Predict Service Performance Research Articles

An optimised grinding target profile considering long-term service performance: A case study of no. 18 high-speed turnout

The design of rail grinding profiles for turnout has always been a significant subject of research. This paper proposes a rail grinding target profile design method that can improve the serviceability of turnout. Firstly, the high-speed turnout rail profile was parameterised by non-uniform rational B-spline (NURBS), with the amount of key section control point grinding used as a design variable. Secondly, considering the evolution mechanism of turnout dynamics performance and rail wear, a turnout long-term service performance prediction model is established based on deep feedforward network (DFN), with relevant evaluation indexes as the objective function. Non-dominated sorting genetic algorithm-Ⅱ (NSGA-Ⅱ) is used to solve this multi-objective optimisation problem. Finally, a comparative analysis of the performance of the turnout profile before and after optimisation is conducted. The computed outcomes demonstrate that after the turnout is ground, all the dynamic performance indicators have substantially improved in the short term. Additionally, the maximum wear on the straight switch rail has been reduced by 31.2 % and the position of the occurrence has shifted backward, which has improved the stressing of the weak rail elements to some extent. In long-term service conditions, the optimised turnout profile sustains a higher level of riding quality compared to the measured profile. Optimisation of the profile can effectively decelerate the rail wear rate and aid in prolonging the service life of the turnout.

Data‐driven and artificial intelligence accelerated steel material research and intelligent manufacturing technology

AbstractWith the development of new information technology, big data technology and artificial intelligence (AI) have accelerated material research and development and industrial manufacturing, which have become the key technology driving a new wave of global technological revolution and industrial transformation. This review introduces the data resources and databases related to steel materials. It then examines the fundamental strategies and applications of machine learning (ML) in the design and discovery of steel materials, including ML models based on experimental data, industrial manufacturing data, and simulation data, respectively. Given the advancements in big data, AI/ML, and new communication technologies, an intelligent manufacturing mode featuring digital twins is deemed critical in guiding the next industrial revolution. Consequently, the application of intelligence manufacturing with digital twins in the iron and steel industry is reviewed and discussed. Furthermore, the applications of ML in service performance prediction of steel products are addressed. Finally, the future development trends for data‐driven and AI approaches throughout the entire life cycle of steel materials are prospected. Overall, this work presents an in‐depth examination of the integration of data‐driven and AI technologies in the steel industry, highlighting their potential and future directions.

Degradation kinetics and service performance prediction of CoSb3-based skutterudite thermoelectric device

Predictable service performance is essentially required for practical applications of thermoelectric (TE) power generators. Sublimation at TE material surface and chemical reaction/diffusion at electrode interface are the major causes for the performance degradation of TE devices. The synergistic effect of surface and interface behaviors coupled with temperature gradient makes the degradation relationship much more complicated, and the accurate prediction of service performance very challenging. In this work, we systematically investigated the sublimation kinetics for p-type Ce0.9Fe3CoSb12 and n-type Yb0.3Co4Sb12 skutterudites. A service performance prediction model (SPPM) is proposed to illustrate the service performance profiles of TE device, in which an equivalent circuit approach is applied to quantitatively link the kinetic parameters of structure and composition evolutions at both surface and interface to the output performance of device. It is found that, the performance degradation is mainly caused by the interfacial structure evolution at early stage, while the influence of surface sublimation becomes dominant in long-term service. The SPPM simulation results are well verified by the long-term evaluation tests of single-leg devices under temperature gradients, demonstrating its potential application to the engineering design of TE power generators.

Federated learning for performance prediction in multi-operator environments

Telecom vendors and operators deliver services with strict requirements on performance, over complex and sometimes partly shared network infrastructures. A key enabler for network and service management in such environments is knowledge sharing, and the use of data-driven models for performance prediction, forecasting, and troubleshooting. In this paper, we outline a multi-operator service metrics prediction framework using federated learning that allows privacy-preserved knowledge-sharing across operators for improved model performance, and also reduced requirements on data transfer within an operator network. Federated learning is compared against local and central learning strategies for multi-operator performance prediction, and it is shown to balance the requirements on data privacy, model performance, and the network overhead. Further, the paper provides insights on how data heterogeneity affects model performance, where the conclusion is that standard federated learning has certain robustness to data heterogeneity. Finally, we discuss the challenges related to training a federated learning model with a limited budget on the communication rounds. The evaluation is performed using a set of realistic publicly available data traces, that are adapted specifically for the purpose of studying multi-operator service performance prediction.

