Envíos recientes

  • An automatic system for defect detection in plastic crates for glass bottles.

    Juarez, Matthews; Cruz, Anderson De La; Vinces, Leonardo; Vargas, Dante (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    The project describes the design and implementation of an automatic system for detecting defects in plastic crates for glass bottles. In all companies there is damage and defects in their cases, crates, or containers due to constant use, as they are reusable, and therefore this problem causes various economic losses and a decrease in production, especially in beverage companies. This system was designed to solve and prevent the crates from having defects in their base and containing waste inside, to obtain less product losses in the bottle packaging area. In this research, it is proposed to design the automatic system, which consists of training a convolutional neural network with a database of 136 photographs of waste and defects in the boxes that will be taken by the HQ Raspberry Camera; then programmed into the Raspberry the process of activating the engine so that the box is moved to the point where it will be detected by the photoelectric sensor and the inspection is performed; and finally it is classified indicating whether or not it is in optimal conditions. This is developed in Python using different libraries such as OpenCV, TensorFlow, Tkinter among others. Our results show that the classification and object detection accuracy reached 91.84% out of a bank of 264 tests performed.
    Acceso restringido temporalmente
  • Optimization of the dimensions of the Tablachaca sand trap dam with the application of HEC-RAS in Peru

    Guillen, Carlos Banos; Aguila, Juan Diego Guerra Del; Gutierrez, Ruben Mogrovejo (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    This article will detail the steps to model a sand trap in the HEC-RAS software and once modeled, which variables can be modified to obtain greater decantation of particles in the sand trap. The sand trap to be modeled is the one found in the Tablachaca dam. In the first place, the process of designing a sand trap and the variables involved will be explained. Then, it will be explained which variables of the sand trap and contour (environment) intervene in the modeling, to develop the numerical modeling in the HEC-RAS software. It has been determined that the sand trap is divided into 4 naves, each approximately 9 meters wide and 120 meters long, and, for modeling, it was decided to model a single nave. Data on the granulometry of the sediments and flows that reach the Tablachaca dam were obtained from previous works. When modeling the sand trap in HEC-RAS, there is a sedimentation layer of approximately 2.54 centimeters on the side closest to the dam (downstream).
    Acceso restringido temporalmente
  • A development of an automated system for the transportation and cutting of raw glass using a suction gripper and a Fletcher cutter with a KUKA robot

    Salazar, Hector; Yoshimoto, Gonzalo; Vinces, Leonardo; Oliden, Jose (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    Currently, industries need to reduce production times, eliminate the possibility of human errors, and increase company profits. However, this is quite challenging since operators, working long hours each day, are prone to making mistakes due to fatigue or the use of outdated techniques. Taking this into account, this paper proposes the development of a hybrid suction and cutting gripper utilizing a Fletcher cutter attached to a KUKA KR60 robot responsible for cutting and transporting raw glass. The robot's motion is programmed using Kuka Sim Pro, while the design and stress analysis of the hybrid gripper were performed in Inventor. The result was an automated system capable of achieving cuts with a precision of 0.025 mm and a speed ratio of approximately twenty cutting and transportation processes per hour.
    Acceso restringido temporalmente
  • A multi-purpose Gripper for KUKA KR-60 welding robot and inspection chamber

