5G and beyond cellular networks promise remarkable advancements in bandwidth, latency, and connectivity. The emergence of Open Radio Access Network (O-RAN) represents a pivotal direction for the evolution of cellular ...
详细信息
ISBN:
(纸本)9781728190549
5G and beyond cellular networks promise remarkable advancements in bandwidth, latency, and connectivity. The emergence of Open Radio Access Network (O-RAN) represents a pivotal direction for the evolution of cellular networks, inherently supporting machine learning (ML) for network operation control. Within this framework, RAN Intelligence controllers (RICs) from one provider can employ ML models developed by third-party vendors through the acquisition of key performance indicators (KPIs) from geographically distant base stations or user equipment (UE). Yet, the development of ML models hinges on the availability of realistic and robust datasets. In this study, we embark on a two-fold journey. First, we collect a comprehensive 5G dataset, harnessing real-world cell phones across diverse applications, locations, and mobility scenarios. Next, we replicate this traffic within a full-stack srsRAN-based O-RAN framework on Colosseum, the world's largest radio frequency (RF) emulator. This process yields a robust and O-RAN compliant KPI dataset mirroring real-world conditions. We illustrate how such a dataset can fuel the training of ML models and facilitate the deployment of xApps for traffic slice classification by introducing a CNN based classifier that achieves accuracy > 95% offline and 92% online. To accelerate research in this domain, we provide open-source access to our toolchain and supplementary utilities, empowering the broader research community to expedite the creation of realistic and O-RAN compliant datasets.
The article presents the design and expected results from the use of a digital twin monitoring and management system. It is a continuation of the multi-step improvement of the sensor assembly line until its full autom...
详细信息
ISBN:
(纸本)9781665465892
The article presents the design and expected results from the use of a digital twin monitoring and management system. It is a continuation of the multi-step improvement of the sensor assembly line until its full automation. Statistical control, machine learning, deep machine learning, fuzzy logic and neural networks have been applied to improve and optimize data selection and analysis. A model of digital twins is applied, in which the analysis and feedback for automatic optimal control are outside the work center of a server or cloud. With this powerful management model, many work centers are serviced. Thus, with the development of a single powerful analysis software from the machine manufacturer, many work centers can be managed. This makes the process more automatic and with a lower cost. A specific goal has been set to speed up the work of the automatic production center for assembling sensors and achieve a production cycle of 5 seconds with improved quality results. This is achieved by optimizing automatic visual control using digital twin analysis. Quality improvement has been achieved by improving the inputs of the assembly process using digital twin analysis.
The prediction of blast furnace gas (BFG) generation in ironmaking processes is crucial for the BFG scheduling work. Due to frequent switching of working conditions of the ironmaking process, the generation of BFG und...
详细信息
ISBN:
(数字)9789887581598
ISBN:
(纸本)9798331540845
The prediction of blast furnace gas (BFG) generation in ironmaking processes is crucial for the BFG scheduling work. Due to frequent switching of working conditions of the ironmaking process, the generation of BFG under each working condition fluctuates greatly. It is difficult to predict accurately during the transition of working conditions. In order to address these problems, this paper proposes a data-driven BFG generation prediction method based on a combination of an event-triggered scheme and a trend self-adaption scheme. In this method, different working conditions are divided by events such as the change of supply of hot air and oxygen. Considering the process characteristics of air reduction and restoration, the decrease and increase trends are predicted by a parameter adaption-based linear logarithmic regression. The model parameters are corrected online to realize trend self-discrimination. Besides, as for the residual sequence after trend fitting, it is modeled by using the long short-term memory (LSTM) network. To validate the effectiveness of the proposed method, actual industrial field data of a steel plant in China are utilized. Simulation experimental results show that the proposed method significantly improves prediction accuracy of the BFG generation flow.
The Maritime Augmented Guidance with Integrated controls for Carrier Approach and Recovery Precision Enabling Technologies (MAGIC CARPET) effectively overcomes the drawbacks of traditional carrier-based aircraft landi...
详细信息
The Maritime Augmented Guidance with Integrated controls for Carrier Approach and Recovery Precision Enabling Technologies (MAGIC CARPET) effectively overcomes the drawbacks of traditional carrier-based aircraft landing methods, improving trajectory response speed and landing accuracy, while significantly easing the control burden for pilot. analysis of the control structure of MAGIC CARPET reveals its high dependency on flight path angle signals. In this paper, a set of state equations and measurement equations for path angle estimation are proposed for nonlinear Kalman filter algorithm. The Unscented Kalman Filter (UKF) is applied to the designed state equations and measurement equations, then a complete nonlinear path angle estimation algorithm is obtained. The algorithm considers the constant drift of inertial sensors and the slow update frequency of GPS data in the design process. In the simulation verification section, this paper establishes sensor error models and aircraft carrier wake turbulence models. The algorithm constructs flight path angle signals in real-time and integrates them into the solution of the Integrated Direct Force control (IDLC) control law. This paper also provides the flight path angle construction results of two other traditional algorithms for comparison. The results illustrate that based on UKF, the flight path angle construction algorithm is not affected by wind disturbances and does not diverge over time, effectively integrating information from inertial sensors and GPS velocity signals. The algorithm can be used in the MAGIC CARPET landing control loop.
