Network Design Method Research Articles

Synchronization Optimization of Pipeline Layout and Pipe Diameter Selection in a Drip Irrigation Network System Based on the Jaya Algorithm

To address the complexity and high computational burden in the design of drip irrigation networks, the Jaya algorithm is utilized to study factors affecting project costs, including equipment and pipeline depreciation and the operation and management costs of the irrigation area. A mathematical model of synchronization optimal design of pipe layout and pipe diameter selection in a drip irrigation network system with constraints on pipe diameter, flow velocity, and pipe pressure is established. Using an irrigation district in Xinjiang, China, as an example, the Jaya algorithm optimization design program was run independently 50 times, and the relative deviation of each optimization result from the optimal solution was calculated. The results show that the annual cost per unit area o is reduced to 635.99 RMB/hm2, a 25.34% reduction compared to the original engineering program, and the investment-saving effect is obvious. The relative deviation is controlled within 3%, which shows that the algorithm has stable convergence performance and can meet the requirements of actual engineering design. The Jaya algorithm eliminates the need for parameter tuning, and it excels in cost savings, algorithm stability, and computational accuracy, making it an effective method for the single-objective optimization design of drip irrigation networks.

Improved high dynamic range imaging using multi-scale feature flows balanced between task-orientedness and accuracy

Deep learning has made it possible to accurately generate high dynamic range (HDR) images from multiple images taken at different exposure settings, largely owing to advancements in neural network design. However, generating images without artifacts remains difficult, especially in scenes with moving objects. In such cases, issues like color distortion, geometric misalignment, or ghosting can appear. Current state-of-the-art network designs address this by estimating the optical flow between input images to align them better. The parameters for the flow estimation are learned through the primary goal, producing high-quality HDR images. However, we find that this ”task-oriented flow” approach has its drawbacks, especially in minimizing artifacts. To address this, we introduce a new network design and training method that improve the accuracy of flow estimation. This aims to strike a balance between task-oriented flow and accurate flow. Additionally, the network utilizes multi-scale features extracted from the input images for both flow estimation and HDR image reconstruction. Our experiments demonstrate that these two innovations result in HDR images with fewer artifacts and enhanced quality.

Towards Non-Region Specific Large-Scale Inundation Modelling with Machine Learning Methods

Traditional flood inundation modelling methods are computationally expensive and not suitable for near-real time inundation prediction. In this study we explore a data-driven machine learning method to complement and, in some cases, replace existing methods. Given sufficient training data and model capacity, our design enables a single neural network instance to approximate the flow characteristics of any input region, opening the possibility of applying the model to regions without available training data. To demonstrate the method we apply it to a very large >8000 km2 region of the Fitzroy river basin in Western Australia with a spatial resolution of 30 m × 30 m, placing an emphasis on efficiency and scalability. In this work we identify and address a range of practical limitations, e.g., we develop a novel water height regression method and cost function to address extreme class imbalances and by carefully constructing the input data, we introduce some natural physical constraints. Furthermore, a compact neural network design and training method was developed to enable the training problem to fit within GPU memory constraints and a novel dataset was constructed from the output of a calibrated two-dimensional hydrodynamic model. A good correlation between the predicted and groundtruth water heights was observed.

Piping network optimization for district heating system using an enhanced Genetic Algorithm searching method

Given the substantial construction and operational expenses associated with a district heating system (DHS), achieving an optimal layout for the piping network is paramount for its successful deployment. In this study, the optimization of DHS piping configuration has been explored. Traditional exhaustive search methods for network design are often impractical due to computational constraints, making Genetic Algorithm (GA) a preferred alternative for navigating the vast search space of optimization problems efficiently. However, GA, which relies on probabilistic heuristics, may not always pinpoints the most effective solutions, particularly those in close proximity to the current near-optimal configuration. To address this issue, an enhanced GA-based neighboring search method for identifying optimal or near-optimal piping layout for DHS more effectively has been developed in this study. When a local minimum is detected in the GA optimization process, the method initiates a neighboring search by selecting an elite candidate. The link with the highest piping cost from the elite candidate's configuration is identified. Subsequently, one of the other nodes in the configuration is connected to the nodes of the identified link to explore solutions beyond the local optimum. This new approach was firstly validated against an Optimal Communication Spanning Tree (OCST) benchmark problem, where it demonstrated superior efficacy by achieving higher success rate and quicker first-hit generation compared to conventional GA method. Specifically, this method showed a 60 % success rate with a minimum first-hit generation number of 140, outperforming the traditional GA's 40 % success rate and 263 generations. Further modification to the OCST benchmark to better simulate a real-world DHS application underscored the ability of this neighboring search method to exceed the previously established optimal configuration, uncovering a “better' solution with superior fitness value. This promising methodology was subsequently applied to the hypothetical design of a DHS piping network, illustrating its potential to enhance the planning and implementation of efficient, cost-effective district heating systems.

