วารสารวิชาการเทคโนโลยีอุตสาหกรรม (J. Ind. Tech.) อยู่ในฐานข้อมูล Thai-Journal Citation Index Centre (TCI) กลุ่ม 1 (2564 - 2567) และ Asean Citation Index (ACI) มีค่า JIF = 0.094 และ T-JIF (3 ปีย้อนหลัง): 0.165 | The Journal of Industrial Technology (J. Ind. Tech.) is indexed in Thai-Journal Citation Index Centre (TCI) Tier 1 (2021 - 2024) and Asean Citation Index (ACI) with impact factor, T-JIF: 0.094 and 3-years T-JIF: 0.165


A System for Cooking Recipe Sharing and Cooking Recipe Finding by an Image of Ingredients using Deep Learning Technique

Electrical and Electronics Engineering

Nowadays, healthy eating is very popular. People start to cook their own food from existing cooking ingredients. However, sometimes they do not know what food can be cooked from existing ingredients. Therefore, they cook the same food, resulting in monotonous eating and not enjoy cooking. This research article presents the design and development of a system for cooking recipe sharing and cooking recipe finding by an image of ingredients using deep learning techniques. Users can use the application on mobile devices to share cooking recipes. Moreover, users can take a picture of ingredients that users already have in the kitchen such as garlic, pork, vegetables, etc. and send that picture into the system to search for cooking recipes from existing ingredients. This process will make users convenient for searching cooking recipes. The main components of the system include (1) A mobile application for general users developed with React Native, which users can add cooking recipes and search for cooking recipes by entering the ingredient names. Also, the user can use the mobile device to take a picture of ingredients to find cooking recipes, (2) Web application developed on the MERN stack for system administrators, which system administrators can add keywords of the search term for ingredients and test the model that has been created, and (3) Deep convolutional neural network using the YOLO algorithm through the Darknet library for creating the image recognition model. The model has taught to be able to recognize 20 types of ingredients using 100 images of each type of ingredient. After training our model for 36,000 rounds, the model has an average loss of 0.0408 with the precision, recall and F1-score at 0.96, 0.98 and 0.97 respectively.

Factors for Success for Online Business Entrepreneurs in the Digital Age

Electrical and Electronics Engineering

The objectives of this research were to: 1) study the success of online business entrepreneurs in the digital age; and 2) examine factors contributing to the success of online business entrepreneurs in the digital age. This research employed quantitative and qualitative research methodologies. In the quantitative research, the sample consisted of 260 online business entrepreneurs, obtained via multi-stage sampling. The sample size was determined based on 20 times the observed variables. Data were collected with the use of a questionnaire and analyzed with a structural equation model. For the qualitative research, in-depth interviews were conducted with 15 key informants including online business entrepreneurs and academic persons in the field of marketing. These informants were selected by purposive sampling. Data were analyzed with content analysis. The research findings showed that: 1) the success of the online business entrepreneurs was rated at a high level; 2) the characteristics of entrepreneurs, information technology, business strategies, and management innovation, all contributed to the success of online business entrepreneurs in the digital age with .05 level of statistical significance. Moreover, the findings also revealed an important point that entrepreneurs in the digital age needed to examine the needs of customers and respond to such needs promptly so that a marketing opportunity could be gained quickly. This could be done with the use of technologies in the digital age. Additionally, online entrepreneurs also needed to adjust their marketing strategies according to the market situations to ensure that they are competitive. They also needed to apply management innovation in the adjustment of business strategies to increase sales and expand their markets. These would align the business according to customer needs, leading to customer satisfaction, word of mouth communication among customers, repeat consumption, and brand loyalty. These findings can be used as guidelines for the development of success of online business entrepreneurs in the digital age by enhancing their potential in terms of marketing competitive advantage, creating and improving trading networks, and applying innovations and modern technologies in the development of their online businesses.

การวินิจฉัยจำแนกโรคใบองุ่นจากภาพถ่ายโดยใช้จีเนติกอัลกอริทึม และแผนผังจัดการตนเองเชิงโครงสร้างปรับตัวได้