Despite the rapid development of edge and fog computing technologies, including significant improvements in the characteristics of communication channels and computing devices themselves, the problems associated with ...
详细信息
ISBN:
(数字)9798350349818
ISBN:
(纸本)9798350349825
Despite the rapid development of edge and fog computing technologies, including significant improvements in the characteristics of communication channels and computing devices themselves, the problems associated with the organization of the computing process in distributed systems remain relevant. This is due to the high dynamism of the environment and the large number of computing devices that operate in it. One of the mentioned problems in the organization of the computing process is the workload relocation problem. It includes the selection of placement options and requires significantly more time resources for the case of coupled tasks in comparison with uncoupled tasks. The need to solve coupled problems is associated with the development of such areas as loT, the Internet of Robotic Things, collaborative robotics, augmented reality, etc. One of the ways to reduce the total solution time of a coupled problem is to reduce the search space of candidate nodes, which can potentially be assigned to subtasks. In this paper, we propose to use a method for reducing the search space based on a combination of ontology analysis and cognitive modeling tools. The ontological model and a cognitive map of the computing infrastructure are developed. Computational experiments are conducted. Application of ontological modeling along with the use of cognitive analysis tools has shown its effectiveness in solving the workload relocation problems in highly dynamic environments. This is confirmed by the results of the conducted experiments. (Abstract)
With the rapid increase in the complexity of electronics, the cost of the functional testing process used to ensure product functionality continues to rise. Optimization modeling based on reliability analysis is an ef...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
With the rapid increase in the complexity of electronics, the cost of the functional testing process used to ensure product functionality continues to rise. Optimization modeling based on reliability analysis is an effective approach to reduce testing costs. However, the reliability calculations of existing methods often exhibit significant deviations, making it challenging to guarantee the effectiveness of the resulting testing strategies in practical applications. To address this issue, this article proposes an optimization modeling method that integrates statistical analysis and reliability analysis. The expression for the reliability of the system's key stage is formulated by analyzing the system's reliability. Statistical analysis is utilized to exploit the inherent reliability information in the enormous processdata to determine the probability of the root causes of system failures. The reliability of the key stage is quantitatively calculated based on the structure of the fault tree tailored for the system. On this basis, a binary optimization model is established to obtain a testing strategy with strong generalization ability and reduce the cost of functional testing. The effectiveness of the proposed method is verified through a simulation case study.
For the 10kV high-voltage special transformer users who adopt the high supply and high meter measurement method, the electric energy metering device is installed in the process of installation. Due to the careless ins...
详细信息
The assessment of the utility of an anonymized data set can be operationalized by the determination of the amount of information loss. To investigate the possible degradation of the relationship between variables afte...
详细信息
Isoconversional analysis (ICA) is one of the most important methods for establishing the kinetics of the complex reactions associated with curing thermosets. An often overlooked or hard to establish feature of these k...
详细信息
ISBN:
(纸本)9781934551417
Isoconversional analysis (ICA) is one of the most important methods for establishing the kinetics of the complex reactions associated with curing thermosets. An often overlooked or hard to establish feature of these kinetics is estimating the uncertainties in the kinetic parameters. In the case of ICA, activation energy is measured at fixed values of reaction conversion. For thermosets the data are typically based on differential scanning calorimetry (DSC). When replicate DSC data are obtained there is no agreement how to utilize the replicates to assess repeatability in the context of ICA. The authors propose that a combinatorial approach be used to assess the variability due to i) experimental variability and ii) linear and nonlinear computations that are used to calculate values of the activation energy. A MATLAB-based analysis was developed to analyze all possible combinations of replicates and using four different ICA methods to establish a conversion map of activation energies along with statistically valid values of standard deviations. The use of these techniques is demonstrated with a benzoxazone resin. This combinatorial technique provides new insights into uncertainty associated with modeling thermoset cure kinetics. This technique may also be used to estimate the uncertainty in isothermal and nonisothermal predictions based on the DSC data and measured activation energies. The MATLAB analysis will be made freely available to other users via the author’s website. It may be applied to any thermally-stimulated process. Copyright 2022. Used by the Society of the Advancement of Material and process Engineering with permission.
The paper considers the construction of a model for classifying the dynamics of change in the parameter of a technical object, which will allow you to predict the change in its state in the process of assessing the de...
详细信息
暂无评论