Multi-level Distribution Research Articles

Multi-source domain self-supervised enhanced transfer fault diagnosis approach with source sample refinement strategy

Existing research in multi-source transfer learning often overlooks the differences among source domain samples and fails to effectively utilize unknown target domain information. To address these limitations, this paper proposes a multi-source domain self-supervised enhanced transfer fault diagnosis method with source sample refinement strategy. Firstly, a joint training mechanism is introduced to train all source predictors, leveraging knowledge from all source domains. Subsequently, a source sample refinement strategy is devised, utilizing a category classifier in conjunction with predefined thresholds to filter out source samples highly similar to the target samples, thereby obtaining weights for each source domain. Then, a multi-level distribution matching mechanism is designed to reduce the distribution discrepancy between refined source samples and target samples, followed by the development of a self-supervised training mechanism to further enhance the cross-domain performance of source predictors. Finally, integrating the weights from each source domain, the trained source predictors are combined to derive the target predictor, yielding the final diagnostic results. Experimental results indicate that the proposed method can achieve better target alignment by leveraging fault information from the unknown target domain, effectively addressing cross-domain diagnosis challenges.

Optimization study of computational methods in coordinated integrated carrying capacity assessment of multi-voltage hierarchies

Abstract In this paper, we take a two-level distribution grid as the infrastructure of a multilevel distribution grid and study the comprehensive carrying capacity assessment model in depth. The minimum value of the maximum access capacity under each scenario is used to assess the maximum carrying capacity of the distribution network, and the maximum access volume of the multilevel distribution network is taken as the objective function, and the particle swarm algorithm is improved to establish the maximum carrying capacity assessment model. Using the alternating direction multiplier method, a two-level distribution grid carrying capacity distributed optimization model is established, and the multilevel distribution grid access volume problem is transformed into the maximum access volume subproblem at all levels of the distribution grid. Comparing the whale algorithm and particle swarm algorithm, the model in this paper converges at 7465 kW access capacity and about 12 iterations, respectively, and the weak degree is below 0.4 at different distribution network states, which is a good performance in terms of optimization accuracy and weak degree. We conduct simulation experiments with the modified IEEE33 nodes and find that using this paper’s model to participate in optimal scheduling reduces the total operating cost of the distribution network system by more than 6.24% compared to not using it. Finally, we use the model in this paper to evaluate the comprehensive carrying capacity of the distribution network in Ningxia, China.

Optimization of emergency allocation of necessities of life based on fractal perspective.

The supply and reserves of emergency necessities of life are important for emergency management in disaster events. The scope of the necessities of life changes with social development, and their reserves and allocation in sudden disaster events continually face new challenges. Timely distribution of the necessities of life during disasters is critical to saving lives and maintaining social order. Therefore, this study proposes a fractal multi-level distribution network (FMDN) optimization model with multiple warehouse points, multiple emergency distribution centers, and multiple disaster points from the perspective of fractal theory. The FMDN model considers the influence of road damage on vehicle speed and the dynamic change in demand at the affected points. The FMDN model aims to minimize the operating costs of a distribution network, including the cost of building emergency reserve points, transportation costs, and penalty costs for lack of demand. Numerical experiments verify the feasibility of the model. The FMDN model is solved using LINGO software programming, and an optimal distribution path and quantity are obtained. Analyzing the numerical example results shows that the model is suitable for emergencies and has good applicability.

A methodology for the strategic design of city logistics networks and its application in Turkish automotive spare parts industry

City logistics approaches and modeling struggles have a significant role in urban areas in increasing the efficiency of logistics operations and reducing traffic jams and their environmental effects. By developing an effective distribution network for cities, it is possible to compete with the changing world and satisfy flexible customer requirements. In this study, as a real-world case, a city logistics model for Istanbul metropolitan area is designed using multi-objective linear programming that considers the different objectives of the stakeholders in cities by integrating the fuzzy Choquet integral technique in a multi-level distribution network for the automotive spare part industry. This paper makes decisions regarding the amount of product flowing among the echelons, the amount of stock to be kept in the warehouses, and the product delays allowed. While minimizing the transportation cost, holding cost and emission levels during these decisions, the study also aims to maximize the service quality in the warehouses. The model is applied to a logistics network of fifty demand points and thirty time periods which can be considered a middle or large-scale problem. In the model, it is also decided to transport the products with electric or fuel vehicles. In the transport sector, electric vehicles are the key to meet future needs for social, health and other human services. The results are discussed under different scenarios. This research allows the use of such a model in making strategic decisions for the distribution network design in big cities.

