Manual Machine Research Articles

Research on X-ray nondestructive defect detection method of tire based on dynamic Snake Convolution YOLO model

Tire X-ray nondestructive testing before leaving the factory is crucial for driving safety. Given the complexity of tire structures and the diversity of defect types, traditional manual visual inspections and machine learning methods face significant challenges in terms of accuracy and efficiency. This study proposes an innovative tire X-ray image nondestructive testing technique based on the YOLOv5 model, incorporating several advanced technologies to enhance detection performance. Specifically, we introduce Dynamic Snake Convolution (DSConv), which adaptively focuses on slender and curved features within tires. Additionally, we have designed a C3 module based on DSConv, specifically targeting slender defects such as cord-overlap and cord-cracking. To improve the detection accuracy of small defects, we redesigned the neck network structure and introduced the Scale sequence feature fusion module (SSFF) and the Triple feature encoding module (TFE) to integrate multi-scale information from different network layers. Furthermore, we developed the Convolution Block Attention Module, integrated into the SSFF, which effectively reduces the interference of complex backgrounds and focuses on defect recognition. In the post-processing stage, we employed the Soft-NMS algorithm to optimize the confidence of candidate detection boxes, enhancing the accuracy of box selection. The experimental results show that compared to the YOLOv5 benchmark model, the algorithm proposed in this study achieved a 5.9 percentage point increase in mAP0.5 and a 5.7 percentage point increase in mAP0.5:0.95, demonstrating superior detection accuracy compared to current mainstream object detection algorithms and effectively completing the nondestructive testing task of tire defects.

A Review of Research on Coding Methods for Open-ended Text Responses in Survey Questionnaires

In fields such as social sciences and market research, open-ended questions can collect richer data information, but how to effectively count and analyse these text answers becomes a key issue. The study mainly explores the three coding methods of open-ended questions in questionnaires, including the definition, process, and application of manual coding, semi-automatic coding, and automatic coding. According to existing literature and data, manual coding has high flexibility and accuracy, but it is inefficient when processing large-scale data; semi-automatic coding combines manual coding and machine learning technology, which can improve efficiency while maintaining a certain degree of accuracy; automatic coding relies on natural language processing technology and deep learning models, which greatly improve coding efficiency, but there is a problem of insufficient accuracy when facing complex semantics. Future research can focus on improving the accuracy of automatic coding through deep learning, developing intelligent semi-automatic systems that reduce manual intervention, and incorporating real-time feedback mechanisms for continuous misappropriation.

Research on Non-Destructive Quality Detection of Sunflower Seeds Based on Terahertz Imaging Technology.

The variety and content of high-quality proteins in sunflower seeds are higher than those in other cereals. However, sunflower seeds can suffer from abnormalities, such as breakage and deformity, during planting and harvesting, which hinder the development of the sunflower seed industry. Traditional methods such as manual sensory and machine sorting are highly subjective and cannot detect the internal characteristics of sunflower seeds. The development of spectral imaging technology has facilitated the application of terahertz waves in the quality inspection of sunflower seeds, owing to its advantages of non-destructive penetration and fast imaging. This paper proposes a novel terahertz image classification model, MobileViT-E, which is trained and validated on a self-constructed dataset of sunflower seeds. The results show that the overall recognition accuracy of the proposed model can reach 96.30%, which is 4.85%, 3%, 7.84% and 1.86% higher than those of the ResNet-50, EfficientNeT, MobileOne and MobileViT models, respectively. At the same time, the performance indices such as the recognition accuracy, the recall and the F1-score values are also effectively improved. Therefore, the MobileViT-E model proposed in this study can improve the classification and identification of normal, damaged and deformed sunflower seeds, and provide technical support for the non-destructive detection of sunflower seed quality.

Design and Development of a Manual Pineapple Processing Machine Capable of Peeling, Coring and Slicing Pineapples for Small and Medium Enterprises

Pineapple processing involves peeling, coring and slicing of pineapple. A simple manual pineapple processing machine was developed to enhance the crude method of processing pineapple using just the knife and to reduce musculoskeletal problems associated with processing large quantity of pineapples with the knife. Hence, the objective of this paper is to design and develop a manual pineapple processing machine capable of peeling, coring and slicing pineapples to be utilized by small and medium enterprises (SME) using Response Surface Method (RSM) and validated using desirability plots. The results of actual and predicted response surface plots confirms pineapple sample weight 1.35 kg, diameter 60, height 110 mm with efficiency of 94.81% as the optimal variables. The desirability plot validated these results with response of 1.47, 0.17, 0.06, 0.22 kg weights of peeled, peel and core of pineapple removed, respectively, machine peeling efficiency at 87.29 % as optimal at 11 seconds. At these optimal conditions, the actual efficiency realized was 94.81 %. The differences within the actual and predicted valuations were lower and not significant statistically, which implied that selected model efficiently predicted the peeling efficiency of the machine. Center Composite Design Rotatable (CCDR) was employed to initiate 20 experimental processes.

