The development of high-performance polymeric sensing materials is urgently needed for the development of force sensors. Hysteresis and sensitivity are considered to be one of the two key metrics for evaluating the performance of force sensors, and their performance-influencing factors and optimisation models have not been addressed. In this paper, a new Kepler optimisation algorithm (HKOA) and a long short-term memory network optimisation model (HKOA-LSTM) based on HKOA are proposed, and analytical models of the hysteresis and sensitivity are derived, respectively. First, multifactor experiments were conducted to obtain experimental data for the prediction models; the prediction models for the hysteresis and sensitivity performance of sensing materials were constructed using response surface methodology (RSM), Random Forest (RF), long short-term memory (LSTM) network, and HKOA-LSTM. Next, the four prediction models were evaluated; the comparison results show that the HKOA-LSTM model performs the best. Finally, the optimal solution of the prediction model is obtained using the multi-objective RIME (MORIME) algorithm. The findings indicate a hysteresis of 3.279% and an average sensitivity of 0.046 kPa⁻¹ across a broad pressure range of 0–30 kPa when the Fe₃O₄ content is 0.665 g, the carbon nanotube (CNT) content is 1.098 g, the multilayer graphene (MLG) content is 0.99 g, and the moulding temperature (MT) is 67 °C. The simulation outcomes for the hysteresis and sensitivity closely align with the experimental test values, exhibiting relative errors of 0.765% and 0.434%, respectively. Furthermore, the sensing performance in this study shows a significant enhancement compared to prior research, with the hysteresis performance improved by 31% and sensitivity increased by 26%. This approach enhances the experimental efficiency and reduces costs. It also offers a novel strategy for the large-scale, rapid fabrication of high-performance flexible pressure sensor materials.

The rapid advancement of humanoid robotics has spurred researchers’ interest in flexible sensors for wide linear range detection. In response, we report a capacitive flexible pressure sensor based on a multi-walled carbon nanotubes/titanium dioxide/polydimethylsiloxane (MWCNTs/TiO₂/PDMS) composite. A micro-hemispherical structure array formed on the composite surface via a templating method reduces the initial capacitance value. Modified carbon nanotubes (F-MWCNTs) were prepared using 2 wt%, 5 wt% and 10 wt% γ-aminopropyltriethoxysilane (APTES), significantly enhancing dispersion and interfacial bonding strength. The synergistic effect of microstructures and MWCNTs surface functionalization further enhances sensing performance. The F-MWCNTs/TiO₂/PDMS pressure sensor modified with 2 wt% APTES exhibits outstanding sensing capabilities: it demonstrates dual-stage sensitivity across a broad linear range of 0–95 kPa (0–13 kPa segment: 1.89 ± 0.49 kPa⁻¹; 13–95 kPa segment: 7.08 ± 0.63 kPa⁻¹), with a response time of 200 milliseconds, maintaining stability over 2500 cyclic loadings. In practical application exploration, this sensor has demonstrated strong adaptability, confirming its significant potential in micro-pressure detection, wearable electronics, and array sensing applications.