Moving Conveyor Belt Research Articles

Fish Detection and Classification using YOLOv8 for Automated Sorting Systems

Automation plays a crucial role in scaling up freshwater fish cultivation to address the future threat of food scarcity and meet growing nutrition needs. The fish industry, in particular, develops automation in the sorting and selection processes. However, research on this technology's development is still very limited. In this work, we propose an approach for detecting and classifying fish running on conveyors. We use YOLOv8, which is the most popular and newest deep learning model for object detection and classification. We conducted our test using the KMITLFish dataset, a moving conveyor belt recording that encompasses common cultivated freshwater fish in Thailand along with some endemic species. As a result, our proposed method was able to accurately detect and classify eight types of fish at a conveyor speed of 505.08 m/h. Moreover, we developed this work using a ready-to-use AI platform, intending to directly contribute to the advancement of automatic fish sorting system technology in the fish industry.

Optical detection of plastic waste through computer vision

An incredibly wide range of plastic products and enormous volumes of generated plastic wastes makes sorting technologies highly important. In order to enhance the efficiency and accuracy of sorting process, this article proposes an Internet of Video Things solution based on the deep learning algorithms for image recognition of plastic waste on a moving conveyor belt and embedded intelligence. In particular, the state-of-the-art object detection models, including Faster R-CNN, RetinaNet and YOLOv8 are used. Target categories of plastic are Polyethylene Terephthalate (PET) and Polypropylene (PP). Furthermore, we implemented quantization techniques for trained models on a commercial off-the-shelf embedded system for fast processing time. We achieved a high mean Average Precision (mAP) metric of 77.74% and accuracy of 95.67% on a test set and are fine-tuned and optimized for the deployment on an Nano embedded system providing 20 frames per second. This research contributes to the field of application of Internet of Things by demonstrating the efficacy of deep learning algorithms run on the embedded system in the industrial plastic waste sorting process. The findings highlight the practical applicability of these algorithms and offer insights into resource management and recycling practices.

Real‐time detection of Fusarium infection in moving corn grains using YOLOv5 object detection algorithm

AbstractReal‐time inspection and removal of individual Fusarium head blight (FHB) infected corn grains from the processing lines has been a challenging issue due to the bulk handling and smaller kernel size. In this study, four different variants (small(s), medium(m), nano(n), and large(l)) of You Only Look Once (YOLO) version 5 object detection technique were trained for the detection of Fusarium infection in a moving monolayer of touching and non‐touching corn grains. The YOLOv5 object detection models were evaluated for their performance in detecting FHB infection in individual corn grains. A heterogeneous dataset containing images and video frames of healthy and FHB infected corn grains in different illuminations was utilized. The mean average precision calculated at Intersection over Union threshold of .5 (mAP@50) was 99%, 98%, 95%, and 96% for YOLOv5‐s, YOLOv5‐m, YOLOv5‐n, and YOLOv5‐l models, respectively. The detection speed in videos was 3.9, 1.6, 9.8, and .8 frames per second for YOLOv5‐s, m, n, and l models, respectively. For non‐touching grains, all four variants of the YOLOv5 model showed 100% precision, but for touching grains, all variants showed false negatives in detection of FHB infection, especially on overlapping kernels. The recall values were found to be 98%, 99%, 96%, and 97% for YOLOv5‐s, m, n, and l models, respectively. The best combination of mAP, detection speed, and lower false negatives was achieved by the YOLOv5‐m model. YOLOv5‐m has the potential for use in real‐time detection of Fusarium infection in corn grains apart from lag time in videos.Practical ApplicationThe developed video analysis technique based on YOLOv5 object detection method will be beneficial for the accurate identification of Fusarium infected corn grains in bulk handling facilities. The individual FHB infected grains could be detected on processing lines and could be used for real‐time inspection replacing the random sampling techniques currently used, thereby preventing the entry of Fusarium mycotoxins in the food chain. For non touching corn grains, all the YOLOv5 model variants showed a 100% precision in identifying the healthy and FHB infected grains. For touching grains, YOLOv5‐m model showed the best combination of mAP, detection speed, and lower false negatives proving appropriate for inspection on moving conveyor belts. The nano model with the lightweight architecture installed in portable devices can be used for immediate detection of FHB infection without lag time.