    Escalante, Wilmer; Ydrogo, Elias; Vinces, Leonardo (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    At present, imperfections are still observed in the welding of the vehicle chassis, due to the fact that the inspection of the welding seam is still carried out manually. In other words, there are still companies that depend on an operator to verify the welding, which has resulted in less durability of the vehicle chassis, as they do not have adequate reinforcement when entering areas where greater strength and traction is required. For this reason, the use of a gripper is proposed, the purpose of which will be to carry out and inspect the weld seam. This mechanism consists of the use of 3 tools: MIG torch, dremel and camera, each tool will be used in a certain period of time independently in order to guarantee the correct welding seam. For this purpose, the analysis of the behaviour of the robotic arm will be taken into consideration by using the Denavit Hartenberg algorithm, which helps us to establish the reference systems for each link of the robot. Firstly, MIG welding is used. Secondly, we wait for a short period of time to let the weld bead cool down, then we use the dremel tool with a twisted conical brush accessory to perform a little reaming to remove some surface impurities. Finally, after waiting a short period of time for the effect to take effect, a Logitech c922 camera is used to capture an image of the bead and perform image processing to see what type of imperfection the weld has. The design uses duraluminium, MDF, zinc-plated rods and ABS filament for the 3D printer. The expected result is to obtain a correct quality control of the welding to guarantee the durability of the fundamental part of the vehicle.
    Acceso restringido temporalmente
  • A training system for taekwondo players with impact and linear displacement data collection

    Vasquez, Sebastian; Turpo, Jelson; Vinces, Leonardo; Vargas, Dante (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    Currently, technology does not accompany Peruvian high performance Taekwondo athletes in an efficient way where there is the ability to read all the physical performance data, obtain a database of it constantly and have a system that allows practicing the slide that is often used as footwork. It should be noted that there is not much prominence of the robotic sector to be applied in sport as well as the lack of data records of specific variables that can quantify the skill of high-level taekwondo players. Therefore, the purpose of this article is to promote technological assistance to increase competitiveness in Peruvian taekwondo players and to improve their physical performance. For this purpose, a training system was implemented, which has 'dommys' (kicking shields) of the official brand 'JCALICU' conditioned with a wooden plate, load cells and piezoelectrics for the reception of kicking data. There is also a paddle that will move radially to receive the axe type kick and, for the linear displacement, a motor with chain transmission will be used. The methodology used is programming, I2C serial communication, numerical simulation and PID control. The result is a training system capable of linear displacement and of displaying the data of force, reaction time and precision of the athletes' kicks in a graphic interface.
    Acceso restringido temporalmente
  • A design of a distillation column to produce an alcoholic beverage based on Blueberries

    Susuki, Ken; Ipanaque, Andres; Vinces, Leonardo (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    In various industries, the fruit is utilized to produce derivative products such as beverages, vitamin C masks, jam, ice cream, pastries, among others. This highlights an area that has not been thoroughly explored: its use as a raw material, once fermented, to produce a distilled beverage with a strong presence of antioxidant properties. Various mathematical calculations were performed to obtain a column capable of distilling the fermented product at a maximum temperature of 98 ^{\circ}\mathrm{C} without damaging the antioxidant compounds present in blueberries. Therefore, calculations were made for the number of stages required in the distillation column, the column diameter, the distance between stages, and the simulation of the distillation process for the fermented blueberry must. Therefore, a novel mechanical design of the distillation column was carried out using the rigorous FenskeUnderwood-Gilliland methodology. Additionally, electronic, and electrical equipment were carefully selected to ensure a robust system capable of withstanding unfavourable climates and environments. The designed system was validated through a temperature-induced mechanical stress analysis using ANSYS R2 2022, followed by numerical simulation. With this innovative mechanical design and temperature control system, a production ratio of 1:7 was achieved compared to the initial batch of 50 L of blueberry must for a blueberry-derived alcoholic beverage with a 40% alcohol content and the presence of antioxidants concentration such as resveratrol.
    Acceso restringido temporalmente
  • A development of a mechatronic system to stimulate cognitive skills in children.