Modularization Design for Smart Industrial Service Ecosystem: A Framework Based on the Smart Industrial Service Identification Blueprint and Hypergraph Clustering

Compared with the conventional industrial product–service system, the smart industrial service ecosystem (SISE) mentioned in this study contains more service activity according to the characteristics of the industrial context, participation of various stakeholders and smart interconnected technologies. This study proposes a detailed modularization design framework for SISE, which can be referenced in various industrial contexts. Firstly, the context-based smart industrial service identification blueprint (SISIB) is proposed to describe the operation model of SISE and identify the service components. The SISIB can ensure that the designers understand the service and work process of the system and improve or carry out the smart industrial service (SIS) component identification. In the case of this article, SIS components from different industrial levels can be systematically identified. Secondly, smart collaboration and sustainable development principles are proposed for measuring the correlation degree among the service components. Considering the complexity and multi-level distribution nature of service components, the hyperedge concept is presented to realize the correlation comparison among the service components, and the evaluation linguistics is applied to handle the decision uncertainties. With this method, the effective correlation comparison between service components can be formed with few hyperedges. Thirdly, the hypergraph clustering theory is applied to define the SISE service module partition. The triangular fuzzy number is first used in hyperedge strength evaluation to comply with the vague linguistics from service design experts. The normalized hypergraph cut principle is realized using the K nearest neighbors (kNN) algorithm, and with this method, the new unified hypergraph and related Laplace matrix can be obtained. Then, the relevant eigenvalue of that Laplace matrix is gained, and the component clustering visualization is realized using the k-means algorithm. After the clustering is performed, several modular design schemes can be gained. In order to select the best modularization scheme, we referenced the modularity concept and realized the quality measurement for the modular design using hypergraph modularity criteria. Regarding these three steps, a detailed modularization case study for a renewable electricity service ecosystem design is presented to verify the viability and feasibility of the study in service modular design. The result showed that the framework in this study can realize the visible and clearance service component identification in a smart connected multi-level industrial context. The modular design scheme based on hypergraph can also achieve high modularity with a more convenient correlation evaluation.

Real Time Drowsiness Detection System Using CNN

Abstract: Driver fatigue and rash driving are the leading causes of road accidents, which result in the loss of valued life and decrease road traffic safety. Driver drowsiness solutions that are reliable and precise are essential to prevent accidents and increase road traffic safety. Various driver drowsiness detection systems have been developed using various technologies that are geared at the specific parameter of detecting the driver's tiredness. This research offers a unique multi-level distribution model for detecting driver drowsiness utilising Convolution Neural Networks (CNN) and. To detect the driver's behaviour and emotion, the driver's face pattern is handled with a 2D Convolution Neural Network (CNN). The suggested model is built with OpenCV, and the experimental findings show that it recognises the driver's emotion and tiredness more efficiently than existing technologies

MDPN: Multilevel Distribution Propagation Network for Few-Shot Image Classification

Due to a shortage of labeled examples, few-shot image classification frequently experiences noise interference and insufficient feature extraction. In this paper, we present a two-stage framework based on the distribution propagation graph neural network (DPGN) called the multilevel distribution propagation network (MDPN). An instance-segmentation-based object localization (ISOL) module and a graph-based multilevel distribution propagation (GMDP) module are both included in the MDPN. To create a clear and full object zone, the ISOL module generates a mask that eliminates background and pseudo-object noises. The GMDP module enriches the level of features. We carried out comprehensive experiments on the few-shot dataset CUB-200-2011 to show the usefulness of MDPN. The results demonstrate that MDPN indeed outperforms DPGN in terms of few-shot image classification accuracy. Under 5-way 1-shot and 5-way 5-shot settings, the classification accuracy of MDPN exceeds the baseline by 8.17% and 1.24%, respectively. MDPN also outperforms the majority of the existing few-shot classification methods in the same setting.

