Design of Amphibious Vehicle for Unmanned Mission in Water Quality Monitoring Using Internet of Things

Advances in machine learning and IoT for water quality monitoring: A comprehensive review

Water holds great significance as a vital resource in our everyday lives, highlighting the important to continuously monitor its quality to ensure its usability. The advent of the. The Internet of Things (IoT) has brought about a revolutionary shift by enabling real-time data collection from diverse sources, thereby facilitating efficient monitoring of water quality (WQ). By employing Machine learning (ML) techniques, this gathered data can be analyzed to make accurate predictions regarding water quality. These predictive insights play a crucial role in decision-making processes aimed at safeguarding water quality, such as identifying areas in need of immediate attention and implementing preventive measures to avert contamination. This paper aims to provide a comprehensive review of the current state of the art in water quality monitoring, with a specific focus on the employment of IoT wireless technologies and ML techniques. The study examines the utilization of a range of IoT wireless technologies, including Low-Power Wide Area Networks (LpWAN), Wi-Fi, Zigbee, Radio Frequency Identification (RFID), cellular networks, and Bluetooth, in the context of monitoring water quality. Furthermore, it explores the application of both supervised and unsupervised ML algorithms for analyzing and interpreting the collected data. In addition to discussing the current state of the art, this survey also addresses the challenges and open research questions involved in integrating IoT wireless technologies and ML for water quality monitoring (WQM).

Towards online surface water quality monitoring technology: A review

The exponential growth of human population and anthropogenic activities have led to the increase of global surface water contamination especially in river, lakes and ocean. Safe and clean surface water sources are crucial to human health and well-being, aquatic ecosystem, environment and economy. Thus, water monitoring is vital to ensure minimal and controllable contamination in the water sources. The conventional surface water monitoring method involves collecting samples on site and then testing them in the laboratory, which is time-consuming and not able to provide real-time water quality data. In addition, it involves many manpower and resources, costly and lack of integration. These make surface water quality monitoring more challenging. The incorporation of Internet of Things (IoT) and smart technology has contributed to the improvement of monitoring system. There are different approaches in the development and implementation of online surface water quality monitoring system to provide real-time data collection with lower operating cost. This paper reviews the sensors and system developed for the online surface water quality monitoring system in the previous studies. The calibration and validation of the sensors, and challenges in the design and development of online surface water quality monitoring system are also discussed.

An IoT-based water contamination analysis for aquaculture using lightweight multi-headed GRU model

Maintaining the quality of water is essential for the health and productivity of aquatic organisms, including fish in aquaculture ponds. However, water contamination can severely impact fish health and survival, making it necessary to develop monitoring systems that can detect early signs of water contamination. Initial deep learning models had limitations in capturing the temporal and spatial dependencies of time-series data, which can lead to inaccurate predictions. In this paper, we propose a smart monitoring system that uses IoT devices to collect water quality data and segment it into contaminated and non-contaminated categories based on a water toxic index (WTI), a measure of water contamination levels. To address the limitations of early deep learning models for classification of toxic and non-toxic water quality, an enhanced light-weight multi-headed gated recurrent unit (MHGRU) model that captures the spatial and temporal dependencies of water quality parameters. Our study demonstrates that the proposed model outperforms existing models, achieving an impressive accuracy of 99.7% when evaluated on real-time data. Notably, our model also excels when tested on a public dataset, achieving an accuracy of 99.12%. In comparison, best performed existing ANN models achieve accuracies of 99.52% and 98.71% on the respective datasets.

Design and Computational Analyses of Nature Inspired Unmanned Amphibious Vehicle for Deep Sea Mining

This paper presents the design calculations, implementations, and multi-engineering based computational constructions of an unmanned amphibious vehicle (UAmV) which efficiently travels underwater to detect and collect deep-sea minerals for investigations, as well as creative usage purposes. The UAmV is expected to operate at a 300 m depth from the water surface. The UAmV is deployed above the water surface near to the approximate target location and swims underwater, checking the presence of various mining, then extracts them using a unique mechanism and stores them in an inimitable fuselage location. Since this proposed UAmV survives in deep-sea regions, the design construction of this UAmV is inspired by hydrodynamic efficient design-based fish, i.e., Rhinaancylostoma. Additionally, standard analytical approaches are followed and, subsequently, the inimitable components such as wing, stabilizers, propellers, and mining storage focused fuselage are calculated. The computational analyses such as hydrodynamic investigations and vibrational investigations were carried out with the help of ANSYS Workbench. The hydrodynamic pressures at various deployment regions were estimated and thereafter the vibrational outcomes of UAmVs were captured for various lightweight materials. The computed outcomes were imposed in the analytical approach and thereby the electrical energy generations by the UAmV’s components were calculated. Finally, the hydrodynamic efficient design and best material were picked, which provided a path to further works on the execution of the focused mission. Based on the low drag generating design profile and high electrical energy induction factors, the optimizations were executed on this work, and thus the needful, as well as suitable UAmV, was finalized for targeted real-time applications.

