Iulian ARAMA

Dr. Iulian ARAMA

Informatics, Universitatea Danubius Galati, Galaţi, Romania
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Viorel N. MÎNZUViorel N. MÎNZU
Viorel N. MÎNZU
GIGeorge Adrian Ifrim
George Adrian Ifrim
Iulian ARAMAIulian ARAMA
Iulian ARAMA
A metaheuristic algorithm can be a realistic solution when optimal control problems require a significant computational effort. The problem stated in this work concerns the optimal control of microalgae growth in an artificially lighted photobioreactor working in batch mode. The process and the dynamic model are very well known and have been validated in previous papers. The control solution is a closed-loop structure whose controller generates predicted control sequences. An efficient way to make optimal predictions is to use a metaheuristic algorithm, the particle swarm optimization algorithm. Even if this metaheuristic is efficient in treating predictions with a very large prediction horizon, the main objective of this paper is to find a tool to reduce the controller’s computational complexity. We propose a soft sensor that gives information used to reduce the interval where the control input’s values are placed in each sampling period. The sensor is based on measurement of the biomass concentration and numerical integration of the process model. The returned information concerns the specific growth rate of microalgae and the biomass yield on light energy. Algorithms, which can be used in real-time implementation, are proposed for all modules involved in the simulation series. Details concerning the implementation of the closed loop, controller, and soft sensor are presented. The simulation results prove that the soft sensor leads to a significant decrease in computational complexity.

28 January 2022 in Automation
Verified
Journal Article
Open access
PDF file
Viorel N. MÎNZUViorel N. MÎNZU
Viorel N. MÎNZU
Iulian ARAMAIulian ARAMA
Iulian ARAMA
The closed-loop optimal control systems using the receding horizon control (RHC) structure make predictions based on a process model (PM) to calculate the current control output. In many applications, the optimal prediction over the current prediction horizon is calculated using a metaheuristic algorithm, such as an evolutionary algorithm (EA). The EAs, as other population-based metaheuristics, have large computational complexity. When integrated into the controller, the EA is carried out at each sampling moment and subjected to a time constraint: the execution time should be smaller than the sampling period. This paper proposes a software module integrated into the controller, called at each sampling moment. The module estimates using the PM integration the future process states, over a short time horizon, for different control input values covering the given technological interval. Only a narrower interval is selected for a ‘good’ evolution of the process, based on the so-called ‘state quality criterion’. The controller will consider only a shrunk control output range for the current sampling period. EA will search for its best prediction inside a smaller domain that does not cause the convergence to be affected. Simulations prove that the computational complexity of the controller will decrease.

30 December 2022 in Inventions
Verified
Journal Article
Open access
PDF file
Viorel N. MÎNZUViorel N. MÎNZU
Viorel N. MÎNZU
Eugen RUSUEugen RUSU
Eugen RUSU
Iulian ARAMAIulian ARAMA
Iulian ARAMA
Execution time is an important topic when using metaheuristic-based optimization algorithms within control structures. This is the case with Receding Horizon Control, whose controller makes predictions based on a metaheuristic algorithm. Because the closed loop’s main time constraint is that the controller’s run time must be smaller than the sampling period, this paper joins the authors’ previous work in investigating decreasing execution time. In this context, good results have been obtained by introducing the “reference control profile” concept that leads to the idea of adapting the control variables’ domains for each sampling period. This paper continues to address this concept, which is adjusted to harmonize with the Particle Swarm Optimization algorithm. Moreover, besides adapting the control variables’ domains, the proposed controller’s algorithm tunes these domains to avoid losing convergence. A simulation study validates the new techniques using a nontrivial process model and considering three modes in which the controller works. The results showed that the proposed techniques have practical relevance and significantly decrease execution time.

6 January 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
Viorel N. MÎNZUViorel N. MÎNZU
Viorel N. MÎNZU
Iulian ARAMAIulian ARAMA
Iulian ARAMA
Using metaheuristics such as the Evolutionary Algorithm (EA) within control structures is a realistic approach for certain optimal control problems. They often predict the optimal control values over a prediction horizon using a process model (PM). The computational effort sometimes causes the execution time to exceed the sampling period. Our work addresses a new issue: whether a machine learning (ML) algorithm could “learn” the optimal behaviour of the couple (EA and PM). A positive answer is given by proposing datasets apprehending this couple’s optimal behaviour and appropriate ML models. Following a design procedure, a number of closed-loop simulations will provide the sequences of optimal control and state values, which are collected and aggregated in a data structure. For each sampling period, datasets are extracted from the aggregated data. The ML algorithm experiencing these datasets will produce a set of regression functions. Replacing the EA predictor with the ML model, new simulations are carried out, proving that the state evolution is almost identical. The execution time decreases drastically because the PM’s numerical integrations are totally avoided. The performance index equals the best-known value. In different case studies, the ML models succeeded in capturing the optimal behaviour of the couple (EA and PM) and yielded efficient controllers.

1 June 2019
Verified
Conference Paper
Closed access
FCFlorin Constantinescu
Florin Constantinescu
MRMihai Rata
Mihai Rata
FEFlorin Roman Enache
Florin Roman Enache
GVGabriel Vataselu
Gabriel Vataselu
VSValentin Stefanescu
Valentin Stefanescu
Iulian ARAMAIulian ARAMA
Iulian ARAMA
Some measurements results aimed to be used to build frequency domain models for nonlinear loads containing thyristors are presented. Following similar procedures to those in our previous papers, the modules and phases dependences on the parameters of the fundamental voltage component are measured for all significant harmonic components of the currents. These results are given for a one thyristor rectifier and a three phase rectifier with three thyristors.

23 April 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
Viorel N. MÎNZUViorel N. MÎNZU
Viorel N. MÎNZU
Iulian ARAMAIulian ARAMA
Iulian ARAMA
Eugen RUSUEugen RUSU
Eugen RUSU
Some optimal control problems need metaheuristics in searching for the optimal solution, especially when the process has certain characteristics like the Photobioreactor for Algae Growth (distributed parameter, nonlinearities, etc.). Particle Swarm Optimization (PSO) algorithms within control structures are a realistic approach; their task is often to predict the optimal control values working with a process model (PM). Owing to numerous numerical integrations, there is a big computational effort that is reflected in a large controller execution time. The authors propose to replace the PSO predictor with a machine learning model that has “learned” the quasi-optimal behavior of the couple (PSO, PM); the training data is obtained through closed-loop simulations over the control horizon. The new controller should preserve the process’s quasi-optimal control. In identical conditions, the process evolutions must also be quasi-optimal. The multiple Linear Regression and the Regression Neural Networks were considered as predicting models. The paper first proposes algorithms for collecting and aggregating data sets for the learning process. Algorithms for constructing the machine learning models, implementing the controllers, and closed-loop simulations are also proposed. The simulations prove that the two machine learning predictors have learned the PSO predictor’s behavior such that the process evolves almost identically. The resulting controllers’ execution time drastically decreased while keeping their optimality.