Pipeline Model Research Articles

A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization.

Inspired by the great success of machine learning (ML), researchers have applied ML techniques to visualizations to achieve a better design, development, and evaluation of visualizations. This branch of studies, known as ML4VIS, is gaining increasing research attention in recent years. To successfully adapt ML techniques for visualizations, a structured understanding of the integration of ML4VIS is needed. In this article, we systematically survey 88 ML4VIS studies, aiming to answer two motivating questions: "what visualization processes can be assisted by ML?" and "how ML techniques can be used to solve visualization problems? "This survey reveals seven main processes where the employment of ML techniques can benefit visualizations: Data Processing4VIS, Data-VIS Mapping, Insight Communication, Style Imitation, VIS Interaction, VIS Reading, and User Profiling. The seven processes are related to existing visualization theoretical models in an ML4VIS pipeline, aiming to illuminate the role of ML-assisted visualization in general visualizations. Meanwhile, the seven processes are mapped into main learning tasks in ML to align the capabilities of ML with the needs in visualization. Current practices and future opportunities of ML4VIS are discussed in the context of the ML4VIS pipeline and the ML-VIS mapping. While more studies are still needed in the area of ML4VIS, we hope this article can provide a stepping-stone for future exploration. A web-based interactive browser of this survey is available at https://ml4vis.github.io.

Research on low carbon emission optimization operation technology of natural gas pipeline under multi-energy structure

In order to reduce the carbon emissions of natural gas pipelines, based on the background of different energy structures, this paper proposes a general low carbon and low consumption operation model of natural gas pipelines, which is used to fine calculate the carbon emissions and energy consumption of natural gas pipeline. In this paper, an improved particle swarm optimization (NHPSO-JTVAC) algorithm is used to solve the model and the optimal scheduling scheme is given. Taking a parallel pipeline located in western China as an example, the case is analyzed. The results show that after optimization, under the existing energy types, the pipeline system can reduce 31.14% of carbon emissions, and after introducing part of new energy, the pipeline system can reduce 34.02% of carbon emissions, but the energy consumption has increased.

Correlations and associations between fluid‐based and morphometric imaging biomarkers through interrogation and integration of data and analysis across two data platforms

AbstractBackgroundThe Global Alzheimer’s Association Interactive Network (GAAIN) and the Critical Path for Alzheimer’s Disease (CPAD) Consortium have undertaken a collaborative effort to establish a mechanism that can help evaluate the relationship between fluid‐based, morphometric imaging biomarkers and clinical trajectories of disease progression, across datasets and analyses pipelines housed by CPAD and GAAIN. Additionally, this collaboration will demonstrate the feasibility of bidirectional integration of data management models and will guide development of a federated image analysis pipeline model across these two platforms.MethodTo enable interoperability, GAAIN’s original architecture is expanded to accommodate the LONI brain structural imaging pipeline. Under this new framework, GAAIN researchers can initiate brain imaging‐related analyses on their servers directly from GAAIN’s graphical interface with the results integrating back into GAAIN for further analyses. Feasibility was demonstrated for the determination of correlations for CPAD’s biomarker and imaging volumetric data. GAAIN’s brain imaging pipeline was executed on CPAD data, allowing for quantification of volumetric images. In turn, blood and volumetric data were inserted in GAAIN allowing further evaluation and analyses.ResultBased on the results, we provide guidelines for a future framework for a federated analysis model that can be utilized from GAAIN and CPAD to establish relationships between blood and brain markers. In this model, for a cohort of interest, analyses of relevant brain marker data can be remotely done in CPAD servers via GAAINs’ federated platform after which results can be inserted back to GAAIN alongside CPAD’s blood marker data. The full capabilities of this federated model will be explored in subsequent work.ConclusionAs data sharing becomes increasingly prominent and mature, the partnership between GAAIN and CPAD will yield ever greater benefits and knowledge and will continue to grow and evolve in response to the changing Alzheimer’s disease landscape. As such, it represents a non‐exclusive door for researchers to make use of the data sets and advanced analytical tools and is intended to leverage the unique competencies of these organizations and lead to the continued evolution of bringing meaningful and high‐impact advances in Alzheimer’s disease.