Rancang Bangun Mesin Espresso dengan Sistem Pre-Charge Pneumatic

The development of technology in the world is growing rapidly, so that technology is able to make everything that is done faster and more effective, such as technology that is developing in the coffee industry. Manual espresso machines are done using human power, so there are limitations to the power needed to make espresso in large quantities at once and lack of time efficiency. This pneumatic system allows for more responsive pressure control compared to manual systems. The Pneumatic Pre-Charge (PCP) system is a system that utilizes natural resources as its main energy source in renewable energy systems such as air. The method used to achieve a more optimal manual espresso machine is to use an experimental research method to test the performance of the espresso machine designed from a combination of a PCP system through empirical data collection to measure how efficient the machine is. The design process produces a manual espresso machine design which can then be developed into a espresso machine. Testing was carried out as many as 210 cycles and was divided into 3 stages of testing, namely a 360 cc cylinder capacity with a pressure of 2700 psi capable of pressing an average of 70 times, showing that the coarser the grind size of the coffee powder used, the time and pressure required will be reduced by requiring a pressure of 35 psi. From the results of this study, further testing is needed on the use of a PCP system espresso machine to validate its usefulness in supporting the needs of making espresso in the coffee industry.

Manual Label and Machine Learning in Clustering and Predicting Student Performance

This study presents the Academic Investment Model (AIM) as a novel approach to predicting student academic performance by incorporating learning styles as a predictive feature. Utilizing data from 138 Marketing students across China, the research employs a combination of machine learning clustering methods and manual feature engineering through a four-quadrant clustering technique. The AIM model delineates student investment into four quadrants based on their time and energy commitment to academic pursuits, distinguishing between result-oriented and process-oriented investments. The findings reveal that the four-quadrant method surpasses machine learning clustering in predictive accuracy, highlighting the robustness of manual feature engineering. The study's significance lies in its potential to guide educators in designing targeted interventions and personalized learning strategies, emphasizing the importance of process-oriented assessment in education. Future research is recommended to expand the sample size and explore the integration of deep learning models for validation.

The effect of temperature, pressure, and grind size on Total Dissolved Solids (TDS) and extraction yield of semi-automatic espresso machines

The number of coffee shops in Indonesia has grown from 1,083 stalls in 2016 to over 2,937 booths in 2019, representing a threefold growth. Coffee shop establishments must provide two essential kinds of equipment: espresso machines, which use pressure, and filter machines, which employ infusion. The issue lies in the exorbitant cost and immense power requirements of semi-automatic and automated espresso machines, which necessitate the use of a manual espresso machine for commercial operations. The equipment can generate satisfactory espresso but encounters several challenges; specifically, the espresso generated is characterized by inconsistency, constantly varying in quality. This might arise due to the erratic nature of the manufacturing process. The two objectives of this study are: (1) to design an economically efficient semi-automatic espresso machine capable of producing products that meet the international quality standards set by the Specialty Coffee Association (SCA standard) and (2) to investigate the impact of critical factors such as pressure, temperature, and grind size, on the consistent quality of the resulting coffee (measured by Total Dissolved Solids (TDS) and extraction yield (EXT)). The research employs the Research and Development (RD) methodology. The research findings indicate that the optimal levels of Total Dissolved Solids (TDS) and extraction yield (EXT) may be attained by using a pressure setting of 8 bars, a temperature of 90ºC, and a grind size of 3.2 on the scale. The technique for optimizing the response resulted in Total Dissolved Solids (TDS) levels of 10.03% and extraction yield (EXT) values of 19.56%. The results have been deemed acceptable based on the criteria set by the global standards of Specialty Coffee Association (SCA).

