Manual Mode Research Articles

Machine learning-based clothing recommendation system for women: case study of Lady's confecciones

This paper presents a clothing recommendation system for women based on their body type, aiming to facilitate the purchasing process on the online sales channel of the company Lady's Confecciones located in the city of Santa Marta, Colombia. For this process, a user interface was designed to function in two ways: using a prediction model that takes as inputs a photograph of the user and their height, and a manual mode that receives the measurements of bust, hip and waist. The prediction model implemented the OpenCV library and the skinned multi-person linear (SMPL) model to process images and predict body shape and pose. Five body types were considered: triangle, apple, rectangle, hourglass and inverted triangle, differentiated by bust, waist and hip measurements, according to the conditions provided by the company. The system was able to predict the body measurements of the female participants with a maximum Pearson correlation coefficient of 0.97. For predicting body type, the best results were obtained for the rectangle body shape, with an accuracy of 92.31%.

Drone inspection path planning with self-organizing neural network of elastic Hebbian learning rule

Abstract As the scale of the power grid continues to expand, inspection scenarios become increasingly complex, and inspection and maintenance work in the power industry faces huge challenges. The traditional manual inspection mode has problems such as high cost, low efficiency, and poor safety. Using electric drones to inspect all equipment nodes in the area can effectively reduce operation and maintenance costs and ensure personnel safety. As a key technology to realize autonomous power inspection, UAV path planning needs to overcome difficulties such as long solution time and intersection of inspection paths. Therefore, this article conducts research on UAV path planning algorithms for large-scale power inspections, which is of great significance to improving the efficiency of power inspections. To avoid the occurrence of path intersections and improve the path planning effect, this paper uses the convex hull property in graph theory to design elastic Hebbian learning rules and proposes a self-organizing neural network algorithm based on elastic Hebbian learning rules.

Digital twin for monitoring threshing performance of combine harvesters

The threshing performance of combine harvesters is crucial for minimizing grain losses. However, threshing is a highly complex process, and direct monitoring is infeasible due to high rotational speeds and concealed locations. This study introduces a method to enhance threshing performance monitoring by using digital twin (DT). A sensor network was developed to acquire on-site data. The DT was constructed by integrating a surrogate model of a discrete element model, which describes system responses, with a neural network predicting the future grain breakage rate (GBR). Test results indicate that the DT improved threshing monitoring capabilities and facilitated online optimization of settings. Compared to manual and feedback control modes, the GBR was reduced by 2.08 % and 1.00 %, and the working speed increased by 1.12 km/h and 1.47 km/h. The practical value of this study lies in reducing grain loss and enhancing harvest efficiency, providing advanced technological support for mechanical grain harvesting.

Разработка кроссплатформенного приложения для управления робототехническим комплексом

A brief analysis of the approaches currently used to develop management programs is provided, their application features, advantages and disadvantages are identified. For the study, the development of a cross-platform appli-cation of control systems for robotic complexes (RTC) was chosen, using the example of RTC with MP-11 robotic manipulators. The structure of the control system includes a controller on the Arduino Mega 2560 Pro Mini board with a loaded low-level program and an upper-level program. The development is carried out on the platform.NET MAUI, which allows you to create an application for Windows, Android, and IOS operating systems on a single code base, i.e. the same code is automatically compiled for all operating systems, taking into account their features and applied elements. The control computer is connected via USB, mobile devices via Bluetooth, while data is programmatically transmitted via a serial port. The description of the modes of operation of the developed application, its functioning algorithms, indicating the features of execution for this type of programs and the appearance of forms with elements located on them is given. The program provides manual and automatic modes of operation, as well as control of not only the RTC, but also its model. The key features of this application are the use of a single code base and design for the implementation of desktop and mobile applications for various operating systems without using network resources, unlike web applications.

User Interface and Navigation System for an Electric Vehicle for the Disabled

The purpose of this work is to link a natural user interface and an autonomous navigation system to a conventional wheelchair with two control modalities: manual and automatic. It is taken into account that not all people have the same type or degree of disability, for this reason we seek to implement a user interface that involves different forms of user-machine interaction, with which the user can choose the manual mode that allows direct commands to control the movement of the chair and the automatic mode, which only needs the point or place where you need to go and through predefined trajectories, the autonomous navigation system will execute the necessary movements for the chair to follow the desired route.

