Real-Time Prediction Method for Performance Degradation Trend Based on Reliability Experimental Data

2013 ◽  
Vol 321-324 ◽  
pp. 757-761 ◽  
Author(s):  
Chen Liang Song ◽  
Zhen Liu ◽  
Bin Long ◽  
Cheng Lin Yang
Keyword(s):  
Experimental Data ◽  
Real Time ◽  
Field Data ◽  
Prediction Method ◽  
Field Method ◽  
Performance Degradation ◽  
New Method ◽  
Time Prediction ◽  
Prediction Result ◽  
The Relationship

According to the real-time prediction for performance degradation trend, the commonly used method is just based on field data. But this methods prediction result will not be so much ideal when the fitting of degradation trend of field data is not good. To solve the problem, the paper introduces a new method which is not only based on field method but also based on reliability experimental data coming from the history experiment. We use the relationship between the field data and reliability experimental data to get the result of the two kinds of data respectively and then get the weights according to the two prediction results. Finally, the final real-time prediction result for performance degradation tendency can obtain by allocating the weights to the two prediction results.

Forecasting Model of Short-Term Traffic Flow Based on Cloud Model

2011 ◽  
Vol 94-96 ◽  
pp. 38-42
Author(s):  
Qin Liu ◽  
Jian Min Xu
Keyword(s):  
Real Time ◽  
Traffic Flow ◽  
Cloud Model ◽  
Prediction Method ◽  
Absolute Error ◽  
Short Term ◽  
Guangzhou City ◽  
Time Prediction ◽  
Real Time Traffic ◽  
Absolute Percent Error

In order to improve the prediction precision of the short-term traffic flow, a prediction method of short-term traffic flow based on cloud model was proposed. The traffic flow was fit by cloud model. The history cloud and the present cloud were built by historical traffic flow and present traffic flow. The forecast cloud is produced by both clouds. Then, combining with the volume of the short-term traffic flow of an intersection in Guangzhou City, the model was calculated and simulated through programming. Max Absolute Error (MAE) and Mean Absolute percent Error (MAPE) were used to estimate the effect of prediction. The simulation results indicate that this prediction method is effective and advanced. The change of the historical and real time traffic flow is taken into account in this method. Because the short-term traffic flow is dealt with as a whole, the error of prediction is avoided. The prediction precision and real-time prediction are satisfied.

scholarly journals A Precise Prediction Method for the Properties of API-Containing Tablets Based on Data from Placebo Tablets

Pharmaceutics ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 601
Author(s):  
Yoshihiro Hayashi ◽  
Kaede Shirotori ◽  
Atsushi Kosugi ◽  
Shungo Kumada ◽  
Kok Hoong Leong ◽  
...  
Keyword(s):  
Experimental Data ◽  
Prediction Method ◽  
Response Surfaces ◽  
Disintegration Time ◽  
Pharmaceutical Ingredients ◽  
Tablet Properties ◽  
Precise Prediction ◽  
Novel Method ◽  
Using Data ◽  
The Relationship

We previously reported a novel method for the precise prediction of tablet properties (e.g., tensile strength (TS)) using a small number of experimental data. The key technique of this method is to compensate for the lack of experimental data by using data of placebo tablets collected in a database. This study provides further technical knowledge to discuss the usefulness of this prediction method. Placebo tablets consisting of microcrystalline cellulose, lactose, and cornstarch were prepared using the design of an experimental method, and their TS and disintegration time (DT) were measured. The response surfaces representing the relationship between the formulation and the tablet properties were then created. This study investigated tablets containing four different active pharmaceutical ingredients (APIs) with a drug load ranging from 20–60%. Overall, the TS of API-containing tablets could be precisely predicted by this method, while the prediction accuracy of the DT was much lower than that of the TS. These results suggested that the mode of action of APIs on the DT was more complicated than that on the TS. Our prediction method could be valuable for the development of tablet formulations.

scholarly journals Real-time prediction method of borehole stability

2008 ◽  
Vol 35 (1) ◽  
pp. 80-84 ◽  
Author(s):  
Chao WU ◽  
Mian CHEN ◽  
Yan JIN
Keyword(s):  
Real Time ◽  
Prediction Method ◽  
Borehole Stability ◽  
Time Prediction

Improving Maneuverability of Power-Assisted Valve for Fire Engines Based on Prediction of Valve Opening Times

2009 ◽  
Vol 21 (5) ◽  
pp. 628-634 ◽  
Author(s):  
Motoki Nakano ◽  
◽  
Takayuki Tanaka ◽  
Shun'ichi Kaneko ◽  
Koichi Yamano ◽  
...  
Keyword(s):  
Real Time ◽  
Prediction Error ◽  
Tracking Error ◽  
Prediction Method ◽  
Initial Value ◽  
Average Prediction Error ◽  
Time Prediction ◽  
Valve Opening ◽  
Impedance Parameters ◽  
Technical Terms

In this paper, we report the development of a power-assisted valve for fire engines. In Japan, the number of firefighters is decreasing year by year; therefore, it is important to reduce the amount of labor involved in firefighting. Although the development of an automatic system is possible in strictly technical terms, firefighting regulations in Japan require that the valve be operated by hand. In this study, we aim to develop a power-assisted system that can be controlled in accordance with the intent of the operator. First, we confirm a relationship between the impedance parameters and valve opening time. From this relationship, we propose a method for predicting the valve opening time based on the initial value of the operation torque. Evaluating this method, we found that the average operation torque and average tracking error are improved by a factor of two. Second, we reduce prediction error by using a real-time prediction method. While a prediction method based on initial torque can adjust parameters only once, the proposed real-time prediction method can update parameters continuously. As a result, the evaluation score of the method improved from 0.46 to 0.29, and average prediction error was improved from 172 ms to 105 ms.

Sign in / Sign up

Export Citation Format

Share Document