Networked control system stability analysis of pipeline system with networked-induced delay

This paper presents the design of Networked Control Systems (NCS) for pipeline systems. NCS plays an important role in controlling and monitoring large-scale systems such as pipeline systems. To implement the NCS, one must derive the pipe model and consider the network communication constraints. Here, the pipeline model is divided into two sections for simplicity. For example, in a long pipeline system, one can use a higher number of sections in order to give a better result for the analysis. Then let’s consider a networked-induced delay as the network communication constraint. The discretize pipe dynamics model is derived to support the NCS scheme in the pipeline system. The stability analysis of the proposed NCS is derived by taking into account the small and the large networked-induced delay. Then the optimal LQR control is designed for both stabilizing and tracking. The stability region of the pipeline system in the NCS scheme with networked-induced delay is derived and depicted to provide stability information. The design of the proposed controller under network constraint (networked-induced delay) must consider the stability plot that is divided into the stable region and unstable region. In this research, let’s assume that it is possible to measure the exact time delay and then consider the allowable sampling time for the controller. The proposed controller is designed by considering the NCS scheme with time delay both for regulator and tracking problems. By using the proposed controller, the pipeline system can be controlled in the presence of network-induced delay, which commonly occurs in a distributed system. The simulation verifies the stability analysis of the proposed optimal control for the pipeline systems with the NCS scheme under networked induced delay

Median Filters on FPGAs for Infinite Data and Large, Rectangular Windows

Efficient architectures and implementations of median filters have been well investigated in the past. In this article, we focus on median filters for very big scientific applications with very large windows and an infinite stream of data, inspired by big data needs in the Square Kilometre Array (SKA) pulsar search engine, but transferable to other big data domains. We propose a novel approach for very large rectangular windows on an FPGA accelerator device able to support the processing of infinite streams of data. OpenCL is used for rapid parameter sweeping and design space exploration based on a pipelined model of the system. Evaluation on a host/accelerator system with an Arria 10 device surpassed 64 million values processed per second considered for the SKA real time requirement, achieving 83.4M value/s while reading from/writing to disk. These results are compared with a state-of-the-art software implementation only achieving 41M value/s for over twice the total system energy cost.

The formation mechanism of the typical hot dry rocks in Hunan Province, China

Abstract Calculated by using the pipeline model, the burial depths of the 150 and 180°C hot dry rocks (HDRs) are 3.20–3.56 and 3.92–4.36 km in the Reshuiwei geothermal field, respectively, while those in the Huitang geothermal field are 3.13–3.50 and 3.84–4.28 km, respectively. Based on the analysis of the geophysical and terrestrial heat flow data, rock thermal generation rates, and the hydrochemical thermometric scale data, we summarized the formation mechanisms of the HDRs in Hunan Province: (i) the boundary deep faults in the welding area have made the intersection part of the deep faults an open tectonic environment, which is beneficial to the upwelling of deep-mantle-sourced thermal matter. (ii) The southeastern Hunan Province is the front region of the West Pacific subduction and retreat. Lithospheric thinning in this area is significant since the Mesozoic era, especially in the Dongting Lake basin, which was formed during extension and depression. This kind of regional lithospheric thinning is favorable for the lateral and upward migration and the intrusion of the deep-mantle-sourced hot substances. (iii) Rocks with high radioactive heat production rates are important crustal thermal sources for the formation of HDRs. Besides that, plutons with similar geological conditions are favorable for the formation of HDR resources. These plutons include the Baimashan pluton and its surrounding areas, and the eastern Dongting Lake plain. Moreover, the intermediate and acid granites distributed in the Chenzhou-Linwu deep fault are also part of the plutons, and the area where the Chenzhou-Linwu deep fault convergent with the Changde-Anren deep fault.

Analysis of the analytical performance models for GPUs and extracting the underlying Pipeline model

This work presents an in-depth study of the analytical models for the performance estimation of GPUs. We show that the models' analytical equations can be derived from a pipeline analogy that models each GPU subsystem as an abstract pipeline. We call this the Pipeline model. All the equations are reformulated based on generic pipeline characteristics, namely throughput and latency. Our analysis shows equivalences between models and reveals substantial problems with some of the equations. Rather than relying on equations, the Pipeline model is then used to simulate the behavior of kernel executions based on the same hardware parameters as the analytical models. The simplicity of the model and relying on simulation mean that this approach needs less assumptions, is more comprehensive and is more flexible. More performance aspects can be taken into consideration. The different models are compared and evaluated empirically with 14 kernels of the Rodinia benchmark suite with varying occupancy. The Pipeline model gives an average MAPE of 24, while the average MAPE values of the other models lie between 27 and 136.