Towards neural network‐based numerical friction models

AbstractFriction contacts can be found in almost all mechanical systems and are often of great technical importance. However, they are usually difficult to describe, and their behavior and influence on the whole system are hard to predict accurately. Modern product design and system operation strongly benefit from numerical simulation approaches today, but reliable friction models still represent a major challenge in this context.To tackle this problem, we employ neural network regression to capture the characteristics of frictional contacts and make them accessible for numerical methods in a minimal intrusive fashion. In particular, we test our approach using a Finite Element model of a 2D cantilever beam subject to stick‐slip vibrations induced by a moving conveyor belt at its free end. As a reference solution, we perform a transient analysis based on a simple analytical friction model, where the kinetic friction force only depends on the normal load and the relative sliding velocity. We take the same friction model, add some artificial noise to mimic uncertainties coming with experimental measurements, and pick a limited set of data points to train a regression neural network. The machine learning friction model is then deployed in the Finite Element code to predict the kinetic friction force acting on the beam tip during the slip phases.The deflection curves obtained by the transient numerical analysis using the new neural network friction model agree well with the reference solution based on the underlying analytical model. The results indicate that data‐driven approaches may also be capable of capturing more complex frictional contacts, including effects of temperature, humidity, and load history. The trained neural network friction models can then be employed in numerical simulations in a minimally intrusive manner. This approach opens up new possibilities to predict individual mechanical system behavior as accurately as possible.

Characterisation and adhesion properties of UV-cured natural rubber-based adhesives

The adhesion properties of rubber adhesives based on SMR-L, ENR-25 and ENR-50 elastomers cured by ultraviolet (UV) light radiation were examined. Various parameters were studied, namely the effects of UV radiation dosages and coating thickness on adhesion properties such as tackiness, peel strength, and shear resistance. Prior to curing, the viscosity of uncured adhesives was analysed in order to understand the effect of adding benzoyl peroxide cross-linker. The reduction of double bonds due to UV-curing was confirmed by FTIR analysis. These adhesives were properly cured after 15 passes (repetitive irradiation on moving conveyor belt) inside UV-curing machine, as proven by both pendulum hardness and gel content tests. Results indicated that for all rubber-based adhesives, 120 μm coated samples showed higher peel strengths than their 60 μm counterparts. ENR-25 based adhesives showed better peel strength as compared to the others, while SMR-L based adhesives possessed higher tackiness and shear resistance than those of ENR-25 and ENR-50 based adhesives.

On the relativistic conveyor belt

A relativistic four-vector fundamental equation formalism is used to analyse processes that are carried out on a conveyor belt, in reference frames S (with the conveyor belt at rest, ground) and (moving conveyor belt frame); these processes involve thermal effects. Examples solved are: a block thrown with initial speed on an inclined plane conveyor belt, and a ring launched with initial linear velocity on a moving belt. For each process, a four-vector fundamental equation is obtained, first in frame S, and then it is transformed by the Lorentz transformation to the process’ four-vector fundamental equation in . It is shown that Newton’s second law and the first law of thermodynamics are no-independent equations. In this description, Newton’s second law in frame , in which forces are non simultaneously applied, includes terms related to linear momentum for heat (relativistic Doppler effect). The first law of thermodynamics in includes the motor’s performed work to keep the belt moving at a constant speed (conveyor belt effect). Classical descriptions of processes are obtained by taking the relativistic equations’ low-speed limit, keeping the conveyor belt effect.

