DISSERTATION ALGORITHM DEVELOPMENT TIPS FOR DEVELOPING MACHINE LEARNING BASED AUTOMATIC VOLTAGE REGULATION (AVR)

In Brief

• You will find the best dissertation research areas / topics for future researchers enrolled in Engineering .
• In order to identify the future research topics, we have reviewed the Engineering literature (recent peer-reviewed studies) on the automatic voltage regulation.
• Automatic Voltage regulation is used to maintain the voltage automatically in a generator.
• The necessity of automatic voltage regulation is discussed in this work.
• The parameters required for the decision and different modes are discussed.
• Machine learning algorithms are suggested for controlling the voltage.

Background

Voltage regulation is an important component of the power system. It is necessary to maintain the voltage of the line or an appliance for optimum performance and minimum loss. Voltage regulation maintains the voltage to the necessary level for the appliance to operate(Wei, Zeng, & Wang, 2019). Automatic Voltage Regulator is a component in an excitation system that monitors the output voltage of a generator or alternator to decide the level of current that must be applied to the key excitation windings(Batmani & Golpîra, 2019). When the output voltage of a generator changes, the excitation current must be adjusted to compensate the power. For this purpose, Automatic Voltage Regulator is used. The voltage is altered by changing the number of flux lines in the coil of the generator which changes the current.

PhD Assistance develop ML algorithms using MATLAB, Simulink  framework and many more to booth secure access control in Networking platforms. Hiring our experts, you are assured with quality and on-time delivery.

To generate electric voltage, there are three key requirements which are conductor, flux and relative motion between these two components. An EMF is induced which this takes place. In a generator, the magnetic component is placed on the rotor, while the conductor is placed on the stator component. During the operation, the magnetic components rotate around the stator creating a change in the magnetic flux lines and hence a current is induced. The voltage in the coil depends on three main things which are the speed of the rotor, flux density and the length of the conductor. When the flux density increases, the current and voltage also increases (Çelik & Durgut, 2018). Similarly, the speed and conductor length are also directly proportional to the parameter.

Usually, during normal operation of the generator, the length of the conductor cannot be changed since it is a physical component. The flux density and the rotor speed can be changed. Synchronous generators run at a constant speed and hence it cannot be changed at will. Hence, only the density of the flux can be modified. This can be done by modifying the field current or the excitation current of the generator. This changes the magnetic field and hence the voltage in the generator. Hence, the voltage regulation is possible through the excitation current. The regulation is different for no load and full load conditions.

 Hire PhD Assistance experts to develop your algorithm and coding implementation for your Computer Science dissertation Services.

During no load, there is no current in the stator. This means that there is voltage in the terminals, but no current since the terminals are open. As the field current is increased, the voltage in the stator is also increased. This relationship takes place linearly up to a certain points after which there is saturation. The stator voltage depends on the speed, excitation current. The saturation modifies the magnetic circuit reluctance which affects the resistance in the circuit. When the field current increases which increases the flux density and then gets saturated. This means that when the flux density reaches a particular value, the linearity changes. Hence, the voltage regulation is possible to a certain extent for no load conditions.

PhD Assistance experts has experience in handling dissertation and assignment in computer science research with assured 2:1 distinction. Talk to Experts Now 

During On Load conditions, the terminals are connected. The voltage depends on the speed, excitation current and loads in the stator terminals. There is a distortion that takes place in the magnetic field by the opposing forces. When the generator is connected to the grid system, there is a stator current in the circuit, which brings in additional magnetic flux as a result of the load current (Jerković Štil & Mehmedović, 2018). This acts in the opposite direction to the rotor flux and distorts the flux in the rotor, which is known as armature reaction. This is undesirable since it creates a loss, however, the voltage can be controlled completely during the loaded condition. In order to maintain the voltage, the excitation current is increased to maintain the magnetic flux.

Figure 1: Model of Automatic Voltage Regulator

In order to keep the voltage constant, the field current must be constantly varied to change the number of flux lines cutting the air gap. Hence, the field current that is required at load depends on the field current used to generate the rated voltage t no load conditions and an additional voltage to cancel the armature reaction. This continuous changing require automatic control of the voltage and current using a concept of Automatic voltage regulation. A controller is required to continuously monitor the parameters and control it. The parameters that are measured are reactive power, terminal voltage, load condition, current, etc. The controller must be able to take in these values and decide how much excitation current must be varied to maintain the voltage in the generator.

PhD Assistance has vast experience in developing dissertation research topics for students pursuing the UK dissertation in computer science. Order Now 

For this, unsupervised machine learning techniques can be used for the control (Zhou, Zhang, Yang, & Ling, 2019). The algorithm will be able to monitor all the parameters in real time and give the output that is most suitable for maintaining the voltage.

Future Scope:

• The machine learning algorithm that is most suitable must be identified. Since, very few factors are involved, light weight algorithms can be used instead of high computation neural networks.
• Smaller sized equipment that has lesser heat loss must be designed for improved efficiency.

Referred Blog

References