Zijing Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zijing Dong has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
Runjun Sun
4 shared publications- Chao Zhi
School of Textile Science and Engineering, Key Laboratory of Functional Textile Material and Product of the Ministry of Education Xi'an Polytechnic University Xi'an Shaanxi China
3 shared publications Chao Zhi
2 shared publicationsChengwei Ying
Zhejiang Shaoxing Yongli Printing and Dyeing Co., Ltd., China
2 shared publicationsHuaxiang Zhao
Zhejiang Shaoxing Yongli Printing and Dyeing Co., Ltd., China
2 shared publicationsLijiang Qian
Zhejiang Shaoxing Yongli Printing and Dyeing Co., Ltd., China
2 shared publications
Latest Publications
- Open Access
- 12 May 2026
- Published by Elsevier in SSRN Electronic Journal
Machine Learning-Enabled Performance Prediction and Design for Flexible Strain Composite Sensors
The sensing performance of flexible strain sensors based on carbon-filled polymer composites is largely governed by processing parameters, such as filler content. Therefore, the exploration of optimal processing parameters is of great significance to the enhancement of material properties. However, the complex coupling among multiple variables renders conventional trial-and-error optimization inefficient for composite development. Here, a data-driven prediction–optimization strategy integrating design of experiments (DoE) with machine learning (ML) is proposed for composite design to optimize the performance of TPU/CNTs-CF/TPU composite strain sensors. Informative experimental datasets are constructed within a high-dimensional parameter space, and a multilayer perceptron (MLP) model is trained to map processing parameters to the sensing performance of the composite. SHAP-based interpretability analysis is further employed to quantitatively elucidate the contribution mechanisms of key composite factors, including carbon loading and carbon nanotube ratio, thereby guiding targeted experiments in high-sensitivity regions and enabling iterative optimization through dataset expansion. As a result, the sensor sensitivity is markedly improved, with the gauge factor (GF) increasing from 15 to 105 while maintaining high predictive accuracy (R² = 0.96). The trained model is subsequently used to screen 600 randomly sampled parameter combinations, from which two optimal composite formulations are identified and experimentally validated, yielding prediction errors as low as 2.3% and 3.1% at 80% strain. Moreover, the optimized composite sensors exhibit excellent stability under cyclic loading and human-motion monitoring. This work offers an efficient and interpretable paradigm to regulate composition-processing-performance relationships, reduce experimental costs, and guide the development of high-performance flexible composite sensing systems.
- 12 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMachine Learning-Enabled Performance Prediction and Design for Flexible Strain Composite Sensors
The sensing performance of flexible strain sensors based on carbon-filled polymer composites is largely governed by processing parameters, such as filler content. Therefore, the exploration of optimal processing parameters is of great significance to the enhancement of material properties. However, the complex coupling among multiple variables renders conventional trial-and-error optimization inefficient for composite development. Here, a data-driven prediction–optimization strategy integrating design of experiments (DoE) with machine learning (ML) is proposed for composite design to optimize the performance of TPU/CNTs-CF/TPU composite strain sensors. Informative experimental datasets are constructed within a high-dimensional parameter space, and a multilayer perceptron (MLP) model is trained to map processing parameters to the sensing performance of the composite. SHAP-based interpretability analysis is further employed to quantitatively elucidate the contribution mechanisms of key composite factors, including carbon loading and carbon nanotube ratio, thereby guiding targeted experiments in high-sensitivity regions and enabling iterative optimization through dataset expansion. As a result, the sensor sensitivity is markedly improved, with the gauge factor (GF) increasing from 15 to 105 while maintaining high predictive accuracy (R² = 0.96). The trained model is subsequently used to screen 600 randomly sampled parameter combinations, from which two optimal composite formulations are identified and experimentally validated, yielding prediction errors as low as 2.3% and 3.1% at 80% strain. Moreover, the optimized composite sensors exhibit excellent stability under cyclic loading and human-motion monitoring. This work offers an efficient and interpretable paradigm to regulate composition-processing-performance relationships, reduce experimental costs, and guide the development of high-performance flexible composite sensing systems.
