KR102481577B1 - Control method and system for efficient energy consumption and fish growth - Google Patents

Abstract

The present invention relates to a control method and system for optimizing fish growth and energy efficiency. a data collection step of collecting internal environment parameters from sensors and external environment parameters from external devices; Data prediction step of pre-processing and dividing the data to calculate predicted environment parameters predicting the environment in the aquarium: Data optimization to calculate optimal growth environment parameters for optimizing the environment in the aquarium using the predicted environment parameters step; and an environment control step of controlling the environment in the aquarium by operating an actuator installed in the aquarium using the predicted environment parameter and the optimal growth environment parameter.

Description

Control method and system for optimizing fish growth and energy efficiency {CONTROL METHOD AND SYSTEM FOR EFFICIENT ENERGY CONSUMPTION AND FISH GROWTH}

The present invention relates to a control method and system for optimizing fish growth and energy efficiency, and more particularly, fish growth and energy efficiency that can provide effective management of resources and energy in an aquarium while appropriately maintaining a fish growth environment. It relates to a control method and system for optimization.

Humanity must overcome the formidable challenge of providing food and livelihoods to over 9 billion people by 2050 due to the impacts of climate change, natural disasters and environmental degradation on natural resources.

The State of World Fisheries and Aquaculture (SOFIA) announced that fish production in 2016 reached an all-time high of 176 million tonnes, with 88% of this fish production consumed.

As such, today fish and fish products are among the most traded foods in the world. According to 2016 statistics, nearly 35% of global fish production is in international trade for direct human consumption or non-food purposes.

However, fish populations can easily decline if fish are caught in larger quantities at a faster rate, making it difficult for fish to reproduce. Over the past 40 years, fish stocks have halved compared to 1970. This increasing pressure on the ocean can upset the ecological balance of the ocean. In order to solve these problems, international organizations, societies, institutions, researchers and individuals must strive to find practical and efficient solutions.

One such solution is the aquaculture industry, which is one of the most productive and prolific concepts that has grown significantly worldwide over the past few years.

Aquaculture is the farming (farming, harvesting and propagation) of fish, shellfish or aquatic plants using brackish, fresh or seawater. Currently, 194 out of 202 countries have an active aquaculture industry. The contribution of aquaculture to global aquaculture and aquaculture production has steadily increased, reaching 46.8% in 2016, an increase of more than 20% compared to 2000.

In general, aquariums can produce fish efficiently, create new types of jobs, and have the advantage of being economical and can be installed anywhere.

However, in aquariums, waste reduction, reuse and recycling are possible, but problems such as lack of water sources, occurrence of diseases, difficulty in management, and flood damage may occur.

According to a report by the Sustainable Fisheries Partnership Foundation (SFP), about 40% of farms are poorly managed and are known to produce fish products infected with the virus.

Therefore, there is an increasing demand for a smart aquarium system capable of systematically and efficiently managing the aquarium.

The present invention was made to solve the above problems, and the present invention aims to achieve minimum energy consumption and maximum fish growth and healthy fish productivity in an actuator by providing optimal environmental parameters in an aquarium.

In addition, the present invention aims to provide an optimal fish growth environment with minimum energy consumption through an embedded machine learning technology based on an optimal embedded control platform for efficient energy consumption and fish growth in an aquarium.

An aquarium environment control method using an aquarium environment control system according to an embodiment of the present invention for solving the above problems is to collect internal environment parameters from sensors installed in the aquarium and external environment parameters from external devices. data collection step; Data prediction step of pre-processing and dividing the data to calculate predicted environment parameters predicting the environment in the aquarium: Data optimization to calculate optimal growth environment parameters for optimizing the environment in the aquarium using the predicted environment parameters step; and an environment control step of controlling the environment in the aquarium by operating an actuator installed in the aquarium using the predicted environment parameter and the optimal growth environment parameter.

According to another embodiment of the present invention, the data prediction step uses an Artificial Neural Network (ANN) or a mathematical Kalman Filter-based prediction module to determine the temperature, PH, conductivity, and water level in the aquarium. The corresponding optimal growth environment parameters can be calculated.

According to another embodiment of the present invention, in the data optimization step, optimal growth environment parameters for optimizing the environment in the aquarium may be calculated based on user set values and system constraints.

According to another embodiment of the present invention, in the data optimization step, an environmental optimization index in the aquarium may be calculated using an objective function of the following equation.

