“…Seven approaches in various settings are compared, that is, the backpropagation NN (BPNN) [37]; support vector machine (SVM) [38], [39]; adaptive neurofuzzy inference system (ANFIS) [40]; genetic neuro-fuzzy inference system (GENFIS) [41]; radial basis function NN (RBFNN) [42]; generalized regression NN (GRNN) [43]; and Gaussian process regression (GPR) [44].…”
Section: A Partial Comparison With Other Approachesmentioning
A transparent digital twin (DT) is designed for output control using the belief rule base (BRB), namely, DT-BRB. The goal of the transparent DT-BRB is not only to model the complex relationships between the system inputs and output but also to conduct output control by identifying and optimizing the key parameters in the model inputs. The proposed DT-BRB approach is composed of three major steps. First, BRB is adopted to model the relationships between the inputs and output of the physical system. Second, an analytical procedure is proposed to identify only the key parameters in the system inputs with the highest contribution to the output. Being consistent with the inferencing, integration, and unification procedures of BRB, there are also three parts in the contribution calculation in this step. Finally, the data-driven optimization is performed to control the system output. A practical case study on the Wuhan Metro System is conducted for reducing the building tilt rate (BTR) in tunnel construction. By comparing the results following different standards, the 80% contribution standard is proved to have the highest marginal contribution that identifies only 43.5% parameters as the key parameters but can reduce the BTR by 73.73%. Moreover, it is also observed that the proposed DT-BRB approach is so effective that iterative optimizations are not necessarily needed. Index Terms-Belief rule base (BRB), building tilt rate (BTR), output control, transparent digital twin (DT).
“…Seven approaches in various settings are compared, that is, the backpropagation NN (BPNN) [37]; support vector machine (SVM) [38], [39]; adaptive neurofuzzy inference system (ANFIS) [40]; genetic neuro-fuzzy inference system (GENFIS) [41]; radial basis function NN (RBFNN) [42]; generalized regression NN (GRNN) [43]; and Gaussian process regression (GPR) [44].…”
Section: A Partial Comparison With Other Approachesmentioning
A transparent digital twin (DT) is designed for output control using the belief rule base (BRB), namely, DT-BRB. The goal of the transparent DT-BRB is not only to model the complex relationships between the system inputs and output but also to conduct output control by identifying and optimizing the key parameters in the model inputs. The proposed DT-BRB approach is composed of three major steps. First, BRB is adopted to model the relationships between the inputs and output of the physical system. Second, an analytical procedure is proposed to identify only the key parameters in the system inputs with the highest contribution to the output. Being consistent with the inferencing, integration, and unification procedures of BRB, there are also three parts in the contribution calculation in this step. Finally, the data-driven optimization is performed to control the system output. A practical case study on the Wuhan Metro System is conducted for reducing the building tilt rate (BTR) in tunnel construction. By comparing the results following different standards, the 80% contribution standard is proved to have the highest marginal contribution that identifies only 43.5% parameters as the key parameters but can reduce the BTR by 73.73%. Moreover, it is also observed that the proposed DT-BRB approach is so effective that iterative optimizations are not necessarily needed. Index Terms-Belief rule base (BRB), building tilt rate (BTR), output control, transparent digital twin (DT).
“…Also, it requires reference frame and PWM block modulation that make this method more complex. In the opposite, we find the direct control methods, such as DTC [7] and DPC [8][9][10]. Those methods are characterized by high performances, quick response drives and simplicity compared to FOC.…”
Section: Introductionmentioning
confidence: 99%
“…However, the presented results show high THD upper the limits imposed by IEEE Std 519, high active and reactive power ripples and a complex control system without treating all DFIG operation modes. In all [8,[10][11][12][13][14][15][16][17][19][20][21][22][23][24][25], authors have controlled the reactive power in the stator side and not the local reactive power compensation ( Q AC ). This indicates that the advantages offered by the WT-DFIG are not taken into account.…”
The main objective of this paper is the performances analysis of an Enhanced Direct Power Control (EDPC), applied to Doubly Fed Induction Generator (DFIG) driven by variable speed Wind Turbine (WT). This control strategy uses hysteresis regulators and switching table for active and reactive powers control. These latter are estimated using rotor currents and grid voltages instead of a traditional measurement of stator currents. In addition, the EDPC switching table is based on the position of the rotor flux instead of the stator flux in order to have better regulation accuracy because the rotor voltage vector directly influences the rotor flux and has a proportional relationship with the active and reactive powers. All the operating modes (sub-synchronous, super-synchronous, synchronous and over-speed) of the variable speed WT-DFIG system and the possibility of local reactive power compensation are reported and discussed in this paper. Depending on the operating zone of the WT, Maximum Power Point Tracking (MPPT) technique and pitch angle control are considered to optimize the wind energy efficiency. The validation of the proposed EDPC strategy has been performed through simulation tests under MATALB/Simulink, the obtained results show robustness and good performances with low THD of the generated currents.
“…This ensures a good energy transfer between the PV and the grid; it also has lower sampling frequency than a conventional DPC which help overcome the problem of energy fluctuations. The vector modulation technique is therefore used to achieve a fixed switching frequency and less power pulsations [9,10].…”
This paper presents a recent technique for photovoltaic grid connected systems based on the use of the (DPC-SVM) to select the optimal switching states to apply to the inverter, where the extended reactive power is used instead of reactive power. This technique allows achieving an optimal control of the inverter which manifests in controlling the converters using an MPPT algorithm instead of controlling each part separately. This yields to a reduced global control system on a large scale. In this context, we suggest a DC-DC boost converter circuit to ensure better behavior of the system. The FMV technique is used to inject specific harmonics in order to eliminate or minimize the undesired harmonics. The SVM model has also been developed for optimal control of the inverter to prove the high performance of the proposed method. All the results are analyzed theoretically. The simulation has shown that this strategy gives satisfactory performances, improvement of the power factor and a reduction of the THD by 37%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.