RESEARCH ARCHIVE

Publications.

Journal articles across AI, signals and intelligent systems. You can also find my work on Google Scholar and ResearchGate.

01 / Journal Articles 22 RECORDS

22 / 22
[01]2027
A figure from the paper showing coal and gangue impacting a hydraulic-support tail beam.PAPER FIGUREEXPAND ↗
Coal–gangue impact modelOriginal paper figure
Coal & gangue2027

Coal gangue recognition based on acoustic frequency-domain characteristics: Evaluating the influence of multiple working conditions on accuracy

Jinxin Kuang, Zipeng Zhang, Shanguo Yang, Mingjie Fang, Songyong Liu, Zhihong Cheng, Houguang Liu

Minerals Engineering, 250, 110878 (2027)

A study of how changing working conditions affect acoustic coal–gangue recognition. It examines frequency-domain characteristics of tail-beam impact signals and the feature drift associated with varying operational parameters.

ResearchGate: October 2026 · Journal issue: January 2027.

[03]2026
BKCad architecture linking EEG and speech embeddings, a diffusion encoder, Bayesian learning, cross-modal attention and confidence-aware fusion.PAPER FIGUREEXPAND ↗
BKCad · model architectureOriginal paper figure
Medical AI2026

Bayesian knowledge-guided confidence aware model based on multimodal pre-trained LLMs for depression detection

Zhihua Wang, Haotian Zhai, Tianrui Jia, Zihan Wang, Haojie Zhang, Kun Qian, Chen Xu, Zipeng Zhang, Wei Xue, Wen Qi, Bin Hu

Pattern Recognition, 180, 114388 (2026)

BKCad brings EEG and speech into a shared representation using pre-trained embeddings and a diffusion encoder. Bayesian uncertainty estimates and cross-modal attention guide confidence-aware fusion for depression detection.

[04]2026
MCL framework showing signal augmentation, spectrograms, dual attention and Mamba branches, contrastive learning and coal–gangue classification.PAPER FIGUREEXPAND ↗
MCL · model architectureOriginal paper figure
Coal & gangue2026

MCL: Mamba-Based Contrastive Learning method for coal gangue identification

Haifeng Qiu, Zipeng Zhang, Bo Zhang, Shanguo Yang, Ningguang Yao, Houguang Liu

International Journal of Coal Preparation and Utilization, 1-26 (2026)

MCL combines dual attention, dual Mamba modules and contrastive learning to distinguish coal from gangue in vibration signals. The framework learns class-specific similarities and differences before fusing representations for classification.

[05]2026
Original xLSTM framework linking an acoustic encoder, TSC-mLSTM blocks, magnitude and complex decoders, and a fault classifier.PAPER FIGUREEXPAND ↗
xLSTM · diagnosis frameworkOriginal paper figure
Fault diagnosis2026

A noise-robust xLSTM-based method for fault diagnosis in gas-insulated Switchgear using acoustic signals under strong noise interference

Hongkai Dong, Yuxuan Zhang, Bo Zhang, Zipeng Zhang, Yuying Shao, Guogang Yuan, Houguang Liu

Expert Systems with Applications, 304, 130827 (2026)

A shared xLSTM-based encoder learns to denoise acoustic signals and detect gas-insulated switchgear faults together. Time–frequency modeling and two spectrogram decoders address diagnosis under strong background noise.

[06]2025
Coal & gangue2025

An innovative hybrid model for ash content prediction in froth flotation based on contrastive learning

Maiqiang Zhou, Zipeng Zhang, Xinyu Cheng, Sijie Yang, Zhiping Wen, Changchun Zhou

International Journal of Coal Preparation and Utilization, 1-25 (2025)

AfricaNet predicts concentrate ash content from coal flotation images. Lighting-based augmentation, wavelet attention and a CRATE-based feature-selection strategy are combined with contrastive learning to model multi-frequency image information.

[07]2025
Original framework of acoustic acquisition, auditory feature extraction, attention-based feature fusion and coal–gangue recognition.PAPER FIGUREEXPAND ↗
Two-level auditory feature fusionOriginal paper figure
Coal & gangue2025

Coal gangue recognition in the strong background noise using two-level auditory feature fusion with attention mechanism

Zheng Yang, Shibo Wang, Shanguo Yang, Songyong Liu, Zipeng Zhang, Houguang Liu

Measurement, 253, 117628 (2025)

Two levels of auditory features are fused with attention to identify caving coal and gangue from sound. The method focuses on retaining useful acoustic information in strong mining background noise.

