Options
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Now showing
1 - 10 of 17
-
PublicationPerformance Prediction of a Reverse Osmosis Desalination System Using Machine Learning( 2021)One of the major challenges that membrane manufacturers, commercial enterprises and the scientific community in the field of membrane-based filtration or reverse osmosis (RO) desalination have to deal with is system performance retardation due to membrane fouling. In this respect, the prediction of fouling or system performance in membrane-based systems is the key to determining the mid and long-term plant operating conditions and costs. Despite major research efforts in the field, effective methods for the estimation of fouling in RO desalination plants are still in infancy, for example, most of the existing methods, neither consider the characteristics of the membranes such as the spacer geometry, nor the efficiency and the day to day chemical cleanings. Furthermore, most studies focus on predicting a single fouling indicator, e.g., flux decline. Faced with the limits of mathematical or numerical approach, in this paper, machine learning methods based on Multivariate Temporal Convolutional Neural networks (MTCN), which take into account the membrane characteristics, feed water quality, RO operation data and management practice such as Cleaning In Place (CIP) will be considered to predict membrane fouling using measurable multiple indicators. The temporal convolution model offers one the capability to explore the temporal dependencies among a remarkably long historical period and has potential use for operational diagnostics, early warning and system optimal control. Data collected from a Desalination RO plant will be used to demonstrate the capabilities of the prediction system. The method achieves remarkable predictive accuracy (root mean square error) of 0.023, 0.012 and 0.007 for the relative differential pressure and permeates Total Dissolved solids (TDS) and the feed pressure, respectively.
-
PublicationCleaning strategies and cost modelling of experimental membrane-based desalination plants( 2021)In Project WASTEC, an experimental Reverse Osmosis (RO) desalination system was developed. It serves as a platform for testing new technologies. For this system, we solved two problems, which are described in this paper. Firstly, we developed and investigated strategies for scheduling chemical enhanced backwashing and chemical cleaning and secondly, due to the experimental nature of the project, several new technological developments with respect to materials and methods were integrated into the system and requires tools for evaluating the economic viability of the new technologies. In this task, the economics of membrane-based desalination will be investigated. Baseline systems of reverse osmosis and pretreatment systems (microfiltration and ultrafiltration) will be economically examined and compared for their investments and operational costs. Sensitivity of the different plant and membrane parameters to the cost will be studied. Results show that with respect to costs, for a 200m3/hr design capacity plant, a volume of water is produced by a MF process at a cost of $0.494 and at a cost of $0.486 by an ultrafiltration process microfiltration. The reverse osmosis process cannot be compared directly, but it required $ 0.49 / m3 for a plant with 56 m3/hour design capacity. The values are in line with the costs reported in literature for membrane-based filtration.
-
-
PublicationDeep Learning for Long and Short Range Object Detection in Underwater Environment( 2021)Docking capabilities are required for long operation of an Autonomous Underwater Vehicle (AUV) due to limited battery and data storage capacity. Docking is composed of four main processes, i.e. homing, plug-in, release and drive-out. The homing part requires detection and localization of the docking station, guidance and control to reach the docking station. Hence, in this paper, we focus on the process of detection and localization. The AUV is assumed to use two sensors for perception of the environment, i.e. an imaging sonar and a monocular camera which is used in close range navigation. Deep learning (DeepL) methods are well-known for good detection and localization. Therefore, in this paper, two DeepL networks will be designed. The first one is for detecting the target object in a sonar image at far range and the other one is for detection of the docking station in the close range using data from an optical camera image. The results from experimental studies in a test basin with an AUV show that the proposed system is able to locate and classify the docking station in both optical and sonar images with detection rate of 94.3% and 80%, respectively.
