Flow Rate Demand Research Articles

Electric machine sizing consideration for ePumps in mobile hydraulics

AbstractEnvironmental concerns have pushed toward electrified technologies for off‐road vehicle actuations that can lower greenhouse gas emissions and reduce energy consumption. Replacing a central diesel engine with a dedicated electric machine (EM) as a prime mover for the hydraulic supply offers several opportunities for so‐called ePumps (aka electric‐driven pumps) to maximize energy efficiency and limit the usage of electric materials. This paper discusses the impact of different choices for the ePumps architecture (i.e., fixed vs. variable displacement pump; variable speed vs. fixed speed electrical machine), and on their main design parameters in terms of size and efficiency. Although the procedure followed in the study could be extended to different types of electric and hydraulic units, the paper particularly considers ePumps based on permanent magnet synchronous machines combined with axial piston machines. The importance of properly considering the ePump drive cycle and its cooling requirements is taken into account while addressing energy efficiency, mass, and overall compactness of the solution. The results show that an ePump based on a variable displacement pump, when compared to fixed displacement ePumps, reduces the electrical machine size both in volume and mass up to 40%, when the high‐pressure demand is not combined with high flow rate demand, thus decreasing the cost of the EM. In all drive cycles, the variable speed EM–fixed displacement pump architecture has a higher efficiency, ranging from 1% to 5%, compared to the case of fixed speed EM–variable displacement pump. Finally, the paper compares the advantages and shortcomings of each ePump architecture presented, based on representative drive cycles.

Decision Strategy Tool for the Design of Natural Treatment Systems for Wastewater (NTSW) from Isolated Livestock Farms

This work proposes a series of strategies and tools for the design and characterization of natural treatment systems of wastewater (NTSW) applied in livestock farms, considering the parameters of flow rate (Q), conductivity (EC) and chemical oxygen demand (COD) of the waste generated, farm location, hydraulic retention time (HRT), and removal/reduction rate targets. The high organic load of the effluent generated in these farms has an important environmental impact, which is amplified in insular or isolated territories. The application of such treatment systems has demonstrated their suitability in these environments, but their design lacks proper characterization and sizing tools for their adequate operation. The proposed tools in this work are based on a collection of experimental data over a ten-year period of application of NTSW in real farms. This work contributes to facilitate the design and implementation of NTSW in farms located in isolated, island, or similar-size environments. Finally, as a practical application, an inventory and implementation of the tool developed for livestock farms on the island of Gran Canaria (Spain) is carried out.

Estimation of Queue Length at Signalized Intersection Under Non-Lane Based Traffic Conditions

Excessive queue length is formed at approaches of signalized intersection if demand flow rate exceeds the saturation flow. The analysis of approaching flow at signalized intersections make easier to predict the queue length for avoiding traffic congestion. At congestion level, queue length reaches to maximum, and the traffic flow becomes zero. Measurement of queuing is essential for design and evaluation of traffic flow facilities. The literature review finds various methods for estimating queue length at signalized intersection under homogeneous and heterogenous traffic flow conditions. Traffic flow data was collected at different intersections in Hyderabad city using videography method. The present study determined queue length at approaches of signalized intersection by using the existing methods given in the literature. The results showed the queue length obtained from different methods are failed to match the queue length as observed in the field. Finally, the study developed a multivariable model for predicting queue length by checking the sensitivity of various factors influencing on queue length at the approach of signalized intersections. Further, the model was validated using field data collected at other approaches based on statistical analysis. Statistical evidence confirmed that the queue length estimated from the proposed model well replicates the queue length observed in the field under the given traffic and roadway conditions. The study recommends that the proposed model works well for the signalized intersection operating with a high proportional share (above 30%) of Two-wheeler in the mixed traffic but limited to operating with higher volume conditions.

A novel air flowrate control method based on terminal damper opening prediction in multi-zone VAV system

Damper opening prediction under demand flowrate is the key for the novel feed-forward control method of damper opening and fan frequency, which is widely applied in the VAV system as well as many other processes. This paper proposed a novel damper opening prediction algorithm under demand air flowrate, and a novel air flowrate control method based on this prediction algorithm, which are both verified by the case simulation. The novel prediction algorithm is based on duct network impedance model, and the maximum opening prediction error can be less than ±1° by 5 groups sample identification. The novel flowrate control method does not need static pressure measurement, and can reduce airflow fluctuation time by 55% and fan power consumption by 21.6% compared with constant static pressure setting method, which is potential to replace the static pressure setting method in VAV air conditioning system. The work of this paper provides the basic algorithm and control method for energy saving control of the duct or pipe network in HVAC system.

