Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Desislava Stoitseva-Delicheva has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Intelligent Forecasting of Smart Home Energy Consumption and Generation Based on Weather Variables

    by Desislava Stoitseva-Delicheva, Snejana Yordanova

    The growing adoption of artificial intelligence (AI) aims to improve global standards of living. However, this trend is accompanied by an increasing demand for energy. AI is rapidly integrating into home energy management systems (HEMS). While numerous artificial neural network (ANN) models have been developed for energy consumption forecasting, they often require significant computational resources and expertise for both development and deployment. This study presents a user-friendly engineering methodology for designing accurate multilayer perceptron (MLP) and Cascade-Forward Network (CFN) models to predict smart home energy consumption and solar generation. The approach emphasises computational simplicity and widespread practical viability. The dataset of 8399 hourly recorded weather and energy variables over the course of a year is extracted from publicly available data. It is randomly split into 70% for training, 15% for validation and 15% for testing. A proposed methodology guides the design, training, validation, and testing of various CFN-MLP models, in which weather variables with the greatest impact on energy generation and consumption are selected for model inputs based on different correlation tests. The identified optimal models each have two weather variables as inputs and two hidden layers of 8 and 16 neurons, balancing high predictive accuracy with low computational load for real-time HEMS deployment. The high prediction accuracy is supported by the small mean squared errors of 0.76 kWh and 0.0046 kWh. The models’ feasibility is facilitated by simple architectures, which demand only two smart sensors for the inputs, are affordable by most homes, and require small memory storage for the models.

  • Open Access

    Gain-Scheduled PID Control of Nonlinear Plant via Artificial Neural Networks

    by Desislava Stoitseva-Delicheva, Snejana Yordanova

    The high-performance control of nonlinear industrial plants in a wide operation range requires intelligent techniques. The aim of the present research is to develop an engineering approach for adaptation of the gains of the well-mastered and widely applied linear PID controller based on an offline-trained backpropagation artificial neural network (BANN) that assesses the plant parameters for the current operation point. The controller’s gains are online-computed from the empirical relationship with the plant parameters. Robust stability and robust performance conditions are derived for the gain-scheduled BANN-PID system. Their fulfilment ensures system feasibility in an industrial environment. The approach is demonstrated for the control of temperature in a laboratory dryer for fruits. The BANN training is based on data derived and validated from experiments using the Takagi–Sugeno–Kang nonlinear plant model. Simulations show that the BANN-PID system outperforms both the gain-scheduled fuzzy logic PID control system, designed in previous research, and the PID real-time control system by reducing overshoot six times and settling time 1.8 times and improving robustness 1.3 times.

  • Open Access

    Investigation on Robustness of Model-Based Fuzzy Logic Control Systems

    by Desislava Stoitseva-Delicheva, Snejana Yordanova

    A novel engineering approach for assessing the robustness of fuzzy logic control (FLC) systems with modified parallel distributed compensation (MPDC) is presented. It addresses the problem of successful implementation and operation in industrial environment of designed systems for the control of complex plants with model uncertainty. The research steps on modified Takagi–Sugeno–Kang (MTSK) plant models MTSKn and MTSKlow already derived and validated for normal and low plant loads from experimental data for the level of the solution in an industrial carbonisation column for soda ash production. MPDC with PI linear local controllers are developed based on the MTSKn plant model, which differ in the parameters that are optimised by genetic algorithms for fitness functions with and without robustness requirements and different random initial parameter values. The MTSKn and each of the designed MPDC are represented according to suggested criteria by a nominal and varied linear plant model and controller, respectively. Then, robust stability and robust performance criteria are derived for the linearised MPDC–MTSKn systems. The system performance and robustness are investigated in the frequency domain and from the simulated reference step responses for MTSKn and MTSKlow, with the results benchmarked against an existing adaptive FLC.


  • Parameter Optimisation of Type 1 and Interval Type 2 Fuzzy Logic Controllers for Performance Improvement of Industrial Control System

    by Desislava R. Stoitseva-Delicheva, Snejana T. Yordanova

    The fuzzy logic controllers (FLC) gain popularity in ensuring stable and high-performance control of nonlinear industrial plants with no reliable model, where the traditional controllers fail. Their standard expert-based design and simple algorithms that meet the demands for fast execution and economical use of computational resources ease their implementation into programmable logic controllers for wide industrial real-time control applications. This research presents a novel approach to enhancing the performance of FLC systems by compensating for the subjectivity inherent in expert-based design through optimization of the parameters of type-1 (T1) and interval type-2 (IT2) PID FLC membership functions (MF) using genetic algorithms. The approach is demonstrated for controlling the solution level in a carbonization column for soda ash production. Simulations reveal that optimization improves the system performance, measured by a newly introduced overall performance indicator for dynamic accuracy, robustness, and control smoothness, by 48% for the T1 FLC system and 30% for the IT2 FLC system. No improvement is observed in the substitute of T1 MF by IT2 MF for both the empirically designed and the optimised FLC.

