دانلود مقاله پشتیبانی رانندگی با کنترل منطق فازی نوع 2
خلاصه
1. مقدمه
2. مفهوم سیستم
3. توسعه سیستم فیزیکی سایبری اینترنت اشیا
4. توسعه ماژول کنترل منطق فازی نوع 2
5. نتایج تجربی
6. نتیجه گیری
بیانیه مشارکت نویسنده CRediT
اعلامیه منافع رقابتی
منابع
Abstract
1. Introduction
2. System concept
3. Developed IoT cyber–physical system
4. Developed type-2 fuzzy logic control module
5. Experimental results
6. Conclusions
CRediT authorship contribution statement
Declaration of Competing Interest
References
چکیده
مدل‌های پیشرفته هوش مصنوعی، سیستم‌های IoT را قادر می‌سازد تا با انعطاف‌پذیری زیادی نسبت به نیازهای کاربران کار کنند. در این مقاله سیستم IoT توسعه یافته خود را برای پشتیبانی رانندگی با استفاده از ماژول کنترل منطق فازی نوع 2 ارائه می کنیم. ما سیستم اینترنت اشیا را برای جمع‌آوری داده‌های مربوط به شرایط رانندگی و ارزیابی آن‌ها با توجه به نیازهای کاربر توسعه داده‌ایم. ماژول کاربردی منطق فازی نوع دوم در تحلیل سیگنال‌های شتاب‌سنج برای تنظیم انعطاف‌پذیر عدم قطعیت ارزیابی انتظارات رانندگی هر راننده استفاده شد. سیستم توسعه یافته ما با رانندگی در جاده های مختلف در اتومبیل های مختلف آزمایش شد و نتایج نشان دهنده کارایی عالی است.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
Advanced models of Artificial Intelligence enable systems of IoT to work with great flexibility to the needs of users. In this article we present our developed IoT system for driving support by the use of type-2 fuzzy logic control module. We have developed the IoT system to collect the data about driving conditions and evaluate them adjusting to the needs of user. Applied module of fuzzy logic of the second type was used in analysis of accelerometers signals to flexibly adjust to uncertainty of evaluation of driving expectations of each driver. Our developed system was tested in different cars by driving on various roads and results show excellent efficiency.
Introduction
Development of real-time Internet of Things (IoT) applications improves technological advances in intelligent transportation and car diagnostic systems. We can read about recent ideas which make Cyber–Physical Systems (CPS) not only supportive to humans but also predictive in potential malfunctions of appliances that we all use in our daily routine. In smart car IoT systems are developed by using sensors and devoted smart technologies to compose innovative control processing.
IoT systems for cars can work with many different features used in control and diagnostics to autonomous driving aspects. In Cao et al. (2020) was presented a model for smart front detection by using Singular Spectrum Decomposition (SSD) model. Model explained in Luque-Vega, Michel-Torres, Lopez-Neri, Carlos-Mancilla, and González-Jiménez (2020) was using SPIN-V sensors to improve procedure of safe parking. We can also implement models which will prevent collisions and help to maintain elements of car engine and suspension in good conditions. Idea presented in Krishnan (2018) was based on readings from ultrasonic sensor which measured distances to objects and helped in managing of safe drive. Very important for smart cars is also design of software. In practice we can use operating system in smartphones and just implement apps to connect to car sensors, i.e. Minnetti et al. (2020) proposed a smartphone based flush measurement to improve car body assembly procedure. System presented in Saeliw, Hualkasin, Puttinaovarat, and Khaimook (2019) was developed as mobile app to support parking procedure by using rfid infrastructure. In Xu et al. (2020) was presented an interesting discussion on networking, communication and applicable wireless technologies which serve as data transfers for smart cars. The model presented in Olivares-Rojas, Reyes-Archundia, Gutiérrez-Gnecchi, González-Murueta, and Cerda-Jacobo (2020) used 5G internet infrastructure to improve smart metering of multi-tire objects.
Conclusions
In this article we present a type-2 fuzzy system for smart driving support. Proposed system is working in IoT infrastructure of accelerometer sensors placed in a car. Data collected in the car is stored in data base from which can be shared with other users of the system, so that results of each driving can be compared to other drivers and also all users can benefit from shared knowledge of road conditions in different localizations. Our proposed model is using knowledge base developed for expert system evaluating road conditions. Proposed model composition enabled better adjustment to driving style which may differ for different people. Thus, all the features of driving can be better evaluated with tolerance to the style of driving of different people.
Results of our experiments showed that developed system is very efficient. We have done experiments by using different cars in various locations. We have also asked various drivers to collect data for us. Proposed type-2 fuzzy logic system enabled flexible adjustment to various driving style and various expectations of drivers, however showing correct result of road condition evaluation in each case.