Research on key technologies for automatic planning of multiple links on a single node

Abstract Aiming at the problems of slow speed and low efficiency existing in the traditional manual planning method of multiple links on a single node, which cannot fully meet the rapid deployment needs of communication nodes, this paper studies and puts forward two automatic planning technologies of single-node-multi-link based on shortest distance priority and minimum angle priority. This is an automatic planning technology that uses the shortest distance priority to determine the pairing relationship between the multi-scattering antenna of the local communication node and the far-end scattering antenna. It aims to solve the issue of cross-redundancy of distance in wrong planning. Automatic planning technology of single-node-multi-link based on minimum angle priority simulates manual planning mode. Using the concept of minimum angle priority, the pairing relationship between the multi-scattering antenna of the local communication node and the remote scattering antenna is determined. This is achieved by calculating and optimizing the minimum angle of two rays that are formed from the origin of the coordinate system of the local communication node to the local scattering antenna and the remote scattering antenna, respectively. Comparative analysis and simulation experiments prove that the two key technologies proposed in this paper can not only effectively avoid the problem of mutual interference between multiple scattering antennas in this node but also improve the efficiency of multi-link planning on a single node.

Closed-loop Control System Design of Wind Rope Hoisting of Transmission Tower

Abstract The traditional wind rope (tricing pendant) hoisting method of power transmission towers mainly relies on manpower to observe the posture of the hanger and adjust the retraction and release speed of the control rope, so as to avoid the scraping of hanger and the assembled tower body. In this paper, the ADAMS/Cable modeling tool is used to establish the transmission tower hoisting dynamic model with the JC27151CG tower as the object, and the reasonable installation position of the tricing pendant retraction system is analyzed. And based on the reasonable installation position, the hoisting strategy and hoisting control system of JC27151CG tower are studied. The main control system hardware of the control device mainly includes Delta PLC, servo driver, AC contactor and DC relay. The main control program is divided into two modes, manual and automatic, with a closed-loop control servo motor system. The manual mode operates the servo motor through buttons to realize forward and reverse rotation. In automatic mode, the system intelligently adjusts the lifting speed and attitude according to the data of the navigation system to ensure a smooth and safe lifting process. The research outcomes not only offer novel theoretical perspectives and methods for the hoisting of power transmission towers but also provide robust technical support for practical engineering operations.

Liquid Flow Control System Using Arduino Microcontroller

Abstract: An automated system presented here is designed to control the flow of fluid or liquid. The system uses automated peristaltic Pump to control the liquid flow. The peristaltic pump used here is designed and developed by the author according to the requirement of the application. The stepper motor movement of pump is controlled by using Arduino Microcontroller. Liquid flow through the pump is controlled in two ways: Automatic and manual mode. Such systems can be used in small industries for fluid separation from slurry or slug. Also can used where pre described amount of liquid or fluid is required in application.

COMPARATION OF PHOTOGRAMMETRY AND TERRESTRIAL LASER SCANNING METHODS FOR EROSION MONITORING IN THE AREA OF DEVIL’S TOWN: PROJECT “DEMONITOR”

<p>Project "Devils’ town Erosion MONITORing - DEMONITOR" involves the monitoring of accessible earth pillars in the area of Devil’s town, by using a combination of several non‐invasive methods. Terrestrial laser scanning (TLS) and photogrammetric imaging with unmanned aircraft (UAV) as a platform showed as great solutions for 3D modeling of this site and erosion monitoring. In this work it is shown that using manual free flight mode for imaging with UAV gave much better results than the missions performed with predefined flight plans. The desired long‐term effect from this research should have a significant part in the overall socioeconomic development of the municipality of Kuršumlija, and the entire Toplica district.</p>

FriiTriga, a triggered controller with an optical beam shutter using a hard disk drive voice-coil actuator

We present in this article the complete setup to build a triggered controller with a mechanical optical shutter. The system is a low cost, Do-It-Yourself, and easy to implement setup with three functionalities: Manual mode, direct mode with TTL signal command and Triggered mode with a TTL signal command. Our setup is primarily intended to be integrated in optical setup where one needs to control the opening time of a light path, but can be used also for any other setup where one wants to send a TTL signal to command another subsystem (in our case the shutter is that subsystem). The shutter used here is hard disk drive voice-coil actuator, which was already demonstrated to have interesting potentialities to be a mechanical shutter.In the Manual mode, this setup achieves an opening and closing time of 3 ms. In Direct mode with TTL signal command, the setup has a delay response time of 19 ms and a minimum open pulse time of 23 ms. This low cost device which can be made with less than 50€, have similar characteristics with commercial ones which can be twenty times more expensive.