Puffing characteristics of berry slice under continuous microwave puffing conditions

To elucidate the puffing characteristics of the berry slice under continuous microwave conditions, heat and mass transfer and deformation of slices were investigated based on the models of coupled multi-physics fields involving electromagnetic heating, heat and mass transfer and solid mechanics. The results indicated that transmission mode of microwaves in a microwave cavity determined the electric field distribution inside slices with interior focusing phenomenon described by higher temperature and lower moisture content at the central region of slices than that of edge. The berry slice volume showed a “invisible-rapid-maintained” deformation under the synergistic effects of temperature, moisture and internal pressure with sample movement. This study may provide guidance for the elucidation of microwave puffing process of the moving slice and the underlying applications such as technology optimization and quality control of slices like berry. Novelty impact statement This work investigates the puffing characteristics of the moving berry slices under a continuous microwave dryer, and elucidates the heat and mass transfer and deformation process of berry slices by means of experiment and simulation. The distribution of alternating electric field profiles with high and low levels determine the absorption of microwave energy, heat and mass transfer in berry slices to induce the volume deformation and uneven distribution. The volume of berry slices laid on moving conveyor belt under continuous microwave puffing undergoes three deformation trends as invisible change followed by rapid expansion till desired shape.

Implementation of a system for classifying moving parts by color

The purpose of this study is the development and implementation of a computer vision system for color identification in a set of parts, which were disposed on a continuously moving conveyor belt. The process for acquiring the images associated with the parts at issue, the preprocessing and treatment phases performed, as well as the results of the recognition of the feature of interest in each of these are exposed. It is worthy to mention that the feature of interest in the analyzed parts was established from three classes different, associated with the primary colors. The results obtained suggest the effectiveness of the implemented vision system, even as a prototype; which was integrated using low-cost and easy-to-use materials, and whose programming was developed in the open-source software Python, using the OpenCV library. Not only an effective recognition of the class corresponding to each part entered is highlighted, but also the possibility that said operation be executed without the conveyor belt used stopping its moving.

Optimal Strategy for Pick-and-Place System with two Robots

In many situations in industry, a sorting process must be performed to separate different or unnecessary items from those on a moving conveyor belt. In this paper we focus on the problem of how to obtain the optimal pick-and-place (PNP) sequence in a conveyor with two robots. Traditional methods are analyzed and their disadvantages are illustrated, and the algorithm we have developed is presented and accelerated using dynamic planning methods. Furthermore, by building PNPTIME tables, our algorithm considers the complex dynamics and geometry of the different robot models in practice. Our algorithm has sufficient computational speed to be suitable for practical PNP applications requiring high throughput, and extensive testing of the algorithm has shown a 10-20% improvement over traditional methods based on greedy methods.

ОПРЕДЕЛЕНИЕ РАБОЧИХ ПАРАМЕТРОВ ЛЕНТОЧНОГО ДРАЖИРАТОРА

Conventional methods of seed pelleting involve using pelletizers with a drum-type working unit. In these devices, pelleting is carried out in a cyclic mode, which makes operational restrictions and complicates the use of pelletizers in the technological line of complex pre-sowing seed treatment. The authors evaluate the effectiveness of belt-type pelleting machines ensuring the continuity of pelleting and significantly increasing the performance. The paper provides some basic requirements to continuous seed pelletizing. The conditions are determined to describe the pellets rolling down the inclined surface of the moving conveyor belt. Consequently, the analytical relationship is established between the inclination angle of the pelletizer belt and the friction coefficient, the pellet diameter and speed of their forward movement along the conveyor belt. The main operating parameters of the belt pelletizer are determined – length, speed, and the inclination angle of the conveyor belt. The obtained mathematical expressions are universal, since they allow analyzing the working parameters of the pelletizers when processing crop seeds with different initial size, weight, and tribotechnical properties. When studying the movement of the coated seeds along the moving belt of the inclined conveyor, the friction force acting on them, the reaction force of the support, the authors took into account the rolling force and the gravity force. Based on the analogy of the translational movement of seeds along an inclined plane to their movement along the inner surface of the drum of an infinitely large radius, the authors established the numerical values of the parameters of continuous pelleting. The paper finishes with a conclusion about possible reducing the dimensions of the belt-type pelletizer. The estimated length of the working area of the conveyor belt is suggested to be the sum of the lengths of several belts inclined to the ground in different planes.

