This paper presents the system, controller, and field test results of an unmanned marine vehicle (UMV) developed to acquire real-time ocean exploration information. The system consists of an unmanned surface vehicle (USV), an unmanned underwater vehicle (UUV), and an underwater cable. The developed platform is a research platform for ocean exploration and was proposed to compensate for the shortcomings of the existing USV, UUV, and towing system. This paper describes the proposed UMV, including the design considerations such as electronics architecture, data management, sensors, and actuators and explains the path control algorithm and controller used to follow the specified path for ocean exploration. In order to confirm the performance of the developed platform and control algorithm, a way-point tracking experiment was performed, and the results are shown.

In manufacturing automation, accurately determining the optimal tool replacement timing is critical yet challenging. Tool condition monitoring (TCM) has been widely studied to address this issue. Cutting force is a key parameter for evaluating tool wear, but conventional force sensors are costly and difficult to implement. This study proposes a cost-effective alternative by estimating cutting forces using spindle vibration data through a long short-term memory (LSTM)-based machine learning model. First, the correlation between cutting force and tool wear is analyzed to emphasize the need for accurate force estimation. Then, vibration data collected from the spindle are used to train an LSTM model, which is effective for time-series data processing. The model is trained with vibration signals from various machining positions, with structured time-series datasets improving performance and generalization. Experimental results show that the developed model accurately estimates cutting forces using short segments of vibration data from a single tool revolution. Additionally, the observed relationship between cutting force and tool wear remains consistent across different machining conditions. This study validates real-time cutting force estimation via spindle vibration monitoring and suggests its potential for tool wear prediction. The proposed method offers a practical, low-cost solution for improving tool condition monitoring in automated machining.

Cutting force is a critical indicator reflecting the interaction between the cutting tool and the workpiece in machining processes. Conventional measurement methods using dynamometers are accurate but costly and challenging for real-time applications. This study proposes a novel transfer learning-based method for estimating milling cutting forces using only spindle vibration signals without direct force sensors. The proposed approach consists of two stages: First, an autoencoder is trained with measured cutting force data to construct a latent feature space. Second, a target encoder aligns spindle vibration signals to this latent space, allowing the decoder to reconstruct estimated cutting forces. To reflect machining parameters into the learning model, the input dataset was constructed by integrating material type, cutting speed, and cutting direction as additional inputs into each model’s inputs. Experiments were conducted on Ti-6Al-4V and STS316L workpieces under various machining conditions. Under normal conditions, the proposed method achieved an average Pearson correlation coefficient (PCC) of 0.9213 ($F_x$) and 0.9072 ($F_y$). Under abnormal transient conditions, robust performance was maintained, with PCC values of 0.8573 ($F_x$) and 0.9202 ($F_y$). The results demonstrate that the proposed method can effectively monitor cutting forces and reflect changes across a variety of machining environments using only vibration signals.

In machining operations, dynamometers are typically used to directly measure the forces acting on cutting tools. However, their high cost and complex setup restrict their use to laboratory environments, making them unsuitable for real-time monitoring in general production settings. To overcome this limitation, this study proposes an autoencoder-based learning model for estimating cutting forces using only spindle vibration signals acquired during milling. The model features a deep neural network (DNN) that takes processed spindle vibration signals as input and predicts latent features derived from cutting force signals through an autoencoder. These predicted latent features are then fed into a pretrained decoder to reconstruct the corresponding cutting force signals. To enhance the model's accuracy and robustness, the raw vibration signals sampled at 20 kHz were filtered with a bandpass filter that spans the effective frequency range of 20–2500 Hz, effectively removing irrelevant noise. For validation, an accelerometer was mounted on the spindle head of a milling machine, and vibration data were collected during cutting. The estimated cutting forces were compared to ground truth measurements obtained from a dynamometer. The model achieved a Pearson correlation coefficient of 0.943, demonstrating that reliable cutting force estimation is achievable using only low-cost vibration sensors.