    Roncalla, Sofia; Salinas, Ten; Vinces, Leonardo; Oliden, Jose (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    Assisted robots for the treatment of learning for children are currently on the rise and this is thanks to the good potential that robots have to communicate and capture their attention. It is proposed to make a humanoid robot called Potts that will be developed in 3D printing and that can be developed in Peru to improve learning in children with autism spectrum disorder (ASD) in different parts of the country. The robot was manufactured in PLA material and has 8 degrees of freedom in addition to being able to have a graphical interface with the user using two touch screens of 3.5 and 7 inches. It will use a Raspberry Pi control and will have an audio system which can communicate various instructions to the children. An experiment was conducted to compare the efficiency of performing a dynamic practiced by a psychologist versus the proposed robot. As a result, it was obtained that the child obtained fewer wrong answers with the robot than with the psychologist (decrease of repetitions up to 50% less). In addition, the percentage of time that the child kept looking at the psychologist or the robot during the dynamic was calculated. A value of 85% was obtained for following the robot compared to 60% of the time that was spent with the psychologist.
    Acceso restringido temporalmente
  • A comparative analysis of the efficiency between different datasets in the identification of dogs and cats in a CNN

    Garcia, Sebastian; Leon, Adrian Ponce De; Vinces, Leonardo; Oliden, Jose (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    Nowadays, several methodologies and algorithms are being developed to improve image recognition and increase efficiency in species identification. In this context, this paper introduces a comparative analysis of the efficiency between different datasets in the identification of dogs and cats in a convolutional neural network (CNN). In this study, a convolutional neural network architecture with 13 layers was evaluated using three different datasets. In the first set, the 'catsvsdogs' database from TensorFlow was used. In the second CNNN, the network was trained using a set of images that included only dog2 and cat2 species. Finally, in the third CNN the network was trained using a set of images that included only dog3 and cat3 species. The hypothesis put forward is that training a convolutional neural network with customized images of specific dogs and cats improves the accuracy in identifying these species compared to using the TensorFlow dataset. The performance of both models was evaluated using standard machine learning metrics. The results show that the accuracy of the convolutional neural network trained with personalized images increased significantly compared to previous results. Specifically, the recognition accuracy of specific dogs and cats improved considerably. In addition, the training time was reduced by approximately 94.8%, from 116 minutes to only 6 minutes. In conclusion, the use of personalized images in the training set can significantly improve the accuracy in identifying these species in a convolutional network, which can be especially useful in applications such as automatic pet feeders, where high accuracy is required when identifying the pet and providing the correct food.
    Acceso restringido temporalmente
  • A design and analysis of a Darrieus Helical vertical axis wind generator by numerical simulation

    Carpio, Jorge; Banda, Kevin; Vinces, Leonardo; Ronceros, Julio (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    This study addresses the problem of pollution and high energy demand in Peru, caused by population growth in the city. It proposes the use of renewable energy as a solution and seeks to analyze and design a vertical-axis wind turbine (VAWT) with variable rotor radius to evaluate its sustainability in Piura, Peru, as a renewable energy option. Climatological data from the Global Wind Atlas and the Capitán FAP Víctor Montes Arias Airport in Talara, Piura, were used. The blades were designed with aerodynamic models from SANDIA laboratories and analyzed using simulation software such as QBLADE and ANSYS FLUENT. The results indicate that the VAWT is efficient (Cp = 0.58) when the blades are contracted at 13.4 m/s. A closed-loop control is proposed to adjust the rotor radius with an anemometer. In addition, the airfoil behavior is observed by pressure and velocity plots in ANSYS FLUENT.
    Acceso restringido temporalmente
  • A system for detecting objects and estimating their distance using a neural network

    Salcedo, Joan; Ramos, Nehemias; Vinces, Leonardo; Vargas, Dante (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    This article proposes using neural networks to solve the challenge of accurately measuring the distance of an object using cameras and digital image processing. For this, a neural network was trained using a data set that includes information on the distance in pixels of the centers of mass of the object detected by the cameras. This data was used to teach the network to make an accurate estimate of the actual distance of the object. Image analysis methods were also used in conjunction with images of the object previously captured and trained with YoloV8 on Roboflow. The results obtained showed a notable improvement in the precision that is obtained when measuring the distance without the tedious calibration that is had in the other approaches considered for this investigation. Overcame the challenges associated with camera calibration due to possible distortion, accuracy, and generalization generated by changing the environment, resulting in an effective solution with 90% accuracy percentage and a dense neural network with an input layer, a hidden layer and an output layer with 2000 training cycles. These results demonstrate the potential of neural networks and image processing to address distance measurement problems in various applications, such as robotics, road safety, and autonomous navigation.
    Acceso restringido temporalmente
  • Simulation of a mechanical prototype for the extraction of soil sampling using PETG and PLA material

