intelligent control according to an embodiment of the present invention.
2 is a view for explaining an MPC controller according to an embodiment of the present invention.
3 is a view showing a ZigBee communication method according to an air dome autonomous driving system through IOT intelligent control according to an embodiment of the present invention.
4 is a view showing an outline of an air dome autonomous driving system according to a wired/wireless communication method for IOT intelligent control of safety and maintenance for an air dome according to an embodiment of the present invention.
5 to 6 are diagrams for explaining an MPC model applied to an INFLATION & HVAC system according to an embodiment of the present invention.
7 is a view for explaining the HVAC system control of the MPC controller according to an embodiment of the present invention.
8 is a view for explaining an autonomous driving method of an air dome during a typhoon operation according to an embodiment of the present invention.
9 is a view for explaining flow rate control data during a typhoon operation according to an embodiment of the present invention.
10 is a view for explaining an autonomous driving method of the air dome during heavy snow driving according to an embodiment of the present invention.
11 is a view for explaining an autonomous driving method when driving an air dome during an indoor air quality improvement driving according to an embodiment of the present invention;
12 is a view for explaining a method for autonomous driving of an air dome when a fire occurs according to an embodiment of the present invention;
13 is a view for explaining the AI learning algorithm according to the autonomous driving of the air dome according to an embodiment of the present invention.

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

Terms used in the embodiments of the present invention may be interpreted as meanings that can be generally understood by those of ordinary skill in the art to which the present invention pertains, unless clearly defined in other meanings. It will be seen that the embodiments are described, and are not intended to limit the present invention.

In the present specification, the singular will be considered to include the plural unless otherwise specified.

In addition, when a part is described as "including" a certain element, it means that the part may further include other elements.

In addition, when a component is described as “upper”, it means above or below the component, and does not necessarily mean that it is located above the direction of gravity.

In addition, when it is described that a component is “connected” or “coupled” to another component, the component is not only directly connected or coupled to another component, but also indirectly through another component. It may include the case of being connected or combined with .

In addition, although terms such as first, second, etc. may be used to describe a certain component, these terms are only for distinguishing the corresponding component from other components, and the essence or order of the corresponding component by the term Or, it is not intended to limit the order or the like.

1 is a diagram illustrating Architecture Inflation & HVAC of data of an air dome autonomous driving system through IOT intelligent control according to an embodiment of the present invention, and FIG. 2 is a diagram for explaining MPC and CASCADE output according to an embodiment of the present invention 3 is a view showing a wireless communication method according to an air dome autonomous driving system through IOT intelligent control according to an embodiment of the present invention, and FIG. 4 is a safety for an air dome according to an embodiment of the present invention. And it is a view showing an outline of an air dome autonomous driving system according to a wired/wireless communication method for IOT intelligent control of maintenance, and FIGS. 5 to 6 are MPC models applied to the INFLATION & HVAC system according to an embodiment of the present invention. It is a drawing for explanation.

1, the air dome autonomous driving system through IOT (Internet of Things) intelligent control of safety and maintenance for the air dome is an air dome 110 through energy efficiency and differential pressure control with IoT-based control. It is a technology to promote the atmospheric stability of the indoor environment of the sensor network 160 that measures the environmental state value transmitted to the gateway, the INFLALTION system 155 including the Inflation module, and the air conditioning (HVAC: An HVAC system 150 including a heating, ventilation, & air conditioning module, an actuator network 170 for controlling the HVAC module, and a communication gateway, an external application program interface (API) that provides weather forecast information ) including a weather forecast providing unit 180, a control unit and a database for acquiring field data, a model predictive control (MPC) algorithm, a database server 130 connected to a user interface from an IP device, and a host It may include a monitoring control system module 140 through the dashboard 120 of the.

The air dome autonomous driving system through IOT intelligent control is a method of networking the information of the IOT sensor linked to each object, and the technology to build a system optimized for economical and immediate response and the collected data are monitored and remote controlled from the central control tower. The IOT sensor may include a differential pressure sensor, a wind speed sensor, a snow sensor, a snow sensor, an air quality detection sensor, a fire detection sensor, etc. disposed inside the air dome 110 .