A Review of Unmanned System Technologies with Its Application to Aquaculture Farm Monitoring and Management

This paper aims to provide an overview of the capabilities of unmanned systems to monitor and manage aquaculture farms that support precision aquaculture using the Internet of Things. The locations of aquaculture farms are diverse, which is a big challenge on accessibility. For offshore fish cages, there is a difficulty and risk in the continuous monitoring considering the presence of waves, water currents, and other underwater environmental factors. Aquaculture farm management and surveillance operations require collecting data on water quality, water pollutants, water temperature, fish behavior, and current/wave velocity, which requires tremendous labor cost, and effort. Unmanned vehicle technologies provide greater efficiency and accuracy to execute these functions. They are even capable of cage detection and illegal fishing surveillance when equipped with sensors and other technologies. Additionally, to provide a more large-scale scope, this document explores the capacity of unmanned vehicles as a communication gateway to facilitate offshore cages equipped with robust, low-cost sensors capable of underwater and in-air wireless connectivity. The capabilities of existing commercial systems, the Internet of Things, and artificial intelligence combined with drones are also presented to provide a precise aquaculture framework.

Design and Implementation of Morphed Multi-Rotor Vehicles with Real-Time Obstacle Detection and Sensing System

Multirotor unmanned aerial vehicles (MUAVs) are becoming more prominent for diverse real-world applications due to their inherent hovering ability, swift manoeuvring and vertical take-off landing capabilities. Nonetheless, to be entirely applicable for various obstacle prone environments, the conventional MUAVs may not be able to change their configuration depending on the available space and perform designated missions. It necessitates the morphing phenomenon of MUAVS, wherein it can alter their geometric structure autonomously. This article presents the development of a morphed MUAV based on a simple rotary actuation mechanism capable of driving each arm’s smoothly and satisfying the necessary reduction in workspace volume to navigate in the obstacle prone regions. The mathematical modelling for the folding mechanism was formulated, and corresponding kinematic analysis was performed to understand the synchronous motion characteristics of the arms during the folding of arms. Experiments were conducted by precisely actuating the servo motors based on the proximity ultrasonic sensor data to avoid the obstacle for achieving effective morphing of MUAV. The flight tests were conducted to estimate the endurance and attain a change in morphology of MUAV from “X-Configuration” to “H-Configuration” with the four arms actuated synchronously without time delay.

Applications of Unmanned Aerial Systems (UASs) in Hydrology: A Review

In less than two decades, UASs (unmanned aerial systems) have revolutionized the field of hydrology, bridging the gap between traditional satellite observations and ground-based measurements and allowing the limitations of manned aircraft to be overcome. With unparalleled spatial and temporal resolutions and product-tailoring possibilities, UAS are contributing to the acquisition of large volumes of data on water bodies, submerged parameters and their interactions in different hydrological contexts and in inaccessible or hazardous locations. This paper provides a comprehensive review of 122 works on the applications of UASs in surface water and groundwater research with a purpose-oriented approach. Concretely, the review addresses: (i) the current applications of UAS in surface and groundwater studies, (ii) the type of platforms and sensors mainly used in these tasks, (iii) types of products generated from UAS-borne data, (iv) the associated advantages and limitations, and (v) knowledge gaps and future prospects of UASs application in hydrology. The first aim of this review is to serve as a reference or introductory document for all researchers and water managers who are interested in embracing this novel technology. The second aim is to unify in a single document all the possibilities, potential approaches and results obtained by different authors through the implementation of UASs.

LDAP: Lightweight Dynamic Auto-Reconfigurable Protocol in an IoT-Enabled WSN for Wide-Area Remote Monitoring