Exploring motivations for algorithm mention in the domain of natural language processing: A deep learning approach

With the formation of the fourth paradigm of scientific research, algorithms have become increasingly important in scientific research. In academic papers, algorithms may be mentioned by scholars with various motivations, using, comparing, or improving algorithms to solve complex research tasks. Identifying these motivations can help scholars discover the relationships between algorithms and further assess their roles and values. Therefore, taking the field of natural language processing (NLP) as an example, this article proposes a complete method to conduct the identification, distribution, and evolution of motivations for mentioning algorithms at the sentence level. Specifically, using manual annotation and machine learning methods, we identify algorithm entities and sentences in the full text of papers, classify motivations for mentioning algorithms by pre-training models and data augmentation techniques, and finally analyze the distribution and evolution of motivations. The results show that the deep learning models trained with the augmented data outperform the traditional machine learning models in the classification task. In academic papers, more than half of the sentences show the direct use of algorithms, while the lowest percentage of motivations are improving algorithms, and the diversity of motivations has been increasing with time. For specific algorithms, grammatical algorithms are mentioned more by the motivation of “description,” while more motivations of “use” are found in the machine learning algorithms category. As time passed, the “use” motivations gradually replaced the “description” motivations for different algorithms, and the number of motivation types decreased significantly. Our research explores the identification, distribution, and evolution of authors’ motivations for mentioning algorithm entities, which could provide a basis for future algorithm relationship identification and influence evaluation using motivations.

Scalable Microwires through Thermal Drawing of Co-Extruded Liquid Metal and Thermoplastic Elastomer.

This article demonstrates scalable production of liquid metal (LM)-based microwires through the thermal drawing of extrudates. These extrudates were first co-extruded using a eutectic alloy of gallium and indium (EGaIn) as a core element and a thermoplastic elastomer, styrene-ethylene/butylene-styrene (SEBS), as a shell material. By varying the feed speed of the co-extruded materials and the drawing speed of the extrudate, it was possible to control the dimensions of the microwires, such as core diameter and shell thickness. How the extrusion temperature affects the dimensions of the microwire was also analyzed. The smallest microwire (core diameter: 52 ± 14 μm and shell thickness: 46 ± 10 μm) was produced from a drawing speed of 300.1 mm s-1 (the maximum attainable speed of the apparatus used), SEBS extrusion speed of 1.50 mm3 s-1, and LM injection rate of 5 × 105 μL s-1 at 190 °C extrusion temperature. The same extrusion condition without thermal drawing generated significantly large extrudates with a core diameter of 278 ± 26 μm and shell thickness of 430 ± 51 μm. The electrical properties of the microwires were also characterized under different degrees of stretching and wire kinking deformation which proved that these LM-based microwires change electrical resistance as they are deformed and fully self-heal once the load is removed. Finally, the sewability of these microwires was qualitatively tested by using a manual sewing machine to pattern microwires on a traditional cotton fabric.

Conversion Design of Arduino-Based Semi-Automatic Clothes Washer

This research aims to develop and evaluate a system that converts a manual clothes washer into an Arduino-based semi-automatic one. The research method used is a method of designing and creating a system for the object of research or called the design method. The system design is used as an object where the system is discussed and tested to find out how the system works and performs itself. The design object is an efficient and practical clothes washing tool.Converting a manual clothes washer into an Arduino-based semi-automatic one is an innovative and efficient solution to increase convenience and effectiveness in the clothes washing process. The design of this conversion model provides a complete guide to convert a manual washing machine into a semi-automatic one, improving the efficiency and convenience of daily use. With proper implementation, this project can provide an effective and cost-effective solution for household users.

Design and Fabrication Onion Harvester

Agriculture plays a vital role in Indian economy. India is a country which is dependent on farming as a main source of income for many families. As far as Indian scenario is concerned, more than 75 percent farmers are belonging to small and marginal land carrying. So any improvement in the productivity related task help to increase Indian farmer’s status and economy. Now a day’s agriculture equipments have lot of limitation and it required more energy to operate. The purpose of the project is to fabricate and enhance the design specifications of onion harvesting machine for multipurpose onion which should be helpful for the farmers having less & marginal land. Further, the comparative study of onion harvesting from manual method, machine method and proposed machine method is discussed. It is observed from the results that, the proposed machine method shows reasonably good result when compared manual method and machine method

구름 분류 방법에 대한 연구

This study is based on the mentorship course in CNU Science Education Institute for the Gifted. Clouds are classified into ten types proposed by Luke Howard and documented in the Cloud Atlas. In this study, we performed the cloud classification using manual approach and machine learning techniques. A total of 365 cloud images were directly taken for the mentorship course. Initially, we visually assessed cloud features in each image and manually classified cloud images into 11 types considering cloud features. The 11 types were named according to their distinguishing features. Subsequently, cloud features in each image were quantified based on the HSV color space. We applied the quantified cloud features to decision tree and k-means clustering algorithm, resulting in classification of clouds into six and three types, respectively. The disparity in the number of classifications between manual and machine learning methods is originated from the relative less features derived from the cloud images and discrepancies between human intuitive criteria and those used in machine learning classification. In the further study, by utilizing a more extensive set of cloud features and samples, well-trained machine learning techniques will allow for a more precise classification of clouds. This is expected to enable the utilization of these results in short-term weather forecasts.