Dual-mode Antenna Tracking System for Rocket Launch Applications

Rocket launches are complex events that require tracking antennas to maintain a communication link. This study introduces a hybrid tracking strategy that combines manual and program modes by utilizing a predetermined trajectory of the rocket. Automatic switching between tracking modes ensures ongoing monitoring, even during unexpected trajectory changes with the monopulse approach. The dual parabolic antenna arrangement enables this switching. The system estimates the monopulse ratio from the signal strength of each antenna, allowing automatic program tracking to shift to manual mode when reception concerns arise. Performance evaluations included manual, programmable, and dual-mode tests. The system responded to human input and automatically aligned the antenna with slight elevation errors during the initial phase. Adjusting the initial elevation reduced the error. The mode transition was examined by measuring the antenna radiation patterns and monopulse ratio. The system’s performance was evaluated in rocket launches, with the rocket trajectory input into the graphical user interface. The antenna exhibited an azimuthal movement of up to 10 °, and the ratio fluctuation values remained within the antenna’s field of view. After 8.8 seconds, the mode switched from program to manual, indicating that the functioning of the system’s functioning was stable.

Development of an unmanned ground vehicle for seed planting

As global population growth intensifies the demand for sustainable food production, the application of robotics to agriculture emerges as a promising solution. This research focuses on the design, development, and deployment of an unmanned ground vehicle for seed planting, also known as a robotic seed planter. The robotic seed planter automates seed planting processes, offering advantages such as increased accuracy, reduced labour requirements, and optimal resource usage. Parametric Technology Corporation (PTC) Creo was used for the structural design, Proteus 8.14 for the circuitry design, and Arduino IDE 2.0 with Visual Studio Code for the programming. The design incorporates seed metering and drilling mechanisms guided by intelligent systems. Results show exceptional accuracy in seed placement (94%), operational efficiency, and adaptability to diverse conditions, with energy consumption relatively low. The planter is equipped with a web application for remote monitoring and control. The application is hosted on one of the microcontrollers and WebSockets protocol is utilized for inter-microcontroller communication. It offers an auto mode for automated planting and Manual mode for easier manoeuvrability. The findings of this study demonstrate the robotic seed planter’s transformative impact on precision agriculture, providing a glimpse into the future of efficient and sustainable farming operations.

Literature Review on Fabrication of Quad Cycle for Handicapped Person

Abstract: In our daily life, we have seen various types of tri-cycles and tri-wheeled vehicles used by the disabled peoples for their locomotion from one place to another. There are several newly developed tri-wheeled vehicles for physically challenged people, which will be operated by manual, electrical and motorized modes. The most commonly used handicapped wheelchair are driven by the manual mode of operation by the use of pedal, but this vehicle provides discomfort to the handicapped persons through weakness in their body and due to their lack of physical fitness in all period of time. Hence, in order to reduce those difficulties various types of moped and modified scooter like vehicles are introduced, which are in the form of semi or fully automated mode of construction and working for their better increase in the comfort for their transportation. This paper overviews the implementation of new conceptual ideas and technologies on handicapped vehicles for the betterment in the preexisting vehicle models for differently abled people and we hope this will be helpful for the further manipulation in developments and provide the guide line for the new innovations in automotive for the physically challenged people.

Control program for the dosing system of dry bulk feed components

The development of intensive farming technologies is impossible without the introduction of modern technologies. The problem of compound feed production in the voiced aspect can be solved not only through the development of new machines and equipment, but also the introduction of modern control systems. The article presents an analysis of existing dispenser control systems. Based on the analysis of programs and control systems, it was revealed that almost all programs are designed to work in limited conditions, some of them do not take into account a number of factors affecting the accuracy of the material supply. Therefore, a control program for a twin-screw dispenser is proposed. When developing the management program, we started from the technological process of dosing. The possibility of controlling two augers was taken into account: first, a large auger (driven by an asynchronous electric motor) turns on and feeds the main part, then it turns off and the second small auger (driven by an asynchronous or stepper motor) turns on, which carries out the filling of the remaining part. In this case, signals about the amount of material supplied are transmitted from weighing sensors (strain gauges). The proposed control program for the twin-screw dispenser is developed for the TM241C24R PLC in the Structured Text (ST) programming language, one of the languages of the IEC61131-3 standard, in the EcoStruxure Machine Expert programming environment. The control is displayed on a liquid crystal display. The main screen displays basic information: the parameters of the electric motor, the recipe and the readings of the weighing sensors. The program allows you to control the operation of dispensers in several modes. In automatic mode, each dispenser supplies only one component. In manual control mode, the dispensers are started and stopped by the operator from the control panel. In this case, it is possible to set the rotation speed of the dispenser shaft. In the dosing mode with two augers, one component is dispensed with two augers. The proposed program will improve the accuracy of dosing in automatic mode.