Mechanical performance degradation investigation on FRP reinforced concrete based on neural network design method

To predict the effect of chemical-freezing coupling erosion on the properties of four kinds of FRP-reinforced concrete. Rapid freeze–thaw tests were conducted. The mass loss rate, relative dynamic elastic modulus, compressive strength, and flexural capacity were tested to investigate the Mechanical Performance of specimens. The compression specimens are cylindrical specimens wrapped with FRP, and the flexural specimens are pasted with FRP prismatic specimens on the pre-cracked side. A database was built based on 45 groups of experimental test results, and the prediction effect of the BP neural network and CNN model on compressive strength and flexural capacity was compared, respectively. The results showed that CNN did a better job. Finally, the maximum number of freeze–thaw cycles of different FRP-reinforced specimens was predicted based on the CNN model with mass loss rate and relative dynamic modulus as the evaluation criteria. This method can provide a new perspective for predicting the durability of FRP-reinforced concrete.

DARTS-based morphological neural network design and application in bearing fault diagnosis

Morphological filters are widely used in data pre-processing, whereas the existing morphological filters are not optimal in terms of performance, since they are designed by combining the basic morphological operators together artificially. Hence, we proposed an automatic morphological neural network design method based on differentiable architecture search (DARTS), which is a neural architecture search (NAS) method. Firstly, the mechanism is revealed that the morphological dilation with flat structural elements behaves the same as Maxpooling without down-sampling. Secondly, morphological dilation and erosion neural network layers were defined. Thirdly, using DARTS and the search space with morphological neural network layers, end-to-end morphological neural network was implemented. Finally, the morphological neural network was successfully applied in bearing fault diagnosis. Experiments on the three datasets show that the proposed method improved the feature extraction capabilities of neural networks, then achieved end-to-end bearing fault diagnosis, and the diagnosis accuracy was improved by more than 2.0%.

IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects.

This study proposed an interpretable multi-scale infrared small object detection network (IMD-Net) design method to improve the precision of infrared small object detection and contour segmentation in complex backgrounds. To this end, a multi-scale object enhancement module was constructed, which converted artificially designed features into network structures. The network structure was used to enhance actual objects and extract shallow detail and deep semantic features of images. Next, a global object response, channel attention, and multilayer feature fusion modules were introduced, combining context and channel information and aggregated information, selected data, and decoded objects. Finally, the multiple loss constraint module was constructed, which effectively constrained the network output using multiple losses and solved the problems of high false alarms and high missed detections. Experimental results showed that the proposed network model outperformed local energy factor (LEF), self-regularized weighted sparse model (SRWS), asymmetric contextual modulation (ACM), and other state of the art methods in the intersection-over-union (IoU) and Fmeasure values by 10.8% and 11.3%, respectively. The proposed method performed best on the currently available datasets, achieving accurate detection and effective segmentation of dim and small objects in various infrared complex background images.

Single-Sided Compensation Network Design Method for Capacitive Power Transfer System Considering Coupling Variation

Single-Sided Compensation Network Design Method for Capacitive Power Transfer System Considering Coupling Variation

A data-driven robust optimization in viable supply chain network design by considering Open Innovation and Blockchain Technology