[mathematical expression]

J = max(α _EC (1-(EC*) ² ) + α _OE (1-(OE*) ² )

(At this time, J is the environmental optimization index in the aquarium, α _EC is the target weight of energy consumption, α _OE is the target weight of the optimal growth environment, EC * = (EC - EC ^min ) (EC ^max -EC ^min ), OE * = (OE - OE ^min )(OE ^max -OE ^min ), EC is the actuator's energy consumption value, EC ^min is the actuator's minimum energy consumption value, EC ^max is the actuator's maximum energy consumption value, OE is the optimal growth environment value, OE ^min is the minimum value of the optimal growth environment, and OE ^max is the maximum value of the optimal growth environment.)

According to another embodiment of the present invention, the environment control step uses a Fuzzy Logic Control (FLC) module to determine the operating level and the operating level of the actuator using the predicted environment parameter and the optimum growth environment parameter. The environment in the aquarium can be controlled by controlling the time.

According to another embodiment of the present invention, the data collection step includes user-desired parameters, indoor environmental parameters, outdoor environmental parameters, and energy driven parameters. Control parameters and power policy variables may be collected. A control system for optimizing fish growth and energy efficiency according to an embodiment of the present invention collects internal environmental parameters from sensors installed in an aquarium, and collects external parameters. a data collection unit that collects external environmental parameters from the device; A data prediction unit that preprocesses and divides the data collected by the data collection unit to calculate a predicted environmental parameter that predicts the environment in the aquarium: an optimal growth environment parameter that optimizes the environment in the aquarium using the predicted environment parameter a data optimization unit that calculates variables; and an environment control unit controlling the environment in the aquarium by operating an actuator installed in the aquarium using the predicted environment parameter and the optimal growth environment parameter.

According to another embodiment of the present invention, the data prediction unit corresponds to the temperature, PH, conductivity, and water level in the aquarium by using an artificial neural network (ANN) or a mathematical Kalman filter-based prediction module. The optimal growth environment parameters can be calculated.

According to another embodiment of the present invention, the data optimization unit may calculate an optimal growth environment parameter for optimizing the environment in the aquarium based on a user's set value and system constraints.

According to another embodiment of the present invention, the data optimization unit may calculate an environmental optimization index in the aquarium using an objective function of the following equation.

[mathematical expression]

J = max(α _EC (1-(EC*) ² ) + α _OE (1-(OE*) ² )

(At this time, J is the environmental optimization index in the aquarium, α _EC is the target weight of energy consumption, α _OE is the target weight of the optimal growth environment, EC * = (EC - EC ^min ) (EC ^max -EC ^min ), OE * = (OE - OE ^min )(OE ^max -OE ^min ), EC is the actuator's energy consumption value, EC ^min is the actuator's minimum energy consumption value, EC ^max is the actuator's maximum energy consumption value, OE is the optimal growth environment value, OE ^min is the minimum value of the optimal growth environment, and OE ^max is the maximum value of the optimal growth environment.)

According to another embodiment of the present invention, the environment control unit uses a fuzzy logic control (FLC) module to determine the operation level and time of the actuator using the predicted environment parameter and the optimal growth environment parameter. It is possible to control the environment in the aquarium by controlling.

According to another embodiment of the present invention, the data collection unit user-desired parameters, indoor environmental parameters, outdoor environmental parameters, energy control parameters parameters) and power policy variables (Power Policy) can be collected.

The present invention can achieve minimum energy consumption and maximum fish growth and healthy fish productivity in the actuator by providing optimal environmental parameters for the aquarium.

In addition, the present invention can provide an optimal fish growth environment with minimal energy consumption through an embedded machine learning technology based on an optimal embedded control platform for efficient energy consumption and fish growth in an aquarium.

1 is a diagram showing a control system for optimizing fish growth and energy efficiency according to an embodiment of the present invention.
2 is a diagram for explaining a control method for optimizing fish growth and energy efficiency according to an embodiment of the present invention.
3 is a diagram for explaining in detail a control method for optimizing fish growth and energy efficiency according to an embodiment of the present invention.
4 is a diagram for explaining a prediction method for optimizing fish growth and energy efficiency according to an embodiment of the present invention.
5 is a diagram for explaining a method for controlling the environment of an aquarium through fuzzy logic control (FLC) according to an embodiment of the present invention.
6 is a graph showing the working level of actuators having the same rated power (watts) according to an embodiment of the present invention.
7 is a graph of membership function according to actuator operation time according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings, a preferred embodiment of the present invention will be described in detail. However, in describing the embodiments, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present invention, a detailed description thereof will be omitted. In addition, the size of each component in the drawings may be exaggerated for description, and does not mean a size that is actually applied.

