Automation Algorithms Research Articles

The Problem of Power Variations in Wind Turbines Operating under Variable Wind Speeds over Time and the Need for Wind Energy Storage Systems

One of the most important and efficient sources of green electricity is catching air currents through wind turbine technology. Wind power plants are located in areas where the energy potential of the wind is high but it varies. The time variation of the wind generates fluctuations in the power produced by the wind farms that is injected into the grid. This elevates, depending on the intensity, problems of network stability and the need for balancing energy, thus raising both technical and cost issues. The present paper analyzes the behavior of a wind turbine (WT) over time in varying wind speed conditions, highlighting that without automation algorithms, a WT is far from the operation at the maximum power point (MPP). However, even when it is brought to operate at MPP, there are still significant variations in the power injected into the network. These power variations can be compensated if the wind system has energy storage facilities for the captured wind. All of these assumptions are analyzed using improved mathematical models and processed in simulations, with experimental data used as input from a wind turbine with an installed power of 2.5 [MW] in operation on the Romanian Black Sea coastal area. Consequently, the paper demonstrates that during an operation in the optimal area, from an energy perspective, the wind turbine’s maximum power point requires a storage system for the captured wind energy.

Lightweight algorithm based on you only look once version 5 for multiple class defect detection on wind turbine blade surfaces

A lightweight wind turbine blade surface multiple class defect detection algorithm based on You Only Look Once version 5 (YOLOv5) is proposed to address the issues of low accuracy, poor efficiency, and high power consumption associated with manual and traditional automation algorithms used for detecting surface defects on wind turbine blades. Firstly, by replacing the Concentrated-Comprehensive Convolution Block module in YOLOv5 with the GhostBottleneckv2 module, the overall parameter count of the model is significantly reduced. Additionally, advocating the inclusion of the Convolutional Block Attention Module (CBAM) into the YOLOv5 backbone network to address the issue of small targets and significant scale variations in surface defects found on wind turbine blades. The YOLOv5 feature fusion module replaces the Feature Pyramid Network (FPN) structure with the Bidirectional Feature Pyramid Network (BiFPN) structure to enhance the fusion capability of multi-scale weighted features. Finally, the optimized model files underwent structured pruning through the application of pruning strategies, retraining fine-tuning, and knowledge distillation techniques. The experimental results on the self-made dataset of surface defects on wind turbine blades indicate that the optimized model has a parameter count that is only 48.79% of the small version of the YOLOv5 model. However, its mean Average Precision (mAP) and frame rate have increased by 5.05% and 8.1 frames/s, respectively, reaching 94.56% and 43.7 frames/s. The lightweight algorithm proposed in this study meets the accuracy and real-time requirements for surface defect detection on wind turbine blades.

In-field grading and sorting technology of apples: A state-of-the-art review

Apple is one of the most popular fruits. In-field grading and sorting of apples would enhance growers’ economic benefits by lowering production costs. This study reviews the key components and progress of the quality inspection algorithm for in-field grading and sorting of apples. Four key components (e.g., conveyor, imaging chamber, sorting actuator, and bin filler) are presented in detail, followed by summarizing the shortcomings of these components. The apple’s external (color, size, and defects) and internal quality inspection technologies, such as optical technologies of visible light, near-infrared (NIR), hyperspectral/multispectral imaging (HSI/MSI), and structured illumination (SI) were presented. Despite the excellent detection performance of emerging technologies (e.g., HSI, MSI, and SI), visible light is still dominantly used for in-filed grading. Challenges in getting information on the whole surface area of the apple, uneven lighting, machine size, throughput, and associated costs hamper the commercialization of apple in-field grading and sorting equipment. At present, more efforts should be devoted to internal quality inspection, by developing reliable, fast, and accurate detection equipment and algorithms. With the advancement of sensors and automation algorithms, as well as the emergence of mechanical systems that are suitable for in-field use, it is anticipated that the apple in-field grading and sorting equipment that inspects both external and internal quality will be realized and commercialized in the near future.