An Online Service Performance Prediction Learning Method

In order to improve the quality of service operations, it is necessary to take the initiative to prevent service failures and service performance fluctuations, instead of triggering handlers when service errors occur. Effective prediction and analysis of the large-scale services performance is an effective and feasible proactive prevention tool. However, the traditional service performance prediction model mostly adopts the full batch training mode, it is difficult to meet the real-time requirements of large-scale service calculation. Based on the comprehensive trade-off between the method of full batch learning and the stochastic gradient descent method, a large-scale service performance prediction model is established based on online learning, and a service performance prediction method is proposed based on small batch online learning. Through properly setting the batch parameters, the proposed approach only need to train the sample data with small batches in one iteration, the time efficiency is improved for large-scale service performance prediction.

Evaluating uncertainties to deliver enhanced service performance in education PPPs: a hierarchical reliability framework

PurposeThis study aims to develop a hierarchical reliability framework to evaluate the service delivery performance of education public–private partnerships (PPPs) effectively and efficiently during long-term operations.Design/methodology/approachThe research design included development and test phases. In the development phase, three performance layers, i.e. indicator, component and system, in the education service delivery system were identified. Then, service component reliability was computed through first order reliability method (FORM). Finally, the reliability of the service system was obtained using dynamic component weightings. A PPP school example in Australia was set up in the test phase, where performance indicators were collected from relevant contract documents and performance data were simulated under three assumptive scenarios.FindingsThe example in the test phase yielded good results for the developed framework in evaluating uncertainties of service delivery performance for education PPPs. Potentially underperforming services from the component to the system level at dynamic timepoints were identified, and effective preventative maintenance strategies were developed.Research limitations/implicationsThis research enriches reliability theory and performance evaluation research on education PPPs. First, a series of performance evaluation indicators are constructed for assessing the performance of the service delivery of the education PPP operations. Then, a reliability-based framework for service components and system is developed to predict service performance of the PPP school operations with consideration of a range of uncertainties during project delivery.Practical implicationsThe developed framework was illustrated with a real-world case study. It demonstrates that the developed reliability-based framework could potentially provide the practitioners of the public sector with a basis for developing effective preventative maintenance strategies with the aim of prolonging the service life of the PPP schools.Originality/valueEvaluating education PPPs is challenging as it involves long-term measurement of various service components under uncertainty. The developed reliability-based framework is a valuable tool to ensure that reliability is maintained throughout the service life of education PPPs in the presence of uncertainty.

Prediction of Service Performance Based on Physical Strength in Elite Junior Tennis Players.

In tennis, service requires a variety of complicated movements. Given the importance of taking the initiative to obtain points in a tennis match, it is crucial to make full use of speed and spin rate of service. Generally, a service that requires a higher spin rate would slow down, and a service that has increased speed would have a decreased spin rate. For players who are disadvantaged in height, although controlling spin rate is essential, slowing down service speed should be avoided. For these players, the challenge of service is to improve the speed without decreasing the spin rate. Players must also be trained to build physical strength required for this skill. It is not uncommon to work on physical training without a racket; however, few studies have reported on the effects of cultivated physical strength on on-court tennis performance. Therefore, this study aimed to propose physical measurements that could be used as indices to improve service performance in 58 elite Japanese junior male players. To test service performance, we used TrackMan tennis radar device to assess speed, spin rate, impact height, and impact depth. To test physical strength, we measured 5- and 20-m sprint, broad jump, medicine ball throw (forward, backward). We used a significant multiple regression equation to predict the first service speed obtained from the broad jump and the Medicine ball throw (backward). Additionally, a strong correlation was obtained between the predicted and measured values. In addition to physical strength, we suggest that the depth of the impact point (taking the hitting point forward toward the net) is important for improving the first service speed. However, we were not able to identify the physical strength test items that improve service spin rate. Other item should be examined in the future to determine the physical strength associated with spin rate. This result could help connect physical training and service performance.