Integrating Vis-SWNIR spectrometer in a conveyor system for in-line measurement of dry matter content and soluble solids content of durian pulp

The prediction of dry matter content (DMC) and soluble solids content (SSC) in durian pulp were performed using a small laboratory scale in-line visible and short wave near infrared (Vis-SWNIR) spectroscopic system. The fiber optic diode array spectrometer with a charged coupled device (CCD) detector in a wavelength range of 450−1000 nm was used for spectral data acquisition. The spectra of the sample were acquired on the moving conveyor belt in two different orientations, including scanning in the upright position of pulps collected in 2018 and the stable position by scanning on the side of the pulps collected in 2019. Partial least squares regression (PLSR) was used to establish the relationship between the spectra and observed DMC and SSC values using the different wavelength ranges, including 450−1000, 700−1000, and 800−1000 nm for the comparison. The results showed that the durian pulp should be scanned in the upright position at the center of the pulp. Moving average smoothing preprocessing combined with the standard normal variate (SNV) for DMC and multiple scatter correction (MSC) for SSC gave the best result. The suitable wavelength range for model development to predict the DMC and SSC was 700−1000 nm and 800−1000 nm, respectively. After comparing the results, the optimum model showed the coefficient of determination of calibration (RC2), and prediction (RP2), root mean square error of prediction (RMSEP), bias, and the ratio of performance to interquartile distance (RPIQ) of 0.88, 0.83, 4.32 %, 1.25 %, and 3.52 for DMC and 0.70, 0.70, 4.0 %, 0.4 %, and 2.2 for SSC prediction.

Chaos identification of a colliding constrained body on a moving belt

In this work, the combination of the 0–1 test for chaos and approximate entropy is applied to a newly established mechanical model instead of the Lyapunov exponent exploration on huge simulations reached on the supercomputer Salomon (Czech Republic). This procedure is applied to the mechanical systems modeled by a system of non-autonomous ordinary differential equations that detects the type of trajectories generated when the system parameters are changed. This new mechanical system is formed by an impact element hanging on a flexible rope, and a moving belt, etc. This contact system with impacts and dry friction is based on numerous industrial applications such as stones falling on a moving conveyor belt. The mathematical model’s systems of equations have three degrees of freedom: two of them correspond to the position of the impact body center of gravity and the third one to the angular rotation. As the main aim, it is shown that the investigated systems exhibit a full range of trajectory types, meaning it can act in both a regular and irregular way. These results are supported by bifurcation diagrams and phase portraits for a suitable choice of drive parameters: the excitation frequency and amplitude.

Coal and Gangue Separating Robot System Based on Computer Vision.

In coal production, the raw coal contains a large amount of gangue, which affects the quality of coal and pollutes the environment. Separating coal and gangue can improve coal quality, save energy, and reduce consumption and make rational use of resources. The separated gangue can also be reused. Robots with computer vision technology have become current research hotspots due to simple equipment, are efficient, and create no pollution to the environment. However, the difficulty in identifying coal and gangue is that the difference between coal and gangue is small, and the background and prospects are similar. In addition, due to the irregular shape of gangue, real-time grasping requirements make robot control difficult. This paper presents a coal and gangue separating robot system based on computer vision, proposes a convolutional neural network to extract the classification and location information, and designs a robot multi-objective motion planning algorithm. Through simulation and experimental verification, the accuracy of coal gangue identification reaches 98% under the condition of ensuring real-time performance. The average separating rate reaches 75% on low-, medium-, and high-speed moving conveyor belts, which meets the needs of actual projects. This method has important guiding significance in detection and separation of objects in complex scenes.