Анализ частотных характеристик токовых датчиков цифрового трансформатора тока и напряжения

Digital measuring current and voltage transformers (DCVT), which incorporate various current and voltage sensors are the key sources of information about processes at modern digital substations. Classic small-sized current transformers, Rogowski coils, magnetotransistor sensors, Hall effect sensors, fiber-optic Faraday effect sensors, as well as shunts can be used as current sensors in DCVTs. For redundancy purposes, current channels are performed in several copies and on different sensors. Sensors that are different in nature have their own set of advantages, which together makes it possible to obtain the effect of eliminating the shortcomings of specific sensors. For example, they may not have a saturation effect or transmit the direct current component quite accurately, which is a significant advantage over classic current transformers. At the mains frequency, the behavior of these sensors is predictable, but their behavior is not well studied at higher and lower frequencies. Thus, it is decided to study the frequency response and phase response of these sensors in a wide frequency range. To solve the problems within the framework of this study, physical experiment, analytical and empirical solution methods have been used. As a result of the study, the frequency response and phase response of current sensors of DCVT in a wide frequency range have been obtained. Analog filter has been designed to correct the signal of the magnetotransistor sensor. The results obtained coincide with theoretical data and can be considered when developing digital relay protection and automation algorithms.

Creation of a complex multivariate integrated model of the oil interfield transport system

Background. In conditions of variability of external and internal factors that directly affect the loading of the existing hydrocarbon transport system, the risks arise associated with the productive capacity of the existing infrastructure and noncompliance with the requirements for the quality of delivered oil. Objective. To create a tool allowing to assess the degree of loading of existing infrastructure facilities and indicators of the commercial quality of oil at commercial delivery sites in the near and long term, the availability of which is essential for risk minimization. Materials and methods. An integrated model in combination with automation tools is an effective tool for making strategic decisions in order to develop the assets of a subsurface user company. Results. By the example of transport infrastructure, the paper describes an approach to using the gathering system model, which jointly with automation algorithms allows solving a number of strategic tasks of oil and gas producers, such as performing multivariate hydraulic calculations and monitoring oil quality in order to verify compliance with the requirements. Conclusions. An integrated model in combination with the developed automation tools is an auxiliary tool for management decision-making. The tool helps to significantly reduce the labor costs for performing calculations and primary processing of the results. The implemented approaches can be used for hydraulic calculations and monitoring of limitations of transportation networks of similar configuration.

The Genesis of AIbyAI Integrated Circuit: Where AI Creates AI

The typical Integrated Circuit (IC) development process commences with formulating specifications in natural language and subsequently proceeds to Register Transfer Level (RTL) implementation. RTL code is traditionally generated through manual efforts, using Hardware Description Languages (HDL) such as VHDL or Verilog. High-Level Synthesis (HLS), on the other hand, converts programming languages to HDL; these methods aim to streamline the engineering process, minimizing human effort and errors. Currently, Electronic Design Automation (EDA) algorithms have been improved with the use of AI, with new advancements in commercial (such as ChatGPT, Bard, among others) Large Language Models (LLM) and open-source tools presenting an opportunity to automate the chip design process. This paper centers on the creation of AIbyAI, a Convolutional Neural Network (CNN) IC entirely developed by an LLM (ChatGPT-4), and its manufacturing with the first fabricable open-source Process Design Kit (PDK), SKY130A. The challenges, opportunities, advantages, disadvantages, conversation flow, and workflow involved in CNN IC development are presented in this work, culminating in the manufacturing process of AIbyAI using a 130 nm technology, marking a groundbreaking achievement as possibly the world’s first CNN entirely written by AI for its IC manufacturing with a free PDK, being a benchmark for systems that can be generated today with LLMs.

Optimization of Number of GCPs and Placement Strategy for UAV-Based Orthophoto Production

Unmanned aerial vehicles (UAVs) have been employed to perform aerial surveys in many industries owing to their versatility, relatively low cost, and efficiency. Ground control points (GCPs) are used for georeferencing to ensure orthophoto geolocation/positioning accuracy. In this study, we investigate the impact of the number and distribution of GCPs on the accuracy of orthophoto production based on images acquired by UAVs. A test site was selected based on regulatory requirements, and several scenarios were developed considering the specifications of the UAVs used in this study. The locations of GCPs were varied to obtain the results. Based on the results obtained for different numbers of GCPs per unit area and distribution of GCPs, it is shown that UAV-based platforms can be more extensively utilized in a range of applications. The findings of this study will significantly impact the development process of GCP automation algorithms and enable a more cost-effective approach when determining target sites for UAV-based orthophoto production.

