A New Lumped Parameter Model for Natural Gas Pipelines in State Space

Wen, Kai; Xia, Zijie; Yu, Weichao; Gong, Junbo

doi:10.3390/en11081971

Cited by 22 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The controller would then use the machine learning based algorithms trend to watch the changes in the segment, potentially recognizing a rupture, information leak and intrusion before all the logical conditions in the evaluations have been met. This is useful when there is a long distance between the upstream and downstream input pipeline PSI for processing [12][13][14][15].…”

Section: Discussionmentioning

confidence: 99%

Intrusion detection system in gas-pipeline industry using machine learning

Dakheel¹,

Dakheel

Abbas

2019

PEN

View full text Add to dashboard Cite

In this paper, we study about the plausibility of building up a total intrusion identification framework for gas pipeline industry utilized in present day man-made AI based frameworks to tell a gas controller of unexpected changes in pipeline working qualities, for example, weight, time interim, delta pipeline PSI and stream rate. This examination assesses the possibility for utilizing AI example of cautions strategies utilizing three able AI calculations, for example, Decision tree, K-Nearest Neighbor and Neural Network to recognize breaks in gas frameworks, like the SCADA rate of progress blend philosophy utilized by the risky fluids pipeline industry. The highlights were extricated from the dataset by evacuating the repetitive information too cleaning the information. The significant commitment to this work is by utilizing choice tree in three distinct degrees for example randomized, advanced and timberland just as utilizing the neural system with 3 layers, 20 units for each concealed layer, 20 preparing rounds and with 2 layers, 50 preparing rounds as appeared in down to earth some portion of this work executed in Matlab R2019a to recognize and foresee the potential assault in the gas pipeline industry. The idea of AI examination considered here shows guarantee, in light of the aftereffects of gas pipeline burst checking under the conditions tried. It can possibly be formed into a compelling crack checking technique, yet additionally testing under genuine world, complex-framework setups, in participation with appropriate AI demonstrating specialists, is expected to all the more likely comprehend the genuine practicality of this adjustment mechanized innovation. Since gases and fluids display diverse physical practices under changing weight and stream conditions an immediate relationship between's the viability in gas versus fluids frameworks can't be accurately expected that why AI would give the answer for variety in Pipeline PSI and complete delta pipeline PSI. For example, bypassing and back-feeding, and various other framework explicit conditions requiring redid arrangements utilizing AI.

show abstract

Section: Discussionmentioning

confidence: 99%

Intrusion detection system in gas-pipeline industry using machine learning

Dakheel¹,

Dakheel

Abbas

2019

PEN

View full text Add to dashboard Cite

show abstract

“…For many tasks of analysis, optimization of gas flows, and their control, this is quite acceptable. Such models for a linear section (simple gas pipeline [1]) can be described by time-dependent algebraic equations [1,2], linear [14][15][16] or nonlinear [9] ordinary differential equations or their systems, transfer functions [6,10,17], systems of algebraic linear equations [8] in cases of discrete-time models.…”

Section: A Brief Overview Of Lumped Parameter Modelsmentioning

confidence: 99%

Analytical solution of linearized equations for transient gas flows in gas pipelines

Beylin

Sukharev

2020

E3S Web Conf.

View full text Add to dashboard Cite

We consider the new class of high precision simplified linear models of transient high-pressure gas flows along linear sections of pipelines. Representatives of this class are obtained from different initial models defined by partial differential equations. The new models are based on the exact solution of the Klein-Gordon equation, which appears as a result of piecewise linear approximation of nonlinear models in the form of Charny’s equations [1–4] or piecewise constant approximation in models that describe deviations of pressure and mass flow rates from their values in the basic stationary mode [10–13, 16–17]. The new class of models has significant advantages over nonlinear simplified models in optimization problems of large-scale networks, reducing the calculation time by more than two orders of magnitude. They are also free from errors of the approximate inverse Laplace transform or dimensionality reduction techniques traditionally applied in such situations.

show abstract

“…u = −Ky. (14) To verify the effectiveness of the algorithm and to eliminate the contingency, six initial states were simulated. The outlet pressure of the compressors and the terminal flow rate were considered as the disturbance of the system.…”

Section: Case Studies Of the Cascade Control Of Natural Gas Pipelinesmentioning

confidence: 99%

“…Following the derivation process in [14], the state space models (Equation 5) is ready to be obtained, where the gas pressure at inlet (P in ) and the mass flow rate at the outlet (M out ) are the input vectors, and the pressure at the outlet (P out ) and the gas mass flow rate at the inlet (M in ) are the output vectors.ẋ = Ax + Bu y = Cx + Du (5) where…”

mentioning

confidence: 99%

The Cascade Control of Natural Gas Pipeline Systems

Wen

Gong

Yan³

2019

Applied Sciences

Self Cite

View full text Add to dashboard Cite

With the boost of natural gas consumption, an automatic gas pipeline scheduling method is required to replace the dispatchers in decision making. Since the state space model is the fundamental work of modern control theory, it is possible that the classical controller synthesis method can be used for the complicated gas pipeline controller design. In this paper, a cascade control algorithm is proposed based on the state space model that is used for the transient flow simulation of the natural gas pipelines. A linear quadratic regulator is designed following the classical optimal control theory. Finally, the transient process with different control methods shows the effectiveness of the cascade control using information of the entire pipeline. According to the hardware configuration of natural gas pipelines, automatic scheduling process is ready to deploy as one step to the intelligent natural gas pipelines.

show abstract

A New Lumped Parameter Model for Natural Gas Pipelines in State Space

Cited by 22 publications

References 12 publications

Intrusion detection system in gas-pipeline industry using machine learning

Intrusion detection system in gas-pipeline industry using machine learning

Analytical solution of linearized equations for transient gas flows in gas pipelines

The Cascade Control of Natural Gas Pipeline Systems

Contact Info

Product

Resources

About