Real-time Identification Algorithm Research Articles

Research on Positioning and Tracking Method of Intelligent Mine Car in Underground Mine Based on YOLOv5 Algorithm and Laser Sensor Fusion

Precise positioning has become a key technology in the intelligent development of underground mines. To improve the positioning accuracy of mining vehicles, this paper proposes an intelligent underground mining vehicle positioning and tracking method based on the fusion of the YOLOv5 and laser sensor technology. The system utilizes a camera and the YOLOv5 algorithm for real-time identification and precise tracking of mining vehicles, while the laser sensor is used to accurately measure the straight-line distance between the vehicle and the positioning device. By combining the strengths of both vision and laser sensors, the system can efficiently identify mining vehicles in complex environments and accurately calculate their position using geometric principles based on laser distance measurements. Experimental results show that the YOLOv5 algorithm can efficiently identify and track mining vehicles in real time. When integrated with the laser sensor’s distance measurement, the system achieves high-precision positioning, with horizontal and vertical positioning errors of 1.66 cm and 1.96 cm, respectively, achieving centimeter-level accuracy overall. This system significantly improves the accuracy and real-time performance of mining vehicle positioning, effectively reducing operational errors and safety risks, providing essential technical support for the intelligent development of underground mining transportation systems.

Real-time lettuce-weed localization and weed severity classification based on lightweight YOLO convolutional neural networks for intelligent intra-row weed control

Competition for nutrients between intra-row weeds and cultivated vegetables is a major contributor to reduced crop yields. Compared with manual weeding, intelligent robots can improve the efficiency of weeding operations. Developing real-time and reliable robotic systems for weed control in vegetable fields is a significant challenge due to the complexity of real-time identification, localization, and classification of vegetables as well as various weed species. The main purpose of this study was to propose a high-performance, lightweight deep learning model and an intra-row weed severity classification algorithm for real-time lettuce identification and weed severity classification. In this study, a scaling factor (τ = 0.5) was chosen to lightweight the YOLOv7 model. A new Multimodule-YOLOv7-L lightweight model was then developed by combining ECA and CA attention mechanisms, ELAN-B3 and DownC modules. The overall performance of the Multimodule-YOLOv7- L was better than that of other deep learning models, including YOLOv7, YOLOv7-Tiny, YOLOv8m, YOLOv5n-Cabbage, SE: YOLOv5x, YOLOv5s_Ghb, MST-YOLO_CBAM, Citrus-YOLOv7, Pineapple-YOLOv7, MS-YOLOv7 and CBAM-YOLOv7. The precision, recall, mAP@0.5, F1-score, model weight and FPS of the Multimodule-YOLOv7- L model were 97.5 %, 95.7 %, 97.1 %, 96.6 %, 18.4 MB and 37.3 FPS (Image resolution about 3000 × 3000), respectively. An intra-row weed severity classification algorithm based on the Multimodule-YOLOv7-L model was proposed for use in a new mechanical-laser collaborative intra-row weeding robot. The developed algorithm achieved a classification accuracy of 100 % in eight lettuce weed scenarios, with the processing time of a single image ranging from 4-13 ms. The results of this study provided valuable reference for the development of intelligent robots for intra-row weed control. The algorithm proposed in this article can be obtained at https://github.com/H777R/The-intra-row-weed-severity-classification-algorithm.git.

Real time electronic-waste classification algorithms using the computer vision based on Convolutional Neural Network (CNN): Enhanced environmental incentives