Identifying learners' topical interests from social media content to enrich their course preferences in MOOCs using topic modeling and NLP techniques.

Interests play an essential role in the process of learning, thereby enriching learners 'interests will yield to an enhanced experience in MOOCs. Learners interact freely and spontaneously on social media through different forms of user-generated content which contain hidden information that reveals their real interests and preferences. In this paper, we aim to identify and extract the topical interest from the text content shared by learners on social media to enrich their course preferences in MOOCs. We apply NLP pipeline and topic modeling techniques to the textual feature using three well-known topic models: Latent Dirichlet Allocation, Latent Semantic Analysis, and BERTopic. The results of our experimentation have shown that BERTopic performed better on the scrapped dataset.

Pipeline, Pathway, Burrow

Pipeline, Pathway, Burrow

Small Leak Location for Intelligent Pipeline System via Action-Dependent Heuristic Dynamic Programming

In the construction process of intelligent pipeline system, pipeline monitoring is an important content to improve the safety of pipeline operation. Small leak location, in particular, is the primary focus of pipeline monitoring due to the unclear pressure drop point. To solve this, in this article, a data driven-based method of small leak location is proposed. First, through the collected pipeline parameters, empirical flow variables, and historical pressure values in pipeline system, a pipeline model based on pressure along pipeline is presented by a three-layer neural network to close to the industrial scenarios. Then, on the basis of the analyzed propagation process of negative pressure wave, an action-dependent heuristic dynamic programming with pressure–distance physical constraints is proposed to obtain the small leak location result. The proposed method is suitable for the collection of only pressure data scenario, which expands the application range. Finally, different cases of small leak location results indicate that the proposed method can locate the leak point, and the field tests further show that the proposed method has satisfactory performances in pipeline leak analysis.

STRIDES: automated uniform models for 30 quadruply imaged quasars

ABSTRACT Gravitational time delays provide a powerful one-step measurement of H0, independent of all other probes. One key ingredient in time-delay cosmography are high-accuracy lens models. Those are currently expensive to obtain, both, in terms of computing and investigator time (105–106 CPU hours and ∼0.5–1 yr, respectively). Major improvements in modelling speed are therefore necessary to exploit the large number of lenses that are forecast to be discovered over the current decade. In order to bypass this roadblock, we develop an automated modelling pipeline and apply it to a sample of 31 lens systems, observed by the Hubble Space Telescope in multiple bands. Our automated pipeline can derive models for 30/31 lenses with few hours of human time and <100 CPU hours of computing time for a typical system. For each lens, we provide measurements of key parameters and predictions of magnification as well as time delays for the multiple images. We characterize the cosmography-readiness of our models using the stability of differences in the Fermat potential (proportional to time delay) with respect to modelling choices. We find that for 10/30 lenses, our models are cosmography or nearly cosmography grade (<3 per cent and 3–5 per cent variations). For 6/30 lenses, the models are close to cosmography grade (5–10 per cent). These results utilize informative priors and will need to be confirmed by further analysis. However, they are also likely to improve by extending the pipeline modelling sequence and options. In conclusion, we show that uniform cosmography grade modelling of large strong lens samples is within reach.

Conceptualizing Value Creation in the Platform Era

Platforms have entered many industries and increasingly dominate markets. As such, they increasingly displace the traditional linear pipeline model of value creation with a web of value-creating interactions among three key players: the platform provider, platform consumers and platform suppliers. Existing conceptualizations of consumer value, however, are still based in the linear pipeline world which raises the need to update these frameworks to the platform era. In this article, we make first important strides towards an overarching platform-based valuation framework which can be applied to any type of platform. We build upon Kumar et al. (2010) by applying and extending the concept of customer engagement value to the platform context. In doing so, we delineate a variety of value components that (a) originate from a platform’s consumers as well as suppliers, (b) generate monetary and non-monetary value for the platform provider, and (c) generate direct and indirect value for the platform provider. Together, these value components holistically capture platform participants’ value creation and assist managers in evaluating the health and sustainability of their platforms.