The research proposes a new method for Viable Supply Chain Network Design (VSCND) that incorporates Open Innovation (OI) and Blockchain Technology (BCT). A robust stochastic optimization and Conditional Value at Risk (CVaR) in the cost function is utilized to develop the model. This model's objective function incorporates the expected value, maximum cost, and CVaR cost. The OI and BCT platforms are suggested for an antifragile policy against disruption. In addition, CO2 emissions and energy consumption are proposed as sustainability requirements. Eventually, minimum demand satisfaction and resilience facilities by incorporating capacity based on specific scenarios are added to the model for an agile strategy. This research entails several parties, including vendors supplying the primary components and manufacturers creating products based on customer preferences. OI and BCT platforms aim to receive demand based on customer specifications and facilitate rapid transactions between components. Risk-averse decision-makers utilize a polyhedral Data-Driven Robust Optimization (DDRO) approach to manage uncertainty and flexible sets. Incorporating OI and BCT as antifragility instruments resulted in a 0.2% cost reduction for VSCNDOIBCT compared to when OI and BCT were not considered. This research suggests that integrating OI and BCT positively affects SC performance overall. The decreasing rate, DDRO coefficient, agility rate, demand variation, and problem size were subjected to a sensitivity analysis.

MTLBORKS-CNN: An Innovative Approach for Automated Convolutional Neural Network Design for Image Classification

Convolutional neural networks (CNNs) have excelled in artificial intelligence, particularly in image-related tasks such as classification and object recognition. However, manually designing CNN architectures demands significant domain expertise and involves time-consuming trial-and-error processes, along with substantial computational resources. To overcome this challenge, an automated network design method known as Modified Teaching-Learning-Based Optimization with Refined Knowledge Sharing (MTLBORKS-CNN) is introduced. It autonomously searches for optimal CNN architectures, achieving high classification performance on specific datasets without human intervention. MTLBORKS-CNN incorporates four key features. It employs an effective encoding scheme for various network hyperparameters, facilitating the search for innovative and valid network architectures. During the modified teacher phase, it leverages a social learning concept to calculate unique exemplars that effectively guide learners while preserving diversity. In the modified learner phase, self-learning and adaptive peer learning are incorporated to enhance knowledge acquisition of learners during CNN architecture optimization. Finally, MTLBORKS-CNN employs a dual-criterion selection scheme, considering both fitness and diversity, to determine the survival of learners in subsequent generations. MTLBORKS-CNN is rigorously evaluated across nine image datasets and compared with state-of-the-art methods. The results consistently demonstrate MTLBORKS-CNN’s superiority in terms of classification accuracy and network complexity, suggesting its potential for infrastructural development of smart devices.

Research on compression pruning methods based on deep learning

In the past decade or so, deep neural networks have continuously refreshed the best performance in tasks such as computer vision and natural language processing, and have become the most concerned research directions. Although deep neural networks have significant performance, they are difficult to deploy on hardware-constrained embedded and mobile devices due to their huge number of parameters, computational and storage costs. Therefore, in recent years, the lightweight design of network structure has gradually become a cutting-edge and popular direction, improving the operation speed and optimizing the storage space under the premise of maintaining the accuracy of the neural network. In this paper, the results achieved by domestic and foreign scholars in deep learning model compression are sorted and classified, and the methods of network pruning, model quantification, knowledge distillation, and lightweight network design are summarized, and the compression effect of related methods on known public models is summarized. Finally, the possible directions, application directions and development trends of future neural network model lightweight research are prospected.

PointCNT: A One-Stage Point Cloud Registration Approach Based on Complex Network Theory

Inspired by the parallel visual pathway model of the human neural system, we propose an efficient and high-precision point cloud registration method based on complex network theory (PointCNT). A deep learning network (DNN) design method based on complex network theory is proposed, and a multipath feature extraction network, namely, Complex Kernel Point Convolution Neural Network (ComKP-CNN) for point clouds is designed based on the design method. Self-supervision is introduced to improve the feature extraction ability of the model. A feature embedding module is proposed to explicitly embed the transformation-variant coordinate information and transformation-invariant distance information into features. A feature fusion module is proposed to enable the source and template point clouds to perceive each other’s nonlocal features. Finally, a Multilayer Perceptron (MLP) with prominent fitting characteristics is utilized to estimate the transformation matrix. The experimental results show that the Registration Recall (RR) of PointCNT on ModelNet40 dataset reached 96.4%, significantly surpassing one-stage methods such as Feature-Metric Registration (FMR) and approaching two-stage methods such as Geometric Transformer (GeoTransformer). The computation speed is faster than two-stage methods, and the registration run time is 0.15 s. In addition, ComKP-CNN is universal and can improve the registration accuracy of other point cloud registration methods.