Development of intelligent protection and automation control systems using fuzzy logic elements

In this article, the causes of technological disturbances in electrical systems are considered, and several characteristic disadvantages of the protection and automation of elements of electrical systems are highlighted. The tendency to decrease the reliability of relay protection associated with the transition from analog to digital types of protection is substantiated. Based on the studied examples, the use of fuzzy logic in protections, the expediency of using fuzzy logic elements in protection devices, and the automation of electrical systems to identify types of short circuits are justified. This article analyzes the most common damages and presents the results of modeling an electrical system with transformer coupling, where all types of asymmetric short circuits were initiated. The dynamics of changes in the symmetrical components of short-circuit currents of the forward, reverse, and zero sequences are determined. Rules have been created for the identification of asymmetric types of short circuits. An algorithm of protection and automation operation using fuzzy logic elements has been developed. The proposed algorithm of protection and automation will reduce the time to determine the type of damage and trigger protections.

Detection of Current Transformer Saturation Based on Machine Learning

One of the tasks in the operation of electric power systems is the correct functioning of the protection system and emergency automation algorithms. Instrument voltage and current transformers, operating in accordance with the laws of electromagnetism, are most often used for information support of the protection system and emergency automation algorithms. Magnetic core saturation of the specified current transformers can occur during faults. As a result, the correct functioning of the protection system and emergency automation algorithms is compromised. The consequences of current transformers saturation are mostly reflected in the main protections of network elements operating on a differential principle. This work aims to consider the analysis of current transformer saturation detection methods. The problem of identifying current transformer saturation is reduced to binary classification, and methods for solving the problem based on artificial neural networks, support vector machine, and decision tree algorithms are proposed. Computational experiments were performed, and their results were analyzed with imbalanced (dominance of the number of current transformer saturation modes over the number of modes with its normal operation) and balanced classes 0 (no current transformer saturation) and 1 (current transformer saturation).

Development of a New Generation High Crushing Capacity Jaw Crusher with an Automatically Adjusted Closed Side Settings

The design and development of a new generation high crushing capacity jaw crusher, developed for the first time in Turkey and whose Closed Side Settings (CSS) may be automatically adjusted hydraulically, were investigated in this study. The calculations for the crusher developed for this purpose were included in the paper. The design modifications made to expand the crusher's jaw stroke from 27 mm to 40 mm were documented, and the capacity increase resulting from this was theoretically calculated and proven by a wide range of field tests conducted after the jaw crusher was manufactured. Field testing and their findings were also thoroughly covered in the paper. The forces on the crusher jaw and bearings, the crusher body geometry and crusher material (via fatigue analysis), and the dynamic performance of the system (via vibration analysis of the carrier system) were examined as the outcome of the FEM (Finite Element Method) and DEM (Discrete Element Method) analyses performed after the theoretical calculations. With improvements made based on the findings gained, the theoretical and practical harmony of the created jaw crusher system was realized. Field testing has proven that the adjustment procedure takes no more than 3 minutes and requires no human participation. As a result of this research, a patent application for the created automation algorithm was filed.

Design Algorithm for Sequential Pneumatic and Electropneumatic Systems

This article presents an alternative automation algorithm for pneumatic sequences that enables the solution of complex sequential problems without the need to organize detection phases into groups. By not using groups to organize movements in detection phases, two benefits can be achieved: firstly, all the drawbacks associated with using groups are eliminated, such as design complexity, difficulty in debugging, increased cost, and difficulty in optimizing the circuit; secondly, it enables the use of logical functions to define each motion in pneumatic actuators. This opens up the possibility to solve logical functions using Boolean algebra techniques, and even their generalization into an algorithm that can be programmed in any language. To validate the proposed algorithm, MATLAB pseudocode is presented. This pseudocode allows obtaining the logical functions needed to build the ladder diagram of any sequence involving up to four double-acting cylinders with any number of phases in a work cycle.