1 is a diagram showing a control system for fish growth and energy efficiency optimization according to an embodiment of the present invention, and FIG. 2 describes a control method for fish growth and energy efficiency optimization according to an embodiment of the present invention. It is a drawing for

As shown in FIG. 1, the control system for optimizing fish growth and energy efficiency according to the present invention is an environmental control system for a smart aquarium and includes various layers with different functions. More specifically, these layers may consist of environment, IoT device, gateway, network, application and server layers.

Environmental parameters are collected and controlled through sensors and actuators.

The IoT gateway layer acts as a bridge between embedded devices, servers and applications. The IoT gateway layer also controls several processes, such as sensing data, temperature, pH, water and conductivity level control processes.

Users can connect to the environment and servers using a user-friendly application via the Internet, and the system that can control the aquarium's environment is composed of servers to include data collection, data preprocessing, prediction, optimization and control modules. can be configured.

According to the present invention, there are internal environment parameters and external environment parameters of the system. The internal parameters include water temperature, pH, conductivity and water level, and the external environmental parameters are solar radiation, temperature, wind speed and humidity.

These variables can be used as input data to prediction modules based on artificial neural networks (ANNs) or mathematical Kalman filters to predict temperature, pH, conductivity and water level variables to control water quality in aquariums. do.

According to the predicted environmental parameters, user-desired settings and system constraints, the objective function-based optimization module calculates the most optimal environmental parameters with efficient energy consumption.

In addition, the fuzzy logic control module calculates the actuator's operating level and operating duration for optimum environmental parameter control.

The logic of fuzzy control is based on IF-THEN, such that if the predicted temperature is lower than the optimum temperature, the heater is activated and increases the water temperature. If the expected temperature is higher than the optimum temperature, the chiller is activated and reduces the temperature to the optimum point. The heater and cooler actuators are deactivated when the expected temperature is within the optimum user desired range.

The same control method is applied to the control of pH, conductivity and water level parameters through actuators.

Referring to FIG. 2 , as a data collection step, internal environmental parameters are collected from sensors installed in the aquarium, and external environmental parameters are collected from external devices.

Thereafter, as a data prediction step, data may be predicted by calculating predicted environmental parameters that predict the environment in the aquarium using the collected data.

More specifically, in this process, the data may be predicted by pre-processing and dividing the data to calculate predicted environmental parameters predicting the environment in the aquarium.

At this time, in the data prediction step, the optimal growth environment parameters corresponding to the temperature, PH, conductivity, and water level in the aquarium are obtained by using an artificial neural network (ANN) or a mathematical Kalman filter-based prediction module. can be calculated.

Then, as a data optimization step, optimal growth environment parameters for optimizing the environment in the aquarium are calculated using the predicted environment parameters.

More specifically, in the data optimization step, optimal growth environment parameters for optimizing the environment in the aquarium may be calculated based on user set values and system constraints.

Thereafter, as an environment control step, an actuator installed in the aquarium is operated to appropriately control the environment in the aquarium using the predicted environment parameter and the optimal growth environment parameter. At this time, in the environment control step, fuzzy logic Using a control (FLC: Fuzzy Logic Control) module, the operation level and time of the actuator are controlled using the predicted environment parameters and the optimal growth environment parameters to appropriately control the environment in the aquarium according to the growth of fish. can

For such environment control, Apache HTTP Server can be configured and used by using MySQL database as an environment control module. Apache is an open-source, free web server software developed and maintained by the Apache Software Foundation. It can connect a server and a user by passing a response file or text according to the user's request.

Apache is a request/response protocol for collaborative, distributed and hypermedia information systems using HTTP for communication and information change, which can provide reliable and efficient communication between clients, IoT devices and servers.

3 is a diagram for explaining in detail a control method for optimizing fish growth and energy efficiency according to an embodiment of the present invention.

Referring to FIG. 3, in the data collection step, user-desired parameters, indoor environmental parameters, outdoor environmental parameters, energy control parameters, and power You can collect policy variables (Power Policy).