Development of a hybrid screen channel liquid acquisition device for reliable microgravity transfer of cryogenic fluids

Refueling spacecraft in orbit offers potential benefits to future extended duration missions including increased spacecraft payload capacity and reduced launch cost. However, a key challenge for refueling cryogenic propellants in microgravity conditions is the acquisition of vapor-free liquid propellants from an in-orbit supply tank. This is especially true when the required liquid flow rate is high but residual liquid in the tank must be minimal. Vane-type Propellant Management Devices (PMDs) excel in stabilizing and distributing liquid, but are more susceptible to gas ingestion, and generally only perform well at lower flow rates and/or under favorable acceleration gradients. Screen channel PMDs do not stabilize and distribute the liquid as well, but are less susceptible to gas ingestion, and perform well at higher flow rates and/or under adverse accelerations. Screened channel LADs appear to hold many advantages for a flight cryogenic system with high demand flow rate, however there are currently no flight cryogenic fluid-based screen channel LADs. To address this need, Creare has been working with NASA Glenn to develop a hybrid Liquid Acquisition Device (LAD) for cryogenic propellants consisting of screened channels with attached guide vanes, and a screened sump. Creare’s design forms the flow channel from screen material itself, allowing much higher acquisition surface area per unit volume as compared to existing designs. The screened channel LAD and screened sump are assembled by Creare’s advanced laser welding processes to reliably maintain the pore structure of the screen adjacent to the bonding joints. After completing a series of fabrication trials to validate the reliability and repeatability of the approach, a prototype screen channel was fabricated, and its performance was characterized in LN2 outflow. Results were found to be consistent with single-phase CFD predictions of this geometry for a partially exposed screen channel. Two-phase CFD analysis was conducted to evaluate the performance of the guide vanes in favorably distributing liquid to enhance expulsion efficiency. Preliminary structural analysis was performed on representative geometry for the LAD assembly to assess stresses of the under 5 g acceleration. Using this screen channel geometry and overall design approach, Creare assembled a laboratory-scale hybrid LAD with four parallel gallery arms, a screened sump, and guide vanes. The assembly has been installed in a large dewar for preliminary evaluation in LN2. This unit is planned for delivery to NASA for follow-on investigations using liquid hydrogen.

Urban regeneration plans: Bridging the gap between planning and design energy districts

District regeneration plans introduce demographic and land use changes that influence their energy balance, modifying electricity and heating/cooling demand.Traditional approaches see urban regeneration projects as independent processes with respect to the energy planning ones, ignoring the European Union targets to move towards the energy transition.Smart energy district approach allows to better solutions from the thermodynamic and economic point of view, and to integrate renewable energy sources, which by their nature are ‘fluctuating,’ with the energy demands using a data centre to menage the energy flows.To evaluate the benefits that a district could obtain when integrating energy planning in regeneration plans, the authors analyse the effects of a different approach to the urban design that goes beyond the traditional tasks of designing districts’ spatial aspects and propose a consistent technical analysis during the decision-making process.To do this, after defining strategic targets related to energy and resource issues, the authors implement different scenarios, evaluating the most suitable technologies that can be integrated in the area. The process of modelling and simulating the energy system hour by hour enables to identify the synergies among the energy sectors. This is done by creating models using different energy tools, as the ones used in this work.The research work analyses a real case for a possible process of urban regeneration, of former industrial area in a district located in the city of Naples, through retrofit and re-use of existing buildings, the construction of new ones and the implementation of smart infrastructures.The overall goal of this work is to present and evaluate different development configuration of a smart energy district when going from the planning to the design phase. The analysed system is designed for matching the power and thermal flow rate demands of the district considered, including the power demand of electric vehicles charging stations, as well as the energy for space heating and cooling. A technoeconomic analysis of three technical alternatives has been implemented, each one characterized by a different energy mix, allowing to verify the most suitable option between the individual and central heating and cooling supply. The work considers all the legislative constrains related to the introduction of the Renewable Energy Sources, required for the construction of new buildings in Italy.