High-efficiency square-hole single-mode waveguide photon sieves for THz waves.

The photon sieve has had the problem of low diffraction efficiency since it was proposed. Dispersion from different waveguide modes in the pinholes also reduces the quality of focusing. To overcome the above drawbacks, we propose a kind of photon sieve working in the terahertz band. In a metal square-hole waveguide, the effective index is determined by the side length of the pinhole. We adjust the optical path difference by changing the effective indices of those pinholes. When the thickness of the photon sieve is fixed, the optical path in a zone is set to be a multilevel distribution from 0 to λ. In this way, the optical path differences caused by the waveguide effect of pinholes are used to compensate for those caused by the positions of pinholes. We also derive the focusing contribution of an individual square pinhole. The simulated example shows a 60 times increase in intensity than that of the equal-side-length single-mode waveguide photon sieve.

Thoracolumbar fascia injury in osteoporotic vertebral fracture: the important concomitant damage

BackgroundThoracolumbar fascia injury (FI) is rarely discussed in osteoporotic vertebral fracture (OVF) patients in previous literature and it is usually neglected and treated as an unmeaning phenomenon. We aimed to evaluate the characteristics of the thoracolumbar fascia injury and further discuss its clinical significance in the treatment of kyphoplasty for osteoporotic vertebral fracture (OVF) patients.MethodsBased on the presence or absence of FI, 223 OVF patients were divided into two groups. The demographics of patients with and without FI were compared. The visual analogue scale and Oswestry disability index scores were compared preoperatively and after PKP treatment between these groups.ResultsThoracolumbar fascia injuries were observed in 27.8% of patients. Most FI showed a multi-level distribution pattern which involved a mean of 3.3 levels. Location of fractures, severity of fractures and severity of trauma were significantly different between patients with and without FI. In further comparison, severity of trauma was significantly different between patients with severe and non-severe FI. In patients with FI, VAS and ODI scores of 3 days and 1 month after PKP treatment were significantly worse compared to those without FI. It showed the same trend in VAS and ODI scores in patients with severe FI when compared to those patients with non-severe FI.ConclusionsFI is not rare in OVF patients and presents multiple levels of involvement. The more serious trauma suffered, the more severe thoracolumbar fascia injury presented. The presence of FI which was related to residual acute back pain significantly affected the effectiveness of PKP in treating OVFs.Trial registrationretrospectively registered.

Real Time Drowsiness Detection System Using CNN

Abstract: Driver fatigue and rash driving are the leading causes of road accidents, which result in the loss of valued life and decrease road traffic safety. Driver drowsiness solutions that are reliable and precise are essential to prevent accidents and increase road traffic safety. Various driver drowsiness detection systems have been developed using various technologies that are geared at the specific parameter of detecting the driver's tiredness. This research offers a unique multi-level distribution model for detecting driver drowsiness utilising Convolution Neural Networks (CNN) and. To detect the driver's behaviour and emotion, the driver's face pattern is handled with a 2D Convolution Neural Network (CNN). The suggested model is built with OpenCV, and the experimental findings show that it recognises the driver's emotion and tiredness more efficiently than existing technologies.

Point-Supervised Video Temporal Grounding

Given an untrimmed video and a language query, Video Temporal Grounding (VTG) aims to locate the time interval in the video semantically relevant to the query. Existing fully-supervised VTG methods require accurate annotations of temporal boundary, which is time-consuming and expensive to obtain. On the other hand, weakly-supervised VTG methods where only paired videos and queries are available during training lag far behind the fully-supervised ones. In this paper, we introduce point supervision to narrow the performance gap with affordable annotating cost and propose a novel method dubbed Point-Supervised Video Temporal Grounding (PS-VTG). Specifically, an attention-based grounding network is first employed to obtain a language activation sequence (LAS). Then pseudo segment-level label is generated based on the LAS and the given point supervision to assist the training process. In addition, multi-level distribution calibration and cross-modal contrast are framed to obtain discriminative feature representations and precisely highlight the language-relevant video segments. Experiments on three benchmarks demonstrate that our method trained with point supervision can significantly outperform weakly-supervised approaches and achieve comparable performance with fully-supervised ones.

