Error Fusion of Hybrid Neural Networks for Mechanical Condition Dynamic Prediction

It is important for equipment to operate safely and reliably so that the working state of mechanical parts pushes forward an immense influence. Therefore, in order to enhance the dependability and security of mechanical equipment, to accurately predict the changing trend of mechanical components in advance plays a significant role. This paper introduces a novel condition prediction method, named error fusion of hybrid neural networks (EFHNN), by combining the error fusion of multiple sparse auto-encoders with convolutional neural networks for predicting the mechanical condition. First, to improve prediction accuracy, we can use the error fusion of multiple sparse auto-encoders to collect multi-feature information, and obtain a trend curve representing machine condition as well as a threshold line that can indicate the beginning of mechanical failure by computing the square prediction error (SPE). Then, convolutional neural networks predict the state of the machine according to the original data when the SPE value exceeds the threshold line. It can be seen from this result that the EFHNN method in the prediction of mechanical fault time series is available and superior.

The eSpiro Ventilator: An Open-Source Response to a Worldwide Pandemic

Objective: To address the issue of ventilator shortages, our group (eSpiro Network) developed a freely replicable, open-source hardware ventilator. Design: We performed a bench study. Setting: Dedicated research room as part of an ICU affiliated to a university hospital. Subjects: We set the lung model with three conditions of resistance and linear compliance for mimicking different respiratory mechanics of representative intensive care unit (ICU) patients. Interventions: The performance of the device was tested using the ASL5000 lung model. Measurements and Main Results: Twenty-seven conditions were tested. All the measurements fell within the ±10% limits for the tidal volume (VT). The volume error was influenced by the mechanical condition (p = 5.9 × 10−15) and the PEEP level (P = 1.1 × 10−12) but the clinical significance of this finding is likely meaningless (maximum −34 mL in the error). The PEEP error was not influenced by the mechanical condition (p = 0.25). Our experimental results demonstrate that the eSpiro ventilator is reliable to deliver VT and PEEP accurately in various respiratory mechanics conditions. Conclusions: We report a low-cost, easy-to-build ventilator, which is reliable to deliver VT and PEEP in passive invasive mechanical ventilation.

Robust Predictive Maintenance for Robotics via Unsupervised Transfer Learning

Industrial robots play an increasingly important role in a growing number of fields. Since the breakdown of a single robot may have a negative impact on the entire process, predictive maintenance systems have gained importance as an essential component of robotics service offerings. The main shortcoming of such systems is that features extracted from a task typically differ significantly from the learnt model of a different task, incurring false alarms. In this paper, we propose a novel solution based on transfer learning which addresses a well-known challenge in predictive maintenance algorithms by passing the knowledge of the trained model from one task to another in order to prevent the need for retraining and to eliminate such false alarms. The deployment of the proposed algorithm on real-world datasets demonstrates that the algorithm can not only distinguish between tasks and mechanical condition change, it further yields a sharper deviation from the trained model in case of a mechanical condition change and thus detects mechanical issues with higher confidence.

Use of Technological Diagnosis in Rail Vehicle Engines Maintenance

The paper aims to classify the maintenance of internal combustion engines in 812 series diesel multiple units, to analyse operating failures, and to identify methods and procedures for determining their current mechanical condition. The paper specifies the required procedures and methods for maintenance starting from the development of the DMU (diesel multiple units) 812 series to the present. It also focuses on understanding how diagnosis and control sensors are attached in individual cable harnesses. A protocol for diagnosing combustion engine defects is proposed in the final part of the paper. A part of the paper is a proposed list of codes for individual faults to facilitate the work. Another method proposed within this paper is the definition and attachment of individual sensor connections on the engine in the EDC (Electronic Diesel Control) M(S) 5 cable harness. Faults leading to engine stop are identified.

PERENDAMAN DENGAN PERASAN BUAH JERUK LEMON (Citrus lemon) DAPAT MENURUNKAN KEKERASAN RESIN KOMPOSIT NANOHYBRID

Composite resin is a restoration material that is often used because the composite resin has good aesthetic value like mimetic the teeth color. Composite resins have a physical and mechanical condition. One of the mechanical condition is hardness. The surface hardness of composite resins is the surface resistance of the composite resin material to the applied pressure. One of the factors influencing composite hardness is the food and beverages consumed. Consuming acidic drinks continuously for a long time period can erode composite resin filling. The purpose of this study was to determine the effect of soaking into a citrus lemon on the hardness of nanohybrid composite resin. This type of research was true experimental with pre-test post-test with control group design using 24 composite resin samples which are divided into 4 groups with 6 samples each. The groups in this study were nanohybrid composite resins soaked with citrus lemon and aqua dest for 60 minutes and 120 minutes. The hardness tested using a Vicker hardness tester. The results of the study using the LSD (Least Significant Difference) test showed that the significance value of p= 0.014 (p<0.05), which means that the use of citrus lemon for 120 minutes affected the hardness of nanohybrid composite resin. In conclusion, soaking with citrus lemon for 120 minutes reduces more the hardness of nanohybrid composite resin compared with soaking for 60 minutes.