At this time, the user-desired parameter is a value set by the user to be most suitable for the environment, and the user can set the minimum and maximum temperature, water level, pH level, or conductivity level most suitable for fish growth.

The Indoor Environmental parameters are data collected from water level sensors with temperature, ph level, conductivity and time-series data collected from the aquarium.

In addition, the outdoor environmental parameters are temperature, humidity, and solar radiation, and the performance of the prediction model can be improved, because when the outside temperature is low, the inside temperature can also be affected.

The energy control parameters represent an operation level and an activation duration as control values of the actuator, and power consumption can be controlled by controlling the operation level and operation time.

The power policy variable corresponds to the energy consumption price of the actuator.

Thereafter, in the data prediction step, data may be predicted by calculating predicted environmental parameters that predict the environment in the aquarium using the collected data.

Thereafter, in the data optimization step, optimal growth environment parameters for optimizing the environment in the aquarium are calculated using the predicted environment parameters.

Thereafter, in the environmental control step, the user-desired parameter, the indoor environmental parameters, the outdoor environmental parameters, the energy control parameters, and the The environment in the aquarium may be controlled by operating an actuator installed in the aquarium using a power policy variable.

4 is a diagram for explaining a prediction method for optimizing fish growth and energy efficiency according to an embodiment of the present invention, and describes an ANN-based prediction module according to the present invention.

ANN algorithms are general purpose learning algorithms and are widely used to solve a wide range of problems such as classification, pattern recognition, regression, time series data processing, and forecasting.

In the optimal aquarium environment control method according to the present invention, temperature, pH, conductivity, and water level are predicted using an ANN-based prediction module.

As shown in FIG. 4, according to the present invention, various external environmental parameters (solar radiation, external temperature, wind speed, humidity) and internal environmental sensing parameters of the fish farm/aquarium ( water temperature, pH level, conductivity, and water level) can be used, and the ANN algorithm can provide the predicted temperature, predicted pH level, predicted conductivity, and predicted water level.

The ANN-based prediction module according to the present invention may execute a data collection process, a data preparation process, a data segmentation process, and a prediction process.

In the data collection process, internal environmental parameters can be collected using temperature, pH, conductivity, and water level sensors installed in the actual water tank, and external environmental parameters can be provided from a separate weather server.

The data collected in this way includes measurements and units of measure such as °C, acid level, μS/cm, %. In the data preparation process, these measurement units were removed and missing data was filled in using data from one step earlier. In general, there is no significant difference in environmental values between the current data and the previous data.

Also, in the data segmentation process, 70% of the data was used for training and the remaining 30% was used for testing the ANN algorithm.

The data prediction process predicts the tank's temperature, pH level, conductivity and water level based on internal and external environmental input parameters.

Since ANN is a powerful modeling technique that can accurately predict non-linear and complex processes of fish environment prediction, ANN was applied considering the non-linear characteristics of aquarium parameters.

Hereinafter, as a data optimization method according to an embodiment of the present invention, a method of calculating optimal growth environment parameters for optimizing the environment in the aquarium using predicted environmental parameters will be described in more detail.

According to the present invention, an objective function is used to maximize fish environmental parameters while efficiently consuming energy based on predicted values, user-desired settings, and system constraints.

According to the present invention, T, pH, C and W represent water temperature, pH level, conductivity and water level, respectively. In addition, the aquarium environment management time is assumed to be one day, a day is divided into T time slots and each slot duration is considered to be 15 minutes, so a day is divided into T = 96 slots.

Table 1 below is for explaining the formula of the present invention.

Notation Description T number of time slots SD Slot Duration (minutes) EP environment parameters T _p , pH _p , C _p , W _p Predicted environmental parameters T _d , pH _d , C _d , W _d Desirable environmental parameters of the aquarium T ^min , pH ^min , C ^min , W ^min Minimum range of desired environmental parameters T ^max , pH ^max , C ^max , W ^max Maximum range of desired environmental parameters T ^opt , pH ^opt , C ^opt , W ^opt Optimal level of environmental parameters EC Energy consumption for actuators (heaters, coolers, water pumps, pH and conductivity controllers) OE Optimal growth environment α _EC, α _OE Target Weight of Energy Consumption and Optimal Growth Environment EC ^min Total energy consumption in the desired minimum parameter range EC ^max Total energy consumption with the desired maximum parameter range EC ^opt Optimal energy consumption with optimal environmental parameters g _max Maximum range between predicted and desired environment variables gr Range of predicted and desired environment variables at time t A ^max Actuator's maximum working level (requires fewer time slots and higher energy consumption) A ^min Minimum operating level of the actuator (more time slots and less energy consumption)

The predicted environmental parameters for the aquarium are shown in Equation 1 below.