-
PublicationAn intelligent management system for aquaponics( 2021)Population rise, climate change, soil degradation, water scarcity, and food security require efficient and sustainable food production. Aquaponics is a highly efficient way of farming and is becoming increasingly popular. However, large scale aquaponics still lack stability, standardization and proof of economical profitability. The EU-INAPRO project helps to overcome these limitations by introducing digitization, enhanced technology, and developing standardized modular scalable solutions and demonstrating the viability of large aquaponics. INAPRO is based on an innovation a double water recirculation system (DRAPS), one for fish, and the other one for crops. In DRAPS, optimum conditions can be set up individually for fish and crops to increase productivity of both. Moreover, the integration of digital technologies and data management in the aquaculture production and processing systems will enable full traceability and transparency in the processes, increasing consumers' trust in aquaculture products. In this paper, the innovations and the digitization approach will be introduced and explained and the key benefits of the system will be emphasized.
-
PublicationDeep Learning Based Model Predictive Control for a Reverse Osmosis Desalination Plant( 2020)Reverse Osmosis (RO) desalination plants are highly nonlinear multi-input-multioutput systems that are affected by uncertainties, constraints and some physical phenomena such as membrane fouling that are mathematically difficult to describe. Such systems require effective control strategies that take these effects into account. Such a control strategy is the nonlinear model predictive (NMPC) controller. However, an NMPC depends very much on the accuracy of the internal model used for prediction in order to maintain feasible operating conditions of the RO desalination plant. Recurrent Neural Networks (RNNs), especially the Long-Short-Term Memory (LSTM) can capture complex nonlinear dynamic behavior and provide long-range predictions even in the presence of disturbances. Therefore, in this paper an NMPC for a RO desalination plant that utilizes an LSTM as the predictive model will be presented. It will be tested to maintain a given permeate flow rate and keep the permeate concentration under a certain limit by manipulating the feed pressure. Results show a good performance of the system.
-
PublicationEnhancing aquaponics management with IoT-based Predictive Analytics for efficient information utilization( 2019)Modern aquaponic systems can be highly successful, but they require intensive monitoring, control and management. Consequently, the Automation Pyramid (AP) with its layers of Supervisory Control and Data Acquisition (SCADA), Enterprise Resource Planning (ERP) and Manufacturing Execution System (MES) is applied for process control. With cloud-based IoT-based Predictive Analytics at the fore marsh, it is worth finding out if IoT will make these technologies obsolete, or they can work together to gain more beneficial results. In this paper, we will discuss the enhancement of SCADA, ERP and MES with IoT in aquaponics and likewise how IoT-based Predictive Analytics can help to get more out of it. An example use case of an aquaponics project with five demonstration sites in different geographical locations will be presented to show the benefits of IoT on example Predictive Analytics services. Innovative is the collection of data from the five demonstration sites over IoT to make the models of fish, tomatoes, technical components such as filters used for remote monitoring, predictive remote maintenance and economical optimization of the individual plants robust. Robustness of the various models, fish and crop growth models, models for econometric optimization were evaluated using Monte Carlo Simulations revealing as expected the superiority of the IoT-based models. Our analysis suggest that the models are generally tolerant to the temperature coefficient variations of up to 15% and the econometric models tolerated a variation of for example feed ration size for fish of up to 4% and by the energy optimization models a tolerance of up to 14% by variations of solar radiation could be noticed. Furthermore, from the analysis made, it can be concluded that MES has several capabilities which cannot be replaced by IoT such as responsiveness to trigger changes on anomalies. It act as proxy when there is no case for sensors and reliably ensure correct execution in the aquaponics plants. IoT systems can produce unprecedented improvements in many areas but need MES to leverage their true potential and benefits.