- 19 February 2025
- Published by SAGE Publications in Textile Research Journal
- Vol. 95 (17-18) , 2202-2217
Flexible fabrics based on BaFe 12 O 19 /PPy/PVDF composite filler for enhancing microwave absorption bandwidth and strength
Magnetic–dielectric composites are an effective strategy for developing efficient microwave absorbers, owing to the synergistic effect of different attenuation mechanisms. In this work, barium ferrite (BaFe 12 O 19 ) powder is first prepared using a microwave-assisted hydrothermal method, and then BaFe 12 O 19 /polypyrrole (PPy) composite powders with different contents of PPy were prepared using an in situ polymerization method. Polyvinylidene difluoride (PVDF) is selected as the film-forming agent, and BaFe 12 O 19 /PPy/PVDF film is prepared using a casting molding process; then polyvinyl alcohol is used as a binder to prepare BaFe 12 O 19 /PPy/PVDF film or fabric with a strong microwave absorption performance. The minimum reflection loss (RL min ) is as high as −36.52 dB at 16.31 GHz for a thickness of 2.5 mm. The adequate absorption bandwidth (RL ≤ −10 dB) is as wide as 7.98 GHz for the same thickness, covering almost all X and K u bands. The absorption mechanism is revealed in detail through an in-depth analysis of the electromagnetic parameters. The synergistic effect of the solid magnetic loss of BaFe 12 O 19 magnetic metal, the intense dielectric loss of PPy, and the superior impedance matching result in excellent microwave absorption capability. The results show that the BaFe 12 O 19 /PPy/PVDF film or fabric is a promising and efficient microwave-absorbing material, being thin and strongly absorbing across a wide bandwidth.
- 19 February 2025
- Published by SAGE Publications in Textile Research Journal
- Vol. 95 (17-18) , 2202-2217
Flexible fabrics based on BaFe 12 O 19 /PPy/PVDF composite filler for enhancing microwave absorption bandwidth and strength
Magnetic–dielectric composites are an effective strategy for developing efficient microwave absorbers, owing to the synergistic effect of different attenuation mechanisms. In this work, barium ferrite (BaFe 12 O 19 ) powder is first prepared using a microwave-assisted hydrothermal method, and then BaFe 12 O 19 /polypyrrole (PPy) composite powders with different contents of PPy were prepared using an in situ polymerization method. Polyvinylidene difluoride (PVDF) is selected as the film-forming agent, and BaFe 12 O 19 /PPy/PVDF film is prepared using a casting molding process; then polyvinyl alcohol is used as a binder to prepare BaFe 12 O 19 /PPy/PVDF film or fabric with a strong microwave absorption performance. The minimum reflection loss (RL min ) is as high as −36.52 dB at 16.31 GHz for a thickness of 2.5 mm. The adequate absorption bandwidth (RL ≤ −10 dB) is as wide as 7.98 GHz for the same thickness, covering almost all X and K u bands. The absorption mechanism is revealed in detail through an in-depth analysis of the electromagnetic parameters. The synergistic effect of the solid magnetic loss of BaFe 12 O 19 magnetic metal, the intense dielectric loss of PPy, and the superior impedance matching result in excellent microwave absorption capability. The results show that the BaFe 12 O 19 /PPy/PVDF film or fabric is a promising and efficient microwave-absorbing material, being thin and strongly absorbing across a wide bandwidth.