The snow sensor is a sensor that comprehensively detects the road surface conditions (temperature, humidity, snow, ice) of the air dome roof. can Through this, when snow accumulates with a snow sensor that provides information on the amount of snow on the roof of the air dome and the degree of melting, the difference between the internal pressure and the external pressure of the air dome makes it possible for the HVAC to operate excessively. Since it becomes a state, it is possible to melt the roof of the air dome through the data acquired from the snow sensor.

The Snow Dept Sensor is a sensor that determines the amount of snow accumulated locally on the roof of the air dome based on the wind direction and wind speed through climate information. It becomes difficult to maintain its shape, which may result in excessive energy consumption. Therefore, the Snow Dept Sensor is usually installed at the flat GL (ground level) next to the air dome and measures the amount of snow accumulated on the road surface. When the road surface is scanned with a laser, the distance and reflectance between the set road surface and the sensor are measured. The way it measures, it can work if snow accumulates in the measuring range.

The MPC algorithm was applied to the control algorithm of the air dome autonomous driving system through IOT intelligent control, and the optimization algorithm was applied for the purpose of optimal balance between indoor air quality and energy consumption rate. Control of indoor air quality is essential for important automatic operation in the air dome. The Predicted Mean Vote (PMV) equation, which expresses non-linear characteristics such as air temperature, wind direction, relative humidity, and average radiant temperature that affects indoor air quality, was applied. PMV index formation can be adjusted with a dimensionless range of ±1 for indoor air condition and a cool/warm detection range of ±2. In general, when the error of indoor air quality is ±3 or more, an undesirable imbalance appears.

At this time, the formula for maintaining the nonlinearity of indoor air quality and indoor atmosphere is as Equation 1 below.

[Equation 1]

here,

, 단열

는

, 면적 계수

, W는 설비 power, 복사 온도

, 풍향

: 풍향에 따른 실내 분위기 interval 0.15

0.25[ms], 또는 상수 0.1[ms]이다. At this time, energy M indicates the amount of energy in the indoor space.

, insulation

is

, area coefficient

, W is the equipment power, radiant temperature

, wind direction

: Indoor atmosphere interval according to wind direction 0.15

0.25 [ms], or constant 0.1 [ms].

In this case, PMV parameters and variables used in the automatic estimation control are shown in Table 1 below.

[Table 1]

As shown in Fig. 2, the MPC controller is a set value directly input by the user through the HMI (Human Machine Interface) touch screen, and the simulated value through the simulator in the PLC that receives the target temperature, pressure, etc. inside the air dome. can receive In addition, the MPC controller may receive external air information from the sensor through ANALOG INPUT (ambient condition) to receive disturbance information. Therefore, the MPC controller can run Inflation & HVAC of the air dome through CASCAE control after calculating with the MPC (Model Predictive Control) algorithm. In this case, the MPC controller is located inside the PLC and can be controlled by an algorithm.

Therefore, the air dome autonomous driving system through IOT intelligent control applies ANN (Artificial neural network) to MPC control to control-following autonomous driving through prediction of non-linear systems of INFLATION & HVAC, and multi-layer multiple neurons. An algorithm that synthesizes a recurrent neural network and a feedforward neural network is applied.

That is, the purpose of the MPC controller in the air dome autonomous driving system through the IOT intelligent control is to learn the data acquired according to the size and use of the air dome 110 to realize a system capable of intelligent autonomous driving through MPC control. For this purpose, it can achieve its purpose as follows. The first air dome is operated stably, the second is energy consumption minimization, thermal stability maintenance, indoor air quality maintenance, operating cost minimization, visual stability, minimal maintenance cost of available equipment, minimization of thermal instability period , where a predicted mean vote (PMV) index is presented to implement thermal stability. According to the standard of human thermal sensation suggested by the American Society of Heating, Refrigeration and Air-conditioning Engineers (ASHRAE) (+3 hot and -3 cold, 0 indicates comfort) Implement automatic follow-up control with the goal.