An innovative approach is needed to boost the economic value of e-waste by improving metal recovery and facilitating the separation of plastics and valuable metal components. Leveraging deep learning and computer vision technology offers a promising solution for automatically categorizing and sorting e-waste components like copper, printed circuit boards (PCB), steel, glass, and aluminum, presenting significant financial and environmental incentives for increased recycling efforts. In this instance, the real-time object identification algorithms YOLO 7 and 5 were used along with TensorFlow version 2.8.0. The e-waste dataset works incredibly well with TensorFlow and YOLO. For the detection of copper, PCBs, and plastic, the F1 values (F1 score is the harmonic mean of precision and recall; precision is the fraction of relevant instances among the retrieved instances whereas recall or sensitivity is the fraction of relevant instances that were retrieved) were as good as 1.0, whereas the score for steel and aluminum was 0.8. The mean average precision (mAP; for a set of queries, it is the mean of the average precision scores for each query) was 0.96 for all classes, with the highest precision for copper (0.99) followed by PCB (0.981). 240 e-waste objects were independently evaluated using the YOLO v7 model, achieving a remarkable ∼94 % prediction accuracy with a batch size of 16, ensuring robust performance. The real-time e-waste component detection was also done using video clips as well as webcam streaming. Deploying real-time e-waste object detection and sorting can significantly narrow the gap between e-waste accumulation and recycling rates, leading to reduced environmental strain and impact.

Developing an Algorithm for Real-Time 3D Identification of Images

Developing an Algorithm for Real-Time 3D Identification of Images

Real-time grid detection in sheet metal fiber laser cutting through coaxial monitoring

Real-time defects’ estimation and control of the cut quality through the coaxial camera monitoring of the kerf are amongst the most promising developments for laser cutting. In industrial systems, sheets are positioned on a metallic grid creating discontinuities in the cutting process due to unpredictable thickness, blown and resolidified material and the time varying position of the grid. The interaction between laser radiation escaping from the kerf and the grid, along with the difficult outflow of molten material, causes changes in the process emission images. These changes influence the defect estimation approach, and, consequently, the control action. In this work, a real-time grid identification and classification-based machine learning algorithm was developed and tested during the fusion cutting of 6 mm thick Al5754, exploiting a NIR coaxial monitoring system. Real-time control experiments with dross estimates were performed, demonstrating a correct identification of the grid and highlighting a feasible industrial application.

Identification of MHD modes on EAST using a deep learning framework

The improvement of plasma parameters is severely limited by magnetohydrodynamic (MHD) instabilities. The identification of MHD modes is crucial for the study and control of MHD instabilities. In this study, an MHD mode identifier is developed based on a temporal convolutional network and long short-term memory (LSTM) network. The identifier is trained and tested on a small dataset containing 33 shots. Firstly, the temporal convolutional network encodes 27 diagnostic signals and then decodes them using LSTM network with different parameters to obtain the MHD modes and their frequency and intensity. The identifier exhibits an accuracy of approximately 98.38% on the test set and can accurately calculate the frequency and intensity of the MHD modes. To further examine the performance of the identifier, seven shots outside the dataset are used for shot-by-shot testing. The identifier can accurately identify the time period of tearing modes, and the identification accuracies of 2/1 and 3/2 tearing modes are 92.7% and 100%, respectively. The identification accuracy of the fishbone mode is slightly worse, only 82.1%. This is because the fishbone mode occurs intermittently. The frequent switching between the fishbone mode and no MHD behavior affects the identification of the fishbone mode. Overall, through the training of the small datasets, the identifier exhibits a good identification performance for the MHD modes. The proposed data-driven identifier can serve as a reference for establishing a large MHD mode database of EAST as well as a real-time MHD identification and control algorithm.

Real-time identification of asphalt mixture segregation during paving process using digital imaging technique and Four-side static moment

The uniformity of the asphalt mixture is severely affected by aggregate segregation during the paving process, and there are many studies that indicate that segregation may lead to early pavement damage. This study aims to develop a real-time asphalt mixture segregation identification algorithm during paving process based on digital imaging technique and the static moment method. Static moments of the aggregate particles relative to the four boundaries of the image were calculated as an evaluation parameter, and the dispersion coefficient between the static moment of segregated asphalt mixture and the value of uniform asphalt mixture was calculated to quantify the degree of segregation. The algorithm was applied in a filed construction project in Yunnan, China. Comparing the result from the proposed algorithm with the sand patch test shows that the proposed algorithm is capable of detecting the segregation of an asphalt mixture in real-time and that it is accurate in identifying the degree of segregation. In addition, the proposed algorithm is more accurate than the sand patch test for areas where the gradation meets the standard but the distribution of the aggregate particles is not uniform.