GazeSwitch: Automatic Eye-Head Mode Switching for Optimised Hands-Free Pointing

This paper contributes GazeSwitch, an ML-based technique that optimises the real-time switching between eye and head modes for fast and precise hands-free pointing. GazeSwitch reduces false positives from natural head movements and efficiently detects head gestures for input, resulting in an effective hands-free and adaptive technique for interaction. We conducted two user studies to evaluate its performance and user experience. Comparative analyses with baseline switching techniques, Eye+Head Pinpointing (manual) and BimodalGaze (threshold-based) revealed several trade-offs. We found that GazeSwitch provides a natural and effortless experience but trades off control and stability compared to manual mode switching, and requires less head movement compared to BimodalGaze. This work demonstrates the effectiveness of machine learning approach to learn and adapt to patterns in head movement, allowing us to better leverage the synergistic relation between eye and head input modalities for interaction in mixed and extended reality.

Dual-threshold control architecture for improved thermal and power management in open-cathode direct methanol fuel cell

A new dual-threshold cascade control scheme is proposed for water management in direct methanol fuel cells. The control architecture is constructed with the goal of adjusting the liquid-level of a methanol solution in an internal storage tank, where this control structure is based on a set point constrained by upper and lower thresholds. The logic of the algorithm is driven by a noninverting and an inverting Schmitt triggers comprising a switching function that sets the master controller on manual mode for periods of time during which the operating temperature of the electricity-generating fuel cell’s stack can be fixed at an optimal value. Automatic control is implemented when either threshold is reached, triggering a level recovery action where the temperature is manipulated to promote or inhibit cathodic evaporative water losses, depending on the existing perturbations. Manual mode is reinstated when a chosen mid liquid-level target is reached. The strategy seeks to avoid water flooding and dry-out states in the device, while ensuring constant power and current production during periods of manual operation. Simulation studies show that the new control method is immune to severe perturbations, which stands in contrast to a standard cascade control scheme that causes significant degradation and unstable electrical performance in the cell under analogous conditions. Unlike the standard cascade control where the operating temperature is seldom close to the optimal operating point, the improved dual-threshold logic is superior such that the desired temperature of operation can be realized during the entire manual mode, enhancing the performance of the variables that critically depend on temperature. The new method realizes a successful power transition from 30 to 40W, demonstrating its ability to meet changes in load demands, where this transfer is implemented by altering the operational temperature from 45°C to 60°C at a constant voltage. The new strategy can be incorporated into a higher-level optimization control layer, where different temperature operating points can be chosen based on user-defined performance criteria. The study focuses on a case of two different points of the polarization curve corresponding to a power of 40W. While the operating point at a current of 2.51A and temperature of 57.5°C has a higher voltage efficiency of 10%, the second point operating at 2.79A and 50°C shows a boost by 7.6% in fuel efficiency over the first point. Hence, a user can choose the optimal operating condition based on specific performance metrics while simultaneously meeting the load demands. Few recommendations are presented to advance this work in the future.

Monitoring and adjustments of combustion parameters in reheating furnaces using a digital tool

Improving the energy efficiency of a reheating furnace is not a simple task because it involves a large number of parameters that, most of the time, are connected in a complex way. To be feasible, the evaluation of such a vast number of variables must be supported by digital tools that are embedded with artificial intelligence. The SMS group has developed a digital tool that effectively supports operators and engineers in enhancing energy efficiency within the reheating furnaces of hot rolling mills. This paper presents a quick study case of the use of Viridis Performance, an application of Viridis Energy & Sustainability Suite, in the analysis and correction of the deviations in the air-gas ratio of a reheating furnace. In this study, a production period of 8 hours was evaluated, during which the air-gas ratio presented a significant deviation. Analysis showed that the probable cause of the deviation was a production stoppage where the furnace control was set to manual mode. A reduction potential of 0.26 Gcal/h and a 13 kg/h decrease in CO2 emissions were identified. Viridis Performance would support the process by guiding the decisions of the operator in a way that energy losses would be avoided or minimized. The potential economic savings were also quantified. This task is performed in the system by Viridis Moneybox, which is another application of Viridis Energy & Sustainability Suite. The results showed potential savings of 13 US $/h. In addition to the gains and savings outlined in this study, the utilization of Viridis Performance encompasses numerous other advantages, such as enhanced operational standardization and improved process capability, to name just a few.