The TEAGE ageing method for asphalt mixtures

Exposure to the environmental conditions, particularly ultraviolet (UV) radiation, temperature, and precipitation, causes progressive and irreversible ageing of the in-service asphalt mixtures. Due to the ageing effect, the initial mechanical performance of the asphalt mixture degrades over time. Thus, the evaluation of the asphalt mixture's performance under aged conditions is essential to predict service performance better and avoid durability issues.This article presents a recently developed method for the accelerated ageing of compacted asphalt mixtures specimens in the laboratory called TEcnico accelerated AGEing (TEAGE). The TEAGE intends to simulate ageing due to the exposure to environmental conditions, allowing a relation with the field conditions (location) and exposure period (age). Four asphalt mixtures were selected and tested for stiffness and fatigue resistance under unaged and aged conditions by TEAGE.The obtained results highlighted the TEAGE potential to implement an accurate field ageing simulation. The aged mixtures presented a more stiff and brittle behaviour, revealed by an increase in stiffness modulus, a decrease in phase angle, and the reduction of the fatigue resistance.

Customer mistreatment and service performance: A self-consistency perspective

The service encounter is an important social context for hospitality service providers who strive to satisfy their need for job competence by delivering excellent customer service. Customer mistreatment may be perceived as a sign of work-related goal failure by hospitality service providers. Building on the literature of goal attainment and failure in the workplace, we propose that hospitality employees, who experience customer mistreatment, undergo diminished organization-based self-esteem (OBSE), decreasing service performance. Moreover, employees’ locus of control is proposed to interact with customer mistreatment and predict service performance through the mediation of OBSE. The results of a multi-wave and multi-source survey, administered to a sample of hotel frontline employees (N = 180) and their direct supervisors (N = 38), show that customer mistreatment has a negative influence on service performance through OBSE, but only among employees with an external locus of control.

Career adaptability and ambidextrous behavior among customer-service representatives: the role of perceived organizational support

With the increasing need for dynamism in the world, organizations and researchers have been interested in how employees can easily cope with change and be flexible on the job by using their foreknowledge and still being open to new ideas to boost their work output. Consequently, there has been an increase in research on ambidexterity. However, much is still unknown regarding the determinants of individual-level ambidexterity. This article examines the importance of career adaptability resources in predicting employees’ ambidextrous behavior and service performance. Our study also demonstrates the mediation role of ambidexterity in the career adaptability–service performance relationship as well as the moderating role of perceived organizational support (POS) in the ambidexterity–service performance relationship. Data were collected from 443 service representatives of telecommunication organizations in two timepoints. Structural equation modeling (SEM) was used to test the research hypotheses. SEM results show that career adaptability positively relates to ambidextrous behavior and service performance. While POS interacts with ambidexterity to positively predict service performance, ambidexterity serves as a mechanism through which career adaptability influences service performance. The study provides insight for practitioners to offer adequate guidance and a supportive working environment for both existing and prospective employees toward training and performance.

Development of the performance prediction algorithms for cloud services

Main stages of data center service performance prediction were discussed, specifically data monitoring and gathering, calculation and prediction of key indexes and performance index prediction. It was proposed to build data center service performance prediction algorithm based on an analysis of the service transactions index, service resource occupancy index and service performance index. Prediction of the indexes is based on chaotic time series analysis that was used to estimate service transactions index time series trend, the radar chart method to calculate the service resource occupancy index value and weighted average method to calculate service performance index. For performance prediction, it is proposed to use a fuzzy judgment matrix with the service transactions index and service resource occupancy index as input values. It was taken into consideration that service transactions index is usually represented by nonlinear time series and thus the index time series parameters had to be predicted by chaos theory and for the calculation of this index, the estimation procedure of Lyapunov exponent value can be used. The radar chart demonstrates service resource occupancy index estimation of shared storage, mobile storage, memory, computational capability and network bandwidth. The prediction technique was based on the fuzzy nearness category that use input values of transactions index and dynamic changes of the service resource occupancy index.