Multi-Source Contribution Learning for Domain Adaptation.

Transfer learning becomes an attractive technology to tackle a task from a target domain by leveraging previously acquired knowledge from a similar domain (source domain). Many existing transfer learning methods focus on learning one discriminator with single-source domain. Sometimes, knowledge from single-source domain might not be enough for predicting the target task. Thus, multiple source domains carrying richer transferable information are considered to complete the target task. Although there are some previous studies dealing with multi-source domain adaptation, these methods commonly combine source predictions by averaging source performances. Different source domains contain different transferable information; they may contribute differently to a target domain compared with each other. Hence, the source contribution should be taken into account when predicting a target task. In this article, we propose a novel multi-source contribution learning method for domain adaptation (MSCLDA). As proposed, the similarities and diversities of domains are learned simultaneously by extracting multi-view features. One view represents common features (similarities) among all domains. Other views represent different characteristics (diversities) in a target domain; each characteristic is expressed by features extracted in a source domain. Then multi-level distribution matching is employed to improve the transferability of latent features, aiming to reduce misclassification of boundary samples by maximizing discrepancy between different classes and minimizing discrepancy between the same classes. Concurrently, when completing a target task by combining source predictions, instead of averaging source predictions or weighting sources using normalized similarities, the original weights learned by normalizing similarities between source and target domains are adjusted using pseudo target labels to increase the disparities of weight values, which is desired to improve the performance of the final target predictor if the predictions of sources exist significant difference. Experiments on real-world visual data sets demonstrate the superiorities of our proposed method.

Reactive Power Compensation and Harmonic Mitigation in Single-Phase Distribution System using Multilevel Converter Based D-STATCOM

This paper presents a study of a single-phase cascaded H-bridge multilevel converter-based Distribution Static Synchronous Compensator (D-STATCOM) with active harmonic filtering capability. For the proper operation of the proposed D-STATCOM, a constant voltage is maintained at its DC bus link using a proportional and integral (PI) controller. Based on instantaneous current errors, gate pulses for controlling duty cycles of the D-STATCOM operation are generated using the hysteresis current control (HCC) technique. The proposed D-STATCOM was modeled and simulated in MATLAB. Simulation results show that the proposed method effectively compensates for reactive power and mitigates current harmonics. The proposed method offers structural simplicity and efficiency without complex calculations.

Entropy exchange and thermal fluctuations in the Jaynes–Cummings model

The time dependence of the quantum entropy for a two-level atom interacting with a single-cavity mode is computed using the Jaynes–Cummings model, when the initial state of the radiation field is prepared in a thermal state with temperature fluctuations. In order to describe the out-of-equilibrium situation, the Super-Statistics approximation is implemented so that the gamma and the multi-level distribution functions are used to introduce the inverse temperature fluctuations. In the case of the gamma distribution, paralleling the Tsallis non-additive formalism, the entropy for the system is computed with the q-logarithm prescription, and the impact of the initial state of the atom is also taken into account. The results show that, in the first distribution, the q-parameter (related to the thermal fluctuations) modifies the partial entropies appreciably. In contrast, the way the inverse temperatures are distributed in the second one may lead to changes in the entropy functions.