Dynamic Analysis and Water Demand Model with EPANET in Drinking Water Distribution Systems

Providing long-term water management in distribution systems is very important for sustainable network management. The basic principle in urban water management is to deliver the desired amount and quality water to the subscribers on time. In order to achieve this, the amount of water demanded in the network should be accurately defined. In demand flow, the amount of demand according to network characteristics, leakage rates, population or number of subscribers, authorized unbilled demand flow in the region should be determined accurately. In the event of a fire in the region, the flow rate required for fire intervention must be provided and sufficient pressure must be created. In order to achieve this, a model in which all components are taken into consideration should be developed in the region. Therefore, this study aimed to create and analyze the demand flow and dynamic model in a distribution system with EPANET. For this purpose, an application was carried out for the pilot isolated region in Malatya central distribution system. During the establishment of the model, necessary data, modeling stages and results obtained were detailed. In the dynamic model, demand flow rates and pressures were monitored for different time periods by making fire analysis.

An integrated fuzzy optimization and simulation method for optimal quality-quantity operation of a reservoir-river system

Abstract In this study, a novel optimization-simulation dynamic approach was developed for optimal water operation of reservoir-river systems to improve the water quality and supply the water demands along a river. To this purpose, the WEAP-QUAL2 K linked model was developed to simulate water quality and quantity, which is dynamically coupled to a fuzzy multi-objective imperialist competition algorithm (FMOICA). The approach's applicability is demonstrated through the case study of the Dez reservoir river in Iran. The simulation and optimization period used was six years (October 2019-September 2025). Stochastic models (SARIMA(1,0,1)(1,1,1)) were used to forecast inflow into the Dez dam reservoir for the simulation period. Given that in the verification stage of the QUAL2 K and WEAP model it was concluded that the model has high accuracy in simulating the parameters of water quality and quantity, two scenarios were considered: the first scenario was used for dynamic coupling of the quantity-quality model (reference scenario), and the second was the fuzzy optimization of a linked model (optimal scenario). The results show that average water supply reliability increased from 86.13% in the reference scenario to 95.76% in the optimal scenario. Also, under the optimal scenario, the river water quality improves. It was also found that environmental flow rate demands of the river are fully supplied in different months.

Development of travel time functions for disrupted urban arterials with microscopic traffic simulation

Urban traffic networks consisting of partially blocked roads often need to remain open to traffic before, during and after disasters because of their vital roles to hazard preparation, emergency response and recovery of urban communities. To conduct effective traffic planning of disrupted transportation networks highly depends on accurate prediction of travel time on partially blocked roads, which is very different from that on intact roads. Due to the lack of appropriate models, travel time prediction approaches developed for intact roads have often been directly applied to partially blocked roads, leading to inaccurate travel time estimates. Unrealistic travel time estimates of partially blocked roads as well as the whole transportation network further affect traffic planning, emergency response and other decision-makings which are heavily reliant on travel time prediction. A new approach to develop travel time functions for partially blocked roads in urban areas is proposed to close this gap based on microscopic traffic simulation. First, an improved model for simulating traffic on partially blocked roads is developed by extending the existing cellular automaton model. Second, the improved traffic model is validated at microscopic and macroscopic levels with measured traffic data from an urban road. Third, traffic simulations under various scenarios with different demand flow rates, truck ratios and blockage ratios are conducted through microscopic simulation experiments. Finally, a set of continuous traffic time functions are further developed for disrupted traffic flow with parameters estimated from the generated traffic data. The developed travel time functions for a typical urban arterial road are then compared with the standard Bureau of Public Roads function. The comparison suggests that the standard Bureau of Public Roads function would considerably underestimate the travel time on partially blocked roads and the proposed travel time functions can offer a more realistic prediction. The proposed methodology of developing the travel time functions of partially blocked roads will be helpful for accurate estimation of traffic demand of post-hazard transportation networks.

Techno-Economic Assessment of an Air-Multiple PCM Active Storage Unit for Free Cooling Application

A latent energy storage (LES) unit is presented in this paper for free space cooling and ventilation application. The unit includes multiple phase change materials (PCM) to advance the thermal performance of common LES units. It is composed by metallic rectangular panels containing commercial paraffins with melting temperatures ranging among 20 °C and 25 °C and surrounded by air channels. The average cooling load of the unit corresponds to approximately 1 kW over 8 h. It fulfils the peak ventilation cooling load during summer of an office building in Portugal. The study provides a techno-economic analysis and the environmental benefits of the LES technology compared to a traditional air conditioning (AC) unit for the cooling and ventilation of an office building. During daytime, the air-multiple PCM unit allows reducing the energy consumption by nearly 200 kWh. The full charging of the PMs during nighttime, requires significant energy consumption due to the high air flowrate demand for full solidification. The competitiveness of such units can be achieved by introducing fins into the panels, allowing double the energy savings. In an overall perspective, the unit presents several benefits such as lower initial cost and reduced maintenance requirements (non-use of refrigerants and batteries) that also allows better personal health issues when related to traditional ACs.