Development and validation of a novel bias network design method for a class AB PA

AbstractIn this paper, the impact of the bias networks on a radio frequency (RF) power amplifier (PA) is analyzed and discussed comprehensively. Both the different sizes and positions of the bias microstrip line circuit have been studied for a broadband class AB PA. Both simulations and measurements show that the performance of the PA can be greatly improved with the adjustment of the bias circuit by effecting the harmonic impedance of the whole matching circuit. Compared with the existing works, the fabricated PA based on the proposed technique provides the best performance, thereby demonstrating the effectiveness of the developed bias circuit optimization method.

Two-Stage Robust Design of Resilient Active Distribution Networks Considering Random Tie Line Outages and Outage Propagation

This paper proposes a two-stage method for the robust design of resilient active distribution networks (ADNs) against high-impact and low-probability (HILP) events. The line hardening and the deployment of remote-controlled switches (RCSs) are considered as two powerful measures for resilience enhancement. Especially, the hardening of tie lines and the deployment of bilateral tie switches are emphasized as part of the resilient design. A novel progressive detection mechanism (PDM) is devised to estimate the potential propagation of outages and identify surviving nodes outside of the minimum outage area after intentional islanding. The proposed PDM method considers potential RCS locations among regular lines and tie lines on outage to calculate the global optimal design scheme. The two-stage robust design model is formulated as a mixed-integer linear programming (MILP). The nested column-and-constraint generation (nested C&CG) algorithm is customized to solve the proposed model. Numerical results on a modified IEEE 33-node distribution system demonstrate the effectiveness and the superiority of the proposed resilience enhancement method.

A globalized robust optimization method for sustainable humanitarian relief network design with uncertain scenario probabilities

Disorganized treatment of casualties and irrational distribution of medical supplies pose significant challenges to relief activities, and recent disasters have brought attention to the need for optimizing emergency humanitarian relief networks. This paper proposes a scenario-based multi-objective globalized robust optimization (GRO) model to provide casualty transport schemes and medical supplies distribution strategies. Three optimization objectives in our proposed model are to minimize costs, carbon emissions, and inventory. A case study is based on the earthquake in Kermanshah, Iran. First, we investigate the sensitivity of the proposed model regarding the safe parameter and budget. Second, some comparative experimental results demonstrate that the GRO model exhibits great robustness in terms of obtain optimal solution. Compared with the nominal model, it can withstand some fluctuations caused by uncertainty and significantly reduce the conservatism of the robust model. Furthermore, simulation testing verifies the reliability of the GRO method though inspecting the probability that the simulated samples make the optimized strategies invalid. Finally, some management implications are obtained. This study highlights the importance of the effective relief activities that can balance life, social, economic, and environmental aspects to enable rational responses to emergencies.

Use of the entropy approach in water resource monitoring systems

Effective management of water resources is possible only with an effectively organized monitoring system. After the emergence and development of information theory, the concept of information entropy found its place in the field of the development of water monitoring systems. The purpose of this work is to review research related to the construction of water monitoring systems and networks that applied the entropy theory in the design process. Methodology. Entropy terms used in the construction of water monitoring systems are summarized. Recent applications of the entropy concept for water monitoring system designs classified by precipitation are reviewed; flow and water level; water quality; soil moisture and groundwater. The integrated method of designing multifactorial monitoring systems is also highlighted. Results. The review analyzes studies and their implementation in the design of water monitoring networks based on entropy. The use of various methods of information theory and their adaptation for use in the design of monitoring networks is demonstrated, with the goal of network design methods being the selection of stations that provide the most information for the monitoring network, while being independent of each other. Through extensive testing, information theory has proven to be a reliable tool for evaluating and designing an optimal water monitoring network. Scientific novelty. This review focuses on studies that have applied information theory or information entropy to construct monitoring networks and systems. Information theory was developed by Shannon in the middle of the last century to measure the information content of a data set and was subsequently applied to solving water resources problems. To date, there are no review studies regarding the design of water monitoring networks based on the concept that entropy will be able to characterize the information specific to the monitoring station or monitoring networks. The main goal is to have the maximum amount of information. Practical significance. The optimal design of the monitoring network can be built based on the specified design criteria; however, the practical application of a new optimal monitoring network is rarely evaluated in a hydrological or other model. It is also important to identify the benefits of entropy-based network design to convince decision-makers of the importance of entropy-based approaches. The optimal network can be subjective, based on the choices made during the entropy calculation and the design method chosen, especially when additional objective functions are considered in the design. This applies to the method chosen to construct the optimal monitoring network, whether it is found using an iterative method where one station is added at a time, or a collection of stations that are added simultaneously. Research has also shown that data length, catchment scale, and the order can affect optimal network design. when using discrete entropy, it was shown that the binning method affects the final network design. Therefore, when selecting options based on the intended application of the monitoring network, a clear understanding and further research is needed to provide recommendations specific to water monitoring networks. In particular, more work is needed on the spatial and temporal scaling of the entropy calculation data to provide robust recommendations for decision-makers.

