|
I | P | C | Fuzzy inference system | Optimization | Fuzzy model |
|
[23] | X | | Mamdani | NA | Prediction of vitality based on humidity, temperature, and shade |
[11] | | X | Mamdani | NA | Control based on error and its derivatives, uses k-means, c-means, and subtractive fuzzy grouping |
[20] | X | | Takagi–Sugeno–Khan (TSK) | NA | Base algorithms for temperature and humidity modelling |
[13] | X | | Hierarchical collaborative fuzzy system | NA | Diffuse models of air temperature and humidity comparing regularized NRLS vs. SLIMHCS vs. physical model |
[2] | | X | Takagi–Sugeno (TS) | NA | A predictive controller based on diffuse hybrid wave model (MBPC) is proposed to regulate the temperature and humidity inside the greenhouse using Gustafson–Kessel (GK) clustering algorithm |
[3] | | X | Mamdani | NA | Control of ventilation speed and heating rate taking into account humidity and temperature |
[4] | | X | Takagi–Sugeno (TS) | NA | Control from a dynamic nonlinear model |
[21] | | X | Mamdani | NA | Control based on optimal ranges of the crop for monitoring and control |
[6] | | X | Mamdani | NA | Control with a design based on thermodynamic equations |
[7] | | X | NA | NA | Definitions of identification and control models. Heuristic, global, and (GA) optimization techniques are addressed |
[18] | X | | ANFIS | NA | Humidity and temperature prediction from census data |
[14] | X | X | Takagi–Sugeno (TS) | Recursive least squares algorithm (RLS) | Analytical greenhouse model with model-based predictive controller using C-means clustering |
[9] | X | X | Mamdani | NA | Physical model of a greenhouse based on the interaction of variables and actuators |
[19] | X | X | Mamdani | NA | Mamdani PID control using a multivariable nonlinear model of transfer functions based on the thermodynamic laws of greenhouse behaviour |
[15] | X | X | Fuzzy neural network (FABPMBP) | ANN three-layer fuzzy optimization feedforward | Fuzzy model for actors, which serves as an input for the three-layer feedforward neural network optimized prediction |
[12] | | X | ANFIS | NA | Greenhouse environment based on Simulink block diagram, humidity, and thermal balance equations combined with ANFIS ventilation controller |
[22] | | X | Mamdani | NA | Expert fuzzy control based on sensor readings to activate certain actuators and a literature review of their effects |
[1] | | X | Fuzzy PID | NA | Fuzzy PID smart greenhouse control |
[24] | | X | Fuzzy numerical conversion algorithm | NA | PTZ control based on MSP430 chip |
[28] | X | X | Mamdani | ANN, GA | Two optimizers are established; the first one uses an ANN to identify the responses of the fruits, affected by the environment, and a GA to find the optimal set points of the environment. In the second optimizer, the ANN is used to identify the environmental responses, affected by a fuzzy controller, and a GA to find the optimal membership functions and the control rules in a fuzzy controller |
[29] | X | | Fuzzy GA | NA | Tomato growth model based on modified Elman lattice and fuzzy GA |
[30] | | X | Node fuzzy controller ZigBee | NA | ZigBee network mushroom greenhouse control with intelligent fuzzy control algorithm as core |
[31] | X | X | Mamdani | NA | Greenhouse multimodel adaptive fuzzy control built on a toggle mechanism that can consider and handle multiple greenhouse climate variables |
[32] | X | | ANFIS | Back propagation, least squares algorithm | Model of the growing process of tomato plants inside the greenhouse using the ANFIS system to predict the effect of meteorological variables and control actuators |
[33] | X | | Takagi–Sugeno (TS) | Recursive weighted least squares algorithm (RWLS) | Temperature and humidity description model based on Gustafson–Kessel (GK) fuzzy grouping techniques to determine both the premises and the consequent parameters of the fuzzy rules and subsequently optimizing their parameters |
[34] | | X | Fuzzy pseudo derivative feedback (FPDF) | GA | Fuzzy pseudo derivative feedback (FPDF) controller |
[35] | X | | ANFIS | NA | Prediction of the level of pest risk in a greenhouse rose by applying ANN and an ANFIS |
[36] | | X | Takagi–Sugeno (TS) | NA | Temperature and humidity control of a greenhouse that integrates ZigBee WSN to design and build an intelligent air conditioner |
[37] | X | X | Mamdani | NA | ANN prediction for temperature in greenhouses. Its purpose is to start a sprinkler irrigation system using a fuzzy expert system (FES) that controls the activation of a water pump to protect against internal freezing |
[38] | X | | ANFIS | NA | Observe the ozone concentration level |
[39] | X | X | Mamdani | NA | Model based on thermodynamic equations for two controller design |
[40] | X | | ANFIS | NA | Modified active greenhouse dryer without load using ambient temperature, relative humidity, global radiation, and experimentation time as inputs |
[41] | | X | Mamdani | NA | Control of GHS parameters such as temperature, humidity, light, soil humidity, and plant irrigation system using fans, heaters, humidifiers, motors, lamps, and irrigation |
[42] | X | | Mamdani | NA | Prediction of natural and forced convection moisture evaporation rate of jaggery in a controlled environment |
[43] | | X | Type 2 Takagi–Sugeno (TS) interval | Linear matrix inequality (LMI) | Model to represent the nonlinear dynamics of the plant subject to uncertainties of the parameters, which are effectively captured by the interval membership functions |
[44] | X | | ANFIS | NA | Greenhouse temperature model based on an adaptive fuzzy logic system with inputs: previous temperature, external temperature, humidity, wind speed, and solar radiation |
[45] | X | | Takagi–Sugeno (TS) | NA | Internal temperature and humidity prediction. The proposed algorithm is based on the decomposition of the fuzzy relationship into subrelationships, through a process of developing fuzzy rules with cluster c-means. |
[46] | | X | Takagi–Sugeno (TS) | NA | Predictive control to regulate the temperature and humidity of the greenhouse |
[47] | | X | Mamdani | NA | Greenhouse ventilation and shutter control |
[48] | X | | ANFIS | NA | Model the greenhouse climate in its values of temperature, hygrometry, and internal radiation |
[49] | X | | Mamdani | NA | Greenhouse rose yield prediction using temperature, solar radiation, humidity, nitrogen, phosphorus, and potassium concentration and leaf area |
[50] | X | | ANFIS | NA | Prediction of humidity and internal temperature |
|