That is, the air dome autonomous driving system is an intelligent autonomous driving system that does not require the manager to manually operate the air dome 110 unless there is a special situation. When an external force occurs and the pressure of the air dome 110 needs to be raised, it automatically detects a crisis and operates safely. Intelligent management that saves energy and maintains excellent HVAC system and indoor air quality through efficient cooling/heating operation. All systems are self-driving systems. This air dome autonomous driving system is an intelligent autonomous driving system that enables the safe and efficient maintenance of the air dome 110 that requires sensitive driving by learning recorded data while driving as well as stored data.

As shown in FIG. 3 , the wireless communication method of the air dome autonomous driving system through the IOT intelligent control may include a Zigbee communication method and a Wi-fi communication method. At this time, the Zigbee communication method of the air dome autonomous driving system through the IOT intelligent control may include a Zigbee Coordinator, a ZigBee Router, and a ZigBee End Device, as shown in FIG. 4 . can

Zigbee Coordinators form networks and connect them with other networks. Each network has only one coordinator. Among them, the ZigBee coordinator may store network-related information and may also serve as a storage for a security key.

ZigBee Router can not only function as an application, but also function as a writer that can forward data from other devices.

A ZigBee End Device includes a function to communicate with a parent node. This relationship allows the node to wait a long time, which can further extend the battery life.

Referring to FIG. 4 , the input device 410 of the air dome autonomous driving system through IOT intelligent control includes a sensor unit, a Zigbee communication module for Zigbee communication with a collection device. The Zigbee Router device can be composed of a module for Zigbee communication and an edge in charge of processing and transmitting the collected data.

According to an embodiment, the input device may receive external force data acting on the outside of the air dome and monitoring data from an IoT sensor disposed inside the air dome.

The external force may include at least one of heavy snow, typhoon, earthquake, and air pollution according to weather outside the air dome.

In this case, the monitoring data may include at least one of differential pressure change information, air quality change information, and fire detection data.

The process (Process, 420) device of the air dome autonomous driving system through IOT intelligent control may include an MPC controller and a dashboard. The optimization module of the MPC controller consists of a thermal model, a suboptimal solver, and a WEATHER FORECAST PROVIDER, and the dashboard device includes a monitor and an edge that can be managed by the administrator. ) can be composed of

As shown in FIG. 5 , the MPC framework 510 performed by the process device 420 in the MPC control architecture is controlled in consideration of the state inside the air dome affected by atmospheric conditions and the interaction between the HVAC energy components. Integrates directivity and INFLATION & HVAC system models. Depending on the output feedback control method applied to the MPC, the online optimization problem aims to determine the control variable (eg HVAC actuator control input). The response of the measured value is consistent with the main media (room temperature, humidity) monitored by the sensor network placed inside, and the control strategy can be constructed by considering the disturbance and estimates for all variables affecting the indoor comfortable atmosphere. can

Disturbance can be divided into measurable and non-measurable, and the measured disturbance can generally be confirmed through dynamic modeling of the air dome 110 , and the unmeasured disturbance results in uncertain results (white noise stochastic noise) of the model accuracy. Since it can be induced, the disturbance model 601 can be configured as shown in FIG. 6 to control the uncertain disturbance.

Referring to FIG. 6 , the thermodynamic behavior and differential pressure of the control-oriented air dome and the INFLATION & HVAC system are applied to the model between the control-oriented air dome and the INFLATION & HVAC system through the application of the MPC model, taking into account disturbances in the selection of the HVAC system MPC formulation logic configuration. Implementation of on-line monitoring optimization through control, and applying the disturbance model 601 to predict the behavior of uncontrolled variables, it may be possible to control the dynamic response of the system.

The first MPC model 610 according to the embodiment is based on the data (v(k)) received from the disturbance model 601 and the data (x(k))} received from the air dome 110 control-oriented ( oriented) MPC control may be performed according to the air dome model 603 . The INFLATION & HVAC system operates according to the internal set-point (u(k+1)) according to the MPC control, and the changed data in the air dome 110 according to the MPC framework 510 again can receive

The second MPC model 620 according to the embodiment is based on the data (v(k)) received from the disturbance model 601 and the data (x(k))} received from the air dome 110 for control-oriented air MPC control may be performed according to the dome model 603 and the control oriented INFLATION & HVAC system model 505 . The air dome 110 and the INFLATION & HVAC systems 150 and 155 operate by the INFLATION & HVAC system control signal according to the MPC control, and the MPC framework 510 receives the changed data in the air dome 110 according to this again. can do.