An Effective ELECTRA-Based Pipeline for Sentiment Analysis of Tourist Attraction Reviews

In the era of information explosion, it is difficult for people to decide on a tourist destination quickly. Online travel review texts provide valuable references and suggestions to assist in decision making. However, tourist attraction reviews are primarily informal and noisy. Most works in this field focus on shallow machine learning models or non-pretrained deep learning models. These approaches struggle to generate satisfactory classification results. To solve this issue, the paper proposes a pipeline model. In the first step of this paper, we preprocess tourist attraction reviews by performing stopword removal, special character removal, redundancy deletion and negation substitution to reduce noise. Then, we propose an ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) classifier for sentiment analysis of tourist attraction review. Finally, we compare our pipeline model with several representative deep text classification models. Extensive experiments have demonstrated the effectiveness of our approach to sentiment analysis of tourist attraction reviews. We not only provide one high-quality dataset for tourist attraction reviews, but our work can also expand and promote the development of sentiment analysis in other domains.

A dynamic fracture finite element model of the buried gas transmission pipeline combining soil constraints and gas decompression

A long-distance natural gas transmission pipeline is the primary solution for natural gas resource distribution. In fact, the longitudinal crack propagation of gas transmission pipelines has always been a concern of the natural gas industry. Because it will cause disastrous accidents once the ductile crack in the pipeline propagates rapidly. Most natural gas transmission pipelines are buried underground to improve the safety of pipeline operation as the backfill soil can absorb energy during the fracture process and restrain the displacements of the flaps. Fracture control is a fundamental requirement for the safe operation of underground pipelines. In this study, the dynamic fracture finite element model of the buried gas pipeline is developed to simulate the actual fracture process instead of the costly full-scale burst experiments. The finite element model incorporates different external soil constraints and internal gas decompression behaviors during pipe rupture in which soil constraints are represented by discrete soil springs, and a user-defined subroutine realizes the gas decompression behavior. The explicit dynamic analysis is employed to simulate the high-speed dynamic fracture process of the pipeline, and the crack propagation is simulated by using the cohesive zone model. Finally, the crack propagation velocity is calculated by this model, and the influence of different internal pressures on the fracture velocity is studied; the crack tip opening angle (CTOA) is predicted, and the effect of soil spring stiffness on CTOA is evaluated.

Research on local buckling failure range of X80 buried steel pipeline under oblique-reverse fault

Permanent ground deformation induced by the earthquake will cause serious damage to long-distance buried oil and gas pipelines, resulting in buckling failure or even cracking damage to pipelines. Based on the ABAQUS program, a 3-D numerical model of X80 buried steel pipeline crossing oblique-reverse fault was established, and the failure characteristics and failure range of local buckling of buried pipeline were systematically analyzed. According to the engineering parameters of the Second West-East Gas Pipeline Project (China), the influence of fault dip angle, displacement, diameter-thickness ratio, burial depth, and internal pressure on the local buckling failure range of the pipeline was discussed in detail. Subsequently, regression analysis was carried out on the numerical results of 1800 sets of the finite element cases, and a semi-empirical prediction equation (“Risk Segment” regression formula) of the local buckling failure range of X80 steel pipeline subjected to oblique-reverse fault displacement was derived. The accuracy and applicability of the formula were verified by the numerical results of 120 practical examples. The results show that the “Risk Segment” regression formula has higher accuracy and is less time-consuming, which is suitable for failure range prediction and local safety design of X80 buried steel pipeline under oblique-reverse fault.

Numerical study on harmful boundary of above-ground section leakage of natural gas pipeline

Natural gas has incomparable advantages compared with other energy, but the accidents caused by natural gas pipeline transportation cannot be ignored. In order to reduce the accident damage, it is necessary to master the concentration distribution of leaked gas in the atmosphere scientifically. The main contribution of this research is to predict the harmful boundary of gas diffusion. Numerical simulation was used to establish the leakage diffusion model of natural gas pipeline exposed to atmosphere. The influences of leakage rate, leakage diameter and wind speed on the harmful boundary of gas were studied. The results show that harmful boundary reaches a stable state after a period of leakage. Leakage rate and leakage diameter contribute to vertical height of harmful boundary, and have little effect in the horizontal direction. Wind speed is the main factor affecting gas diffusion path. Increasing wind speed results in decrease of vertical height and increase of horizontal distance of harmful boundary, gas diffusion develops near the ground in the downwind direction. The quantitative formula between harmful boundary of gas diffusion and influencing factors is proposed. This work has a great guiding significance for emergency rescue work in engineering.

Tensile Strain Capacity Prediction Model of an X80 Pipeline with Improper Transitioning and Undermatched Girth Weld.