-
PublicationModel-based management strategy for resource efficient design and operation of an aquaponic system( 2018)
;Reyes Lastiri, Daniel ;Geelen, Caspar ;Cappon, Hans J. ;Rijnaarts, Huub H.M. ;Baganz, Daniela ;Kloas, WernerKeesman, Karel J.Aquaponics is a technique that combines aquaculture with hydroponics, i.e. growing aquatic species and soilless plants in a single system. Commercial aquaponics is still in development. The main challenge consists in balancing the conditions required for the growth of multiple species, leading to dynamic a system with high complexity. Mathematical models improve our understanding of the complex dynamics in aquaponics, and thus support the development of efficient systems. We developed a water and nutrient management strategy for the production of Nile tilapia (Oreochromis niloticus) and tomato (Solanum lycopersicum) in an existing INAPRO aquaponic demonstration system in Abtshagen, Germany. This management strategy aims for improved water and nutrient efficiency. For this purpose, we developed a system-level mathematical model and simulation. In our simulations, we found that the existing configuration and water management of the Abtshagen aquaponic system results in an excessive amount of water discharged from the RAS. Therefore, sending more nutrient-rich water from fish to plants can help reducing water and fertilizer consumption. However, this water transfer may lead to excess concentrations of some nutrients, which could stress fish, plants or both. For the Abtshagen system, our simulations predicted excess concentrations of total suspended solids (TSS) for the fish, and sodium (Na+) and ammonium nitrogen (NH -N) for the plants. Furthermore, our simulations predicted excess calcium (Ca2+) and magnesium (Mg2+) for plants, due to the use of local fresh water with relatively high concentrations of those ions. Based on our simulations, we developed an improved management strategy that achieves a balance between resource efficiency and water quality conditions. This management strategy prevents excess levels of TSS for fish, and Na+ and NH -N for plants. Under the improved management strategy, simulated water requirements (263 L/kg fish and 22 L/kg tomato) were similar to current commercial RAS and greenhouse horticulture. Simulated fertilizer requirements for plants of N, Ca and Mg (52, 46 and 9 mg/kg tomato, respectively) were one order of magnitude lower than in high efficient commercial closed greenhouse production. -
PublicationOptimal utilization of renewable energy in aquaponic systems( 2018)Aquaponic systems require energy in different forms, heat, solar radiation, electricity etc. Typical actuator components of an aquaponic system include pumps, aerators, heaters, coolers, feeders, propagators, lights, etc., which need electrical energy to operate. Hybrid Energy Systems (HES) can help in improving the economic and environmental sustainability of aquaponic systems with respect to energy aspects. Energy management is one of the key issues in operating the HES, which needs to be optimized with respect to the current and future change in generation, demand, and market price, etc. In this paper, a Decision Support System (DSS) for optimal energy management of an aquaponic system that integrates different energy sources and storage mechanisms according to priorities will be presented. The integrated model consists of photovoltaic and solar thermal modules, wind turbine, hydropower, biomass plant, CHP, gas boiler, energy and heat storage systems and access to the power grid and district heating. The results show that the proposed method can significantly increase the utilization of HES and reduce the exchange with the power grid and district heating and consequently reduce running costs.
-
PublicationOptimal control of free-floating autonomous underwater vehicles for manipulation tasks in shallow sea culture collection( 2018)
;Li, Daoliang ;Du, Ling ;Bao, Jianhua ;Li, PuThere is an urgent demand for collection operations in the shallow sea cultivation. However, there have been very few investigations on underwater robots for this purpose. The overall objective of this paper is to investigate approaches for combined free-floating AUV and manipulation arm systems to autonomously collect shallow sea culture under complicated underwater conditions. For this purpose, following targets will be gained: 1)Development of new approaches for fast and precise identification and positioning of shallow sea culture (e.g. sea cucumber, dead fish) under complicated underwater conditions (e.g. convoluted terrain, weak light, fluctuating stream);2)Development of a detailed dynamic model for the combined AUV and manipulator system (UVMS) which can be applied for stable and reliable control to autonomously collect sea culture under complicated underwater conditions;3)Development of an optimal control strategy to realize operations for the combined AUV and manipulation arm to autonomously collect shallow sea culture subject to multiple operating constraints. The above objectives can be fulfilled by answering the following questions. A system design to to reliably identify the target object, which need imaging data processing, segmentation and classification, to estimate its position relative to the object, which calls for a position estimator that fuses imaging data (e.g., sonar, vision) with IMU measurements, to control its position relative to the object for station-keeping and the tool at the end of the arm system need to be set in the right position and orientation. The dynamics of both the AUV and the arm system (MS), their interactions with the environment need to be modeled, and to minimize the time, minimum energy, minimum error and smoothness to a target position.