1,720,973 research outputs found
AI Techniques for Waste Water Treatment Plant Control. Case Study: Denitrification in a Pilot-Scale SBR
No full textOptimal set of control parameters for Wastewater Treatment Plants and optimization of instruments placement.
No full textSummary - Nowadays the management of Wastewater Treatment Plants (WWTPs) is even more based on automated and efficient techniques. This contributes largely to the need for a focus on the quality of the information coming from the instruments on the plants.
The relationship between signals and process can help the detection of the best set of parameters in order to control functioning and efficiency of WWTPs, also supported by "intelligent" systems.. Another important point in order to control properly the acquired data, is to know in detail the phases and the operational state of the plant. From that derive the type and the positioning of the instruments in relation with of the process phases. This study starts from an accurate literature update together with the monitoring of real plant management data. This study proposes parameters, control sections and analytical methods indispensable for monitoring and automatic control of full scale plants with urban sewage coming from combined sewer systems
A wawelet based heuristic to dimension Neural Networks for simple signal approximation
No full textBefore training a feed forward neural network, one needs to define its architecture. Even in simple feed-forward networks, the number of neurons of the hidden layer is a fundamental parameter, but it is not generally possible to compute its optimal value a priori. It is good practice to start from an initial number of neurons, then build, train and test several different networks with a similar hidden layer size, but this can be excessively expensive when the data to be learned are simple, while some real-time constraints have to be satisfied. This paper shows a heuristic method for dimensioning and initializing a network under such assumptions. The method has been tested on a project for waste water treatment monitoring
Energy efficient WWTPs: simulation and validation of a decision support system through modelling
No full textMathematical modelling has been tested as a decision support system to management of a biological WWTP, aimed at optimizing energetic efficiency. A conventional activated sludge plant has been studied and the ASM1 mathematical model has been implemented, calibrated and validated, by using West 2012, DHI software. Optimal operating strategies, under different operating conditions, such as variable influent loading, have been defined. Also, indicators concerning energy efficiency and effluent quality have been defined and quantified
Artificial Intelligence based rules for event recognition and control applied to SBR systems
No full textThis work proposes a modular, configurable, online signal analyzer and event detector which can be applied to the control of SBR plants. The control system was developed using pH, ORP and dissolved oxygen process parameters as input, combining neural networks and fuzzy logic rules in an attempt to identify different operational conditions related to the SBR phases (i.e. oxic, anoxic). A set of training signals was analyzed, identifying general features that are then matched in order of detecting global process events, defined using high-level rules. The detection software achieved a percentage of true positives higher than 90% whereas false negatives were mostly due to noisy or ambiguous si
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Monitoring the performance of soft sensors used in WWTPs by means of formal verification
No full textIn Waste-Water Treatment Plant (WWTP) automation, "soft" sensors might be used in conjunction with "hard" sensors to improve the reliability of the measurements, or even to replace the latter when they would be too expensive or difficult to maintain. Unfortunately, many soft sensors are created using black-box data mining techniques such as neural networks or Bayesian networks. These algorithms approximate the relation between simpler, more easily available data and the desired "sensed" quantity. However, they are usually dependent on the training data and cannot always generalise correctly when processing completely different inputs. Like their hardware counterparts, then, soft sensors may have input validity ranges. Moreover, they may be subject to "failures" when analysing inputs for which the training algorithm could not capture the input-output relation correctly. Due to their black-box nature, it is quite difficult to obtain a 100% accurate soft sensor and even more to debug it. So, in our approach, we propose to deploy a soft sensor together with a dedicated monitoring sub-system that processes the inputs and the outputs of the sensor itself. This monitor, created using a specific type of rules supporting the concept of "expectation", applies some logic criteria to define whether a particular sensing is acceptable or not for the purpose of the application using the soft sensor. We will discuss different types of criteria, both qualitative and quantitative, and how they impact the confidence in the estimated measurements. As a use case, we will present a soft sensor for the estimation of the nitrogen compounds in the aeration tank of a 500 litres pilot scale WWTP. Its performance, both in presence and in absence of the monitoring system, will be compared to a real nitrogen sensor placed in the same tank
A hybrid, integrated IEDDS for the Management of Sequencing Batch Reactors
Full text linkAbstract: A Sequencing Batch Reactor (SBR) is a particular kind of wastewater treatment plant (WWTP), where all treatment processes take place in a single reactor tank, according to a fixed temporal sequence. SBR offers several advantages in terms of reduced costs, minor impact and greater flexibility with respect to traditional WWTPs. However, an optimal cost/performance ratio can only be achieved if the treatment processes are continuously monitored and controlled. In this paper, we present a hybrid, distributed, knowledge-based (Intelligent) Environmental Decision Support System (IEDSS) specifically dedicated to the management of SBRs. The IEDSS is responsible for verifying, ensuring and enforcing the compliance of the processes with the optimal operation policies and the current regulations. The core of the IEDSS is composed by a hybrid, declarative knowledge base that encodes the knowledge and best practices for the management of the plant. It relies on OWL ontologies to describe the plant and its hardware equipment, business processes to model the plants treatment cycles, business rules to encode decision-making policies, an improved variant of Event Calculus (EC) to manage the temporal aspects and a compliance mechanism based on extended Event-Condition-Action rules (ECA rule) to monitor and check the compliance of its evaluations and decisions. The system as a whole has been implemented using open source technologies and has been tested on data coming from a pilot plant fed with real urban wastewater
- …
