The standard camera- and force plate-based set-up for motion analysis suffers from the disadvantage of being limited to laboratory settings. Since adaptive algorithms are able to learn the connection between known inputs and outputs and generalise this knowledge to unknown data, these algorithms can be used to leverage motion analysis outside the laboratory. In most biomechanical applications, feedforward neural networks are used, although these networks can only work on time normalised data, while recurrent neural networks can be used for real time applications. Therefore, this study compares the performance of these two kinds of neural networks on the prediction of ground reaction force and joint moments of the lower limbs during gait based on joint angles determined by optical motion capture as input data. The accuracy of both networks when generalising to new data was assessed using the normalised root-mean-squared error, the root-mean-squared error and the correlation coefficient as evaluation metrics. Both neural networks demonstrated a high performance and good capabilities to generalise to new data. The mean prediction accuracy over all parameters applying a feedforward network was higher (r = 0.963) than using a recurrent long short-term memory network (r = 0.935).

(Artificial) neural networks have become increasingly popular in mechanics and materials sciences to accelerate computations with model order reduction techniques and as universal models for a wide variety of materials. However, the major disadvantage of neural networks remains: their numerous parameters are challenging to interpret and explain. Thus, neural networks are often labeled as black boxes, and their results often elude human interpretation. The new and active field of physics-informed neural networks attempts to mitigate this disadvantage by designing deep neural networks on the basis of mechanical knowledge. By using this a priori knowledge, deeper and more complex neural networks became feasible, since the mechanical assumptions can be explained. However, the internal reasoning and explanation of neural network parameters remain mysterious. Complementary to the physics-informed approach, we propose a first step towards a physics-explaining approach, which interprets neural networks trained on mechanical data a posteriori. This proof-of-concept explainable artificial intelligence approach aims at elucidating the black box of neural networks and their high-dimensional representations. Therein, the principal component analysis decorrelates the distributed representations in cell states of RNNs and allows the comparison to known and fundamental functions. The novel approach is supported by a systematic hyperparameter search strategy that identifies the best neural network architectures and training parameters. The findings of three case studies on fundamental constitutive models (hyperelasticity, elastoplasticity, and viscoelasticity) imply that the proposed strategy can help identify numerical and analytical closed-form solutions to characterize new materials.

Detailed knowledge about contamination and passivation compounds on the surface of lithium metal anodes (LMAs) is essential to enable their use in all-solid-state batteries (ASSBs). Time-of-flight secondary ion mass spectrometry (ToF-SIMS), a highly surface-sensitive technique, can be used to reliably characterize the surface status of LMAs. However, as ToF-SIMS data are usually highly complex, manual data analysis can be difficult and time-consuming. In this study, machine learning techniques, especially logistic regression (LR), are used to identify the characteristic secondary ions of 5 different pure lithium compounds. Furthermore, these models are applied to the mixture and LMA samples to enable identification of their compositions based on the measured ToF-SIMS spectra. This machine-learning-based analysis approach shows good performance in identifying characteristic ions of the analyzed compounds that fit well with their chemical nature. Moreover, satisfying accuracy in identifying the compositions of unseen new samples is achieved. In addition, the scope and limitations of such a strategy in practical applications are discussed. This work presents a robust analytical method that can assist researchers in simplifying the analysis of the studied lithium compound samples, offering the potential for broader applications in other material systems.