Temperature data-driven fire source estimation algorithm of the underground pipe gallery

This paper presents the design and hardware-in-the-loop (HIL) experimental validation of a data-driven estimation method for the state of charge (SOC) in the lithium-ion batteries used in hybrid electric vehicles (HEVs). The considered system features a 1.25 kWh 48 V lithium-ion battery that is numerically modeled via an RC equivalent circuit model that can also consider the environmental temperature influence. The proposed estimation technique relies on nonlinear autoregressive with exogenous input (NARX) artificial neural networks (ANNs) that are properly trained with multiple datasets. Those datasets include modeled current and voltage data, both for charge-sustaining and charge-depleting working conditions. The investigated method is then experimentally validated using a Raspberry Pi 4B card-sized board, on which the estimation algorithm is actually deployed, and real-time hardware, on which the battery model is developed, namely a Speedgoat baseline platform. These hardware platforms are used in a hardware-in-the-loop architecture via the UPD communication protocol, allowing the system to be validated in a proper testing environment. The resulting estimation algorithm can estimate the battery SOC in real-time, with 2% accuracy during real-time hardware testing.

Download Full-text

Epidemic Source Detection over Dynamic Networks

Electronics ◽

10.3390/electronics9061018 ◽

2020 ◽

Vol 9 (6) ◽

pp. 1018

Author(s):

Jaeyoung Choi

Keyword(s):

Dynamic Model ◽

Dynamic Networks ◽

Dynamic Network ◽

Estimation Algorithm ◽

Estimation Methods ◽

Source Detection ◽

Source Estimation ◽

Contact Information ◽

Node Connectivity ◽

Over Time

Epidemic source detection is one of the most crucial problems in statistical inference. For example, currently, the debate continues to reveal when and where the first spread of COVID-19 occured. For this problem, most of the works have assumed a static network topology, that is, the connections between nodes do not change over time. This is impractical because many nodes have some mobility in the network, or the connections can be changed. In this paper, we focus on the dynamic network, in the sense that the node connectivity varies over time. We first introduce a simple dynamic model, named k-flip dynamic such that k > 0 connections in the network may be changed with some probability at each time. Next, we design a proper estimation algorithm using some investigation for the contact information between infected nodes, named dynamic network source estimation (DNSE)(k) for the dynamic model. We perform various simulations for the algorithm compared to several existing source estimation methods. Our results show that the proposed algorithm outperforms and is efficient for finding the epidemic source compared to other methods. Further, we see that the detection probability for our proposed algorithm can be above 45% when we use budget to investigate the contact information from the infected nodes under some practical setting of k.

Download Full-text

Optimal Missing Value Estimation Algorithm for Groundwater Levels

Proceedings ◽

10.3390/proceedings2110698 ◽

2018 ◽

Vol 2 (11) ◽

pp. 698 ◽

Cited By ~ 1

Author(s):

Klemen Kenda ◽

Filip Koprivec ◽

Dunja Mladenić

Keyword(s):

Missing Data ◽

Missing Values ◽

Estimation Algorithm ◽

Data Driven ◽

Data Imputation ◽

Missing Data Imputation ◽

Groundwater Levels ◽

Data Driven Approach ◽

Value Estimation ◽

Missing Value Estimation

In this study an algorithm for missing data imputation is presented. The algorithm uses measurements from neighboring sensors to estimate the missing values. Data-driven approach is used and methodology chooses the optimal available combination of modeling algorithm and available measurements to produce an estimate from the model with lowest error. The methodology was tested on Ljubljana polje aquifer data and has produced close to perfect results.

Download Full-text

DATA DRIVEN PERFORMANCE EVALUATION IN SHIPBUILDING

Brodogradnja ◽

10.21278/brod71403 ◽

2020 ◽

Vol 71 (4) ◽

pp. 39-51

Author(s):

Umran Bilen ◽

◽

Sebnem Helvacioglu

Keyword(s):

Cost Estimation ◽

Structural Design ◽

Data Science ◽

Rapid Development ◽

Estimation Algorithm ◽

Data Driven ◽

Medium Size ◽

Analysis Techniques ◽

Use Of Data ◽

Evaluation Of Performance

Rapid development in data science keeps paving the way for use of data for many purposes in shipbuilding, both for product development and production, such as Industry 4.0 have been developing many industries. Similar to other industries the evaluation of performance in shipbuilding is the key to success which is closely connected to productivity and lowered costs. Data mining and analysis techniques are used to create effective algorithms to evaluate the performance, also by means of cost estimation based on parametric methods. However, it is usually not very clear how data are collected, organised and prepared for analysing and deriving valuable knowledge as well as algorithms. In most of the cases, having this data requires either continuous investment in expensive software or expensive external expertise which are generally not available for small and medium size shipyards. In this study, considering the needs of the small and medium sized shipyards, a step-by-step methodology is proposed which could be easily applied with widely available low budget software. The application is demonstrated with a case to evaluate the performance of early phase structural design with a data driven cost estimation algorithm.

Download Full-text