[Equation 1]

EPF _p = [T _p , pH _p , C _p , W _p ]

Here, Tp, pHp, Cp, and Wp are the predicted temperature, pH, conductivity, and water level using the ANN-based prediction model.

For each value, the user can set a very desirable range of values for the aquarium environment parameter as shown in Equation 2 below.

[Equation 2]

EPF _d = [T _d , pH _d , C _d , W _d ]

The setting value desired by the user is allowed in Equation 3 below for the minimum and maximum ranges of each parameter.

[Equation 3]

T _d = [T ^min , T ^max ]

pH _d = [pH ^min , pH ^max ]

C _d = [C ^min , C ^max ]

W _d = [W ^min , W ^max ]

Based on your desired range, the maximum value will result in the best settings for your environment, and the minimum value will be the best value for your environment parameters.

Assume optimal environmental parameters at time t at which the desired environmental setting can be achieved as shown in Equation 4 below.

[Equation 4]

EPF ^opt = [T ^opt , pH ^opt , C ^opt , W ^opt ]

The optimal value is between the minimum range and the maximum range desired by the user as shown in Equation 5 below.

[Equation 5]

[T^min, T^max]T ^opt

[T ^min , T ^max ]

[pH^min, pH^max]pH ^opt

[pH ^min , pH ^max ]

[C^min, C^max]C ^opt

[C ^min , C ^max ]

[W^min, W^max]W ^opt

[W ^min , W ^max ]

As in Equation 6 below, the objective function considers two of the total energy consumption (EC) introduced into the aquarium and the optimum growth environment (CC).

The total energy consumption can be calculated according to the energy consumption of the actuator, the time and work level and the operating period. Using the minimum operating level of the actuator consumes less energy but requires more operating period to achieve the optimum condition. .

[Equation 6]

_heat ^min +

_cooler ^min+

_pump ^min

_pHCont. ^min+

_{conductcontr.} ^min EC ^min =

_heat ^min +

_cooler ^min +

_pump ^min

_pHCont. ^min +

_{conduct control.} ^min

Actuators at their maximum working level consume more energy but require less operating duration to achieve optimal conditions.

[Equation 7]

_heat ^max +

_cooler ^max+

_pump ^max

_pHCont. ^max+

_{conductcontr.} ^max EC ^max =

_heat ^max +

_cooler ^max

_pump ^max

_pHCont. ^max +

_{conduct control.} ^max

OE of Equation 8 means an environment optimized for an aquarium in a stable environment.

[Equation 8]

*A

*A

At this time, gr describes the range between the predicted environmental parameter range and the desired environmental parameter range at time t.

A suitable environment within a farm or aquarium depends on the operating level and duration of the actuator.

Running the heater actuator at its minimum operating level introduces a time lag in achieving the optimal environment and gmax (the maximum range between actual and desired levels for each aquarium parameter).

Equation 8 above explains the climatic suitability according to the minimum and maximum operating levels of the actuator.

Actual input parameters are classified into three categories 'low, medium and very high' according to the level of the actual input parameters, each requiring different times and operating cycles to achieve an optimal environment.

For example, if the actual temperature level is low, the heater should be activated. When the heater is activated to its maximum operating level, it takes 3-time slots to achieve an optimal environment.

When the heater is activated to a minimum operating level, the actuator takes 4 time slots to achieve optimal environmental parameters as shown in Equation 9 below. The same applies to other actuators.

[Equation 9]

+

*A_heat ^min OE ^min =

+

*A _heat ^min

+

*A_heat ^max OE ^max =

+

*A _heat ^max

Here, gr denotes a range between the predicted environmental parameter range and the desired environmental parameter range at time t.

[Equation 10]

_heat ^min +

_cooler ^min+

_pump ^min

_over ^min OE ^min =

_heat ^min +

_cooler ^min +

_pump ^min

_over ^min

_heat ^max +

_cooler ^max+

_pump ^max

_over ^max OE ^max =

_heat ^max +

_cooler ^max

_pump ^max

_over ^max

The objective function is a convex combination of the two cost indices of Equation 10, and is expressed as Equation 11 below.