[08]2025
Fault diagnosis2025

A temporal-frequency contrastive learing method for acoustic-based mechanical fault detection in gas-insulated switch-gear

Yeduo Sheng, Bo Zhang, Zipeng Zhang, Yuying Shao, Guogang Yuan, Jianshu Liu, Houguang Liu

Nondestructive Testing and Evaluation, 41, 4541-4563 (2025)

Self-supervised contrastive pre-training learns consistent time–frequency representations of switchgear acoustics. A small labeled target set then adapts the model for fault diagnosis across operating conditions.

[09]2025
Original architecture of LRetUNet showing its encoder-decoder, high-frequency filter modules and retentive blocks.PAPER FIGUREEXPAND ↗
LRetUNet · model architectureOriginal paper figure
Audio & speech2025

LRetUNet: A U-Net-based retentive network for single-channel speech enhancement

Yuxuan Zhang, Zipeng Zhang, Weiwei Guo, Wei Chen, Zhaohai Liu, Houguang Liu

Computer Speech & Language, 93, 101798 (2025)

LRetUNet combines a U-Net with a retentive mechanism and an FFT-based high-frequency filter. It explores lightweight single-channel speech enhancement while preserving information important to speech clarity.

[10]2025
Coal & gangue2025

Graph and frequency leverage: a novel coal gangue identification method

Jiang Li, Zipeng Zhang, Shanguo Yang, Songyong Liu, Shibo Wang, Houguang Liu

Engineering Research Express, 7, 025543 (2025)

Frequency features from tail-beam impact and vibration signals are converted into graphs. A graph convolutional network uses relationships between these features to distinguish coal and gangue during top-coal caving.

[11]2025
Original coal–gangue identification framework with vibration acquisition, feature-enhancement and amplitude–frequency perception modules.PAPER FIGUREEXPAND ↗
Amplitude–frequency perception networkOriginal paper figure
Coal & gangue2025

Intelligent coal gangue identification: A novel amplitude frequency sensitive neural network

Zipeng Zhang, Zhencai Zhu, Bin Meng, Zheng Yang, Mingke Wu, Xinyu Cheng, Binhong Li, Houguang Liu

Expert Systems with Applications, 274, 126880 (2025)

Feature-enhancement blocks and amplitude–frequency perception modules capture impact patterns in coal–gangue vibration signals. A retention mechanism supports a compact model for rapid identification.

[12]2025
Original overview of MSGJO algorithm evaluation, robot path-planning simulations and robot experiments.PAPER FIGUREEXPAND ↗
MSGJO · study overviewOriginal paper figure
Optimization2025

MSGJO: a new multi-strategy AI algorithm for the mobile robot path planning

Baiyi Wang, Zipeng Zhang, Darius Andriukaitis, Xinhua Liu, Dezheng Hua, Zhixiong Li, Govind Vashishtha, Sumika Chauhan

The International Journal of Advanced Manufacturing Technology, 137, 5081-5109 (2025)

MSGJO extends golden jackal optimization with adaptive convergence, an enhanced search strategy and genetic mutation. The algorithm is applied to mobile-robot path planning with static and dynamic obstacles.

[13]2024
Original acoustic fire-detection framework showing signal acquisition, pre-training, classification and evaluation matrices.PAPER FIGUREEXPAND ↗
Acoustic fire and combustible detectionOriginal paper figure
Audio & speech2024

A novel intelligent indoor fire and combustibles detection method based on multi-channel transfer learning strategy with acoustic signals

Zhihua Wang, Zipeng Zhang, Zhuoyue Wang, Jiaming Lu, Weiguang An

Process Safety and Environmental Protection, 189, 1217-1225 (2024)

A two-stage acoustic framework first detects fire, then identifies burning materials. A Transformer-based detector guides a parallel Circuits-LSTM-Conformer model for combustible classification.

[14]2024
Original CFENet framework showing acoustic acquisition, feature encoders, contrastive representations and fault classification.PAPER FIGUREEXPAND ↗
CFENet · contrastive diagnosisOriginal paper figure
Fault diagnosis2024

CFENet: A contrastive frequency-sensitive learning method for gas-insulated switch-gear fault detection under varying operating conditions using acoustic signals

Zipeng Zhang, Houguang Liu, Yuying Shao, Jianhua Yang, Songyong Liu, Guogang Yuan

Engineering Applications of Artificial Intelligence, 135, 108835 (2024)

CFENet uses frequency-sensitive contrastive learning to diagnose switchgear faults from acoustic signals. Feature and embedding encoders learn representations that account for changing operating voltages.