The role of climate change and decentralization in urban water services: A dynamic energy-water nexus analysis

Urban water services, including drinking water supply and wastewater treatment, are highly energy dependent, contributing to the challenges described under the water-energy nexus. Both future climate change and decentralized water system adoptions can potentially influence the energy use of the urban water services. However, the trend and the extent of such influences have not been well understood. In this study, a modeling framework was developed to quantify both the separate and the combined influences of climate change and decentralization on the life cycle energy use of the urban water cycle, using the City of Boston, MA as a testbed. Two types of household decentralized systems were considered, the greywater recycling (GWR) systems and the rainwater harvesting (RWH) systems. This modeling framework integrates empirical models based on multilinear regression analysis, hydrologic modeling, water balance models, and life cycle assessment to capture the complex interactions among centralized water services, decentralized water system adoptions, and climate parameters for cumulative energy demand (CED) assessment, considering all residential buildings in Boston. It was found that climate change alone will slightly increase the energy use of the centralized systems towards the end of the century, due to the cancelation effect amongst changes in water quality, flow rate, and space and water heating demand. When decentralization is considered alone, we found economically viable decentralized systems may not necessarily produce energy savings. In fact, RWH adoptions may increase energy use. When climate change and decentralization are combined, they will increase the water yield and cost savings of the decentralized systems, while reducing the energy use from the centralized systems. When the centralized systems are further added into the picture, the CED of the entire urban water cycle is projected to increase by 0.9% or 2.3% towards the end of the century under climate change if GWR or RWH systems are adopted by respective cost saving positive buildings.

Machine learning assisted development of IT equipment compact models for data centers energy planning

In most data centers, performance reliability is often ensured by setting the amount of airflow provided by the cooling units to substantially exceed that which is needed by the IT equipment. This overly conservative strategy requires additional energy expenditure, which inevitably results in a huge amount of energy being wasted by the cooling system. To eliminate adopting such wasteful policies, conducting proper management of airflow, temperature, and energy is critical. To that end, this work proposes a novel approach to developing a compact IT equipment model at off-design conditions. This model is designed to support thermal and energy management functions in data centers. The benefit of this model is that it can accurately predict not only the IT equipment power consumption, but also the amount of flowrate required for the equipment and the air temperature leaving the equipment. While the compact model’s power consumption was derived as a function of CPU utilization, its flowrate demand and exhaust temperature were obtained from a dynamic detailed CFD model. Results from the compact model were validated with experiments where the maximum mismatch was found to be 5.7% in the outlet temperature field and 11.4% in flowrate. Compared to a state-of-the-art IT equipment compact model, the developed model was found to reduce the prediction error of the equipment’s flowrate and outlet air temperature by up to 5.2% and 9.3 % that of the state-of-the-art IT equipment compact model, respectively.

Trajectory control in roundabouts with a mixed fleet of automated and human‐driven vehicles

AbstractThis paper presents a methodology to control the trajectory of cooperative connected automated vehicles (CAVs) at roundabouts with a mixed fleet of CAVs and human‐driven vehicles (HVs). We formulate an optimization program in a two‐dimensional space for this purpose. A model predictive control‐based solution technique is developed to optimize the trajectories of CAVs at discretized time steps based on the estimated driving behavior of HVs, while the actual behavior of HVs is controlled by a microscopic traffic simulator. At each time step, the location and speed of vehicles are collected, and a decomposition‐based methodology optimizes CAV trajectories for a few time steps ahead of the system time. The optimization methodology has convexification, alternating direction method of multipliers, and cutting plane decomposition components to tackle the complexities of the problem. We tested the solution technique in a case study roundabout with different traffic demand flow rates and CAV market penetration rates. The results showed that increasing the CAV market penetration rate from 20% to 100% reduced total travel times by 2.8% to 35.8%. The analyses indicate that the presence of cooperative CAVs in roundabouts can lead to considerable improvements.