[Equation 11]

EC* = (EC - EC ^min )(EC ^max -EC ^min )

OE* = (OE - OE ^min )(OE ^max -OE ^min )

Here, EC ^min , EC ^max , OE ^min , and OE ^max represent the minimum and maximum values achievable in energy consumption (EC) and optimal environment (OE).

The final objective function to be maximized is expressed as in Equation 12 below.

[Equation 12]

J = max(α _EC (1-(EC*) ² ) + α _OE (1-(OE) ² )

At this time, J is the environmental optimization index in the aquarium, T _a <T _d ^min <T ^opt <T _d ^max , W _a <W _d ^min <W ^opt <W _d ^max , 0 <EC ^min <EC ^opt <EC ^max , 0 <CC _min <CC ^opt <CC ^max .

On the other hand, when controlling the environment of the aquarium according to the present invention, a Fuzzy Logic Control (FLC) module is used to control the operation level and time of the actuator using the predicted environment parameters and the optimal growth environment parameters. The environment in the aquarium can be controlled.

5 is a diagram for explaining a method for controlling the environment of an aquarium through fuzzy logic control (FLC) according to an embodiment of the present invention.

Hereafter, referring to FIG. 5 , an environment control method using a fuzzy logic control (FLC) module will be described in detail.

The basis of fuzzy control is fuzzy logic, which is closer to human thinking and natural language than conventional control methods. there is.

The predicted and optimized environmental parameters are the input variables of the fuzzy logic control (FLC) module, whereas the output variables are the operating level and operating time of the actuator.

The fuzzy logic control (FLC) module consists of three essential components: fuzzification, inference mechanism, and defuzzification.

As the first component, the actual input parameters are converted into language parameters; as the second component, the inference engine uses "IF-THEN" rules to find the verbal output for the specific conditions of the decision problem; and as the third component, As in defuzzification, linguistic variables are converted to numeric parameters.

Since each linguistic variable is linked to a confidence variable, each has its own confidence value. The input parameters to the fuzzy system are predicted and optimized levels of temperature, pH, conductivity and water level sensing data, and the fuzzy logic control (FLC) module determines the most desirable operating level and operation for the actuator based on the predicted and optimized sensing values. time can be calculated.

In the purge process, all input and output parameters of the system are converted into fuzzy language variables, where 1) expected temperature, pH, conductivity and water level (very low, medium, high, very high) as input variables, 2 as input variables. ) with optimized temperature, pH, conductivity and water level (optimum), as output variables 3) actuator operating level (minimum, medium and maximum), also as output variable 4) actuator operating duration (off, very little, normal) , many, very many).

As can be seen from the input parameters, the predicted environmental sensing data values can be divided into four categories. Other input parameters are optimized with environmental values, and the objective function can compute the optimal level for each parameter per unit.

According to the fuzzy rule, the system can provide the working level and actuation time for the variable level actuator. For comparison, the operating level of the actuator can be selected from three levels: minimum, medium and maximum. Energy is consumed.

The graph of a membership function can be described based on input and output parameters. The membership function represents the degree of truth of the fuzzy logic. Range values of input and output variables can be obtained through experiments.

No input value Glossary of Terms very low (x1, x2) Low (x2, x3) Normal (x3, x4) high (x4, x5) Very high (x6, x7) One Prediction temperature (°C) -5-10 5-20 15-30 20-35 30-40 2 predicted pH 0-4 3-7 6-10 9-13 12-14 3 Predicted Conductivity (μ) 10-400 350-750 700-1100 1050-1450 1400-2000 4 Prediction level (mm) 0-100 75-175 150-225 200-300 275-350

No input value Glossary of Terms optimal (x1, x2) One Optimum temperature (°C) 20-25 2 Optimal pH 6.5-8.0 3 Optimal conductivity (μ) 150-500 4 Optimal water level (mm) 300-320

Table 2 is for explaining terms for predicted input values, and FIG. 3 is for explaining terms for optimized input values.

The predicted and optimized levels are denoted by VL, L, N, H and VH, representing very low, low, medium, high and very high, respectively.

6 is a graph showing the working level of actuators having the same rated power (watts) according to an embodiment of the present invention.