SyDeBO: Symbolic-Decision-Embedded Bilevel Optimization for Long-Horizon Manipulation in Dynamic Environments

This study proposes a Task and Motion Planning (TAMP) method with symbolic decisions embedded in a bilevel optimization. This TAMP method exploits the discrete structure of sequential manipulation for long-horizon and versatile tasks in dynamic environments. At the symbolic planning level, we propose a scalable decision-making method for long-horizon manipulation tasks using the Planning Domain Definition Language (PDDL) with causal graph decomposition. At the motion planning level, we devise a trajectory optimization (TO) approach based on the Differential Dynamic Programming (DDP) and Alternating Direction Method of Multipliers (ADMM), suitable for solving constrained, large-scale nonlinear optimization in a distributed manner. Distinct from conventional geometric motion planners, our approach generates highly dynamic manipulation motions by incorporating the full robot and object dynamics. Furthermore, in lieu of a hierarchical planning approach, we solve a holistically integrated bilevel optimization problem involving costs from both the low-level TO and the high-level search. Simulation and experimental results demonstrate dynamic manipulation for long-horizon object sorting tasks in clutter and on a moving conveyor belt.

УСТРОЙСТВО И СПОСОБ УПРАВЛЕНИЯ СВЧ-ОБРАБОТКОЙ СЕМЯН НА КОНВЕЙЕРНОЙ ЛЕНТЕ

The sowing qualities of seeds – such as germination, germination energy, weight of 1000 seeds, etc., are the factors ensuring high yields of agricultural crops. Technological methods of seed and grain treatment with the UHF MEMF (microwave electromagnetic fi eld of ultrahigh frequency) energy involve the use of various types of microwave devices, diff ering both in operating principle and in design. In fact, the process of microwave treatment of seeds is similar to the process of heat treatment of dielectric materials. Therefore, depending on the goal of treatment, microwave devices should provide some kind of selectivity of microwave heating, a high conversion factor of microwave energy into thermal energy, uniformity of microwave treatment of the bulk of material, protection of the microwave generator and electromagnetic safety. During the microwave treatment of seeds, it is important to ensure uniform treatment of the bulk of seeds and automatically maintain optimal treatment modes (microwave heating modes). An installation design is proposed for microwave treatment of seeds. A specifi c feature of the proposed design is that seeds are processed on a moving belt under an emitter with the process control and regulation according to the speed and fi nal heating temperature. Moreover, the microwave source intensity depends on the load (a layer of seeds on the conveyor belt). The authors also propose an algorithm for the microprocessor control of the device. Thus, the proposed design of the installation for treating seeds in a layer under the emitter on a moving conveyor belt, as well as the technological algorithm for matching the microwave source with the load ensure the compliance with the processing modes in strictly specifi ed ranges of the fi nal temperature and microwave heating rate of the material, as well as protect the microwave source from refl ected electromagnetic waves.

On obtaining information about the structure and quality of investigated objects revealed from streams of data through the method for identifying structures

This work is devoted to the study of the possibility of using the Method of Identifying Structures in solving important practical problems. The first task is to recognize the type of raw material on the moving conveyor belt based on the reflected radar signal. The second is to determine the structure of the subsurface layer based on data obtained by gamma-ray logging and borehole measurements. The conducted research shows the effectiveness of the proposed method and possibility to obtain more information about the quality and state of the object by not only looking at a single measurement, but instead looking at consecutive measurements as on a data stream.

Identification and Analysis of Blood Group with Digital Microscope Using Image Processing

Blood group identification is an essential examination for transfusion and also for lot of health check procedures. Conventional micro plate system is painstaking. In this study, an automatic moving conveyor belt setup was developed to assist the diagnosis procedure. Blood group identification is done based on the images acquired through light microscopes. A blood distribution on polystyrene coated bio paper and the captured image data has been analysed using Image Acquisition software. The image morphological patterns were analysed to obtain the identification blood group by capturing its microstructure. At end of each test, based on the clumping and its image morphology of the corresponding colour coding was analysed to identify the blood groups. The focus on the present study is to investigate the chance of quick and precise, sensitivity and concurrent identification of blood group will weigh up its usefulness in the routine use.

