Qi Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qi Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Bentian Hao
Field Engineering College, Army Engineering University, Nanjing, China
1 shared publication - Chaochang Liu
Field Engineering College, PLA Army Engineering University, Nanjing 210001, China
1 shared publication - Fanfei Dai
Training Base, Army Engineering University of PLA, Xuzhou 221116, China
1 shared publication - Hao Peng
Field Engineering College, PLA Army Engineering University, Nanjing 210001, China
1 shared publication - Jinfeng Jiao
Combat Support Noncommissioned Officer College, PLA Army Engineering University, Xuzhou 221000, China
1 shared publication - Liyan Zhu
Field Engineering College, PLA Army Engineering University, Nanjing 210001, China
1 shared publication
Latest Publications
- Open Access
- 12 November 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (11) , 993
Data-Driven Component-Wise Forecasting of Heterogeneous Vehicle–Environment Temperature Channels for Infrared-Oriented Applications
Forecasting heterogeneous vehicle–environment temperatures requires models that accommodate differences in amplitude, persistence and meteorological response while keeping component-model proliferation manageable. This study presents a channel-adaptive component forecasting framework and directed reuse of frozen dominant-component predictors. RIME selects complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) parameters using decomposition quality. A common component predictor combines static feature weighting, dilated causal convolution, historical-window bidirectional long short-term memory encoding, temporal attention and an autoregressive highway (DConvFTA-BiLSTM-AR). A field campaign in Xuzhou, China, provides 14,217 consecutive one-minute records from 64 vehicle and environmental temperature channels. Fourteen channels spanning contrasting materials and thermal regimes were benchmarked using a chronological 70/20/10 split, train-fitted scaling and decomposition restricted to the train–validation prefix. Under observed future meteorological inputs, macro MAE was 0.264 °C and macro MSE was 0.430 °C2. The MAE was 13.7% lower than that of CEEMDAN-LSTM, the strongest neural baseline by macro MAE, in the evaluated interval. Directed reuse tests identify compatible source–recipient pairs while retaining recipient-specific predictors for non-dominant components and the residual. For 13 exposed-surface channels, a fixed-emissivity Planck transformation gives mean self-emitted 8–14 μm radiant-exitance MAE and channel RMSE of 0.593 and 1.280 W/m2. These results establish component forecasting and partial predictor reuse as useful tools for the evaluated heterogeneous thermal array and provide temperature inputs for downstream infrared analysis.
- 12 November 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (11) , 993
Open AccessData-Driven Component-Wise Forecasting of Heterogeneous Vehicle–Environment Temperature Channels for Infrared-Oriented Applications
Forecasting heterogeneous vehicle–environment temperatures requires models that accommodate differences in amplitude, persistence and meteorological response while keeping component-model proliferation manageable. This study presents a channel-adaptive component forecasting framework and directed reuse of frozen dominant-component predictors. RIME selects complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) parameters using decomposition quality. A common component predictor combines static feature weighting, dilated causal convolution, historical-window bidirectional long short-term memory encoding, temporal attention and an autoregressive highway (DConvFTA-BiLSTM-AR). A field campaign in Xuzhou, China, provides 14,217 consecutive one-minute records from 64 vehicle and environmental temperature channels. Fourteen channels spanning contrasting materials and thermal regimes were benchmarked using a chronological 70/20/10 split, train-fitted scaling and decomposition restricted to the train–validation prefix. Under observed future meteorological inputs, macro MAE was 0.264 °C and macro MSE was 0.430 °C2. The MAE was 13.7% lower than that of CEEMDAN-LSTM, the strongest neural baseline by macro MAE, in the evaluated interval. Directed reuse tests identify compatible source–recipient pairs while retaining recipient-specific predictors for non-dominant components and the residual. For 13 exposed-surface channels, a fixed-emissivity Planck transformation gives mean self-emitted 8–14 μm radiant-exitance MAE and channel RMSE of 0.593 and 1.280 W/m2. These results establish component forecasting and partial predictor reuse as useful tools for the evaluated heterogeneous thermal array and provide temperature inputs for downstream infrared analysis.
- Open Access
Dynamic Compressive Mechanical Properties of Polyvinyl Alcohol Fiber-Reinforced Geopolymer Composites
Polyvinyl alcohol (PVA) fibers are commonly added to fiber-reinforced geopolymer composites (FRGC) to enhance their properties; however, systematic research on the dynamic mechanical properties of polyvinyl alcohol fiber-reinforced geopolymer composites (PVA-FRGC) is still required. In this study, an orthogonal experimental design was adopted to investigate the effects of the fly ash/slag ratio, fiber length, and fiber volume content on the dynamic mechanical properties (dynamic compressive strength, fragmentation degree, and energy absorption capacity) of PVA-FRGC. A split Hopkinson pressure bar (SHPB) was used to test the dynamic mechanical properties of the material. The results indicate that the fly ash/slag ratio, fiber length, and fiber volume content all exert significant effects on the dynamic compressive strength and energy absorption capacity of PVA-FRGC. The addition of PVA fibers significantly improves the dynamic compressive strength of PVA-FRGC, which reaches 157.52 MPa, 183.26 MPa, and 210.68 MPa under three different strain rates ranging from 75.4 s−1 to 179.6 s−1, respectively. Although the energy absorption capacity of PVA-FRGC is not significantly improved, the integrity of the specimens after fragmentation is remarkably enhanced. Specifically, under the three load levels, the average particle sizes of PVA-FRGC are 241.43%, 245.04%, and 127.80% higher than those of plain geopolymers, respectively. Considering the comprehensive dynamic mechanical properties, a fly ash/slag ratio of 5:5, a fiber length of 9 mm, and fiber volume content of 2.0% can be regarded as the local optimal mix proportion.
Open AccessDynamic Compressive Mechanical Properties of Polyvinyl Alcohol Fiber-Reinforced Geopolymer Composites
Polyvinyl alcohol (PVA) fibers are commonly added to fiber-reinforced geopolymer composites (FRGC) to enhance their properties; however, systematic research on the dynamic mechanical properties of polyvinyl alcohol fiber-reinforced geopolymer composites (PVA-FRGC) is still required. In this study, an orthogonal experimental design was adopted to investigate the effects of the fly ash/slag ratio, fiber length, and fiber volume content on the dynamic mechanical properties (dynamic compressive strength, fragmentation degree, and energy absorption capacity) of PVA-FRGC. A split Hopkinson pressure bar (SHPB) was used to test the dynamic mechanical properties of the material. The results indicate that the fly ash/slag ratio, fiber length, and fiber volume content all exert significant effects on the dynamic compressive strength and energy absorption capacity of PVA-FRGC. The addition of PVA fibers significantly improves the dynamic compressive strength of PVA-FRGC, which reaches 157.52 MPa, 183.26 MPa, and 210.68 MPa under three different strain rates ranging from 75.4 s−1 to 179.6 s−1, respectively. Although the energy absorption capacity of PVA-FRGC is not significantly improved, the integrity of the specimens after fragmentation is remarkably enhanced. Specifically, under the three load levels, the average particle sizes of PVA-FRGC are 241.43%, 245.04%, and 127.80% higher than those of plain geopolymers, respectively. Considering the comprehensive dynamic mechanical properties, a fly ash/slag ratio of 5:5, a fiber length of 9 mm, and fiber volume content of 2.0% can be regarded as the local optimal mix proportion.