Junbo Liu, Yaping Huang, Shengchun Wang, Xinxin Zhao, Qi Zou and Xingyuan Zhang
This research aims to improve the performance of rail fastener defect inspection method for multi railways, to effectively ensure the safety of railway operation.
Abstract
Purpose
This research aims to improve the performance of rail fastener defect inspection method for multi railways, to effectively ensure the safety of railway operation.
Design/methodology/approach
Firstly, a fastener region location method based on online learning strategy was proposed, which can locate fastener regions according to the prior knowledge of track image and template matching method. Online learning strategy is used to update the template library dynamically, so that the method not only can locate fastener regions in the track images of multi railways, but also can automatically collect and annotate fastener samples. Secondly, a fastener defect recognition method based on deep convolutional neural network was proposed. The structure of recognition network was designed according to the smaller size and the relatively single content of the fastener region. The data augmentation method based on the sample random sorting strategy is adopted to reduce the impact of the imbalance of sample size on recognition performance.
Findings
Test verification of the proposed method is conducted based on the rail fastener datasets of multi railways. Specifically, fastener location module has achieved an average detection rate of 99.36%, and fastener defect recognition module has achieved an average precision of 96.82%.
Originality/value
The proposed method can accurately locate fastener regions and identify fastener defect in the track images of different railways, which has high reliability and strong adaptability to multi railways.
Details
Keywords
Yuanyuan Fan, Tingyu Sui, Kang Peng, Yingjun Sang and Fei Huang
This paper aims to collect the energy consumption data and carry out energy consumption analysis of chemical enterprises, which is helpful to grasp the working conditions of each…
Abstract
Purpose
This paper aims to collect the energy consumption data and carry out energy consumption analysis of chemical enterprises, which is helpful to grasp the working conditions of each equipment accurately and to perfect the demand side management (DSM) for the user in the terminal.
Design/methodology/approach
The paper proposes a load monitoring system of chemical enterprises to collect the energy consumption data and carry out energy consumption analysis. An Elman neural network based on sparrow search algorithm is proposed to predict the power consumption change and distribution trend of enterprises in the future production cycle. The calculation efficiency and prediction accuracy have been significantly improved.
Findings
The paper analyzes the energy saving effect of energy efficiency management as well as “avoiding peak and filling valley” measures, and reasonable control requirements and assumed conditions are put forward to study the operability of enterprise energy saving measures from the DSM.
Research limitations/implications
Because of the chosen enterprise data, the prediction accuracy needs to be further improved. Therefore, researchers are encouraged to test the proposed methodology further.
Practical implications
The paper includes implications for the development of energy consumption analysis and load forecasting of chemical enterprises and perfects the DSM for the user.
Originality/value
This paper fulfills an identified need to study how to forecast the power load and improve the management efficiency of energy consumption.
Details
Keywords
Monica Lopez-Campos, Salvatore Cannella, Pablo A. Miranda and Raul Stegmaier
The purpose of this paper is to propose and model collaboration and information exchange enabler strategies, designed to accomplish significant improvements in supply chain (SC…
Abstract
Purpose
The purpose of this paper is to propose and model collaboration and information exchange enabler strategies, designed to accomplish significant improvements in supply chain (SC) performance. Some of these improvements to the SC include the reduction of the bullwhip effect and increased customer and SC partner benefits. The authors propose a fully collaborative replenishment model. The study details the information flow required to implement new SC collaboration strategies, clarifying a specific strategy for information sharing involving inventory levels (on hand, in process, etc.), orders and demand forecast.
Design/methodology/approach
The authors suggest the adoption of business process modelling (BPM) methodology, aimed at identifying which information should be shared by SC partners, in order to create fully collaborative strategies.
Findings
The features of BPM allow for the effortless integration of the modelled information collaboration strategies into a general network information system, creating a flexible structure that can be quickly and even automatically adapted to new conditions.
Research limitations/implications
In this paper, a serial SC has been analysed, but enterprises also commonly manage more complex kind of chains. Chains composed of more than one member in the same echelon, divergent chains, convergent chains, network chains are all different configurations that require their own algorithm. The authors use the order up to policy, but there are other policies that can be considered to extend the scope of the model.
Practical implications
BPM, specifically through Unified Modelling Language (UML) and Business Process Modelling Notation standards, represents a suitable technique to develop and implement new SC collaboration practices, serving as a communication link between managers and software developers.
Social implications
The expected results of this work imply the proposal of a reference model for collaborative supply chain (CSC) organisations, contributing to the enhancement of value creation for the whole CSC.
Originality/value
The aim of this paper is to clarify the information-sharing algorithm required to implement a collaborative structure for an SC. This algorithm is expressed using the BPM technique, specifically UML and Business Process Model and Notation standards.
Propósito
Este documento propone y modela estrategias de colaboración y habilitación de intercambio de información, diseñadas para lograr mejoras significativas en el rendimiento de la cadena de suministro (SC). Algunas de estas mejoras incluyen la reducción del efecto látigo y mayores beneficios para los clientes y socios de la cadena de suministro. Proponemos un modelo de reabastecimiento totalmente colaborativo. El estudio detalla el flujo de información requerido para implementar nuevas estrategias de colaboración en la cadena de suministro, aclarando una estrategia específica para el intercambio de información que involucra niveles de inventario (en mano, en proceso, etc.), pedidos y previsión de la demanda.
Diseño/metodología/enfoque
Sugerimos la adopción de la metodología de Modelado de Procesos de Negocio, dirigida a identificar qué información debe ser compartida por los socios de la cadena de suministro, a fin de crear estrategias totalmente colaborativas.
Hallazgos
las características del Modelado de Procesos de Negocio permiten la integración, sin un excesivo esfuerzo, de las estrategias de colaboración modeladas en un sistema de información general, creando una estructura flexible que puede adaptarse rápida e incluso automáticamente a las nuevas condiciones.
Limitaciones/implicaciones de la investigación
en este documento, se ha analizado una cadena de suministro en serie, sin embargo las empresas también suelen administrar cadenas más complejas. Cadenas compuestas de más de un miembro en el mismo escalón, cadenas divergentes, cadenas convergentes, cadenas de red, son todas configuraciones diferentes que requieren su propio algoritmo. Igualmente, en este artículo usamos la política de pedido “order up to” aunque también existen otras políticas que se pueden considerar para ampliar el alcance del modelo.
Implicaciones prácticas
el modelado de procesos BPM, específicamente a través del Lenguaje Unificado de Modelado (UML) y estándares para la notación de Modelado de Procesos de Negocio (BPMN), representa una técnica adecuada para desarrollar e implementar nuevas prácticas de colaboración de cadena de suministro, que sirve como un enlace de comunicación entre los gerentes y los desarrolladores de software.
Implicaciones sociales
los resultados esperados de este trabajo implican la propuesta de un modelo de referencia para la colaboración de las organizaciones de la cadena de suministro, contribuyendo a la mejora de la creación de valor para toda la cadena de suministro colaborativa.
Originalidad/valor
el objetivo de este documento es aclarar el algoritmo de intercambio de información requerido para implementar una estructura colaborativa para una cadena de suministro. Este algoritmo se expresa utilizando la técnica BPM, específicamente a través de los estándares UML y BPMN.