    Culqui, Marcelo; Quispe, Jhon; Vinces, Leonardo (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    Corn production in Perú during the last five years has been reduced for various reasons and the inefficient application of technology, because the progress of technology has been decreasing the intervention of the human hand in the field. For example, the use of automated pivot irrigation systems has had a positive impact on the efficiency of irrigation administered to the plants; however, this system has resulted in the neglect of the plants in the first months, generating a final production lower than that estimated for each harvest season. In view of this, the use of Unmanned Aerial Units (UAV) is proposed in order to collect soil samples around the cultivated field to be delivered to the laboratory for analysis. This mechanism consists of an arm with two degrees of freedom including an extractor that presents an auger with a worm inside, in turn it will have a rotational movement through a reduction box, the design will be manufactured in PLA and PETG material to be implemented in the UAV and perform extractions of samples of sand and soil present in Olmos, Lambayeque, Peru. In addition, this model includes a storage tank for the samples obtained to be able to perform up to three samples at different points during a single flight. The expected result is to obtain up to three samples in a range of 250 grams per extraction point in one flight, so the sampling depth will be 16 cm and a diameter of 6 cm.
    Acceso restringido temporalmente
  • An autonomous navigation system for an unmanned surface vehicle for plastic waste collection

    Figueroa, Piero; Marsano, Luis; Vinces, Leonardo; Vargas, Dante (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    This article proposes the design of an autonomous navigation system intended for Unmanned Surface Vehicles (USVs) in the form of catamarans with differential propulsion, whose primary function is the collection of plastic waste in aquatic environments such as seas and lakes. The fundamental goal of this system is to optimize the operational capabilities of the USVs by increasing their navigational autonomy, consequently reducing the costs associated with their operation and production. In this context, the vehicle has been mathematically modeled, and a navigation system composed of four essential components has been established. The first component involves heading control, which utilizes GPS and IMU to estimate the orientation of the USV. The second component is the obstacle avoidance system, which employs a lidar sensor. The third component is a collection system that relies on a computer vision model with convolutional neural networks to detect different types of plastics and manage the collection process. Finally, an architecture has been designed to facilitate the interconnection of all the aforementioned control systems.
    Acceso restringido temporalmente
  • A numerical simulation of the mechanical structure of an ankle exoskeleton oriented to elderly people

    Rojas, Ammir; Vinces, Leonardo; Ronceros, Julio (Institute of Electrical and Electronics Engineers Inc., 2022-01-01)
    This paper presents the numerical simulation of a 3D mechanical design of an ankle exoskeleton for elderly users. The ankle is one of the most injury-prone joints due to its irregular - sphere shape and elderly people are more prone to this damage (approximately 80% of patients with a history of ankle sprain undergo surgery for post-traumatic ankle osteoarthritis [1]). This problem generates a decrease in muscular resistance on the legs, loss of motor skills, loss of mobile autonomy, etc. The simulation of this exoskeleton is intended to reduce these problems by means of this low-cost mechanism, since similar options exist, but they are not within the economic reach of all. For this reason, anatomical measurements of an elderly user were taken to obtain an ergonomic and easy-to-use mechanical design. Biomechanical calculations were also performed on the ankle to define its displacement and rotation angles. Finally, the designed parts were assembled to validate the mobility of the system and numerical simulations were performed to determine safety coefficients, Von Misses stress, and deformations within the Autodesk Inventor 3D CAD software.
    Acceso restringido temporalmente
  • AR and VR Training System for Children with ASD: A Detailed and Innovative Review

