Asim Shahzad

Dr. Asim Shahzad

Department of Control Science and Engineering, Shandong University, Jinan, Shandong, China
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
9 June 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Asim ShahzadAsim Shahzad
Asim Shahzad
FLFuzheng Liu
Fuzheng Liu
Mingshun JiangMingshun Jiang
Mingshun Jiang
FZFaye Zhang
Faye Zhang
ZGZhaohui Gan
Zhaohui Gan
Deep learning models for bearing fault diagnosis often struggle to preserve discriminative features under variable operating conditions and unable to effectively capture multi-scale signal patterns. To overcome these challenges, Entropy-Augmented Kronecker Convolutional Feature Pyramid (EKCFP) was proposed, a novel framework with three core contributions. First, we developed a permutation entropy fusion, a method that directly combines signal complexity analysis with raw vibration inputs via dedicated channels, enabling simultaneous learning of temporal dynamics and information-theoretic properties. Second, a Frequency-Spatial Convolution layer (1DFSC) jointly used dilated convolution and channel attention to extract localized spatial relationships and feature fusion. Third, CNN-based Kronecker Convolution Feature Pyramid (KCFP) integrated batch normalization, adaptive pooling, and stochastic dropout within a compact architecture, achieving greater parameter efficiency. Rectified Linear Unit (ReLU) was used to improve training in order to increase network representation and efficiency. Tests on the HFZZ dataset (Shandong University Intelligent Sensors Center) and Paderborn University bearing data across several fault types show EKCFP achieves 99.94% mean accuracy—exceeding existing multi-scale feature extraction techniques. Ablation experiments highlighted the entropy channel and attention mechanism significance, boosting diagnostic consistency under variable operating conditions. These findings established a novel methodological framework for integrating entropy-driven feature learning with spatial-frequency analysis, advancing the development of explainable deep architectures for mechanical fault diagnostics.

18 December 2025 in Measurement Science and Technology
Verified
Journal Article
Closed access
Asim ShahzadAsim Shahzad
Asim Shahzad
ALAnqi Li
Anqi Li
FLFuzheng Liu
Fuzheng Liu
Mingshun JiangMingshun Jiang
Mingshun Jiang
FZFaye Zhang
Faye Zhang
YJYingzhe Jia
Yingzhe Jia
Sensor based time-series vibrational signals are difficult to classify under variable operating conditions, particularly during frequency overlapping RPM shifts. The current preprocessing techniques struggle to detect frequency overlapped faults, as their shifting frequency patterns fail to align with the fixed scales. The proposed study designs a frequency-aware transformer fusion, an adaptive hybrid architecture that replace absolute frequency analysis with adaptive pattern recognition on a unified transient energy map. The utilization of continuous wavelet transform and Volterra series form a transient energy map and provides a short-term memory, which replaces the absolute frequency analysis to the pattern recognition. After that, the encoded energy map is processed via a dual block, comprising two concurrent branches: a Kronecker convolutional feature pyramid for repetitive transients and a channel attention MLP block that highlights semantic structures within the transient energy maps. The outputs of these parallel branches are fused through a Swin Transformer module, which uses frequency-aware shifting windows to confidently diagnose frequency overlapped faults. This modular fusion strategy enables the model to learn robust representations across both local and global temporal scales. Experimental validation on multi-class sensor position datasets obtained from Shandong University, Case Western Reserve University and PU demonstrates superiority over state-of-the-art methods. Ablation experiments demonstrate the significance of the dual-branch and dual-attention mechanisms, which enhance diagnostic consistency under frequency overlapped conditions.

6 November 2025 in Journal of the Franklin Institute
Verified
Journal Article
Closed access
Asim ShahzadAsim Shahzad
Asim Shahzad
FLFuzheng Liu
Fuzheng Liu
Mingshun JiangMingshun Jiang
Mingshun Jiang
FZFaye Zhang
Faye Zhang
LRLiying Ren
Liying Ren

29 September 2026 in Electronics
Verified
Journal Article
Open access
PDF file
ZLZhizhen Liu
Zhizhen Liu
AAAsif Ali
Asif Ali
Asim ShahzadAsim Shahzad
Asim Shahzad
Battery swapping stations (BSSs) can help shorten the refueling time for electric vehicles (EVs), but their widespread deployment will need decisions on station placement, battery availability, the number of chargers, photovoltaic (PV) capacity, grid import, accessibility, and emissions. This study proposes a decomposed mixed-integer linear programming and geographic information system (MILP–GIS) framework to optimize the planning of BSSs using renewable energy in a Shenzhen GIS–traffic planning case. Each year, the MILP decides on the location and size of the BSS, the PV capacity, battery packs, charging power, aggregate state of charge, reserve inventory, and grid import; a representative post-siting hourly feasibility layer then verifies the PV availability, charging power, aggregate state of charge, reserve inventory, and grid import. The case has 16 demand zones, 24 screened candidate sites and 24 hourly demand slices derived from Shenzhen GIS–traffic inputs that were aggregated into publicly releasable demand-zone and candidate-site tables. A PV investment cost is annualized once, and charging/discharging losses are taken as an electricity charging-input on the grid electricity cost side. The results demonstrate that the six-station R40 portfolio can cut the annualized cost from 49.07 to 46.78 million CNY/year compared to the case of the grid only, and grid-related CO2 emissions decrease from 22.05 to 9.92 kt/year as the renewable-energy target increases from 0% to 55%, under the base-case techno-economic assumptions. The levelized service cost (LSC) is dominated by the cost of the grid, the cost of the battery, PV capital expenditure (CAPEX), and the demand level, as revealed by the cost audit, station-level, ablation, and sensitivity results. When compared to EV infrastructure planning using benchmarking with GIS-score, p-median and energy-only baselines, the proposed framework provides a better cost–coverage–carbon trade-off in dense urban EV infrastructure planning.