Differential evolution-based convolutional neural networks: An automatic architecture design method for intrusion detection in industrial control systems

Industrial control systems (ICSs) are facing serious and evolving security threats because of a variety of malicious attacks. Deep learning-based intrusion detection systems (IDSs) have been widely considered as one of promising security solutions for ICSs, but these deep neural networks for IDSs in ICSs have been designed manually, which are extremely dependent on expert experience with numerous model parameters. This paper makes the first attempt to develop an automatic architecture design method of convolutional neural networks (CNNs) based on differential evolution (abbreviated as DE-CNN) for the intrusion detection issue in ICSs. The first phase of the proposed DE-CNN is the off-line architecture optimization of the CNNs constructed by three basic units such as ResNetBlockUnit, DenseNetBlockUnit, and PoolingUnit, including encoding the architecture parameters of a CNN as a population, evaluating the fitness of the population by the validation accuracy and the number of CNN model parameters, implementing the evolutionary process including mutation and crossover operations, and selecting the best individual from the population. Then, the optimal CNN model obtained by the off-line optimization of DE-CNN is deployed for the online IDSs. The experimental results on two intrusion detection datasets in ICSs including SWaT and WADI have demonstrated the superiority of the proposed DE-CNN to the state-of-the-art manually-designed and neuroevolution-based methods under both unsupervised and supervised learning in terms of Precision, Recall, F1-Score and the number of the CNN model parameters.

Multimodal Public Transit Network Design Method Based on Hub-and-Spoke Infrastructure

This paper presents a two-phase method for generating a hub-and-spoke network for a multimodal public transit network (MPTN). The first phase addresses the problem of clustering in MPTNs, which is a key operation in solving the hub location problem (HLP) in MPTN design. However, previous work often oversimplifies or neglects the clustering phase, so this study presents a spatial clustering algorithm that can process real urban MPTNs without reducing their size or dividing them into zones. The algorithm is tested on four large city datasets and compared with popular spatial clustering algorithms. In the second phase, a heuristic algorithm is presented that aims to maximize network coverage. The proposed method is tested using the MPTN of Greater London and the resulting hub-and-spoke network is compared with the Journey API provided by Transport for London. The results show that the total travel time is improved by 16.9% with a strict hubbing policy. Transportation planners can adapt the proposed method to their specific needs by changing the size and number of clusters using the cluster scaling factor ([Formula: see text]) parameter and including or excluding any criteria in the decision equations.

Local Grid Planning and Design

This design is based on Etap simulation software to complete the following steps: analysis of original data, determination of power grid voltage level and preliminary selection of power grid connection scheme, technical and economic operation of optimal scheme, operation characteristics and material statistical calculation. Through this design, I have mastered the general principles and common methods of power network planning and design. I am skilled in using Etap simulation software to cultivate my analytical ability in various aspects of technology and economy, improve my ability of calculation, data analysis and arrangement, and design specification compilation.

A flexible algorithm for network design based on information theory

Abstract. A novel method for atmospheric network design is presented, which is based on information theory. The method does not require calculation of the posterior uncertainty (or uncertainty reduction) and is therefore computationally more efficient than methods that require this. The algorithm is demonstrated in two examples: the first looks at designing a network for monitoring CH4 sources using observations of the stable carbon isotope ratio in CH4 (δ13C), and the second looks at designing a network for monitoring fossil fuel emissions of CO2 using observations of the radiocarbon isotope ratio in CO2 (Δ14CO2).