Augmenting the design of a nozzle used in abrasive jet machining process with computational fluid dynamics

The nozzle is an important part that affects the performance of the abrasive jet machining. It is a micromachining process, where the target material is being eroded by the effect of a high-speed continuous flow of abrasive particles, which are move out from a nozzle. A nozzle is required to carry out the particles to remove the material with the help of a large velocity of the microjet. The common nozzle shape presently used in this process is a rectangle and circular shape, which gives a low flow rate and further demands to reduce the material removal rate (MRR). In this work, three different geometrical types of nozzles: (i) convergent nozzle (25 mm) length, (ii) convergent nozzle (50 mm) length, (iii) modified convergent nozzle has been designed. The simulations of the flow have been analyzed using computational fluid dynamics. The velocity and pressure of the particles inside the nozzle were compared. The results show the improvements in the modified convergent nozzle are about 42.84 m/s of velocity and the pressure inside the nozzle tip is about 994424.5 Pa. Due to the swirl flow in a modified convergent nozzle, the high material removal rate is achieved.

A review of the state-of-the-art nanofluid spray and jet impingement cooling

Nanofluid spray/jet impingement cooling is widespread and finds applications in many scientific and industrial paradigms. Because of these ubiquities of nanofluid spray/jet impingement cooling, this branch of fluid dynamics has attracted great attention from the scientific community. The performance of nanofluid spray/jet impingement cooling very often depends on the nanoparticle concentration, shape, and size of the nanoparticle, as well as the mass flow rate of the nanofluid. These aspects lead to interesting variants of the thermo-hydrodynamic analysis of the nanofluid, which are studied meticulously, and some new functionalities are established such as high heat flux removal capacity, temperature uniformity, lower flow rate demand, and no thermal resistance to the heated test surface. We provide an overview of nanofluid spray/jet impingement cooling with an emphasis on the parametric effects, such as the Reynolds number, jet to test surface distance, the Prandtl number, the confinement of the jets, test plate inclination, and the roughness of the test surface, on the underlying phenomenon. Also, we aptly discuss the essential features of the nanofluid spray/jet impingement cooling, which includes spray properties, cooling fluid properties, substrate properties, and environmental conditions, which affect the heat transfer of spray cooling.

Selection, control and techno-economic feasibility of Pumps as Turbines in Water Distribution Networks

Abstract Water Distribution Networks (WDNs) are becoming an attractive area of application for small hydropower, which can contribute to the development of distributed energy generation from renewable sources. Indeed, WDNs experience considerable water leakages due to their age and water management authorities often divide the WDNs by inserting Pressure Reducing Valves (PRVs), which waste a potentially recoverable hydraulic head. The replacement of PRVs with Pump as Turbines (PaTs) can be considered as an economically feasible solution to achieve both an effective pressure control and a throttling energy recovery. The selection, installation and control strategy of a PaT in a WDN must consider the variability of the pressure and the flow rate demand. Starting from the evaluation of the available head and the water demand, in this work, we describe a methodology to select from pump catalogues the most suitable PaT and the best control criteria for a specific WDN. Then, knowing the pump geometry, it is possible to predict the characteristic curve of the pump operating as a turbine by using a 1-D performance prediction model. The WDN of a town in the Apulia region (Southern Italy) has been used as a case study. Finally, a techno-economic evaluation has been carried out by considering both economic and environmental benefits.

Towards simulating non-lane based heterogeneous road traffic of less developed countries using authoritative polygonal GIS map

Microscopic traffic simulators have become efficient tools to conduct different analytic studies on roads, vehicles, behavior of drivers, and critical intersections, which lead towards a well-planned traffic solution. Devising a realistic and sustainable traffic solution requires replication of the real traffic scenario in a simulator. For example, to simulate the traffic stream of less developed countries, we need to simulate non-lane based heterogeneous traffic stream, i.e., motorized and non-motorized vehicles, with their on road behaviors such as irregular pedestrian, illegal parking, violation of laws pertaining lanes, etc. However, most of the existing traffic simulators are unable to mimic the unstructured road traffic stream of less developed countries with their diversified behaviors. We also need to represent the corresponding geographical maps as a list of nodes and edges with relevant geographic information such as length and width of the edges to feed the simulator. However, we lack a Geographic Information System (GIS) protocol to construct an effective simulator readable road network from authoritative polygonal GIS maps. State-of-the-art GIS protocol often converts the geographical maps using polyline data collected from less-credible OpenStreetMap. Although polyline data has length information (for example, length of a street), it lacks width information limiting its capability of being an effective simulator readable road network map. Therefore, in this work, we propose a new microscopic traffic simulator to handle unstructured road traffic stream of less developed countries with their diversified behaviors. To feed the simulator, we also propose a novel parsing algorithm to construct an effective simulator-readable road network from GIS maps through extracting both length and width information of the edges and develop parser based on the algorithm. Our parsing algorithm realizes a delicate blending of geometry with computation over road points to eventually generate the simulator-readable road network. Our simulator receives the network topology generated by our parser, traffic routes, and traffic demand flow rates as input, visualizes the traffic flows, and provides relevant traffic statistics. To evaluate sustainability of our proposed parser and simulator in real-life scenarios, we evaluate our parser by parsing GIS street maps of four different areas resulting in 86% accuracy on an average and evaluate our simulator after necessary calibration using real traffic data resulting in 99% accuracy in terms of travel time.