Multi-objective reinforcement learning for autonomous drone navigation in urban areas with wind zones

Drones can be used for tasks such as data collection and logistics in civil engineering. Current research on autonomous drones mainly focuses on planning a safe path and avoiding obstacles in a static environment. However, navigating a drone in complex environments like urban areas involves many dynamic constraints, such as building layout, winds, and signal coverage, which are interdependent. The wind factor is the most important among these environmental factors, which may cause a drone to lose control or even crash. This paper presents a multi-objective navigation reinforcement learning algorithm (MONRL) for the drone to navigate and avoid obstacles in an unknown environment when dynamic wind zones present, with only imagery data about the building layouts. Based on a deep reinforcement learning and memory architecture, the drone develops policies to prioritize navigation decisions, optimizing the path while minimizing negative impact of winds with only sparse sensor data, in our case, camera inputs. By leveraging the advantages of the proposed method in estimating the environmental factors from previous trials, no aerodynamic force sensors are needed for the drone to develop effective strategies to navigate to target while counteracting to milder winds and dodging aways from stronger winds. The proposed method was tested in a virtual environment, and a real model of New York City. The method is expected to contribute to new automation algorithms for urban aerial logistics and future automated civil infrastructure inspection.

What Are the Advantages of a FE-EPMA or FE-SEM (Even When Not Analyzing Submicron Features at Low kV and High Beam Current)?

Abstract Field emission electron probe microanalyzers (EPMA) and scanning electron microscopes (SEM) have improved in both the hardware and software. They have become workhorse instruments for imaging secondary (SE) and backscattered (BSE) electrons. Recent advancements in technology provide qualitative quantitative analysis and X-ray maps at lower kVs and higher beam current without significantly enlarging the beam diameter. On EPMAs and SEMs with W and LaB6 electron guns, spatial resolution for microanalysis was ∼1 micron. Now, with field emission (FE) guns, resolution of 300 nm for quantitative analysis and mapping of elements well below 100 nm are possible. Software has also become more user-friendly and has advanced automation algorithms that allow the “non-expert” EPMA user to collect data. However, the best part of automation sits in the user’s chair. The new EPMAs and SEMs can collect very good data, but if they don’t answer the question that is being asked, they have no use.

A Toolbox for Designing 3D‐Printing‐Ready Pneumatic Circuits for Controlling Soft Robots

The robotics field has witnessed a rapid increase in the popularity of soft pneumatic robots due to their adaptability to unstructured environments and safe human–robot interaction. However, many of them are still controlled by rigid solenoid valves and microcontrollers. Recent research works have introduced various electronics‐free computational devices for soft robotic applications. Yet, connecting these individual components into pneumatic circuits still remains challenging. The manual circuit design, fabrication, and piping process can bring inefficient circuit layout, redundant tubing, unreliable fittings, and potentially human mistakes. This work presents an open‐source toolbox for automatically designing pneumatic circuits for soft robotic applications. The toolbox takes the desired computation function along with some space constraints as inputs, and generates a 3D‐printable file of a pneumatic circuit that can be fabricated and used directly. This is achieved by efficiently positioning the logic gates and air channels while considering the workspace constraints, fabrication limits, material cost, and system complexity. The versatility of the design automation algorithm has been tested with two different truth tables and six different workspaces. The work also showcases utilizing the toolbox to design a computational circuit that governs the movements of a soft robotic hand with four pneumatic actuators.

ColO-RAN: Developing Machine Learning-Based xApps for Open RAN Closed-Loop Control on Programmable Experimental Platforms