8 th Symposium on Mechanics of Slender Structures 2019 (MoSS2019)

8 th Symposium on Mechanics of Slender Structures 2019 (MoSS2019)

Pickled and dried mustard foreign matter detection using multispectral imaging system based on single shot method

This paper investigated a usage of multispectral imaging system based on single shot method for detecting the foreign matter (FM) in the pickled and dried mustard (PDM) on a moving conveyor belt. Multispectral images of PDM and FM in a quiescent state and the PDM mixed with FM in a moving state were respectively obtained using the multispectral imaging system with a spectral range from 676 to 952 nm and spatial resolution of 409 × 216 pixels. Pure pixel data of PDM and FM were extracted from multispectral images of the PDM and the FM in a quiescent state. For the pixel-level classification, the support vector machine (SVM) and the back propagation neural network (BPNN) were applied to develop models to classify FM and PDM on the full bands, respectively. The classification accuracy and the mean prediction time of SVM model were 98.23% and 6.8s; the classification accuracy and the mean prediction time of BPNN model were 98.07% and 0.04s. The BPNN model was selected as the optimal model considering the classification accuracy and prediction time synthetically. Using the optimal model to detect FM in the PDM during the moving process, the identification accuracy of FM was 97.9%. The results demonstrated that multispectral imaging system could be used for the online detection of foreign matter in the pickled and dried mustard.

Hydrodynamic Kelvin-Voigt Model Transportation System

The hydrodynamic Kelvin-Voigt model of production systems with a flow method of organizing production is considered. The main macro parameters of the state of the production line and the relationship between them are determined. The analysis of the main characteristics of models of elastic elements, which are used to analyze the occurrence of the dynamic stresses in a moving conveyor belt, is presented. A boundary value problem for elastic longitudinal vibrations in a conveyor belt with a moving material is formulated. It is assumed that the deformation of the conveyor belt element corresponds to the Kelvin-Voigt model and there is no sliding of the moving material on the belt. When determining the forces of resistance to motion acting on an element of the belt, the recommendations of DIN 22101: 2002-08 were used. The analysis of the Kelvin-Voigt model of the elastic element is carried out and the distinctive features of the model are demonstrated. The justification of the choice of the Kelvin-Voigt model of an elastic element for describing the process of occurrence of the longitudinal vibrations in a conveyor belt is given. The dependence of the non-uniform flow of material and the magnitude of tensions in the belt is estimated. An expression is written for the speed of propagation of disturbances along a moving conveyor belt with the material. The reasons for the acceleration and deceleration of the conveyor belt associated with the uneven supply of material at the entrance of the transport system are determined. The relationship between the speed of a conveyor belt and the mass of material along a section of the conveyor is demonstrated. It is shown that an increase in the power of the electric motor at the start and acceleration of the conveyor belt, as well as a decrease in power during the braking and stopping of the conveyor belt, is the cause of the appearance of dynamic stresses in it. The characteristic phases of the initial movement of the conveyor belt with the material are analyzed. The process of occurrence of dynamic tensions with the constant and variable acceleration of the conveyor belt for the phase of acceleration and deceleration of the conveyor belt is investigated. For the analysis, a dimensionless model of a conveyor line was used. An expression is obtained for static and dynamic tensions in the conveyor belt. The amplitude of oscillations of dynamic stresses and the characteristic time of damping of oscillations in a conveyor belt is estimated. A quadratic dependence of the speed of damping of a wave of dynamic tensions with an increase in the oscillation frequency is demonstrated. An inversely proportional dependence of the characteristic decay time of the generated dynamic tensions on the value of the viscosity coefficient of the composite material of the conveyor belt is shown.