  • RES Digital Twin for Smart Energy Management Flexibility Research

    by Metody Georgiev, Alexandra Georgieva, Desislava Stoitseva-Delicheva, Dilyana Gospodinova, Kostadin Milanov


  • Load-bound Fuzzy Logic Control of an Industrial Nonlinear Plant

    by Snejana Yordanova, Milen Slavov, Desislava Stoitseva-Delicheva

    Most industrial plants have load dependent nonlinear characteristics. In the present research a Sugeno fuzzy logic controller (FLC) on the principle of parallel distributed compensation (PDC) is developed that considers the variance in the load and the plant nonlinearity. It consists of separate controllers for each boundary load and a PDC-based soft blender for their common control action as a function of the load. The controllers are designed for the boundary loads. First, PI PDC are developed to better compensate the plant nonlinearity based on, derived and validated from experimental data, Takagi-Sugeno-Kang (TSK) plant models. The PI PDC replicates the TSK plant model structure but with local PI controllers tuned with respect to the corresponding TSK local linear plant models. Second, PI controllers are designed based on the mean values of the TSK local plant models parameters. The suggested PDC load-bound controllers PI PDC and PI are applied for the control of level in a carbonisation column for soda ash production. The simulation investigations show that the PDC load-based PI PDC compensates best the system nonlinearity and improves its robustness to changes in the load compared to the PDC load-bound PI and the ordinary PDC and PI control systems designed for one load.


  • Design and Genetic Algorithms Based Optimisation of Industrial Adaptive PID FLC System of Liquid Level

    by S. T. Yordanova, M. N. Slavov, D. R. Stoitseva-Delicheva

    Задача регулирования уровня предварительно карбонизированного раствора на технологической установке по производству кальцинированной соды требует применения не традиционных, классических, а современных интеллектуальных подходов, позволяющих учитывать сложность процесса, его нелинейность и воздействия промышленных помех. Для решения данной задачи в работе предлагается использовать безмодельные контроллеры нечеткой логики FLC с эмпирической онлайн-настройкой, реализованные в режиме реального времени в программируемом логическом контроллере общего назначения PLC. Целью исследования является параметрическая оптимизация генетическим алгоритмом стратегии адаптивного PID FLC регулятора. При этом для адаптации параметров настройки PID FLC используется модель Sugeno. Здесь PD FLC регулятор, в зависимости от значения регулируемого уровня, эмпирически определяет с помощью своих функций принадлежности три зоны линеаризации и выполняет для каждой зоны мягкое смешивание коэффициентов передачи усилителя и интегратора. Предложены две стратегии адаптации для онлайн- автоматической настройки постоянной времени интегратора совместно с коэффициентами передачи усилителя и дифференциатора PD FLC. Локальные параметры системы регулирования технологической установки, в свою очередь, автоматически оптимизируются генетическим алгоритмом. Компьютерное моделирование и промышленные эксперименты показали высокую эффективность синтезированной системы регулирования за счет автоматической настройки параметров PID FLC с оптимизированными локальными значениями.


  • Parallel Distributed Compensation for the Control of Processes in Anaerobic Organic Wastewater Treatment

    by Snejana Yordanova, Desislava Stoitseva-Delicheva

    The aim of the present investigation is to develop a simple approach for the design of a fuzzy logic controller (FLC) based on a derived Takagi-Sugeno-Kang (TSK) plant model using the principle of parallel distributed compensation (PDC) in order to improve the control of the biogas production rate in the anaerobic organic wastewater treatment. A fifth order nonlinear model that fits the experimental data from a laboratory bioreactor is used to study via simulation the plant step responses for two boundary values of the main disturbance - the initial organic load. Two TSK plant models are obtained to approximate the step responses via genetic algorithms minimization of the modelling error. Each TSK model is built of a Sugeno model with plant output as input and three outputs – the membership functions of belonging of the plant output to three linearization zones. The local plant in each zone is modelled by time-lags. Then two PDC on the same Sugeno models are designed with local linear PI controllers tuned with respect to the corresponding local linear plant model. Another Sugeno model with input the concentration of the initial organic waste distributes by weighted average the plant output to the inputs of the Sugeno models of the two PDC. The PDC based system shows via simulation a reduced dynamic error compared to a designed model-free Mamdani PI FLC.


  • Industrial Bound Design and Application of Fuzzy Logic PID Controller for Liquid level in Carbonisation Column

    by Snejana Yordanova, Milen Slavov, Georgi Prokopiev, Desislava Stoitseva-Delicheva

    A novel approach for the design of a fuzzy logic controller (FLC) is suggested in order to improve the control of the liquid level in a carbonisation column for soda ash production. It considers the impact of the industrial environment and the signals, equipment, programmable logic controller (PLC) and real time control restrictions. A PID FLC is designed with inputs the system error and the rate of level computed via sliding average to smooth the reference step response and reduce disturbances and noise impact. The defuzzyfication is simplified and the control effort decreased assigning proper output singletons. The pre- and PI post-processing parameters are tuned in an off-line genetic algorithms based minimization of a novel fitness function of the system error and the control variance for prolonging actuator’s and valve’s lifetime. The FLC is implemented in a general purpose PLC. The real time level control shows an improved system performance.


  • Energy Efficient Temperature Control

    by Desislava Stoitseva-Delicheva

    the paper presents energy efficient control algorithm for temperature control based on mathematical dependencies such as Hamiltonian function and Pontryagin’s maximum principle. The algorithm is applied to a nonlinear temperature control plant and the results are compared with those of a fuzzy logic control system.