The third MPC model 630 according to the embodiment includes data (v(k)) received from the disturbance model 601 , data (x(k)) received from the air dome 110 } and the disturbance model 601 . ), MPC control may be performed according to the control-oriented air dome model 603 based on data according to the load model 607 . The INFLATION & HVAC system operates according to the MPC control, and thus the changed data in the air dome 110 may be received by the MPC framework 510 again.

The air dome model shown in FIG. 6 may implement a closed control loop for realizing control prediction.

In consideration of solving the MPC schema optimization problem according to the MPC model, the equation for the closed control loop is as Equation 2 below.

[Equation 2]

은 계수에 의한 가중치, J는 시간 참고 신호 값 P_ref ,

는 time-varying 파라미터, 0 또는 1 이다.here,

is the weight by coefficient, J is the time reference signal value P _ref ,

is a time-varying parameter, 0 or 1.

According to an embodiment, when the air dome is in the normal driving mode during autonomous driving, the processor device receives the differential pressure change information, determines the differential pressure change, and operates the air conditioning system according to the model predictive control corresponding to the differential pressure change. control, determine whether the differential pressure in the air dome is stabilized in response to the known harmonization system control, verify the differential pressure stabilization state in the air dome, store autonomous driving data according to the differential pressure change, and store the stored autonomous driving data Learning can be performed based on

Again, referring to FIG. 4 , the output device 430 of the air dome autonomous driving system through IOT intelligent control includes a display unit, a control unit, and a sensing unit. can do.

7 is a diagram for explaining HVAC system control of an MPC controller according to an embodiment of the present invention. 8 is a diagram according to an embodiment of the present invention;

Referring to Figure 7, in the Electrically driven HVAC MPC controller architecture, the supervisory model prediction controller (Supervisory MPC Controller, 710) is a weather forecast (Weather forecast), power cost (Electricity cost), power consumption (Power consumption), air dome horizontal size ( MPC control of the HVAC 150 may be performed based on the air dome horizon size), the execution time period, and the temperature and pressure of the air dome room.

The supervisory model predictive controller 710 may control a local level ventilation controller and a local level air dome temperature controller according to the MPC control of the HVAC 150 .

The HVAC 150 may perform outdoor air intake, indoor air return, or exhaust and return air exhaust according to a local level ventilation controller.

On the other hand, the HVAC 150 controls the pressure reduction and capacity control valve (PRV) and the bypass valve (BV) according to the local level air dome temperature controller (Local level air dome ) to supply purified air or cooling/heating. have.

8 is a view for explaining a method for autonomous driving of an air dome during a typhoon operation according to an embodiment of the present invention. 9 is a view for explaining flow rate control data during a typhoon operation according to an embodiment of the present invention.

Referring to FIG. 8 , when the air dome autonomous driving system is autonomously driving in the normal driving mode ( S810 ), the air dome autonomous driving system may detect a differential pressure change according to pressure data inside the air dome ( S820 ).

After the step S820, the air dome autonomous driving system may control the pressure fan in the air dome 110 to autonomously operate based on the differential pressure change (S830). In this case, the autonomous operation of the pressure fan may be operated by MPC control of the INFLATION 155 .

After the step S830, the air dome autonomous driving system may determine whether the pressure difference in the air dome 110 according to the autonomous driving of the pressurized fan is stabilized (S840).