- 15 March 2024
- Published by SAGE Publications in Textile Research Journal
- Vol. 94 (15-16) , 1771-1785
FabricGAN: an enhanced generative adversarial network for data augmentation and improved fabric defect detection
When deep learning is applied to intelligent textile defect detection, the insufficient training data may result in low accuracy and poor adaptability of varying defect types of the trained defect model. To address the above problem, an enhanced generative adversarial network for data augmentation and improved fabric defect detection was proposed. Firstly, the dataset is preprocessed to generate defect localization maps, which are combined with non-defective fabric images and input into the network for training, which helps to better extract defect features. In addition, by utilizing a Double U-Net network, the fusion of defects and textures is enhanced. Next, random noise and the multi-head attention mechanism are introduced to improve the model’s generalization ability and enhance the realism and diversity of the generated images. Finally, we merge the newly generated defect image data with the original defect data to realize the data enhancement. Comparison experiments were performed using the YOLOv3 object detection model on the training data before and after data enhancement. The experimental results show a significant accuracy improvement for five defect types – float, line, knot, hole, and stain – increasing from 41%, 44%, 38%, 42%, and 41% to 78%, 76%, 72%, 67%, and 64%, respectively.
- 15 March 2024
- Published by SAGE Publications in Textile Research Journal
- Vol. 94 (15-16) , 1771-1785
FabricGAN: an enhanced generative adversarial network for data augmentation and improved fabric defect detection
When deep learning is applied to intelligent textile defect detection, the insufficient training data may result in low accuracy and poor adaptability of varying defect types of the trained defect model. To address the above problem, an enhanced generative adversarial network for data augmentation and improved fabric defect detection was proposed. Firstly, the dataset is preprocessed to generate defect localization maps, which are combined with non-defective fabric images and input into the network for training, which helps to better extract defect features. In addition, by utilizing a Double U-Net network, the fusion of defects and textures is enhanced. Next, random noise and the multi-head attention mechanism are introduced to improve the model’s generalization ability and enhance the realism and diversity of the generated images. Finally, we merge the newly generated defect image data with the original defect data to realize the data enhancement. Comparison experiments were performed using the YOLOv3 object detection model on the training data before and after data enhancement. The experimental results show a significant accuracy improvement for five defect types – float, line, knot, hole, and stain – increasing from 41%, 44%, 38%, 42%, and 41% to 78%, 76%, 72%, 67%, and 64%, respectively.
- 22 November 2023
- Published by SAGE Publications in Textile Research Journal
- Vol. 94 (3-4) , 494-507
BaFe12O19/graphene/polyaniline coatings for flexible fabrics with enhanced microwave absorption
In this study, barium ferrite (BaFe12O19) was used as the basic microwave-absorbing material and compounded with graphene and PANI. Then, BaFe12O19, BaFe12O19/graphene, and BaFe12O19/graphene/PANI were mixed with waterborne polyurethane and coated on nylon fabrics by the cast coating method to prepare flexible microwave absorbing materials. The microwave absorbing performance of BaFe12O19/graphene/PANI coated fabric is significantly improved in comparison with BaFe12O19 and BaFe12O19/graphene coated fabric, which mainly comes from the synergistic effects of magnetic loss, dielectric loss, and conductivity loss. The BaFe12O19/graphene/PANI coated fabric has a minimum reflection loss value of –37.36 dB (at 13.76 GHz) and an effective absorption bandwidth of 5.40 GHz (12.44–17.84 GHz) when the thickness is 1.2 mm. Consequently, the facile preparation route and excellent performance make the BaFe12O19/graphene/PANI composite a promising candidate for efficient microwave absorbence.
- 22 November 2023
- Published by SAGE Publications in Textile Research Journal
- Vol. 94 (3-4) , 494-507
BaFe12O19/graphene/polyaniline coatings for flexible fabrics with enhanced microwave absorption
In this study, barium ferrite (BaFe12O19) was used as the basic microwave-absorbing material and compounded with graphene and PANI. Then, BaFe12O19, BaFe12O19/graphene, and BaFe12O19/graphene/PANI were mixed with waterborne polyurethane and coated on nylon fabrics by the cast coating method to prepare flexible microwave absorbing materials. The microwave absorbing performance of BaFe12O19/graphene/PANI coated fabric is significantly improved in comparison with BaFe12O19 and BaFe12O19/graphene coated fabric, which mainly comes from the synergistic effects of magnetic loss, dielectric loss, and conductivity loss. The BaFe12O19/graphene/PANI coated fabric has a minimum reflection loss value of –37.36 dB (at 13.76 GHz) and an effective absorption bandwidth of 5.40 GHz (12.44–17.84 GHz) when the thickness is 1.2 mm. Consequently, the facile preparation route and excellent performance make the BaFe12O19/graphene/PANI composite a promising candidate for efficient microwave absorbence.