Drishti : Real-Time Object Recognition for the Visually Impaired

In 2017, the World Health Organization (WHO) reported that nearly 284 million individuals worldwide experienced some degree of visual impairment, with approximately 39 million individuals suffering from total blindness. People with visual impairments often rely on assistance from others or use canes to move around and identify obstacles. Our proposed system aims to aid the visually impaired by identifying and classifying common objects in real-time, as well as recognizing text from various sources such as documents and signs. This system provides voice feedback to enhance understanding and navigation, and utilizes depth estimation algorithms to determine a safe distance between objects and individuals, promoting self-sufficiency and reducing dependence on others. We employ the COCO image dataset, which contains everyday objects and people, and utilize the Mobilenet SSD algorithm for real-time object identification. To enable real-time Optical Character Recognition (OCR) Text-To-Speech functionality, we employ advanced technologies such as OpenCV, Python, and Tesseract for text detection and recognition, and the Pyttsx3 library for converting recognized text into audible speech. Our proposed system is dependable, affordable, realistic, and feasible.

A dual-loop active vibration control technology with an RBF-RLS adaptive algorithm

Active control strategies have been widely used in micro-vibration isolation with higher performance requirements. Aiming at the problem of insufficient vibration isolation performance due to time delay in feedback control, the ground-based feedforward active control is introduced to compensate in advance for higher pursuit. However, the inaccuracy of the feedforward control reference model severely restricts the vibration isolation performance. With the assistance of RBF neural network algorithm for accurate real-time identification of online model, a feedforward-feedback dual-loop active hybrid control (DAHC) strategy based on the RBF-RLS adaptive algorithm is proposed in this paper. The adaptive feedforward control uses the RBF neural network algorithm to identify the accurate model of the system online, and input it to the transverse filter of the RLS adaptive control algorithm for recursive calculation, which can effectively reduce the system error caused by the inaccuracy of the model. The experimental results show that the accuracy of online model affects the amplitude attenuation performance by 57.1%. DAHC strategy can greatly reduce the resonance peak by 25.02 dB in micro-vibration. Real applicative experiment further proves the effectiveness of our proposed algorithm.

A real-time identification method of network structure in complex network systems

This paper develops a real-time identification algorithm for structures of network systems. We have already proposed a structure identification method for nonlinear network systems with nonlinear couplings by combining Koopman operator theory and a sparse identification method. However, the proposed method is only applicable for offline use under the assumption that the state of an isolated system is available. To relax this assumption, this paper shows that the dynamical model of isolated systems can be extracted from measured data of interconnected systems under some weak restrictions on network structures. We also modify the identification algorithm to obtain real-time identification results with fewer calculation resources and analyse the convergence of the proposed methods. Numerical examples demonstrate that the proposed method can identify network structures in real-time and detect changes in networks correctly.

An automatic real-time cable modal frequency identification and tracking algorithm by combining recursive band-pass filter and recursive Hilbert transform

Cables are essential elements in bridge engineering. The cable force is usually determined by the vibration method using the cable modal frequency. This paper proposes a real-time online identification method of cable modal frequency based on band-pass filter and Hilbert transform. A recursive form of band-pass filtering (RBF) is employed so that the original signal can be filtered for the target frequency band to obtain a single modal signal of the target order of the cable. The recursive Hilbert transform (RHT) is then used to obtain a real-time resolved signal for real-time frequency identification, allowing for real-time identification and tracking of the time-varying modal frequencies at the cable's target order. This method is more efficient than traditional time–frequency analysis methods. According to numerical simulations and actual measurement data. The method is noise-resistant and does not necessitate priori information of the order. The method allows online identification and tracking of time-varying frequency of interest at a specific order. The procedure can be applied to the real-time identification of cable incident frequencies in an online monitoring system, and can also provide a basis for further real-time identification of time-varying cable forces.

Decision support system for real-time segmentation and identification algorithm for wires in mobile terminals using fuzzy AHP method

Decision support system for real-time segmentation and identification algorithm for wires in mobile terminals using fuzzy AHP method

Robust trocar identification and its application in robotic minimally invasive surgery.