Cellular networks are undergoing a radical transformation toward disaggregated, fully virtualized, and programmable architectures with increasingly heterogeneous devices and applications. In this context, the open architecture standardized by the O-RAN Alliance enables algorithmic and hardware-independent Radio Access Network (RAN) adaptation through closed-loop control. O-RAN introduces Machine Learning (ML)-based network control and automation algorithms as socalled xApps running on RAN Intelligent Controllers. However, in spite of the new opportunities brought about by the Open RAN, advances in ML-based network automation have been slow, mainly because of the unavailability of large-scale datasets and experimental testing infrastructure. This slows down the development and widespread adoption of Deep Reinforcement Learning (DRL) agents on real networks, delaying progress in intelligent and autonomous RAN control. In this paper, we address these challenges by discussing insights and practical solutions for the design, training, testing, and experimental evaluation of DRLbased closed-loop control in the Open RAN. To this end, we introduce ColO-RAN, the first publicly-available large-scale O-RAN testing framework with software-defined radios-in-the-loop. Building on the scale and computational capabilities of the Colosseum wireless network emulator, ColO-RAN enables ML research at scale using O-RAN components, programmable base stations, and a ”wireless data factory”. Specifically, we design and develop three exemplary xApps for DRL-based control of RAN slicing, scheduling and online model training, and evaluate their performance on a cellular network with 7 softwarized base stations and 42 users. Finally, we showcase the portability of ColO-RAN to different platforms by deploying it on Arena, an indoor programmable testbed. The lessons learned from the ColO-RAN implementation and the extensive results from our first-of-its-kind large-scale evaluation highlight the importance of experimental frameworks for the development of end-toend intelligent RAN control pipelines, from data analysis to the design and testing of DRL agents. They also provide insights on the challenges and benefits of DRL-based adaptive control, and on the trade-offs associated to training on a live RAN. ColO-RAN and the collected large-scale dataset are publicly available to the research community.

Information flows’ movement analysis in the integrated accounting and analytical system of individual entrepreneurs in the web business on marketplaces sphere

The annual increase in the number of individual entrepreneurs in comparison with the decrease in the number of legal entities, especially in the form of microbusiness in the field of online commerce on marketplaces, reflects the relevance of the chosen topic. The analysis of scientific articles over the past year confirms that research on the specifics of the individual entrepreneurs’ activities is aimed primarily at the external interaction of entrepreneurs and the state. The scope of internal control and the features of accounting for individual entrepreneurs have not been previously considered by scientists. Earlier in the works of scientists, business management processes, elements of a balanced scorecard system and stages of the accounting process were included for a simplified structure of an integrated accounting and analytical system. The study purpose is to optimize information flows in the accounting and analytical system of individual entrepreneurs in the field of web business on marketplaces. As a result of the study, the information movement has been clarified in order to fix indicators of strategic goals and the formation of tax accounting registers. The goals’ components and system’s objectives of balanced indicators for individual entrepreneurs have been formed, considering the specifics of web business on marketplaces. The tasks’ interrelation is reflected and the possible connection of universal indicators within the framework of strategic goals is described. These studies can be used as the development of state recommendations on accounting by individual entrepreneurs as an alternative to existing ones for organizations. Further studies may be devoted to assessing the effectiveness of the accounting and analytical system for individual entrepreneurs and clarifying the algorithm of automation, as well as obtaining information when accounting within such a system.

Distributed intelligence for pervasive optical network telemetry

Optical network automation and failure management require measuring the status and the performance of the different network devices to anticipate any degradation and ensure the quality of the provided services, i.e., optical connectivity. Such pervasive network telemetry entails collecting large amounts of measurements and events from different sources and with very fine granularity, which given the amount and variety of telemetry sources and the size of each measurement and event, imposes requirements that are hard to achieve without large investments. In this paper, we analyze the main limitations of telemetry architectures relying exclusively on centralized systems for data analysis and propose an architecture with distributed intelligence. Data aggregation techniques, especially conceived for optical network telemetry, are presented with the objective of reducing data dimensionality. Illustrative results from our experimental telemetry system reveal a reduction of 3 orders of magnitude in terms of total data volume without introducing significant error and processing delay and, more importantly, helping network automation algorithms to identify meaningful changes in the network status.

Machine Learning-Mediated Ultrasensitive Detection of Citrinin and Associated Mycotoxins in Real Food Samples Discerned from a Photoluminescent Carbon Dot Barcode Array.