IoT (Internet of Things)-based remote monitoring and controlling applications are increasing in dimensions and domains day by day. Sensor-based remote monitoring using a Wireless Sensor Network (WSN) becomes challenging for applications when both temporal and spatial data from widely spread sources are acquired in real time. In applications such as environmental, agricultural, and water quality monitoring, the data sources are geographically distributed, and have little or no cellular connectivity. These applications require long-distance wireless or satellite connections for IoT connectivity. Present WSNs are better suited for densely populated applications and require a large number of sensor nodes and base stations for wider coverage but at the cost of added complexity in routing and network organization. As a result, real time data acquisition using an IoT connected WSN is a challenge in terms of coverage, network lifetime, and wireless connectivity. This paper proposes a lightweight, dynamic, and auto-reconfigurable communication protocol (LDAP) for Wide-Area Remote Monitoring (WARM) applications. It has a mobile data sink for wider WSN coverage, and auto-reconfiguration capability to cope with the dynamic network topology required for device mobility. The WSN coverage and lifetime are further improved by using a Long-Range (LoRa) wireless interface. We evaluated the performance of the proposed LDAP in the field in terms of the data delivery rate, Received Signal Strength (RSS), and Signal to Noise Ratio (SNR). All experiments were conducted in a field trial for a water quality monitoring application as a case study. We have used both static and mobile data sinks with static sensor nodes in an IoT-connected environment. The experimental results show a significant reduction (up to 80%) of the number of data sinks while using the proposed LDAP. We also evaluated the energy consumption to determine the lifetime of the WSN using the LDAP algorithm.

Formation tracking of multiple amphibious robots with unknown nonlinear dynamics

Cooperative tracking control problem of multiple water–land amphibious robots is discussed in this article with consideration of unknown nonlinear dynamics. Firstly, the amphibious robot dynamic model is formulated as an uncoupled nonlinear one in horizontal plane through eliminating relatively small sway velocity of the platform. Then cooperative tracking control algorithm is proposed with a two-stage strategy including dynamic control stage and kinematic control stage. In dynamic control stage, adaptive consensus control algorithm is obtained with estimating nonlinear properties of amphibious robots and velocities of the leader by neural network with unreliable communication links which is always the case in underwater applications. After that, kinematic cooperative controller is presented to guarantee formation stability of multiple water–land amphibious robots system in kinematic control stage. As a result, with the implementation of graph theory and Lyapunov theory, the stability of the formation tracking of multiple water–land amphibious robots system is proved with consideration of jointly connected communication graph. At last, simulations are carried out to prove the effectiveness of the proposed approaches.

Development of Response Surface Model of Endurance Time and Structural Parameter Optimization for a Tailsitter UAV

This study designed a vertical take-off and landing tailsitter unmanned aerial vehicle (UAV) with a long endurance time. Nine parameters of the tailsitter UAV were investigated. Using a 2^k full factorial test, 512 experiments on the nine parameters were conducted at their maximum and minimum values. The time coefficient and air resistance were calculated using the computational fluid dynamics (CFD) method under different parameter combinations. The analysis of variance determined that the specific factors influencing the time coefficient and air resistance were the root chord, wingtip chord, wingspan, and sweep angle. By carrying out a central composite design (CCD) test, 25 sample points of the four particular factors were constructed. The time coefficient and air resistance were simulated under different structural parameter combinations using the CFD method. CFD simulation was verified by carrying out a wind tunnel test, and the results revealed that the aerodynamic coefficient error was less than 5%, while the air resistance error was less than 6%. The response surface methodology (RSM) for the time coefficient and air resistance was established using a genetic aggregation method. A multi-objective genetic algorithm (MOGA) was used to optimize the parameters with regard to the maximum time coefficient and minimum air resistance. The optimal structural parameters were wing root chord length at 315 mm, wingtip chord length at 182 mm, wingspan length at 1198 mm, and sweep angle at 16°. Compared with the original layout and size, the time coefficient of the new design of the tailsitter UAV improved by 19.5%, while the air resistance reduced by 34.78%. The results obtained by this study are significant for the design of tailsitter UAVs.

Adaptive Water Sampling Device for Aerial Robots

Water quality monitoring and predicting the changes in water characteristics require the collection of water samples in a timely manner. Water sample collection based on in situ measurable water quality indicators can increase the efficiency and precision of data collection while reducing the cost of laboratory analyses. The objective of this research was to develop an adaptive water sampling device for an aerial robot and demonstrate the accuracy of its functions in laboratory and field conditions. The prototype device consisted of a sensor node with dissolved oxygen, pH, electrical conductivity, temperature, turbidity, and depth sensors, a microcontroller, and a sampler with three cartridges. Activation of water capturing cartridges was based on in situ measurements from the sensor node. The activation mechanism of the prototype device was tested with standard solutions in the laboratory and with autonomous water sampling flights over the 11-ha section of a lake. A total of seven sampling locations were selected based on a grid system. Each cartridge collected 130 mL of water samples at a 3.5 m depth. Mean water quality parameters were measured as 8.47 mg/L of dissolved oxygen, pH of 5.34, 7 µS/cm of electrical conductivity, temperature of 18 °C, and 37 Formazin Nephelometric Unit (FNU) of turbidity. The dissolved oxygen was within allowable limits that were pre-set in the self-activation computer program while the pH, electrical conductivity, and temperature were outside of allowable limits that were specified by Environmental Protection Agency (EPA). Therefore, the activation mechanism of the device was triggered and water samples were collected from all the sampling locations successfully. The adaptive water sampling with Unmanned Aerial Vehicle-assisted water sampling device was proved to be a successful method for water quality evaluation.