The differential pressure is the most sensitive and accurate external pressure change when a typhoon hits the air dome. It collects the operating data of the air dome and sets the most suitable differential pressure range to operate autonomously according to changes in external force. As the external force increases, the pressure inside the air dome changes as well, so the pressure setting range is changed according to the change. can be driving

)를 기준으로 범위값 ±β를 벗어나게 되면 설정된 압력값 α가 상승되고 상승된 압력값 α에 범위값 ±β가 새로운 범위폭을 가지고 운전될 때, 설정 최대의 압력값 α가 되면 더 이상 상승하지 않는데 이 최대 압력값 α는 설계 당시 지역 계수의 하중조건을 고려하여 설정될 수 있다.The differential pressure stabilization determination is based on how far the DP (Differential Pressure) ± range value deviates from the set pressure value measured by a plurality of differential pressure sensors, the initially set pressure value α (

), the set pressure value α rises when it deviates from the range value ±β based on the However, this maximum pressure value α can be set in consideration of the load conditions of local coefficients at the time of design.

At this time, the formula for the range of the set point operating pressure value α is input considering (α+nβ)±β according to the nth order (0 to n), and then the formula for automatic operation is as shown in Equation 3 below.

[Equation 3]

는 실내와 실외 압력 차 Pa, C는 conversion factor 1 Pa.m.sec²/kg,

는 대기 온도에 따른 공기 밀도 kg/m³, g는 중력상수, 9.8kg/sec², H는 설계 높이 이상 m,

는 neutral 압력에 따른 설계 높이m, T_i는 실내 온도, T_o는 외기 온도이다.here,

is the difference between indoor and outdoor pressure Pa, C is the conversion factor 1 Pa.m.sec ² /kg,

where is the air density according to the air temperature kg/m ³ , g is the gravitational constant, 9.8 kg/sec ² , H is the design height, m,

is the design height m according to the neutral pressure, T _i is the room temperature, and T _o is the outside air temperature.

Referring to FIG. 9, FIG. 9(a) shows a flow rate graph according to PID control (proportional integral control). Existing PID control causes a delay in reaching the objective function due to the occurrence of overshoot. Therefore, the MPC controller is used to suppress the occurrence of overshoot through prediction in advance, and to reach the objective function according to the natural increase or decrease. .

9(b) shows a [MPC (Model Predictive Control) flow rate graph. The MPC control of the present invention is an AI-MPC that selects PMV from a sensor representing the operation of an external air sensor and an INPLATION FAN, creates a predictive model, and according to the set point value, predictive control as shown in Equation 4 below. implement a control strategy.

[Equation 4]

At this time, as the floor area of the airdome, h is the height of the airdome and the outlet flow, v1 is the outdoor air inlet opening level, g is the gravitational acceleration, and the blower is linear qin ~ N, where N is the rotational speed of the blower.

In the linear and discrete process of the air dome system, Ts is a time step, and since the controller must be able to work at various opening levels, the last time step is linearized as in Equation 5 below in hn-1.

[Equation 5]

Accordingly, a prediction model as shown in Equation 6 below can be obtained based on Equations 4,5.

[Equation 6]

Equation 6 is derived through the obtained control rule and objective function. The objective function is determined by the prediction and the value representing the linearity in the control, and the objective function is changed by recalculation by the controller every time. At this time, MPC tuning is selected in consideration of appropriate values, Hc, Hp, λ, and the like.

Referring back to FIG. 8, when the differential pressure is stabilized after step S840 (YES in S840), the air dome autonomous driving system may verify the stabilization state (S860). In this case, the air dome autonomous driving system may verify the stabilization state of the air dome autonomous driving system based on the differential pressure sensor data and the snow load sensor data.

On the other hand, after the step S840, if the differential pressure is not stabilized (NO in S840), the air dome autonomous driving system re-receives the differential pressure sensor data (S850), reconfirms the received differential pressure data (S852), and the air dome ( 110) check items (open/closed state of the door, whether there is an abnormality in the pressure fan, close the damper) (S854), and it may be determined whether the differential pressure in the air dome 110 is stabilized (S856).

After the step S856, when the differential pressure is not stabilized (NO in S856), the air dome autonomous driving system may perform the autonomous driving of the pressurized fan in the emergency operation mode (S858). After the step S858, the air dome autonomous driving system may re-receive the differential pressure sensor data (S850).