A study on the 3D fluid flow of MHD micropump

In this paper, a 3D model of magnetohydrodynamic (MHD) micropump with a rectangular channel was modeled and numerically simulated based on the finite volume method. Effects of geometrical parameters such as depth, width, and length of the side electrodes were studied on the maximum flow rate, maximum pressure, and energy rate of the rectangular MHD channels in constant electric current and constant power supply modes. The multiple attributes decision-making method was used in order to identify the most effective geometrical parameters on the performance of the micropump. Wider channels with long electrodes are identified to be in favor of high performance for high flow rate, high pressure, and energy-efficient demands. A case study of new profile with a widened channel in the pumping section was proposed, and its new geometrical parameters are introduced. Studies at constant energy rate of 1 mW showed that the extension of the channel width (electrode walls) can increase the flow rate up to 1.23 μl/min (34% increase in comparison with non-extended channel). Additionally, it was found that when the extension parameter is set to 3.5 (D/w = 3.5), the flow rate is independent of the elongation parameter (r/R).

Evaluation strategy of particle swarm optimization and it’s application in pumping station system optimal operation

To deal with the high energy consumption issue of existing pumping station operation modes, an optimization model ensuring the flow rate and safety demands of pumping station and aiming at the minimum operating power of the system, is established based on basic Particle Swarm Optimization (PSO), which can provide theoretical support for the optimal operation of pumping station. When solving high dimension problems, PSO is easy to get into local optimum and has a slow convergence rate at the later stage of iteration. In order to overcome the shortcomings mentioned above, the Halton sequence is used to generate the initial population randomly, at the same time the inertia weight reducing along the opening downward parabola and Simulated Annealing(SA) are employed, too. The Improved Hybrid Particle Swarm Optimization (IHPSO) is implemented in Matlab. And it is applied to calculate the optimization schemes of the pumping station system of the South-to-North Water Transfer Project in China. The results show that the convergence and stability of the IHPSO are better than the PSO, and IHPSO can effectively solve pumping station optimization operation with multiple variables. The power of the optimum scheme based on IHPSO is about 7.68% less than that based on PSO, and it is decreased about 11.51% compared with the designed scheme.

Design of a neural network based predictive controller for natural gas pipelines in transient state

In a natural gas network the gas pressure decreases continuously due to friction. The compressor stations are placed in strategic locations of networks to make up for the lost pressure. This ensures the delivery of time-varying customer demands in desirable pressure. Howbeit, the compressor's operational costs constitute the major portion of a network costs.Different approaches can be used to find the optimum operation of the gas network compressor's when the demand profiles are known from the historical data. However, the demand profiles may become different from their long time average. For this case, a novel on-line predictive control scheme is presented in this work. This scheme finds the near optimum operation of the compressor more easily and in much less computational time, while eliminating the necessity of re-solving the optimization problem.The proposed strategy utilizes two multi layered neural networks (MLNNs) for on-line prediction and control tasks. The NN predictor is used for on-line prediction of highly nonlinear dynamics of the gas network in transient state. The on-line NN controller uses the prediction information to find the near optimum control inputs (rotational speeds of the compressors) to provide the new desired demands. This can be achieved by tracking the previously obtained optimum outlet pressures of the network.The controller results are validated with another controller which uses the particle swarm optimization (PSO) algorithm as the optimizer. To investigate the controller operation in performing the optimization task, its simulation results are compared with global optimum results, which assert its suitable performance.To investigate the robustness of the control scheme, the network outlet demand flow rates are changed in two different scenarios. Moreover, the performance of the controller is evaluated in the presence of noise and disturbances, which confirms its efficiency and accuracy.