Electrical and Electronics Engineering

อุตสาหกรรมการเกษตรเป็นอุตสาหกรรมที่สำคัญอย่างหนึ่งของประเทศไทย และในปัจจุบันได้มีการนำนวัตกรรมเข้ามาใช้เพื่อพัฒนาเทคโนโลยีทางเกษตรเพิ่มขึ้นอย่างต่อเนื่อง โดยเฉพาะเทคโนโลยีในการประมวลผลภาพและคอมพิวเตอร์วิทัศน์ ปัญหาที่สำคัญอย่างหนึ่งในอุตสาหกรรมการเกษตร คือการใช้สารเคมีมากเกินจำเป็นในการควบคุมโรคพืช ทำให้เกิดปัญหาต่าง ๆ ขึ้น เช่น ปัญหาทางสิ่งแวดล้อม อันตรายต่อสุขภาพ และสิ้นเปลืองค่าใช้จ่าย เพื่อลดปัญหาดังกล่าวหากสามารถพิจารณาลักษณะอาการของโรคพืชในสภาวะเริ่มต้นได้ จะสามารถลดปริมาณความเสียหายทางผลผลิต และหลีกเลี่ยงการใช้สารเคมีมากเกินจำเป็นได้ งานวิจัยนี้ได้นำเสนออัลกอริทึมสำหรับการวินิจฉัยจำแนกโรคใบองุ่นจากภาพถ่ายในสภาวะแวดล้อมจริง กระบวนการทำงานของระบบประกอบไปด้วยจีเนติกอัลกอริทึม (Genetic Algorithm : GA) และแผนผังการจัดการตนเองเชิงโครงสร้างปรับค่าได้ (Structure-Adaptive Self-Organizing Feature Map : SASOM) เรียกว่า อัลกอริทึม GA-SASOM ซึ่งโครงสร้างหลักของการจำแนกรูปแบบของโรคใบองุ่นของระบบได้ใช้โครงสร้างพื้นฐานของ GA ที่มีการพัฒนารูปแบบของโครโมโซมใหม่โดยได้พัฒนารูปแบบของแผนผังโนด (node map) ของ SASOM ขึ้นมาใหม่ เรียกว่า แผนผังโครโมโซม (chromosome map) ซึ่งแต่ละแผนผังโครโมโซมใช้แทนคุณลักษณะสี และลวดลายของรูปแบบ 1 รูปแบบที่ต้องการจำแนกรูปแบบ และนำมาใช้เป็นแบบจำลองคุณลักษณะเด่นของภาพโรคพืชของใบองุ่น งานวิจัยนี้ได้ทดสอบระบบการจำแนกรูปแบบโดยใช้โรคใบองุ่น 4 โรคดังนี้ โรคอีบุบ โรคราสนิม โรครานํ้าค้าง และโรคราแป้ง ซึ่งแต่ละภาพมีขนาด รูปร่าง ลักษณะการวางตัวของใบองุ่น และอยู่ในสภาวะแสงที่ต่างกัน ซึ่งผลการทดสอบระบบมีความแม่นยำสูงสุดถึง 94.35 เปอร์เซ็นต์

Probe Designing for Corrosion Inspection under Insulated Surface by Using Eddy Current Method

Electrical and Electronics Engineering

Insulation has mostly been used for preventing heat loss of substance in metal pipeline and later introduces corrosion at the metal-insulation interface. An inspection system is designed to detect the corrosion under the insulation on the outside of pipe wall based on a nondestructive testing associated with the eddy current technique. This research was to design and develop prototype devices suitably used for testing. Detecting probes designed and manufactured were of two types. C iron core probe and pick up coil iron core probe. Flat specimen with localized uniform corrosions was machined and inspected. The signal frequency of 300 – 1000 Hz induced by a function generator was applied to detect the corrosion, and the results were demonstrated by an oscilloscope. The experimental results revealed that the pick up coil iron core probe can detect corrosion effectively more than C iron core probe and the diameter of uniform corrosion detected was equal or greater than 6 millimeters. Depth of uniform corrosion of 1 – 6 millimeters at 300 to 400 Hz frequency can be detected, and the method can also detect through the color coating and insulation with the total thickness of less than 3 millimeters.

Maintenance Management for Risk Reduction of High Voltage Transformer

Electrical and Electronics Engineering

Power transformer is one of significant electrical equipments in power system. As it has high acquisition cost and failure consequences to the network, its proper maintenance task should be planned effectively. Nowadays, risk-based maintenance of power transformer in substation has played a critical role increasingly. The maintenance management is recommended by combining two evaluations: transformer condition and transformer importance. The condition evaluation is performed by electrical and insulating oil testing with their associated limitation to classify into good, suspect and poor condition. The importance evaluation is performed by load criticality, system stability, failure possibility, and failure consequence with three levels of low, moderate and high impacts. Score and weighting techniques are utilized in the analysis. The risk matrix is then developed by these two evaluations with nine zones of recommended maintenance actions for the power transformers in order to reduce the risk. A number of power transformers installed in 115 kV and 230 kV transmission systems are selected for the risk evaluation due to available and qualified data. The sample power transformer with rating of 230 kV, 200 MVA is presented as an example with its test results. Finally, the proposed method can be applied with the fleet of power transformers and other high voltage equipments in the network.

Study of Sound Harmonics on Induction Motor control by Inverter

Electrical and Electronics Engineering

This article presents the study of Sound Harmonics on Induction Motor control by Inverter AC drives. The propose technique does measure the harmonics of sound generated by induction motor without contact. Moreover, from the measured harmonic level, we can analyze the operation of induction motor control by inverter AC drives. Therefore, the studies of sound harmonic consist of two main procedures. The first procedure is used to measure the electrical properties comparing with the characteristic of sound harmonic. The second procedure is used to simulate of the operation on MATLAB / SIMULINK. For these two procedure, we set the frequency of the motor ( fm) at 5, 25, 50, 75 Hz for controlling the speed rate of motor, then adjusts the frequency switching ( fs ) of the inverter at 4, 8, 12kHz for controlling the stability of motor. From the experiment results, harmonic at the motor frequency (fm) at 75 Hz and switching frequency (fs) at 12 kHz, Harmonic, there are high amplitude of 200V and a sound level of 41.38 - 63.01 dB. But, at switching frequency (fs) at 4 kHz, Harmonic, there are low amplitude of 40V and a sound level of 41.40 - 71.95 dB. Then, comparison with the simulation results on MATLAB/SIMULINK, it appears an average error of 1.19%. In conclusion, the harmonic amplitude is directly proportional to the frequency of switching. But, it s inversely proportional to the sound level because at the high switching frequency will cause a rotor current to more pure sinusoidal wave. The rotation of the motor is more stable and smooth and sound level is decreases.

Get alert for journal's news

Get alert for journal's news. You can recieve journal up-to-date information by giving your email to us.