Solution–processed organic solar cells (OSC) have been explored widely due to their low cost and convenience, and impressive power conversion efficiencies (PCEs) which have surpassed 18%. In particular, the optimization of film morphology, including the phase separation structure and crystallinity degree of donor and acceptor domains, is crucially important to the improvement in PCE. Considering that the film morphology optimization of many blends can be achieved by regulating the film–forming process, it is necessary to take note of the employment of solvents and additives used during film processing, as well as the film–forming conditions. Herein, we summarize the recent investigations about thin films and expect to give some guidance for its prospective progress. The different film morphologies are discussed in detail to reveal the relationship between the morphology and device performance. Then, the principle of morphology regulating is concluded with. Finally, a future controlling of the film morphology and development is briefly outlined, which may provide some guidance for further optimizing the device performance.

Deep learning vision systems excel at pattern recognition yet falter when inputs are noisy or the model must explain its own confidence. Fuzzy inference, with its graded memberships and rule transparency, offers a remedy, while parameterized quantum circuits can embed features in richly entangled Hilbert spaces with striking parameter efficiency. Bridging these ideas, this study introduces a innovative Highly Quantized Fuzzy Neural Network (HQFNN) that realises the entire fuzzy pipeline inside a shallow quantum circuit and couples the resulting quantum signal to a lightweight CNN feature extractor. Each image feature is first mapped to a single qubit membership state through repeated angle reuploading. Then a compact rule layer refines these amplitudes, and a clustered CNOT defuzzifier collapses them into one crisp value that is fused with classical features before classification. Evaluated on standard image benchmarks, HQFNN consistently surpasses classical, fuzzy enhanced and quantum only baselines while using several orders of magnitude fewer trainable weights, and its accuracy degrades only marginally under simulated depolarizing and amplitude damping noise, evidence of intrinsic robustness. Gate count analysis further shows that circuit depth grows sublinearly with input dimension, confirming the model's practicality for larger images. These results position the model as a compact, interpretable and noise tolerant alternative to conventional vision backbones and provide a template for future quantum native fuzzy learning frameworks.