[16]2024
Original speech-enhancement framework combining complex spectrograms, attention, time and frequency modules and a magnitude mask.PAPER FIGUREEXPAND ↗
Multi-stage speech enhancementOriginal paper figure
Audio & speech2024

Multi-stage strength estimation network with cross attention for single channel speech enhancement

Zipeng Zhang, Yuchen Ding, Wei Chen, Yutao Chen, Weiwei Guo, Houguang Liu

Signal, Image and Video Processing, 18, 6937-6948 (2024)

Cross-attention fuses complementary representations for single-channel speech enhancement. A multi-stage strength-estimation network combines FFT-based and sequential features to model both frequency and temporal structure.

[17]2024
Original CST-UNet architecture showing real and imaginary input branches, downsampling, masked bottleneck and upsampling skip connections.PAPER FIGUREEXPAND ↗
CST-UNet · model architectureOriginal paper figure
Audio & speech2024

CST-UNet: Cross Swin Transformer Enhanced U-Net with Masked Bottleneck for Single-Channel Speech Enhancement

Zipeng Zhang, Wei Chen, Weiwei Guo, Yiming Liu, Jianhua Yang, Houguang Liu

Circuits, Systems, and Signal Processing, 43, 5989-6010 (2024)

CST-UNet introduces Cross-Swin-Transformer blocks and a masked bottleneck into a U-Net. Concise hidden representations and skip connections balance speech-enhancement detail with computational cost.

[18]2024
Original gas-insulated switchgear fault-detection framework showing waveform and spectrogram branches, feature fusion and classification.PAPER FIGUREEXPAND ↗
Acoustic feature-fusion frameworkOriginal paper figure
Fault diagnosis2024

Gas-insulated switch-gear mechanical fault detection based on acoustic using feature fused neural network

Zipeng Zhang, Houguang Liu, Guogang Yuan, Jianhua Yang, Songyong Liu, Yuying Shao, Yang Zhang

Electric Power Systems Research, 230, 110226 (2024)

Waveform and spectrogram branches extract complementary acoustic features from gas-insulated switchgear. A fusion module combines voltage-related information and auto-encoded spectrogram features for mechanical fault detection.

[19]2024
Fault diagnosis2024

Gas-insulated switch-gear mechanical fault detection based on acoustic feature analysis using a multi-state pre-trained neural network

Zhihua Wang, Zipeng Zhang, Yuying Shao, Kun Qian, Houguang Liu, Bin Hu, Björn W Schuller

Measurement Science and Technology, 35, 076121 (2024)

A frequency regressor and an audio-spectrogram Transformer auto-encoder are pre-trained on switchgear acoustics. Their features are combined in a multi-stage training framework for mechanical fault detection under varying voltages.

[21]2024
Original physiological loudness figure showing outer, middle and inner ear mechanics and the associated loudness model.PAPER FIGUREEXPAND ↗
Physiological loudness modelOriginal paper figure
Audio & speech2024

A Sound Quality Evaluation Method for Vehicle Interior Noise Based on Auditory Loudness Model

Zhiheng He, Hui Guo, Houguang Liu, Yu Zhao, Zipeng Zhang, Shanguo Yang

Sound & Vibration, 58, 47-58 (2024)

A human-ear physiological model estimates auditory loudness from vehicle interior noise. A neural network combines this estimate with other psychoacoustic parameters to predict subjective sound-quality judgments.

[22]2024
Original diagram of reverse-learning competition between an original population and reverse-learning solutions.PAPER FIGUREEXPAND ↗
HWEAVOA · reverse-learning competitionOriginal paper figure
Optimization2024

A nonlinear African vulture optimization algorithm combining Henon chaotic mapping theory and reverse learning competition strategy

Baiyi Wang, Zipeng Zhang, Patrick Siarry, Xinhua Liu, Grzegorz Królczyk, Dezheng Hua, Frantisek Brumercik, Z. Li

Expert Systems with Applications, 236, 121413 (2024)

HWEAVOA combines Henon chaotic initialization, elite populations, adaptive inertia and reverse-learning competition. These strategies seek to balance exploration and exploitation in multimodal numerical optimization.

Bibliographic metadata is linked to DOI records. Years follow Crossref bibliographic records. ResearchGate dates can differ from journal issue dates; differences are noted where relevant.

Research figure

VIEW SOURCE ↗OPEN IMAGE ↗