Referring to FIG. 6 , it indicates that current water level detection data is between 200 and 350 mm per minute. In the graph, if the current water level is between 200 and 230 mm, it can be assumed that the purge set is marked very low, and if the water level is between 305 and 320 mm, the purge set is marked high. Similarly, it can be applied to the other labels, namely low, medium and high, and the optimized water level is calculated between the minimum and maximum set points desired by the user.

According to the present invention, the user can insert desired setting values into the system through the basic application simulator, and can calculate new optimal parameters under various conditions.

As described above, the output parameters are the actuation level and actuation time of each actuator.

According to the present invention, an embodiment using five types of actuators, such as a heater, a cooler, a water pump, a PH controller, and a conductivity controller, has been described, but it can also be applied to various other types of actuators.

These actuators are automatically activated based on predicted sensing data per unit.

In general, if Tp < To, the heater should be activated, and if To < Tp, the cooler should be activated. If Wp < Wo, the water pump is activated in the case of the aquarium system water level. If Wo<Wp, the water level may be lowered by operating the second water pump.

The operating level of the variable speed actuator can be divided into three categories: minimum level, medium level and maximum level, and these operation levels can be denoted as MinLev, MedLev and MaxLev. Power consumption is different depending on the work level and speed of the actuator. Figure 5 shows the range of actuator power ratings according to these three working levels: minimum, medium and maximum.

x1, x2, x3 and x4 represent the range points of the membership function graph for the output parameters, and the power consumption is different according to the operation process of each actuator.

On the other hand, Table 4 below shows typical power ratings of aquarium actuators in units of one minute at three operation levels.

When operating at minimum operating levels, the water pump actuator consumes a power range of 600 (x1) to 1000 (x2) watts per minute. When the water pump is running at medium operating level, it requires 1000 (xx2) to 1400 (x3) watts. At maximum operating levels, the water pump draws between 1400 (x3) and 1800 (x4) watts per minute. The same applies to all other actuator parameters and power ratings.

No actuator Power Rating (Watts) min(x1, x2) Medium (x2, x3) max (x3, x4) One water pump 600-1000 1000-1400 1400-1800 2 overflow system 30-120 120-210 210-300 3 dehumidifier 700-800 800-900 900-1000 4 humidifier 400-500 500-600 600-700

As explained earlier, the correct duration selection of actuators plays an important role in both the automation and efficient energy management of an aquarium. If the predicted sensing data indicates very low, the actuator should operate at one of the working levels (minimum, medium or maximum). Depending on the work level or speed of the actuator, the operating time of the actuator also varies until the optimum environment for controlling the actuator environment is reached. More specifically, when the water pump is running at its minimum operating level, it is time-consuming. Conversely, if the water pump is running at full operating level, little time is needed.

7 is a graph of membership functions according to actuator operation time (minutes) according to an embodiment of the present invention.

There are six membership functions for the output variable of the actuator operating time. These membership functions are denoted OFF, VLT, LT, NT, MT, and VMT, abbreviated to actuator off, very little time, little time, normal time, many hours and many hours.

The operating time of the actuator is described in minutes and the time range is determined and obtained according to agricultural and technical knowledge. This membership function is allowed for the lifetime of all actuators.

If the current sensing data equals the optimal data, the operating time of the actuator is 0 minutes and there is no need to activate the actuator (OFF). If the current sensing data is very low compared to the optimized data, the actuator must be activated a very large amount of time (12-15 min) to achieve the desired optimal growth environment.

In the detailed description of the present invention as described above, specific embodiments have been described. However, various modifications are possible without departing from the scope of the present invention. The technical spirit of the present invention should not be limited to the above-described embodiments of the present invention and should not be defined, and should be defined by not only the claims but also those equivalent to these claims.