Experimental and Computational Methodology for the Determination of Hydrodynamic Coefficients Based on Free Decay Test: Application to Conception and Control of Underwater Robots

Hydrodynamic coefficients are essential for the development of underwater robots; in particular, for their design and navigation control. To obtain these coefficients, several techniques exist. These methods are usually experimental, but, more recently, some have been designed by a combination of experiments with computational methods based on Computational Fluid Dynamics (CFD). One method for obtaining the hydrodynamic coefficients of an ROV (Remote Operated Vehicle) is by using an experimental PMM (Planar Motion Mechanism) or CWC (Circular Water Channel); however, the use of these experimental infrastructures is costly. Therefore, it is of interest to obtain these coefficients in other ways, for example, by the use of simple experiments. The Free Decay Test is an ideal type of experiment, as it has a low cost and is simple to implement. In this paper, two different free decay tests were carried out, to which three different methods for obtaining coefficients were applied. They were compared with results obtained by CFD simulation to conduct a statistical analysis in order to determine their behaviours. It was possible to obtain values of the drag and added mass coefficients for the models analysed, where the values were obtained for an Underwater Drone Robot (UDrobot).

Autonomous In Situ Measurements of Noncontaminant Water Quality Indicators and Sample Collection with a UAV

The objective of this research was to conduct in situ measurements of electrical conductivity (EC), pH, dissolved oxygen (DO), and temperature, and collect water samples simultaneously at different depths using an unmanned aerial vehicle (UAV). The UAV system consists of a hexacopter, water sampling cartridges (WSC), and a sensor node. Payload capacity and endurance of the UAV were determined using an indoor test station. The UAV was able to produce 106 N of thrust for 10 min with 6.3 kg of total takeoff weight. The thrust-to-weight ratio of the UAV was 2.5 at 50% throttle. The decision for activating the water sampling cartridges and sensor node was made autonomously from an onboard microcontroller. System functions were verified at 0.5 m and 3.0 m depths in 6 locations over a 1.1 ha agricultural pond. Average measurements of EC, pH, DO, and temperature at 0.5 m depth were 42 µS/cm, 5.6, 8.2 mg/L, and 31 °C, while the measurements at 3 m depth were 80 µS/cm, 5.3, 5.34 mg/L, and 24 °C, respectively. The UAV-assisted autonomous water sampling system (UASS) successfully activated the WSC at each sampling location. The UASS would reduce the duration of water quality assessment and help practitioners and researchers to conduct observations with lower operational costs. The developed system would be useful for sampling and monitoring of water reservoirs, lakes, rivers, and ponds periodically or after natural disasters.

An Investigation on Pervasive Technologies for IoT-based Thermal Monitoring

Indoor thermal monitoring is a crucial requirement for home automation, which fits inside the ever-growing Internet of Things (IoT) paradigm. The IoT ecosystem aims at connecting every device exploiting specific functions, deployed in a particular place, in order to give the chance to the users to monitor and/or control some aspects of their life, or to demand this task to a proper software. In the thermal monitoring context, IoT provides new opportunities for a dense and/or large-scale distribution of sensors, which have to gather data in order to effectively control the Heating, Ventilation and Air Conditioning (HVAC) system. Several wireless technologies can be exploited for this scope. However, they involve different benefits and drawbacks. In particular, this study is focused on Radio Frequency Identification (RFID) and Bluetooth®, which represent two well-known wireless technological standards used by commercial electronics but suitable also for pervasive IoT systems. These technologies are discussed and compared from several points of view, i.e., flexibility, reliability, battery life and cost of the system. A theoretical analysis highlights their benefits for the application context and evaluates their suitability to dense and large-scale monitoring systems. The theoretical results are supported by an experimental analysis based on the implementation and test of two different systems, one using RFID and the other using Bluetooth technology.

Towards the Internet of Flying Robots: A Survey

The Internet of Flying Robots (IoFR) has received much attention in recent years thanks to the mobility and flexibility of flying robots. Although a lot of research has been done, there is a lack of a comprehensive survey on this topic. This paper analyzes several typical problems in designing IoFR for real applications, including wireless communication support, monitoring targets of interest, serving a wireless sensor network, and collaborating with ground robots. In particular, an overview of the existing publications on the coverage problem, connectivity of flying robots, energy capacity limitation, target searching, path planning, flying robot navigation with collision avoidance, etc., is presented. Beyond the discussion of these available approaches, some shortcomings of them are indicated and some promising future research directions are pointed out.