Meanwhile, after the step S856, when the differential pressure is stabilized (YES in S856), the air dome autonomous driving system may verify the stabilization state based on data received from the differential pressure sensor and the wind speed sensor (S860). In the air dome autonomous driving system, to know the force of the load against the external force of the air dome, the measured value of the differential pressure sensor alone cannot accurately determine how large the load was applied to the air dome, so the data from the wind speed sensor refers to the size of the transmitted load. data can be applied.

At this time, the formula for calculating the wind speed of the air dome surface is as Equation 4 below.

[Equation 4]

,

,

는 실외 정압 압력,

는 무차원 바람의 표면 압력 0.5~0.8, C는 conversion factor 0.04 Pam³/kg.mps²,

는 외기 공기 밀도 kg/m³, s는 shelter factor 0.4,

는 풍속 mps(m/s) 이다.here,

is the outdoor static pressure,

is the surface pressure of the dimensionless wind 0.5~0.8, C is the conversion factor 0.04 Pam ³ /kg.mps ² ,

where is the outdoor air density kg/m ³ , s is the shelter factor 0.4,

is the wind speed in mps (m/s).

After the step S860, the air dome autonomous driving system may store driving record data in a stable state and data of each IOT sensor in the air dome, and learn the stored data and weather API (S870).

Although it is impossible to accurately predict the rapidly changing climate, the air dome autonomous dome autonomous driving system can perform intelligent automatic control learned based on historical external force data, weather API data, and real-time collected data.

After the step S870, the air dome autonomous driving system may perform autonomous driving in a normal driving mode (S880).

10 is a view for explaining a method for autonomous driving of an air dome during heavy snow driving according to an embodiment of the present invention.

Referring to FIG. 10 , when the air dome autonomous driving system is autonomously driving in the normal driving mode ( S1010 ), the air dome autonomous driving system may detect a differential pressure change according to pressure data inside the air dome ( S1020 ).

After the step S1020, the air dome autonomous driving system may collect object data in the air dome 110 (S1022). In this case, the object data may be data received from a differential pressure sensor, a snow depth sensor, and a snow sensor.

After the step S1022, the air dome autonomous driving system may monitor the operation of the snow melting device and collect snow data (S1024), and operate the snow melting device based on the received snow measurement data (S1026).

After the step S1026, the air dome autonomous driving system may re-measure the snow sensor according to the operation of the snow melting device (S1028). After the step S1028, the air dome autonomous driving system may re-receive the differential pressure sensor data (S1050).

On the other hand, after the step S1020, the air dome autonomous driving system may control the pressure fan in the air dome 110 to autonomously operate based on the differential pressure change (S1030). In this case, the autonomous operation of the pressure fan may be operated by MPC control of the INFLATION 155 .

After the step S1030, the air dome autonomous driving system may determine whether the pressure difference in the air dome 110 according to the autonomous driving of the pressurized fan is stabilized (S1040).

After the step S1040, when the differential pressure is stabilized (YES in S1040), the air dome autonomous driving system may verify the stabilization state (S1060). In this case, the air dome autonomous driving system may verify the stabilization state of the air dome autonomous driving system based on the differential pressure sensor data and the snow load sensor data.

On the other hand, after the step S1040, if the differential pressure is not stabilized (NO in S1040), the air dome autonomous driving system re-receives the differential pressure sensor data (S1050), reconfirms the received differential pressure data (S1052), and the air dome ( 110) check items (open/closed state of the door, whether there is an abnormality in the pressurized fan, close the damper) (S1054), and it can be determined whether the differential pressure in the air dome 110 is stabilized (S1056).

After the step S1056, when the differential pressure is not stabilized (NO in S1056), the air dome autonomous driving system may perform the autonomous driving of the pressurized fan in the emergency operation mode (S1058). After the step S858, the air dome autonomous driving system may re-receive the differential pressure sensor data (S1050).

Meanwhile, when the differential pressure is stabilized after the step S1056 (YES in S1056), the air dome autonomous driving system may verify the stabilization state based on data received from the differential pressure sensor and the snow load sensor (S1060). Since the air dome autonomous driving system does not know exactly how large the load was applied to the air dome only with the measured value of the differential pressure sensor in order for the air dome to know the force of the load against the external force, the data from the snow cover sensor is referred to the size of the transmitted load data can be applied.