Claims (12)

A method for controlling fish growth and energy in an aquarium using an aquarium environment control system,
A data collection step in which the data collection unit collects internal environmental parameters from sensors installed in the aquarium and external environmental parameters from an external device;
A data prediction step in which a data prediction unit pre-processes and divides the collected data to calculate predicted environmental parameters predicting the environment in the aquarium:
a data optimization step in which a data optimization unit calculates optimum growth environment parameters for optimizing the environment in the aquarium using the predicted environment parameters; and
An environment control step in which an environment control unit operates an actuator installed in the aquarium using the predicted environment parameter and the optimal growth environment parameter to control the environment in the aquarium;
The data optimization step,
A control method for optimizing fish growth and energy efficiency in which the data optimization unit calculates an environmental optimization index in the aquarium using an objective function of the following equation.
[mathematical expression]
J = max(α _EC (1-(EC*) ² ) + α _OE (1-(OE*) ² ))
(At this time, J is the environmental optimization index in the aquarium, α _EC is the target weight of energy consumption, α _OE is the target weight of the optimal growth environment, EC * = (EC - EC ^min ) (EC ^max -EC ^min ), OE * = (OE - OE ^min )(OE ^max -OE ^min ), EC is the actuator's energy consumption value, EC ^min is the actuator's minimum energy consumption value, EC ^max is the actuator's maximum energy consumption value, OE is the optimal growth environment value, OE ^min is the minimum value of the optimal growth environment, and OE ^max is the maximum value of the optimal growth environment.)
The method of claim 1,
The data prediction step,
The data prediction unit uses an artificial neural network (ANN) or a mathematical Kalman filter-based prediction module to calculate the optimal growth environment parameters corresponding to temperature, PH, conductivity and water level in the aquarium Control methods for optimizing fish growth and energy efficiency.
The method of claim 1,
The data optimization step,
Fish growth and energy efficiency in which the data optimization unit calculates the optimal growth environment parameters to minimize the energy consumption of the actuator while maintaining the growth environment in the aquarium at a certain level based on the user's environment setting reference value and system constraints Control methods for optimization.
delete The method of claim 1,
In the environmental control step,
The environment control unit uses a Fuzzy Logic Control (FLC) module to control the operation level and time of the actuator using the predicted environment parameter and the optimal growth environment parameter to control the environment in the aquarium. Control methods for optimizing fish growth and energy efficiency.
The method of claim 1,
The data collection step,
The data collector collects user-desired parameters, indoor environmental parameters, outdoor environmental parameters, energy control parameters, and power policy parameters. Control methods for optimizing fish growth and energy efficiency.
a data collection unit that collects internal environmental parameters from sensors installed in the aquarium and external environmental parameters from external devices;
A data prediction unit that preprocesses and divides the data collected by the data collection unit to calculate predicted environmental parameters that predict the environment in the aquarium:
a data optimization unit that calculates optimal growth environment parameters for optimizing the environment in the aquarium using the predicted environment parameters; and
An environment control unit controlling the environment in the aquarium by operating an actuator installed in the aquarium using the predicted environment parameter and the optimal growth environment parameter,
The data optimization unit,
A control system for optimizing fish growth and energy efficiency that calculates an environmental optimization index in the aquarium using the objective function of the following equation.
[mathematical expression]
J = max(α _EC (1-(EC*) ² ) + α _OE (1-(OE*) ² ))
(At this time, J is the environmental optimization index in the aquarium, α _EC is the target weight of energy consumption, α _OE is the target weight of the optimal growth environment, EC * = (EC - EC ^min ) (EC ^max -EC ^min ), OE * = (OE - OE ^min )(OE ^max -OE ^min ), EC is the actuator's energy consumption value, EC ^min is the actuator's minimum energy consumption value, EC ^max is the actuator's maximum energy consumption value, OE is the optimal growth environment value, OE ^min is the minimum value of the optimal growth environment, and OE ^max is the maximum value of the optimal growth environment.)
The method of claim 7,
The data prediction unit,
Fish growth and energy that calculates the optimal growth environment parameters corresponding to the temperature, PH, conductivity and water level in the aquarium using an artificial neural network (ANN) or a mathematical Kalman filter-based prediction module. Control systems for optimizing efficiency.
The method of claim 7,
The data optimization unit,
A control system for optimizing fish growth and energy efficiency that calculates optimal growth environment parameters for optimizing the environment in the aquarium based on user set values and system constraints.
delete The method of claim 7,
The environmental control unit,
Fish growth and energy controlling the environment in the aquarium by using a fuzzy logic control (FLC) module to control the operation level and time of the actuator using the predicted environment parameter and the optimal growth environment parameter Control systems for optimizing efficiency.
The method of claim 7,
The data collection unit,
Fish collecting User-desired parameters, Indoor Environmental parameters, Outdoor Environmental parameters, Energy Control parameters and Power Policy parameters Control systems for optimizing growth and energy efficiency.

Images