- Open Access
- 1 September 2023
- Published by SAGE Publications in Journal of Industrial Textiles
- Vol. 53
Sensing performance of textile strain sensors with different weave structures
Many conductive fabrics have been widely used as fabric strain sensors in recent years due to their excellent flexibility. In this study, high-tenacity polyester warp yarn and silver-coated nylon weft yarn were used to produce six types of conductive fabrics with different structures. The surface morphology of silver-coated nylon yarn was observed under a microscope, and the yarn was placed in an airtight container to test the effect of different humidity on the resistance of the yarn. DM6500 digital multimeter was used to test the resistance sensitivity, fatigue resistance, repeatability, and antistatic properties of conductive fabric samples. The results showed that the change in yarn surface material, external humidity, and strain affected the change in yarn resistance. Different weave structures affected the sensing performance of the fabric. The tighter the structure, the better the sensitivity and antistatic properties, the looser the structure, the better the fatigue resistance and repeatability. Two types of fabric and nylon gloves with different structural tightness are used to make intelligent data gloves. The results showed that both fabrics had good application prospects in limb movement detection.
- 1 September 2023
- Published by SAGE Publications in Journal of Industrial Textiles
- Vol. 53
Open AccessSensing performance of textile strain sensors with different weave structures
Many conductive fabrics have been widely used as fabric strain sensors in recent years due to their excellent flexibility. In this study, high-tenacity polyester warp yarn and silver-coated nylon weft yarn were used to produce six types of conductive fabrics with different structures. The surface morphology of silver-coated nylon yarn was observed under a microscope, and the yarn was placed in an airtight container to test the effect of different humidity on the resistance of the yarn. DM6500 digital multimeter was used to test the resistance sensitivity, fatigue resistance, repeatability, and antistatic properties of conductive fabric samples. The results showed that the change in yarn surface material, external humidity, and strain affected the change in yarn resistance. Different weave structures affected the sensing performance of the fabric. The tighter the structure, the better the sensitivity and antistatic properties, the looser the structure, the better the fatigue resistance and repeatability. Two types of fabric and nylon gloves with different structural tightness are used to make intelligent data gloves. The results showed that both fabrics had good application prospects in limb movement detection.
- 3 May 2023
- Published by SAGE Publications in Textile Research Journal
- Vol. 93 (17-18) , 4179-4190
Design and characterization of multi-functional ternary composites with a hierarchically porous and filled-microperforated plate structure
To effectively overcome the shortcomings of common polyurethane (PU) insulation materials in terms of flame retardancy, mechanical properties, and sound absorption, a new multi-functional insulation material needs to be developed. Here, simple materials such as PU and silica aerogel (SA) combined with a special three-dimensional spacer fabric were used to design an innovative SA/PU/spacer fabric (SPS) ternary composite. It integrates a “hierarchically porous” and “filled-microperforated plate” structure. The superior structure design endows the new type of composite with a remarkable performance while maintaining low density (0.198 g/cm3). Specifically, the SPS composite was difficult to ignite by alcohol lamps compared with PU and SA/PU, and its thermal conductivity and compression modulus can reach 0.0392 W/(m·k) and 1.5 MPa, respectively. Moreover, the average absorption coefficient of the SPS composite (7.5 mm thickness) is 0.62, and its noise reduction coefficient per unit thickness (0.37) exceeds most reported sound absorption materials. From these results, the SPS composite provides a convenient and low-cost method to improve the overall performance of traditional thermal insulation material, which is of great significance in the fields of construction and transportation.