After the step S1060, the air dome autonomous driving system may store driving record data in a stable state and data of each IOT sensor in the air dome, and learn the stored data and weather API (S1070).

After the step S1070, the air dome autonomous driving system may perform autonomous driving in a normal driving mode (S1080).

11 is a view for explaining an autonomous driving method when an air dome is operated during an indoor air quality improvement operation according to an embodiment of the present invention.

Referring to FIG. 11 , when the air dome autonomous driving system is autonomously driving in the normal driving mode (S1110), the air dome autonomous driving system may detect a change in indoor air quality inside the air dome (S1120).

After the step S1120, the air dome autonomous driving system may operate the air cleaning system in response to the sensed indoor air quality (S1130). In this case, the air cleaning system may operate a photoplasma.

After the step S1130, the air dome autonomous driving system may perform autonomous driving of the pressurized fan and the HVAC fan (S1140).

After the step S1140, the air dome autonomous driving system may perform differential pressure change detection and filter differential pressure detection (S1150).

After the step S1150, the air dome autonomous driving system may determine whether to drive as the first type (Type1) according to the indoor air quality check result (S1160)

After step S1160, if it is possible to drive in the first type (YES in S1160), the air dome autonomous driving system operates with the return air exhaust damper in a closed state, the return air blocking damper in an open state, the outside air intake damper in a closed state, and air The purification and sterilization device may be operated in an operating state (S1170).

After the step S1170, the air dome autonomous driving system may determine whether the indoor air quality is in a normal state (S1180).

On the other hand, after the step S1160, when it is impossible to drive in the first type (NO in S1160), the air dome autonomous driving system is set to the second type (Type 2), and the return air exhaust damper is opened in an open state, and the return air is blocked. It is possible to operate the damper in the closed state, the outdoor air intake damper in the open state, and the air purification and sterilization device in the operating state (S1175).

After the step S1175, the air dome autonomous driving system may determine whether the indoor air quality is in a normal state (S1180).

After the step S1180, when the indoor air quality is not normal (NO in S1180), the air dome autonomous driving system may determine whether it is acceptable to drive as the first type (Type1) according to the indoor air quality check result (S1160). )

Meanwhile, after the step S1180, when the indoor air quality is normal (YES in S1180), the air dome autonomous driving system may operate in the first type (Type1) while maintaining the HVAC operation (S1190).

After the step S1190, the air dome autonomous driving system may perform a normal operation (S1195).

12 is a view for explaining a method for autonomous driving of an air dome when a fire occurs according to an embodiment of the present invention.

Referring to FIG. 12 , when the air dome autonomous driving system is autonomously driving in the normal driving mode (S1210), the air dome autonomous driving system may receive fire detection data inside the air dome (S1220). The fire detection data may include flame detection data and smoke detection data.

After the step S1220, the air dome autonomous driving system determines the level of fire detection itself (S1222), and if the risk level is higher than or equal to a preset level (S1224), the manager and the central center emergency alarm can be operated (S1226). ).

On the other hand, after the step S1220, the air dome autonomous driving system operates the fire alarm alarm in the air dome 110 (S1230), turns on the emergency evacuation light (S1232), and operates the fire extinguishing device ( S1234).

After the step S1234, the air dome autonomous driving system may determine whether the fire situation is released (S1240).

After the step S1240, when the fire situation is released, the air dome autonomous driving system may verify the stabilization state of the air dome autonomous driving system based on the fire detection data (S1250).

After the step S1250, the air dome autonomous driving system may operate the indoor air quality purification system after detecting toxic substances and harmful gases (S1252).

In addition, after the step S1250, the air dome autonomous driving system may store driving record data in a stable state and data of each IOT sensor in the air dome, and learn the stored data and the weather API (S1260).

After the step S1260, the air dome autonomous driving system may perform autonomous driving in a normal driving mode (S1270).

13 is a diagram for explaining an AI learning algorithm according to autonomous driving of an air dome according to an embodiment of the present invention.

Referring to FIG. 13 , the air dome autonomous driving system may perform data pre-processing based on data received from the IoT sensor ( S1410 ).