Economically viable remote sensing of foodborne contaminants using minimalistic chemical reagents and simultaneous automation calls for a concrete integration of a chemical detection strategy with artificial intelligence. In a first of its kind, we report the ultrasensitive detection of citrinin and associated mycotoxins like aflatoxin B1 and ochratoxin A using an Alizarin Red S (ARS) and cystamine-derived carbon dot (CD) that aptly amalgamate with machine learning algorithms for automation. The photoluminescence response of the CD as a function of various solvents and pH is used to generate array channels that are further modulated in the presence of the mycotoxins whose digital images were acquired to determine pixelation, essentially creating a barcode. The barcode was fed to machine learning algorithms that actualize and intertwine convoluted databases, demonstrating Extreme Gradient Boosting (XGBoost) as the optimized model out of eight algorithms tested. Spiked samples of wheat, rice, gram, maize, coffee, and milk were used to evaluate the testing model where an exemplary accuracy of 100% even at 10 pmol of mycotoxin concentration was achieved. Most importantly, the coexistence of mycotoxins could also be detected through the CD array and XGBoost synergy hinting toward a broader scope of the developed methodology for smart detection of foodborne contaminants.

Energy Recovery Optimization by Means of a Turbine in a Pressure Regulation Node of a Real Water Network Through a Data-Driven Digital Twin

In recent years, various devices have been proposed for pressure regulation and energy recovery in water distribution and transport networks. To provide a real net benefit, they require a dedicated long-distance management system in order to carry on both hydraulic regulation and electricity production without direct human manual operations. This work presents a new proposal for the management of a pressure regulation system based on the PRS turbine. The proposal is applied to a real water distribution network, named Montescuro Ovest pipeline, at the San Giovannello station. The Real Time Control (RTC) logic currently applied at San Giovannello station is first presented and discussed. A new Advanced Real Time Control (ARTC) logic is then proposed, based on direct configuration of the turbine and the surrounding valves as computed by the solution of an optimization problem. In ARTC a digital twin, including the hydraulic model of the surrounding network, provides a one-to-one relationship between the configuration parameters and the state variables, i.e. flow rates and pressures. The digital twin model equations are continuously updated on the basis of the recorded measures. Besides providing almost identical performance to the current RTC logic in the current operational scenario, the improved ARTC is more robust, in that it guarantees better hydropower generation in modified operational scenarios, as shown in specific tests. The proposed methodology constitutes a new approach to regulating the valves in hydroelectric plants which are currently regulated with traditional automation algorithms.

Algorithm for automation of the method of testing statistical hypotheses according to the Pearson criterion by the means of MATLAB

The purpose of the work is to develop and improve the methods of computer modeling and digitalization of procedures for testing statistical hypotheses according to consent criteria for use in high-tech software and measuring complexes of automated control systems. In most cases that are important for practice, the analysis of the statistical properties of distributions requires multiple checks performed using numerical methods, which require the tools of powerful software and computing environments. Examples of such cases are the procedures for finding information subsets of features in regression and statistical analysis, as well as identifying parameter deviations in automated control systems. It is noted that the tasks of processing experimental data do not always fit into the framework of the theory of normal processes and have exclusively such hypotheses. To test such hypotheses, modern mathematical statistics has developed criteria based on specially developed probabilistic rules that distinguish between zero and alternative hypotheses. Moreover, if for the testable (zero) hypothesis the distribution of statistics is known exactly or approximately, then for the alternative it has a greater degree of uncertainty and it (the alternative) itself is not a complete negation of the null hypothesis. As the zero and alternative hypotheses move away from each other, the statistics of the consent criterion begins to take a larger absolute value than with the null hypothesis, which allows us to build a critical area on the basis of estimating the set of this statistics values. However, the use of analytical methods for statistical analysis to determine the discrepancy between empirical and hypothetical statistics in practice is associated with the use, as a rule, of complex computational calculation algorithms and the implementation of high requirements for the assessment accuracy, which they cannot provide. To solve this problem, it is proposed to use numerical methods of computer modeling and integration of probability density of distribution according to the Simpson algorithm using the tools of built-in functions of the Statistics Toolbox of the MATLAB environment. The proposed method for automation of statistical analysis of zero and alternative hypotheses is implemented on the example of applying the Pearson criterion to verify compliance with the normal distribution of two random data samples, one of which meets the normal distribution law. The obtained graphic and numerical results of computer modeling confirm the correspondence of one of the testable distributions to a given normal distribution according to the null hypothesis.