ЭКОНОМИЧЕСКАЯ ЭФФЕКТИВНОСТЬ СИСТЕМЫ ЭНЕРГООБЕСПЕЧЕНИЯ ВАРОЧНОГО КОТЛА С ПРОПОРЦИОНАЛЬНЫМ РЕГУЛИРОВАНИЕМ РАСХОДА ГАЗА

Until recently, heating of rural houses was carried out with coal or wood. Animal feed and food were prepared on electric stoves or on gas stoves with gas cylinder fuel. These are labor-intensive and energy-consuming technologies. The intensively developing gasification of rural areas makes it possible to universally transfer the heating of rural houses and the preparation of feed and food to natural gas. In the presented work, the main evaluation indicator of the digester is the efficiency factor. Equations are given that describe the useful energy consumption for preparing the product in a digester, as well as heat losses for heating metal structures, for compensating for energy losses from the boiler casing, for purging the steam jacket, and energy losses with flue gases. The energy consumption per unit of production was determined when loading the boiler from 100 to 20 liters. It has been revealed that the efficiency of the boiler decreases by almost 2 times if, instead of 100 liters, the cooking tank is loaded with only 20 liters. Based on experimental data, the useful component of the energy spent on heating 100 liters of water to a boil was determined and the boiler efficiency in automatic and manual mode was determined, which was: in automatic mode, efficiency = 0.84, in manual mode, efficiency = 0.7. Taking into account experimental data, the total gas consumption for the full cycle of feed preparation in automatic and manual modes was determined. The annual operating costs from burning gas in a digester in automatic and manual modes and cost savings on energy supply for the feed preparation process were determined.

Tuning the Proportional-Integral-Derivative Control Parameters of Unmanned Aerial Vehicles Using Artificial Neural Networks for Point-to-Point Trajectory Approach.

Nowadays, trajectory control is a significant issue for unmanned micro aerial vehicles (MAVs) due to large disturbances such as wind and storms. Trajectory control is typically implemented using a proportional-integral-derivative (PID) controller. In order to achieve high accuracy in trajectory tracking, it is essential to set the PID gain parameters to optimum values. For this reason, separate gain values are set for roll, pitch and yaw movements before autonomous flight in quadrotor systems. Traditionally, this adjustment is performed manually or automatically in autotune mode. Given the constraints of narrow orchard corridors, the use of manual or autotune mode is neither practical nor effective, as the quadrotor system has to fly in narrow apple orchard corridors covered with hail nets. These reasons require the development of an innovative solution specific to quadrotor vehicles designed for constrained areas such as apple orchards. This paper recognizes the need for effective trajectory control in quadrotors and proposes a novel neural network-based approach to tuning the optimal PID control parameters. This new approach not only improves trajectory control efficiency but also addresses the unique challenges posed by environments with constrained locational characteristics. Flight simulations using the proposed neural network models have demonstrated successful trajectory tracking performance and highlighted the superiority of the feed-forward back propagation network (FFBPN), especially in latitude tracking within 7.52745 × 10-5 RMSE trajectory error. Simulation results support the high performance of the proposed approach for the development of automatic flight capabilities in challenging environments.

The impact of the presence and utilization policy of a dedicated lane on drivers’ preference to use automation and driving behaviour on motorways

Dedicated Lanes (DLs) have been proposed as a potential alternative for the deployment of Connected and Automated Vehicles (CAVs) to facilitate platooning and increase motorway capacity. However, the impact of the presence and utilization policy of such a lane on drivers’ preference to use automation and their behaviour has not yet been thoroughly investigated.In this study, a driving simulator experiment is conducted, where participants drive a CAV in the presence of a DL with different utilization policies. Drivers have the possibility to choose between driving in an automated mode or in a manual mode. In automated mode they could adjust the driving speed and time headway and initiate automated lane changes. Two utilization policies were examined: mandatory versus optional use of DLs when driving in an automated mode. The impact of the presence and utilization policy of the DL on drivers’ preference to use automation and their behaviour in car-following and lane changing are investigated.The study found that while the presence of a DL does not increase drivers’ preference for automation use, it encourages drivers to utilize the DL more when the utilization policy is mandatory (i.e., drivers can only use automation mode when driving on this lane). Furthermore, drivers are more conservative in automated mode and when driving in mixed traffic. However, they perform closer car-following and merge into smaller gaps when driving on DLs which on one hand can increase the capacity of the DLs, but on the other hand can increase the risk of collisions. These results are useful for road operators, and in setting-up a more realistically traffic simulation studies.