As an important component of strain-based design, the tensile strain capacity (TSC) concept has been extensively used for pipelines that experience expectable plastic strain for both installation and service. However, some stress-based designed pipelines have experienced unforeseen plastic strain in the past decade that resulted in failure. It seems that the tensile strain capacity has gradually become an important requirement for geohazard risk management and pipeline maintenance of stress-based design pipelines. The tensile strain capacity of an X80 pipeline is investigated. The assessment in this work was based on the fracture initiation–control-based limit state. This limit state corresponds to the onset of stable tearing and generally provides a reasonably conservative estimate. Besides that, factors such as wall thickness, material’s strain hardening capacity, toughness, weld strength mismatch, HAZ (heat-affected zone) softening, pipe wall thickness, high–low misalignment, and internal pressure were also investigated to construct a prediction model of the X80 vintage pipeline.

Testing the Performance of a Water Restrictor With the Orifice Principle

The habit of wasting water is widespread. One of the solutions is to “force” the consumer to conserve water by restricting the flow using a restrictor with the orifice principle. The aim of this study was to determine the performance of a restrictor in a pipeline model by defining the discharge coefficient obtained experimentally from the output discharge with or without the restrictor in static pressure water, and to examine the variation based on the tap opening. The restrictor had an opening at the center of the cylinder with a 2.5 mm diameter and it was installed in a water tap of 0.5 inches diameter based on the market. The effectiveness of the tool in reducing the water was determined by the discharge coefficient. Based on the results, it was found that the restrictor was capable of reducing the water discharge output by 60%-70% for discharge inputs ranging from 0.15 to 0.25 l/s. Moreover, the reduction for discharge inputs below 0.15 l/s resulted in an efficiency ranging from 30%-40%. The discharge output using the restrictor was approximately 0.06 to 0.07 l/s. The contraction coefficient and expansion coefficient were 1.720 (experimental) and 1.484 (theoretical).
 Keywords: water wasting reduction, water restrictor, orifice principle, experimental approach

Optimization of Oil Pipeline Operations to Reduce Energy Consumption Using an Improved Squirrel Search Algorithm

To achieve the goal of achieving carbon-neutral by 2060, the government of China has put forward higher requirements for energy conservation and consumption reduction in the energy industry. Therefore, it is necessary to reduce energy consumption in the process of transporting oil. In this paper, an optimization model that minimizes the total energy consumption of the entire pipeline system is proposed and the squirrel search algorithm (SSA) is used to solve the optimization model. Meanwhile, to improve the performance of the SSA, two strategies are proposed. One is the adaptive inertia weight strategy, and the other is the multi-group co-evolution strategy. The adaptive inertia weight can adjust the step size of the flying squirrels according to the difference of the objective function value and multi-group co-evolution is introduced to improve population diversity. The improved SSA is named multigroup coevolution-adaptive inertia weight SSA (MASSA). A total of 20 benchmark functions are used to test the performance of MASSA, including unimodal functions and multimodal functions. Compared with the other four algorithms, MASSA has better performance and convergence capabilities. In the case study experiment, an optimization model of the oil pipeline is built, which takes the minimum energy consumption of the whole pipeline as the objective function. Compared with the actual operating conditions, the electricity consumption optimized by MASSA decreases by 399,018.94 kgce, and the thermal energy dissipation decreases by 113,759.25 kgce. The total energy consumption is reduced by 512,778.19 kgce, which is 9.62%. These results indicate that the two improvement strategies are significant, and optimizing the operating parameters can reduce energy consumption.

Extended State Observer-Based Fuzzy Adaptive Backstepping Force Control of a Deep-Sea Hydraulic Manipulator with Long Transmission Pipelines

The force tracking control of deep-sea hydraulic manipulator systems with long transmission pipelines is disposed via fuzzy adaptive backstepping control based on an extended state observer in this paper. The pipeline model is established and then used to estimate the pressures in cylinder chambers, which are used to obtain the output force. In this process, the velocity of the piston, which is unmeasured, is needed, and an extended state observer is constructed to estimate the unmeasurable velocity signal. To cope with parameter uncertainties caused by changes in working depth, an adaptive algorithm is combined with the backstepping controller. Fuzzy logic is employed to design self-tuners that can automatically adjust the control parameters to guarantee force control performance from shallow seas to deep seas. The experimental results illustrate the success of the proposed control method. Comparative experimental results demonstrate that the extended state observer-based fuzzy adaptive backstepping controller has a relatively better tracking performance in different working conditions.