- 3 May 2023
- Published by SAGE Publications in Textile Research Journal
- Vol. 93 (17-18) , 4179-4190
Design and characterization of multi-functional ternary composites with a hierarchically porous and filled-microperforated plate structure
To effectively overcome the shortcomings of common polyurethane (PU) insulation materials in terms of flame retardancy, mechanical properties, and sound absorption, a new multi-functional insulation material needs to be developed. Here, simple materials such as PU and silica aerogel (SA) combined with a special three-dimensional spacer fabric were used to design an innovative SA/PU/spacer fabric (SPS) ternary composite. It integrates a “hierarchically porous” and “filled-microperforated plate” structure. The superior structure design endows the new type of composite with a remarkable performance while maintaining low density (0.198 g/cm3). Specifically, the SPS composite was difficult to ignite by alcohol lamps compared with PU and SA/PU, and its thermal conductivity and compression modulus can reach 0.0392 W/(m·k) and 1.5 MPa, respectively. Moreover, the average absorption coefficient of the SPS composite (7.5 mm thickness) is 0.62, and its noise reduction coefficient per unit thickness (0.37) exceeds most reported sound absorption materials. From these results, the SPS composite provides a convenient and low-cost method to improve the overall performance of traditional thermal insulation material, which is of great significance in the fields of construction and transportation.
- Open Access
- 2 December 2022
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 7 (49) , 45381-45385
Large Magnetodielectric Effect of BaTiO3–BaFe12O19 Composites in a Low Magnetic Field
A microwave sintering procedure has been developed to achieve high quality multiferroic composites of (1 - x)BaTiO3-xBaFe12O19 (x = 0.05, 0.10, 0.15, and 0.20). X-ray diffraction, scanning electron microscopy, and impedance spectra indicate that BaFe12O19 particles are isolated homogeneously by BaTiO3 particles. In a 1.8 T magnetic field, a large room temperature magnetodielectric effect over 4.3% is observed in the 0.8BaTiO3-0.2BaFe12O19 composite. The total mechanical energy dissipation (Q -1) for the BaTiO3-BaFe12O19 composites was composed of the mechanical damping of BaFe12O19, the mechanical damping of BaTiO3, and the loss at the interface. The mechanical damping of BaFe12O19 plays the dominant role in the variation of Q -1.
- 2 December 2022
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 7 (49) , 45381-45385
Open AccessLarge Magnetodielectric Effect of BaTiO3–BaFe12O19 Composites in a Low Magnetic Field
A microwave sintering procedure has been developed to achieve high quality multiferroic composites of (1 - x)BaTiO3-xBaFe12O19 (x = 0.05, 0.10, 0.15, and 0.20). X-ray diffraction, scanning electron microscopy, and impedance spectra indicate that BaFe12O19 particles are isolated homogeneously by BaTiO3 particles. In a 1.8 T magnetic field, a large room temperature magnetodielectric effect over 4.3% is observed in the 0.8BaTiO3-0.2BaFe12O19 composite. The total mechanical energy dissipation (Q -1) for the BaTiO3-BaFe12O19 composites was composed of the mechanical damping of BaFe12O19, the mechanical damping of BaTiO3, and the loss at the interface. The mechanical damping of BaFe12O19 plays the dominant role in the variation of Q -1.
- 1 August 2014
- Published by Elsevier in Materials Letters
- Vol. 128, 263-266
Morphological evolution of tridymite crystal in SrO–BaO–Nb2O5–CaO–SiO2–B2O3 ferroelectric glass-ceramic
- 1 August 2014
- Published by Elsevier in Materials Letters
- Vol. 128, 263-266
Morphological evolution of tridymite crystal in SrO–BaO–Nb2O5–CaO–SiO2–B2O3 ferroelectric glass-ceramic