Ensuring the reliability and efficiency of computer numerical control (CNC) machines is crucial for industrial production. Traditional anomaly detection methods often struggle with uncertainty in vibration data, leading to misclassifications and ineffective predictive maintenance. This study proposes rough long short-term memory (RoughLSTM), a novel hybrid model integrating rough set theory (RST) with LSTM to enhance anomaly detection in CNC machine vibration data. RoughLSTM classifies input data into lower, upper, and boundary regions using an adaptive threshold derived from RST, improving uncertainty handling. The proposed method is evaluated on real-world vibration data from CNC milling machines, achieving a classification accuracy of 94.3%, a false positive rate of 3.7%, and a false negative rate of 2.0%, outperforming conventional LSTM models. Moreover, the comparative performance analysis highlights RoughLSTM’s competitive or superior accuracy compared to CNN–LSTM and WaveletLSTMa across various operational scenarios. These findings highlight RoughLSTM’s potential to improve fault diagnosis and predictive maintenance, ultimately reducing machine downtime and maintenance costs in industrial settings.

As technology continues to evolve, the hydraulic power steering system (HPS) used for steering control in vehicles has begun to be changed by the electric power steering (EPS) system, which offers the advantage of better controllability. In this study, it is aimed to control an EPS motor, which has been modeled, more precisely and stably using an innovative control method. The effects of a PID control designed with a new approach, on the system are investigated to compare it with the Ziegler Nichols, Internal Model Control (IMC), Tyreus Luyben, and Haugen methods mentioned in the study. The foundation of the presented design technique is based on calculating the optimal proportional gain ( k_p ) value to minimize the error rates of the settling time ( t_s ) and maximum overshoot ( M_p ) in a stable loop, and then deriving the other PID controller parameters. This process is achieved by forming a loop in the stable area and calculating the optimum controller parameters. When looking at the results obtained, the responses of the PID controller calculated using the new approach are found to be more satisfactory compared to the responses of the PID controllers designed using other methods such as Ziegler-Nichols, IMC, Tyreus-Luyben, and Haugen.

In this study, the effects of cracks in the columns of a single degree of freedom (SDOF) steel structure model on the system responses due to the decrease in the equivalent spring coefficient were investigated. The crack in the columns was modeled as an edge crack, and the crack was thought to behave like a spring. The crack is considered as the mode I crack type (opening mode) specified in linear fracture mechanics. In order to examine the responses of the system under the influence of different excitations, the changes in displacement, acceleration, and power spectral density responses under the influence of harmonic excitation at a frequency equal to the fundamental frequency of the SDOF model and six different earthquake excitations were examined.

Manyetik levitasyon sistemleri, mühendislik sistemlerinde sürtünmeyi en aza indiren çözümler sunduğundan, güncel mühendislik çalışmalarına tabidirler. Bu çalışmada, yeni bir PI-PD kontrolcü tasarım prosedürü sunulmuştur. PI-PD kontrolcüleri, bir PI (iç çevrim) ve bir PD (dış çevrim) kombinasyonundan oluşur. İç çevrimin amacı, açık çevrim kararsız sistemi kararlı kılmaktır. Dış çevrimin amacı, kapalı çevrim sisteminin toplam performans gereksinimlerini sağlamaktır. Tasarım prosedürü, kontrolcü parametreleri düzleminde kararlılık sınır eğrisi kullanılarak çizilen kararlı bölgenin elde edilmesine ve bu bölgenin ağırlıklı geometrik merkezinin (AGM) hesaplanmasına dayanır. Tasarım prosedüründe, ilk olarak, iç çevrim için PD kontrolcü parametrelerinin düzlemindeki kararlı bölge ve bunun ağırlıklı geometrik merkezi hesaplanır. İç çevrim, belirtilen AGM kontrol parametreleri kullanılarak tek bir bloğa indirgenir ve ardından prosedür, farklı tasarımlarda faz ve kazanç marjı performans gereksinimlerini uygulayan bir test fonksiyonu kullanılarak dış çevrim PI denetleyicisi için tekrarlanır. Deneysel çalışma, önerilen metodoloji ile tasarlanan PI-PD kontrolcünün literatürde bulunan alternatiflere göre daha üstün performans sergilediğini göstermektedir.

This study aims to classify vibration data obtained from old CNC milling (brownfield) machines used in industrial production processes with machine learning algorithms. The analysis of data obtained from such machines is of critical importance in order to increase the efficiency of old production machines and optimize production processes. In the study, vibration data collected from three different CNC machines under real production conditions for two years were used. The collected data were analyzed with various machine learning algorithms, especially overfitting prevention techniques, and the performances of these algorithms were compared. The results showed that the proposed machine learning methods can classify the information obtained from vibration data with high accuracy rates. The algorithms used provided an effective solution for early detection of tool wear, operational errors and other production problems caused by vibration, thus enabling more efficient management of production processes. The study presents an innovative method for modernizing old machines in particular within the framework of Industry 4.0, and provides important practical contributions in terms of improving industrial processes, optimizing maintenance processes and increasing overall efficiency.

In this paper, a simple design method is presented to adjust the parameters of a proportional-integral derivative PID controller to be applied to different systems. In this method, PID controller is designed based on setting the optimal proportional gain according to the desired performance (settling time, overshoot). Determining the other parameters of the PID controller by adjusting the optimum ratio gain (k p ) in a stable loop that minimizes the settling time (t s ) and the error rate of the overshoot (M p ) constitutes the basis of the method. The Routh Rurwitz criterion is used to guarantee stability. The performance of the controller designed with the proposed method has been evaluated on three different transfer functions. With this method, the PID controller works successfully without destroying parameters and without complex mathematical formulation. It has been observed that the proposed method provides better closed loop performance compared to the methods reported recently.