In minimally invasive surgery (MIS), instruments pass through trocars which are installed through the incision points. This forms a fulcrum effect and imposes significant constraint. For robotic manipulative operations, the real-time trocar information is a prerequisite. Systems acquire this knowledge either with a prior registration procedure or through coordinated control of their joints. A robust and real-time trocar identification algorithm based on least square (LS) algorithm was proposed in the context of human-robot co-manipulation scenario. Both in vitro and in vivo experiments were performed to verify the effectiveness of the proposed algorithm. The estimated trocar coordinates expressed in the robot base frame were further leveraged to implement an instrument gravity compensation function. An LS based approach can be employed to robustly estimate the real-time trocar information so as to implement more practical robotic functions.

Adaptive model predictive control for actuation dynamics compensation in real-time hybrid simulation

Hybrid simulation is used to obtain the dynamic response of a system whose components consist of physical and numerical substructures. The coupling of these substructures is achieved by actuation systems, which are commanded in closed-loop control setting. To ensure high fidelity of such hybrid simulations, performing them in real-time is necessary. However, real-time hybrid simulation poses challenges since the inherent dynamics of the actuation system introduce time delays, thus modifying the dynamic response of the investigated system. Therefore, a tracking controller is required to adequately compensate for such time delays. In this study, a novel tracking controller is proposed for dynamics compensation in real-time hybrid simulations. It is based on adaptive model predictive control, a linear time-varying Kalman filter, and a real-time model identification algorithm. Within the latter, auto-regressive exogenous polynomial models are identified in real-time to estimate the changing plant dynamics. A parametric virtual case study, encompassing a virtual motorcycle, is used to validate the performance and robustness of the proposed controller. Results demonstrate the effectiveness of the proposed controller for real-time hybrid simulations.

Adaptive bradycardia assessment in preterm infants

In preterm infants, bradycardias associate to critical health conditions. Standard algorithm for bradycardia identification assumes baseline heart rate (BHR) equal to 150bpm and identifies bradycardias when heart rate (HR) decreases below 100bpm. Since preterm infants show BHR varying from 120bpm to 160bpm, a new adaptive algorithm for real-time bradycardia identification was presented. The adaptive algorithm continuously adjusts BHR by averaging HR over the preceding 10-minute window after eliminating out-of-range HR values, and identifies bradycardias when HR decreases below 67% of BHR. Both standard and adaptive algorithms were evaluated using long-term (20.3–70.3h) electrocardiographic recordings of ten preterm infants ("Preterm Infant Cardio-respiratory Signals" database by Physionet). Bradycardias were characterized in terms of rate (BR, h−1) and depth (BD, bpm). Being also indexes of infants’ health conditions, gestational age at birth (GA, days), birth weight (BW, kg) and HR were used to evaluate performances of the algorithms. Association between BR and BD vs GA, BW and HR was evaluated by computation of the correlation coefficient (ρ). Overall, standard and adaptive algorithms identified 516 and 546 bradycardias, respectively; median BR and BD values were comparable (1.25h−1 and 76bpm vs 1.26h−1 and 70bpm, respectively). However, the adaptive algorithm provided higher BD for HR>150bpm, and vice versa. Significant (p value<0.05) correlations were found between BR and HR (ρ=0.69), BR and BW (ρ=−0.76), and BR and HR (ρ=0.76) only when using the adaptive algorithm. Thus, the adaptive algorithm is superior to the standard algorithm and represents a potentially clinically useful tool for real-time bradycardia assessment in preterm infants.

Research on model predictive peak current control algorithm for real-time inductance Identification

Compared with the traditional PI control, the current loop based on model predictive control has better dynamic performance and is widely used in the field of power electronic control. Peak current control (PCC) can conveniently protect the peak current of inductance, avoid the saturation of inductance, and easily realize the over-current protection of converter. In this paper, a model predictive peak current control algorithm for real time inductance identification is proposed for BOOST converter, and a method of double sampling peak current and valley current is proposed to realize real time identification of inductance value in a sampling period, which improves the dynamic performance and robustness of the algorithm. Simulation and experiment show that the proposed method can identify the inductance value in real time and track the reference value of the inductance current in two control periods.

