Xukuan Xu

Mr. Xukuan Xu

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 August 2022 in Batteries & Supercaps
Verified
Journal Article
Open access
FZFranco Martín Zanotto
Franco Martín Zanotto
DDDiana Zapata Dominguez
Diana Zapata Dominguez
EAElixabete Ayerbe
Elixabete Ayerbe
IBIker Boyano
Iker Boyano
CBChristine Friederike Burmeister
Christine Friederike Burmeister
AFAlejandro A. Franco
Alejandro A. Franco
Lithium‐ion battery (LIB) manufacturing requires a pilot stage that optimizes its characteristics. However, this process is costly and time‐consuming. One way to overcome this is to use a set of computational models that act as a digital twin of the pilot line, exchanging information in real‐time that can be compared with measurements to correct parameters. Here we discuss the parameters involved in each step of LIB manufacturing, show available computational modeling approaches, and discuss details about practical implementation in terms of software. Then, we analyze these parameters regarding their criticality for modeling set‐up and validation, measurement accuracy, and rapidity. Presenting this in an understandable format allows identifying missing aspects, remaining challenges, and opportunities for the emergence of pilot lines integrating digital twins. Finally, we present the challenges of managing the data produced by these models. As a snapshot of the state‐of‐the‐art, this work is an initial step towards digitalizing battery manufacturing pilot lines, paving the way toward autonomous optimization.

17 January 2024 in Energy Technology
Verified
Journal Article
Open access
SSSimon Stier
Simon Stier
XXXukuan Xu
Xukuan Xu
LGLukas Gold
Lukas Gold
MMMichael Möckel
Michael Möckel
One of the key challenges of data management for smart manufacturing is dealing with data originating from both physical processes and virtual digital technologies. As image and sensor‐based production monitoring deliver a wealth of data along the process chain, artificial intelligence (AI) enables enhanced data analysis and new insight regarding relevance of observed process deviations. With constantly increased availability of data from manifold and specific sources, the complexity and heterogeneity of information structures are also growing rapidly. This is especially true for highly variable research, scale‐up, and pilot production, which poses new demands on data acquisition, data management, and data preprocessing. Herein, a unified framework for integrating an ontology and graph‐based data space with data acquisition and data analytics to improve data consistency, documentation of workflows, as well as the reproducibility of observations and results is presented. The framework consists of several open‐source web services that form an ontology‐based data space where physical and virtual process chains are represented by a semantic data fabric built from findable, accessible, interoperable, and reusable resource descriptions framework self‐descriptions. The feasibility of the proposed framework is demonstrated for a laboratory‐scale Li‐ion battery cell production facility with AI applied to two data analytics use cases.

31 December 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
XXXukuan Xu
Xukuan Xu
DLDonghui Li
Donghui Li
JBJinghou Bi
Jinghou Bi
MMMichael Moeckel
Michael Moeckel
Design of experiments (DOE) is an established method to allocate resources for efficient parameter space exploration. Model based active learning (AL) data sampling strategies have shown potential for further optimization. This paper introduces a workflow for conducting DOE comparative studies using automated machine learning. Based on a practical definition of model complexity in the context of machine learning, the interplay of systematic data generation and model performance is examined considering various sources of uncertainty: this includes uncertainties caused by stochastic sampling strategies, imprecise data, suboptimal modeling, and model evaluation. Results obtained from electrical circuit models with varying complexity show that not all AL sampling strategies outperform conventional DOE strategies, depending on the available data volume, the complexity of the dataset, and data uncertainties. Trade-offs in resource allocation strategies, in particular between identical replication of data points for statistical noise reduction and broad sampling for maximum parameter space exploration, and their impact on subsequent machine learning analysis are systematically investigated. Results indicate that replication oriented strategies should not be dismissed but may prove advantageous for cases with non-negligible noise impact and intermediate resource availability. The provided workflow can be used to simulate practical experimental conditions for DOE testing and DOE selection.

25 July 2025 in Batteries
Verified
Journal Article
Open access
PDF file
XXXukuan Xu
Xukuan Xu
SSSimon Stier
Simon Stier
AGAndreas Gronbach
Andreas Gronbach
MMMichael Moeckel
Michael Moeckel
Pilot production is a critical transitional phase in the process of new product development or manufacturing, aiming at ensuring that products are thoroughly validated and optimized before entering full-scale production. During this stage, a key challenge is how to leverage limited resources to build data infrastructure and conduct data analysis to establish and verify quality control. This paper presents the implementation of a cyber–physical system (CPS) for a lithium battery pilot assembly line. A machine learning-based predictive model was employed to establish quality control mechanisms. Process knowledge-guided data analysis was utilized to build a quality prediction model based on the collected battery data. The model-centric concept of ‘virtual quality’ enables early quality judgment during production, which allows for flexible quality control and the determination of optimal process parameters, thereby reducing production costs and minimizing energy consumption during manufacturing.

10 June 2025 in IEEE Access
Verified
Journal Article
Open access
XXXukuan Xu
Xukuan Xu
JBJinghou Bi
Jinghou Bi
MMMichael Moeckel
Michael Moeckel
HWHajo Wiemer
Hajo Wiemer
SISteffen Ihlenfeldt
Steffen Ihlenfeldt
Applying machine learning (ML) techniques in the context of limited data remains a challenge of practical importance. Questions on both the sufficiency of a given dataset for ML data analysis and data acquisition planning arise. Both aspects are quantitatively addressed in this work. The first one is treated as part of dataset diagnostics, which includes the analysis of learning curves, the quantification of confidence intervals (CI) during model evaluation and further dataset metrics. Regarding data generation, data sufficiency considerations must cover both model training and testing. Twenty case datasets are diagnosed, and serve as a reference for establishing an empirical rule for data sufficiency estimation. The results indicate that the relevant aspects are the ratio of data volume to the number of input features, the complexity of the involved data correlations and the applied definition of the small data regime. The presented framework allows for an improved pre-assessment of data sufficiency for a typical given dataset and facilitates a reliable implementation of ML in data volume-limited contexts.

22 March 2024
Verified
Conference Paper
Open access
XXXukuan Xu
Xukuan Xu
MMMichael J. Moeckel
Michael J. Moeckel
Lithium-ion battery cell production is conducted through a multistep production process which suffers from a notable scrap rate. Machine learning (ML) based process monitoring provides solutions to mitigate the impact of substantial scrap rates by repeated multifactorial quality predictions (virtual quality gates) along the process line. This enables an early rejection of battery cells which are unlikely to reach required specifications, avoids further waste of resources at later process steps and simplifies recycling of rejected cells. A hierarchical architecture is used to apply ML algorithms first for process-adapted feature extraction which is guided by a priori knowledge on typical production anomalies. In a second step, these features are correlated with end-of-line quality control data using explainable ML methods. The resulting predictions may lead to pass or fail of a battery cell, or -in the context of flexible production- may also trigger adjustments of later process steps to compensate for detected deficiencies. An example ML based quality control concept is illustrated for a pilot battery cell production line.