    Huamanchahua, Deyby; Valenzuela-Lino, Yadhira; Ortiz-Zacarias, Jhon; Manco-Fernandez, Fiorela (Institute of Electrical and Electronics Engineers Inc., 2022-01-01)
    Augmented Reality (AR) and Virtual Reality (VR) are emerging technologies that have increased their implementation in research. This has allowed the construction of interactive systems that have become part of modern teaching methodologies. The use of these technologies for the development of training systems provides opportunities for improvement in teaching environments, especially for children with Autism Spectrum Disorder (ASD). They require special education due to their different abilities. Previous research has developed learning systems for children with ASD with different approaches and methodologies. Thus, the present article provides a detailed review of AR/VR educational systems oriented to children with autism. We obtained 24 research papers on the topic from 2017 to 2022, which shows a lack of research works in AR and VR for special education of people with ASD.
    Acceso restringido temporalmente
  • A design and analysis of an autonomous ground vehicle to automate the process of transplanting rice

    Caballero, Roel; Palma, Ricardo; Vinces, Leonardo (Latin American and Caribbean Consortium of Engineering Institutions, 2023-01-01)
    Precision agriculture brought with it the implementation of new digital technologies, mainly autonomous vehicles, satellite images, IoT and artificial intelligence, to provide economic, productive, and environmental benefits in the agricultural field. However, the main applications are focused on data management and monitoring of crop fields, so agricultural processes such as planting and harvesting are not yet fully automated. A clear example of this occurs in the cultivation of rice, which despite being one of the most important agricultural products in the world, the manual production method continues to predominate in developing countries. This work presents a design of an autonomous terrestrial vehicle capable of carrying out the rice transplantation process, having as its main characteristics its ability to move in the field of cultivation at a speed of 0.75m/s, transport a payload of up to 20kg and possess an autonomy of 1 hour. Which translates into an effective field capacity (EFC) of 0.21 ha/h, an operational equivalence of 7 workers/hour and an increase in the productivity of the transplant process of 200% with respect to the manual process. It seeks to provide farmers in developing countries with an affordable option, supported by numerical simulations, with which they can obtain the benefits of precision agriculture in the process of transplanting rice. In such a way, that the manual production of rice and its disadvantages such as low productivity, the physical consequences for the farmers and the limitations against expensive machinery are replaced by the automation proposal.
    Acceso abierto
  • Numerical simulation of a greenhouse coffee drying system using a continuous flow of hot air

    Casas, Jose A.; Chavez, Julio; Oliden, Jose; Vinces, Leonardo (Institute of Electrical and Electronics Engineers Inc., 2022-01-01)
    This paper presents the development and validation of a Coffee Bean Drying System that corresponds to the capacities and needs of small coffee farmers in Peru, which are specifically harvested in regions greater than 800 meters above sea level. This dryer utilizes hot air, which will be introduced into the drying area by a fan, it will be heated using electrical resistances thanks to the principle of Convection, and a new air distribution system will homogenize the flow and speed of the hot air to which the trays filled with coffee beans will be exposed. The coffee beans will enter with an approximate humidity of 50% and will leave the drying chamber with a degree of humidity between the range of 11% to 13%. The thermodynamic analysis of the system was carried out using Computational Fluids Dynamic (CFD) through the ANSYS program, obtaining as a result the validation of the geometry and effectiveness of the hot air distribution system in the dryer, and concluding that the implementation of said element in the system will correspond to an increase in the total efficiency of the Coffee Dryer once implemented.
    Acceso restringido temporalmente
  • Integration of a robotic arm Lynxmotion to a Robotino Festo through a Raspberry Pi 4

