Workshop introduces fundamentals of waste water treatment, operation and monitoring. Discussion begins with characterization of wastewater/solid waste and different techniques available. Then biological wastewater treatment will be classified with the objective of understanding aerobic, anaerobic, suspended, attached growth processes and will be presented with established industrial wastewater treatment plants. Overview of organic carbon, bio Phosphorous and nitrogen removal will be presented. Successful design and operation of any wastewater/solid waste treatment plant require knowledge on microorganisms involved, specific reactions they perform, nutritional needs and more importantly environmental and operating parameters which affect for their better performance. Different unit operations belong to primary, secondary and tertiary treatment and their performance will be also discussed. Reactor types used in typical aerobic and anaerobic processes will be presented with the objective of guiding environmental engineer for screening different options. Significance of applying simulations for analysis of wastewater treatment plant will be presented with AQUASIM 2.1f dynamic simulator.
Deep learning allows computational models to learn and represent data with hierarchy of abstraction by implicitly capturing intricate structures of large‐scale data in terms of general features. Deep learning methods encompass neural networks, hierarchical probabilistic models, and many unsupervised and supervised feature learning algorithms. Recently deep learning methods have been shown to outperform in several tasks, such as object detection, speech processing, handwriting synthesis, etc.
At the same time, recent advances in machine learning have made remarkable development to many areas of interest: data-driven or domain-oriented applications can significantly benefit or even promote the development of algorithms, optimization approaches, and network architectures.
Workshop presents existing applications and new research directions on deep learning for engineering, focusing on state-of-the-art methods, such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), autoencoders, and their graphical model, sparse coding, and kernel machine based variants.
Photovoltaic (PV) power conversion systems gain attraction due to low energy pay-back time and low carbon foot print compared to other renewable energy technologies such as wind. Centralized and distributed power conversion systems are used to convert solar energy into electrical energy. Distributed PV power conversion systems are frequently used in small and medium scale applications. Module and sub module level power converters are used in distributed systems such as roof-top PV. However, intermittent nature and seasonal behavior of the solar energy limits the applications of PV as a continuous power source. Energy storing element can be integrated to the system to circumvent this drawback. Application specific energy storing methods improve power processing capability of the system. Such an integration can be done using DC systems due to in-born characteristics of renewable generators and energy storing elements. This gives rise to concept of micro and nano-grids based on DC. DC nano-grids with integrated communication capabilities improve user experience with respect to the concept of zero net energy home. Power electronic converters and communication protocols having energy transfer capability play a significant role in the realization of such a system.
In this workshop, we are going to talk about existing PV power conversion systems architectures and converter topologies to identify limitations of the state of the art technologies. The proposed system architectures such as networked DC nano-grids to circumvent those limitations will be discussed emphasizing current trends.
The tools and concepts developed in the areas of process control and process optimisation has relevance and applicability in all process industries ranging from petrochemicals to biotechnology based production. Process control and real time optimization has the potential to increase plant capacity, reduce energy consumption and increase plant reliability at very low capital costs. The main reason for this low capital costs is because these tools purely work by better managing the unit operations and does not require the installation of additional equipment. In this workshop, we will cover the area of process control and real time optimization from both an industrial and theoretical point of view, and discuss both established and state of the art ideas. We will also discuss implications of applying Process Systems Engineering (PSE) methods and tools together with real world examples and case studies from petrochemical production and industrial bio-based production. While we will look into a couple of case studies across different process industries, we also encourage you to bring your industrial cases studies to discuss. The intended audience for this workshop is both industry and academia.