Predicting the online performance of video service providers on the internet

Video services on the Internet are not able to offer consistent and assured performance to users or third-party applications. Measuring levels of performance over time is difficult, and obtaining accurate measures in real time is problematic; thus, reactive measures to address loss of performance are also problematic. The ability to predict service performance can be viewed as an important added-value, one that can help users or third-part applications select the proper online service provider. With this aim in view, we have designed a measurement system and deployed it in eleven provinces and cities in China to monitor two popular websites, Youku and Tudou. The analysis indicates that the performance trend of these two service providers followed daily changing patterns, such as rush hour traffic and lower service workloads at midnight; this is consistent with user behaviors. It was also confirmed that the future performance was related to the historical records. Based on these findings, we have decided to investigate the use of modified time series models to forecast the performance of such video services. Meanwhile, some machine learning models are implemented and compared as baseline models, such as Artificial Neural Network, Support Vector Machine, and Decision Tree. In addition, a hybrid model, which is generated by combining different machine learning models, is also studied as the baseline. An investigation shows that time series models are much more suitable to this prediction problem than baseline models in most situations. To alleviate the data sparseness problem in training the predictor, a new predictor that combines different information sources is proposed, thus improving prediction precision. Furthermore, the predictor is quite stable, and we have discovered that the average performance estimation is more accurate if the model is updated within 2–3 days, which is useful in some applications, e.g., video source analysis and recommendation systems.

A service oriented manufacturing grid system with uncertain information

Purpose – The increase in demand variability created by manufacturing enterprises presents new challenges for increasing resource usage and sharing flexibility. For this reason, it is of great importance to research manufacturing grids and their service modes. The purpose of this paper is to establish a systematic strategy and a system tool for manufacturing grid systems. Design/methodology/approach – A manufacturing service oriented manufacturing grid (MSoMG) system is presented with open grid service architecture as the system architecture and GT3.9 as a development tool. A framework is proposed to support MSoMG by providing advisory tools and methods for uncertain information analysis and processing, multi-objective decision making of manufacturing grid service execution, manufacturing grid service performance prediction based on knowledge template, and flexible manufacturing grid service scheduling and solution. The methodology of the adopted rough set is discussed in detail. Finally, the design support strategies for MSoMG are investigated to guide the coordination of manufacturing activities. Findings – Many conventional methods and models become very limited for manufacturing grid service with uncertain information. The processing of uncertain information and reasonable application flow can help to improve the completion rate and reliability of manufacturing grid services. Practical implications – This research provides a solid foundation for manufacturing gird operations and can promote the use of a manufacturing grid mode. Originality/value – A MSoMG system is presented. The manufacturing grid service with uncertain information is considered as well as design support strategies.

A critical review of the influence of hydrogen on the mechanical properties of medium-strength steels

AbstractAs medium-strength steels are promising candidates for the hydrogen economy, it is important to understand their interaction with hydrogen. However, there are only a limited number of investigations on the behavior of medium-strength steels in hydrogen. The existing literature indicates that the influences of hydrogen on the tensile properties of medium-strength steels are mainly the following: (i) the steel can be hardened by hydrogen, as demonstrated by an increase in the yield stress or ultimate tensile stress; (ii) some steels can be embrittled by hydrogen, as revealed by lower yield stress or ultimate tensile stress; (iii) in most cases, these steels may experience hydrogen embrittlement (HE), as indicated by a reduction in ductility. The degree of HE mainly depends on the test conditions and the steel. The embrittlement can lead to catastrophic brittle fracture in service. The influence of hydrogen on the fatigue properties of medium-strength steels is dependent on many factors such as the stress ratio, temperature, yield stress of the steel, and test frequency. Generally, the hydrogen influence on fatigue limit is small, whereas hydrogen can accelerate the fatigue crack growth rate, leading to a shorter fatigue life. Inclusions are an important factor influencing the properties of medium-strength steels in the presence of hydrogen. However, it is not possible to predict the influence of hydrogen for any particular steel that has not been experimentally evaluated or to predict service performance. It is not known why similar steels can have different behavior, ranging from good resistance to significant embrittlement. A better understanding of the microstructural characteristics is needed.

Load Index Metrics for an Optimized Management of Web Services: A Systematic Evaluation

The lack of precision to predict service performance through load indices may lead to wrong decisions regarding the use of web services, compromising service performance and raising platform cost unnecessarily. This paper presents experimental studies to qualify the behaviour of load indices in the web service context. The experiments consider three services that generate controlled and significant server demands, four levels of workload for each service and six distinct execution scenarios. The evaluation considers three relevant perspectives: the capability for representing recent workloads, the capability for predicting near-future performance and finally stability. Eight different load indices were analysed, including the JMX Average Time index (proposed in this paper) specifically designed to address the limitations of the other indices. A systematic approach is applied to evaluate the different load indices, considering a multiple linear regression model based on the stepwise-AIC method. The results show that the load indices studied represent the workload to some extent; however, in contrast to expectations, most of them do not exhibit a coherent correlation with service performance and this can result in stability problems. The JMX Average Time index is an exception, showing a stable behaviour which is tightly-coupled to the service runtime for all executions. Load indices are used to predict the service runtime and therefore their inappropriate use can lead to decisions that will impact negatively on both service performance and execution cost.