    Diaz, Bryan; Pacheco, Nicolas; Vinces, Leonardo (Institute of Electrical and Electronics Engineers Inc., 2022-01-01)
    The robotic mobile system Robotino, developed by FESTO, is a robotic platform oriented towards research and education, which is why it has a reduced amount of actuators of limited real functionality. This article proposes the integration of a Raspberry Pi 4 to a Robotino FESTO with the purpose of expanding the number of digital inputs this robot has, in addition to allow the input of analog signals by serving as a communication interface between devices through an ethernet connection. In this way, the installation of robotic arm Lynxmotion AL5 with 5 degrees of freedom to the Robotino through the Raspberry Pi 4 is proposed so that it performs additional functions and applications without interfering with the digital inputs of the Robotino, that are already used by the sensors and accessories installed by default. By establishing the connection between both devices (Robotino and Lynxmotion AL5 robotic arm),a mobile system of 7 degrees of freedom of great versatility will be obtained. Results validation was made with the Robotino View simulation software and through real tests.
    Acceso abierto
  • Transtibial Electromechanical Prosthesis Based on a Parallel Robot: A Innovate Review

    Huamanchahua, Deyby; Osores-Aguilar, Diego; Leon-Sales, Victor Andre; Valenzuela-Lino, Yadhira S.; Huallanca-Escalera, Harold (Institute of Electrical and Electronics Engineers Inc., 2022-01-01)
    In recent years, the development of prosthetic limbs has increased due to the various studies that have been carried out around Biomechanics. These technological advances have allowed many amputee patients to return to their daily activities and, in some cases, to recover their social life. However, there are still limitations for some types of prostheses such as passive prostheses, mainly those intended for people with transtibial amputations since they do not perform the physiological function of the joints. Therefore, in-depth research on transtibial prostheses has been carried out. The search period spans from the year 2018 to the year 2021. Information was considered in a simplified and well-structured manner on the design of a transtibial electromechanical prosthesis. Therefore, we will analyze its main features related to its design and application in the patient.
    Acceso restringido temporalmente
  • Knee and Ankle Exoskeletons for Motor Rehabilitation: A Technology Review

    Huamanchahua, Deyby; Otarola-Ruiz, Cesar Luciano; Quispe-Pina, Ana; De La Torre-Velarde, Elvis J. (Institute of Electrical and Electronics Engineers Inc., 2022-01-01)
    Exoskeletons have been around since 1890 when a passive device was developed to assist movement. Although the exoskeleton initially focused on the whole body, it has become increasingly focused on a more specific area, which makes rehabilitation work more feasible and, consequently, less costly. Therefore, the purpose of the article is to present a systematic review of trends in the technical area of knee and ankle exoskeletons for rehabilitation purposes. The objective is to provide the interested researcher with a structured matrix that integrates essential components and mechanisms in the development of knee and ankle exoskeletons. As a methodology, specialized databases in biomechanics were used that aided in the collection of research conducted between 2019 and 2022. The filtering process resulted in the selection of 37 investigations. Finally, it was concluded that innovations in exoskeletons contribute to patient rehabilitation and that there is still room for further improvement in the implementation of projects on a commercial scale and the development of new exoskeletons based on previous research.
    Acceso restringido temporalmente
  • A Strategy of Potential Fields and Neural Networks in the Control of an Autonomous Vehicle Within Dangerous Environments

    Chávez, Luisa; Cortez, Angel; Vinces, Leonardo (Springer Science and Business Media Deutschland GmbH, 2022-01-01)
    This article focuses on the development of an autonomous navigation system by generating real-time 3D maps of different urban environments with different properties within simulation software. This system used the Pioneer 3-DX vehicle, a LiDAR sensor, GPS, and a gyroscope. For the elaboration of the trajectory, the mathematical tool of artificial potential fields was used, which will generate an attractive field to a dynamic goal identified by the robot and repulsive to the obstacles present in the environment, recognized with great precision thanks to the use of a neural network. The topology neural network 8–16–32 was developed using forward propagation, reverse propagation, and gradient descent algorithms. By combining the tools of potential fields and neural networks, a path was traced through which the robotic system will be able to move freely under an off-center point kinematic control algorithm. Finally, a 3D map of the environment was obtained to provide information on the morphology and most outstanding characteristics of the deployment environment to users who use the system.
    Acceso restringido temporalmente

Más