Hierarchical Distribution Network Topology Formulation and Dimensionality Reduction Using Homeomorphism Transformation

The scales of the power distribution networks in real-world power grids expand quickly while the network structures are becoming more and more complex. The power grid companies analyze the power distribution networks in different business scenarios with different topology models. In this work, we propose a hierarchical graph model to describe the medium-voltage distribution network (which is a typical power distribution network in power grids) based on homeomorphic transformation. The hierarchical graph model preserves the basic network topology described by the traditional Common Information Model (CIM). Firstly, the nodes in the distribution network topology are classified according to graph theory. Secondly, three typical business scenarios of distribution network topology analysis are summarized, and the original model is simplified by progressive dimensionality reduction method to meet the analysis requirements of different scenarios, the simplified method consists of three abstract levels: critical path, core path and minimal path, and can effectively reduce the space complexity of the model while maintaining the topological properties. Thirdly, a multi-level distribution network topology construction and mapping method based on the graph database is proposed. It is used to realize the rapid conversion and traceability between different levels of topology. Finally, a practical distribution network in a county is used as an example to verify the effectiveness of the proposed method in the aspects such as topology rendering and path searching. The evaluation indicates that the proposed model can visualize the distribution network intuitively. The model can also speed up the visualization and path searching significantly.

CNN Based Driver Drowsiness Detection System Using Emotion Analysis

The drowsiness of the driver and rash driving are the major causes of road accidents, which result in loss of valuable life, and deteriorate the safety in the road traffic. Reliable and precise driver drowsiness systems are required to prevent road accidents and to improve road traffic safety. Various driver drowsiness detection systems have been designed with different technologies which have an affinity towards the unique parameter of detecting the drowsiness of the driver. This paper proposes a novel model of multi-level distribution of detecting the driver drowsiness using the Convolution Neural Networks (CNN) followed by the emotion analysis. The emotion analysis, in this proposed model, analyzes the driver’s frame of mind which identifies the motivating factors for different driving patterns. These driving patterns were analyzed based on the acceleration system, speed of the vehicle, Revolutions per Minute (RPM), facial recognition of the driver. The facial pattern of the driver is treated with 2D Convolution Neural Network (CNN) to detect the behavior and driver’s emotion. The proposed model is implemented using OpenCV and the experimental results prove that the proposed model detects the driver’s emotion and drowsiness more effectively than the existing technologies.

Iterative Prediction-and-Optimization for E-Logistics Distribution Network Design

The emergence of online retailers has brought new opportunities to the design of their distribution networks. Notably, for online retailers that do not operate offline stores, their target customers are more sensitive to the quality of logistic services, such as delivery speed and reliability. This paper is motivated by a leading online retailer for cosmetic products on Taobao.com that aimed to improve its logistics efficiency by redesigning its centralized distribution network into a multilevel one. The multilevel distribution network consists of a layer of primary facilities to hold stocks from suppliers and transshipment and a layer of secondary facilities to provide last-mile delivery. There are two major challenges of designing such a facility network. First, online customers can respond significantly to the change of logistics efficiency with the redesigned network, thereby rendering the network optimized under the original demand distribution suboptimal. Second, because online retailers have relatively small sales volumes and are very flexible in choosing facility locations, the facility candidate set can be large, causing the facility location optimization challenging to solve. To this end, we propose an iterative prediction-and-optimization strategy for distribution network design. Specifically, we first develop an artificial neural network (ANN) to predict customer demands, factoring in the logistic service quality given the network and the city-level purchasing power based on demographic statistics. Then, a mixed integer linear programming (MILP) model is formulated to choose facility locations with minimum transportation, facility setup, and package processing costs. We further develop an efficient two-stage heuristic for computing high-quality solutions to the MILP model, featuring an agglomerative hierarchical clustering algorithm and an expectation and maximization algorithm. Subsequently, the ANN demand predictor and two-stage heuristic are integrated for iterative network design. Finally, using a real-world data set, we validate the demand prediction accuracy and demonstrate the mutual interdependence between the demand and network design. Summary of Contribution: We propose an iterative prediction-and-optimization algorithm for multilevel distribution network design for e-logistics and evaluate its operational value for online retailers. We address the issue of the interplay between distribution network design and the demand distribution using an iterative framework. Further, combining the idea in operational research and data mining, our paper provides an end-to-end solution that can provide accurate predictions of online sales distribution, subsequently solving large-scale optimization problems for distribution network design problems.