Online pressure–volume–temperature measurements of polypropylene using a testing mold to simulate the injection‐molding process

AbstractTo obtain accurate prediction of service performance and service life of polymers and to optimize the processing parameters, a modified online measurement was used to measure the pressure–volume–temperature (PVT) properties of polymers under certain processing conditions. The measurement was based on an injection molding machine, and it was used to obtain the PVT data of polymers directly with a special testing mold under normal processing conditions. The PVT properties of a semicrystalline polymer, polypropylene, were measured through both an online testing mold and a conventional piston–die dilatometer. The PVT properties were correlated by a modified two‐domain Tait equation of state. The differences between the two groups of PVT data measured were investigated, and relative differences, especially in the rubbery state because of different cooling or heating measuring modes and sample forms, were observed. Numerical simulations of injection‐molding processes were carried out by Moldflow software with both of the types of PVT data. The resulting online PVT data exhibited improvement in the accurate prediction of shrinkage and warpage. © 2010 Wiley Periodicals, Inc. J Appl Polym Sci, 2010

Creep of PVDF monofilament sutures: service performance prediction from short-term tests

Isothermal short-term creep of poly (vinylidene fluoride) (PVDF) monofilament sutures was determined at several temperatures between 10 and 90 °C under the stress of 10 MPa. Long term service performance was predicted for 10 decades of time. The compliance master curve as a function of time fits a hyperbolic sine equation. The temperature shift factor as a function of the temperature a T ( T) is accurately represented by a general equation based on free volume. A simple relationship between the two parameters of the equation is explored. The viscoelasticity of PVDF is also seen in dynamic mechanical analysis performed at the frequency of 1 Hz. The origin of the viscoelastic character well present in the deformability of the PVDF in service is due to the occurrence of the α c relaxation that is active at ∼50 °C ( E″ peak at 1 Hz).

Survey of status of test methods for accelerated durability testing

A survey was made of test methods, standardised and in use, for accelerated durability testing of polymers. Consideration is given to the relevant features and differences between standards, the repeatability and comparability of data, the level of use of standards and the acceptance of accelerated durability tests, especially to predict service performance.

Testing Transmission Lubricants: The Importance of Thermal Response

The performance of transmission systems, especially those of high criticality and specific torque capacity such as those in helicopters, depends strongly on lubricant behaviour. However, economic load capacity evaluation of lubricants involves the correlation of test results obtained from simple tests in order to predict service performance, which is an unreliable step. In this paper the role of the thermal characteristics of the test machine is explored and the results used to resolve the apparent contradictions in the ranking order obtained from different test methods. A simple method for calculating the bulk and surface temperatures in disc machines is given together with corresponding experimental confirmation. The performance of two lubricants that show a reversal in ranking order at a particular temperature is examined.

Mechanical Fatigue of Rubber

Abstract Fatigue failure of rubber under repeated loading is reviewed. The process considered is that occurring in the absence of appreciable temperature rise as a result of the development of one or more cracks. A fracture mechanics approach, based on the elastic energy available for crack propagation, enables the crack growth and fatigue behavior to be interrelated quantitatively and is helpful from both basic and applied viewpoints. Initiation of mechanical crack growth is governed by a critical value of the available energy, which is of similar magnitude for various elastomers and can be related approximately to the primary bond strength and molecular structure. Once this value is exceeded, the characteristics of growth vary markedly for different elastomers and appear to be influenced primarily by the elastic hysteresis of the rubber at high strains. Although the mechanical deformations are the basic driving force, the crack growth and fatigue behavior can also be strongly affected by atmospheric oxygen and ozone and the mechanisms of action of these gases are described. Implications of the work from the testing and service viewpoints are considered. A major problem in applying the fracture mechanics approach is to determine the energy available for crack growth in a component of complex shape. Recently-developed methods of doing this are discussed and the quantitative application of the approach to predict service performance is illustrated.