A Real-Time Identification Algorithm and Epidemic Model Associated with Social Distancing Index for Control Applications: COVID-19 Analysis and Simulations in the United States

Marcus V Americano da Costaa1* and Igor M L Patarob2 Author Affiliations 1Department of Chemical Engineering (DEQ), Federal University of Bahia (UFBA), 02 Professor Aristides Novis, Brazil 2CIESOL, Department of Informatics, University of Almer´ıa, Ctra. Almer´ıa, Spain Received: February 09, 2021| Published: February 16, 2021 Corresponding author: Marcus V Americano da Costaa, Department of Chemical Engineering (DEQ), Federal University of Bahia (UFBA), 02 Professor Aristides Novis, Brazil DOI: 10.26717/BJSTR.2021.33.005477

Design and Development of a High-Speed UAS for beyond Visual Line-of-Sight Operations

This paper provides details on best practices for vehicle design for BVLOS missions, with a focus on robust control links and real-time health monitoring.The development work presented herein focuses on a specific mission to set the speed and distance world record for a fully autonomous vehicle, requiring development of analytic tools for estimating vehicle range and endurance, as well as models for predicting command and control link integrity while operating BVLOS. Range and endurance estimates are developed using a novel real-time system identification algorithm onboard the vehicle for aerodynamic parameter estimation, and propulsion system characterization. Flight-testing methods and results are presented demonstrating the capabilities of these algorithms, with results from a unique test-case involving an unintended fault during the record flight. In addition to the vehicle performance assessment, Friis-based models are introduced to provide a pseudo real-time communications link range assessment. The predictive communications range models were refined using specific antenna and system characterization data measured in a compact range facility resulting in a detailed link budget useful for addressing BVLOS command and control requirements. The combination of aircraft and radio-frequency performance prediction models with supporting flight-testing techniques applied to small unmanned aerial systems provides critical insight into the design of future vehicles, and validation of existing systems tasked with performing BVLOS missions.

BIM based cyber-physical systems for intelligent disaster prevention

The cyber-physical systems (CPS) has emerged in the last decade and become one of the most cutting-edge research fields. CPS is a highly integrated system of communication, computing, and control strategies. Although CPS has been studied and applied in some fields such as intelligent transportation, intelligent manufacturing, intelligent buildings, and smart cities, there is a lack of research on CPS based intelligent disaster prevention and mitigation structural system. Because structural disaster prevention and reduction have their own characteristics, it is necessary to investigate CPS based technology and system for intelligent structural disaster prevention and reduction. In this paper, a preliminary study is conducted on cyber-physical based intelligent structural disaster prevention technologies and structural systems using the Building Information Model (BIM) platform. The proposed CPS consists of the multi-source data precision sensing and intelligent control technology in the physical subsystem/layer, reliable data transmission network in the communication subsystem/layer, and real-time identification algorithm of structural state and adaptive control strategy in the information subsystem/layer. Moreover, BIM platform and Internet of things (IoT) technology are adopted for constructing the cloud architecture of CPS to achieve a high degree of integration of monitoring, identification and control, and to improve the real-time and accurate intelligent monitoring of structural disaster prevention and mitigation.

Synchronized Measurement Technology Supported Online Generator Slow Coherency Identification and Adaptive Tracking

In an electric power system, slow coherency can be applied to identify groups of the generating units, the rotors of which are swinging together against each other at approximately the same oscillatory frequencies of inter-area modes. This serves as a prerequisite-step of several emergency control schemes to identify power system control areas and improve transient stability. In this paper, slow coherent generators are grouped based on the direction and the strength of electromechanical coupling between different generators. The proposed algorithm performs low-pass filtering of generator frequency measurements. It adaptively determines the minimal number of the measurements to be processed in an observation window, and performs data selectivity to prevent mixing of interfering coherency indices. Finally, it adaptively tracks grouping changes of slow coherent generators and determines a finite number of groups for an improved affinity propagation clustering. The proposed algorithm is implemented as an online MATLAB program and verified in real-time using RTDS power system simulator with the integration of actual synchronized measurement technology components as hardware-in-the-loop. The obtained results demonstrate the effectiveness of the proposed algorithm for robust and near real-time identification of grouping changes of slow coherent generators during the quasi-steady-state and electromechanical transient period following a disturbance.