After the step S1410, the air dome autonomous driving system may perform Assign Input and Targets (S1420).

After the step S1420, the air dome autonomous driving system may perform data normalization (S1430).

After the step S1430, the air dome autonomous driving system may perform iterative calculations for acquiring the target model (S1340).

After the step S1340, the air dome autonomous driving system may determine whether the target repetition for the repetition calculation is less than a preset number (S1350).

After the step S1350, when the iteration count is less than the preset number, the air dome autonomous driving system may apply the increment of the repetition target to a specific function of the learning network (S1360).

After the step S1360, the air dome autonomous driving system may calculate the fitness G based on the network weight and the bias record (S1362, S1364).

After step S1364, the air dome autonomous driving system may determine whether the calculated value of fitness G exceeds the optimal fitness value (S1370).

After the step S1370, when the calculated value of fitness G does not exceed the optimal fitness value (NO in S1370), the air dome autonomous driving system may determine whether the target repetition for repeated calculation is less than a preset number (S1350). ).

Meanwhile, after step S1370, when the calculated value of fitness G exceeds the optimal fitness value (YES in S1370), the air dome autonomous driving system may record the value of fitness G as the best network weight (S1380). .

In the above, the preferred embodiment of the present invention has been mainly described, but this is merely an example and does not limit the present invention. Those of ordinary skill in the art to which the present invention pertains can variously modify and change the embodiments by adding, changing, deleting or adding components within the scope that does not depart from the technical spirit of the present invention described in the claims. It will be possible, and this will also be included within the scope of the present invention.

110: air dome
120: dashboard
130: database server
140: monitoring control system
155: INFLALTION system (pressurization system)
150: HVAC system
160: sensor network
170: actuator network
180: weather forecast provider
410: input device
410: process device
410: output device
510: MPC framework
710: supervisory MPC controller

Claims (8)

In the air dome autonomous driving system,
an input device for receiving external force data acting on the outside of the air dome and monitoring data from the IoT sensor disposed inside the air dome;
a process device for performing autonomous driving control based on weather forecast information, the monitoring data, and autonomous driving learning data stored in a database; and
an output device including an air conditioning system operating based on the autonomous driving control;
The process device is
When the air dome is in the normal driving mode during autonomous driving,
Receive the differential pressure change information to determine the differential pressure change,
controlling the air conditioning system according to a model predictive control corresponding to the differential pressure change;
determining whether the differential pressure in the air dome is stabilized in response to the control of the air conditioning system;
verifying the differential pressure stabilization state in the air dome,
An air dome autonomous driving system, characterized in that it stores autonomous driving data according to a change in differential pressure, and performs learning based on the stored autonomous driving data.
The method of claim 1,
The external force is
Air dome autonomous driving system, characterized in that it includes at least one of heavy snow, typhoon, earthquake, and air pollution.
3. The method of claim 2,
The monitoring data is
The air dome autonomous driving system comprising at least one of the differential pressure change information, air quality change information, and fire detection data.
delete In the autonomous driving method implemented in the air dome autonomous driving system,
Receiving external force data acting on the outside of the air dome and monitoring data from an IoT sensor disposed inside the air dome;
performing autonomous driving control based on weather forecast information, the monitoring data, and external force data learned in a database; and
operating an air conditioning system based on the autonomous driving control;
The autonomous driving control
when the air dome is in a normal driving mode during autonomous driving, receiving differential pressure change information and determining a differential pressure change;
controlling the air conditioning system according to a model predictive control corresponding to the differential pressure change;
determining whether the differential pressure in the air dome is stabilized according to the HVAC system control;
verifying a differential pressure stabilization state in the air dome; and
Storing data according to autonomous driving, and performing learning based on the stored autonomous driving data.
Air dome autonomous driving method.
6. The method of claim 5,
The external force is
Air dome autonomous driving method comprising at least one of heavy snow, typhoon, earthquake, and air pollution.
7. The method of claim 6,
The monitoring data is
at least one of the differential pressure change information, air quality change information, and fire detection data
Air dome autonomous driving method comprising the.




delete

Images