A Multi-level Watermarking Algorithm for RasterGeographic Data Based on Watermark Information Segmentation Mechanism

This paper presents a multi-level digital watermarking algorithm suitable for raster geographic data. First, the new problems caused by the multi-level distribution of raster geographic data and its impact on watermark embedding/detection are analyzed; and then, a watermark information segmentation mechanism is designed, the multi-level watermark embedding strategy is established on this basis, thereby building the multi-level digital watermarking algorithm of raster geographic data based on the watermark segmentation mechanism with the traditional robust digital watermarking algorithm as the prototype; finally, the experimental comparison and analysis of the multi-level watermarking algorithm and the prototype algorithm are made. Results show that the proposed multi-level digital watermarking algorithm not only maintains the performance of the prototype algorithm, but also effectively solves new problems caused by the multi-level circulation of raster geographic data, such as multi-copyright protection and multi-user tracking, and has a high practical value.

ЕФЕКТИВНІСТЬ СИСТЕМИ УПРАВЛІННЯ РОЗПОДІЛОМ ТА ЗБУТОМ ПРОДУКЦІЇ ТОРГОВЕЛЬНОГО ПІДПРИЄМСТВА

The theoretical substantiation of the distribution and sales management system of a trade enterprise is carried out in the article. The role of distribution and sales policy of the enterprise in realization of the purposes and tasks of business activity is shown. Sales activities of enterprises occupy a leading place in the management system. It has a goal subordinated to the management of strategic development of the enterprise, aimed at forming a system of support, taking into account industry characteristics, internal and external problems. The use of scientifically approaches to the management of sales activities of industrial enterprises will allow managers to make effective decisions. Sales is an integral part of marketing activities of the enterprise, which consists of a holistic process of bringing products to the final consumer through the use of marketing measures to study the needs, formation and stimulation of demand for products to meet consumer needs and make a profit. The organization of sales management system of a trade enterprise, which provides for the development, planning, coordination, organization and control of relevant measures and key indicators of efficiency and scale of product promotion in order to establish long-term relationships with business partners in a strategic partnership. The problems of sales management and distribution of a commercial enterprise are studied. The efficiency of the distribution and sales system is analyzed and practical ways to solve the research and production problem, which is to develop recommendations for the management of the distribution system and sales policy of the organization, the development of practical recommendations for its improvement. The directions of improvement of the system of distribution and sale of products are substantiated. In order to increase payment discipline in settlements with counterparties to improve sales activities in the direction of sales through a single-level (and multilevel) distribution channel, it is recommended to identify key aspects to be specified in supply and sale agreements. To improve the implementation of the strategy of management of distribution and sales of products, it is proposed to reorganize the scheme of implementation of logistics processes in the enterprise. To increase the financial efficiency of sales activities, it is proposed to introduce an optimal CRM-system for automation of business processes and interaction with customers in the direction of sales through the zero distribution channel.

Research on Multi-level Distribution Strategy Based on Energy Internet

Smart city energy Internet is to comply with the trend of sustainable energy development, urban power energy as the center, comprehensive utilization of all kinds of energy, especially renewable energy, to achieve interconnection and common optimization. Based on the background of distribution network in Disney Park, this paper studies the regulation, operation and management strategy of distribution network of smart city energy Internet. This paper describes the characteristics of the energy Internet, and then analyzes the key technologies that affect power grid regulation, operation and management. The paper investigated the distribution network construction in Shanghai Disney Park under the background of urban energy Internet pilot region to understand the allocation of distributed energy in the park grid. Through simulation calculation and analysis, this paper puts forward a distribution network regulation and management scheme suitable for the characteristics of energy Internet. In this paper, the study found that with the rapid development of power grid, especially all kinds of distributed energy access, the new lines are becoming more. In a wide range of power grid structure is becoming more and more complex, in order to ensure the reliability of power supply and power supply quality, scientific regulation under the background of urban energy Internet development mode, enhancing the management level of power grid is the inevitable developing trend of power grid.