Both artificial intelligence (AI) and domain knowledge from human experts play an important role in manufacturing decision making. Smart manufacturing emphasizes a fully automated data-driven decision-making; however, the AI incubation process involves human experts to enhance AI systems by integrating domain knowledge for modeling, data collection and annotation, and feature extraction. Such an AI incubation process not only enhances the domain knowledge discovery but also improves the interpretability and trustworthiness of AI methods. In this article, we focus on the knowledge transfer from human experts to a supervised learning problem by learning domain knowledge as interpretable features and rules, which can be used to construct rule-based systems to support manufacturing decision making, such as process modeling and quality inspection. Although many advanced statistical and machine learning methods have shown promising modeling accuracy and efficiency, rule-based systems are still highly preferred and widely adopted due to their interpretability for human experts to comprehend. However, most of the existing rule-based systems are constructed based on deterministic human-crafted rules, whose parameters, such as thresholds of decision rules, are suboptimal. Yet the machine learning methods, such as tree models or neural networks, can learn a decision rule based structure without much interpretation or agreement with domain knowledge. Therefore, the traditional machine learning models and human experts’ domain knowledge cannot be directly improved by learning from data. In this research, we propose an interpretable neural network (INN) model with a center-adjustable sigmoid activation function to efficiently optimize the rule-based systems. Using the rule-based system from domain knowledge to regulate the INN architecture not only improves the prediction accuracy with optimized parameters but also ensures the interpretability by adopting the interpretable rule-based systems from domain knowledge. The proposed INN will be effective for supervised learning problems when rule-based systems are available. The merits of the INN model are demonstrated via a simulation study and a real case study in the quality modeling of a semiconductor manufacturing process. The source code of this work is hosted here: https://github.com/XiaoyuChenUofL/Interpretable-Neural-Network .

Tendon-driven mechanisms are one of the most popular mechanisms for transmitting force and power from a distance. The energy efficiency of a tendon-driven system can be improved if it can maintain the actuation force while not moving, without mechanical work. This can be achieved by using a brake. A brake without an additional actuator is preferred for achieving compactness of the entire system. We present a novel passive brake mechanism - the capstan brake, which consists of a capstan, rollers, and one-way clutches. The friction between the capstan and tendon amplifies a small resisting force (originating from an inactivated motor) to gain enough brake force. Because no additional actuator is involved, no energy is consumed to generate the brake force. In addition, the one-way clutch enables the capstan to rotate in the winding direction. Therefore, the brake force is only exerted when needed, and the performance of the entire device does not decrease owing to the use of the capstan brake. The brake force of the system is limited to handling the safety issues. If the external load exceeds the maximum brake force, the brake becomes back-drivable again. The limit level can be controlled by changing the number of times the tendon is wound around the capstan. Another issue for a tendon-driven system is that the tendon escapes from a spooler when the tendon does not maintain proper tension. By implementing the rollers with the capstan brake, the tendon cannot escape from a spooler even though the tendon is not pulled by an external load in all actuating situations. The performance of the proposed brake mechanism was evaluated through several tests. The results showed that the capstan brake is suitable to be applied to the wearable robotic hand, which is one of the prospective applications of the brake. The force loss caused by the brake was negligible and the brake operated properly even though the tendon was not pulled by an external load in all actuating situations.