PEMBUATAN MESIN PRESS HIDROLIK MANUAL BERKAPASITAS 20 TON

Abstract A manual hydraulic press machine with a capacity of 20 tons is a production tool that functions to press or press thick-layered workpieces with the help of a hydraulic pump. The aim of this research is to determine the process of making a manual hydraulic press machine with a capacity of 20 tons. In this research, the research method used is a descriptive qualitative research method, because this research will only explain the process of making a 20 ton capacity manual hydraulic press machine, therefore research activities are only limited to finding out about tools and materials. what is needed in the process of making the machine and also about the process of making the machine. Based on research, the appropriate materials used in the process of making a 20 ton capacity manual hydraulic press machine are materials that have been well tested, such as UNP ST 37 iron material which produces a maximum tensile strength of 481,559 N/nm2 with a loading force of 77, 5000 kN. and in testing assental iron with a diameter of 16mm and a length of 24cm, it produces a bending test of 17.6044 kgf/mm2 with a loading force of 3,575.06 kgf, has a yield load of 56.4063 kN and a tensile load of 350.490 N/nm2. Apart from that, in making a manual hydraulic press machine with a capacity of 20 tons, there are several processes, namely design, measuring, cutting, welding, smoothing, assembling, punching, and painting and tensile testing on ST 37 steel plates.

Comprehensive Design and Development of a Manual Briquette Machine

This comprehensive research delves into the intricacies of designing and developing a manual briquette machine, aimed at facilitating the conversion of biomass waste into a sustainable and environmentally friendly source of energy. By exploring various design considerations, material selections, and mechanical configurations, this study aims to present a comprehensive analysis that underscores the potential of manual briquette machines to positively impact global energy sustainability.

Planting and Harvesting Mechanization on Productivity, Energy Efficacy and Profitability of Potato Production

Potato occupied the first position among all the vegetables in respect of area and total production in Bangladesh. Effective and efficient use of energy are necessary for an improved agricultural production. Therefore, this research was undertaken for potato production to assess productivity, quantify energy flow and financial profitability of different production systems. The experimented four systems were manual planting and manual harvesting, machine planting and manual harvesting, manual planting and machine harvesting and machine planting and machine harvesting, respectively. The experiment was conducted at Farm Machinery and Postharvest Process (FMP) Engineering Division of Bangladesh Agricultural Research Institute (BARI) during 2017-18. Yield of potato including yield contributing characters for different treatments was not significantly varied. Direct energy was the highest in mechanical planting and harvesting system (25%) and the lower manual planting and harvesting system (18%). Indirect energy shared 82% in manual planting and harvesting system, 78% in machine planting and manual harvesting system, 80% in manual planting and mechanical harvesting system, and 75% in machine planting and machine harvesting system, respectively. The largest source of indirect energy consumption was from fertilizer (22-27% of the total energy). The higher specific energy of 1.93 MJ/kg was found in manually planted and mechanized harvesting system. The higher product value was from manual planting and mechanical harvesting system. The highest BCR (2.25) was found from machine planted and machine harvested followed by manually planted and mechanically harvested plot (2.16), machine planted and manually harvested plot (1.93) and manual planting and harvesting plot (1.91). Thus, mechanically planted and harvested system can be recommended for potato production since it can reduce 52% labour requirement than manual method and can give higher BCR among the tested production methods.

Converting laundry work of women in underdeveloped countries from risk of musculoskeletal disorders to a sustainable intervention: A design with holistic approach

AbstractMore than half of the population in impoverished areas around the world, which lack sufficient energy and water, do not have washing machines. Due to a lack of resources and economic reasons, the mechanical task of modern washing machines requiring electrical energy can only be done through hand washing. Additionally, water fetching and laundry work are predominately assigned to women due to socio‐cultural dynamics in disadvantaged areas. The repetitive motions involved in washing over extended periods of time, coupled with awkward body positions, often lead to musculoskeletal disorders in women. This study aims to improve women's work safety and living conditions through a product design for laundry washing. First, the ergonomic risk associated with women's body postures while washing clothes on the floor was evaluated to better understand the impact of the intervention and rapid upper extremity assessment (RULA) method was used for this purpose. Subsequently, the design process for a manual washing product, which operates without electricity, can handle bulk laundry and facilitates easier and more ergonomic work instead of directly scrubbing clothes, was initiated as a remedial intervention. Recognizing that laundry work is a multidimensional experience in women's lives beyond its ergonomic aspects, a holistic design methodology was adopted, incorporating various design approaches to create concepts that better integrate with the lives of woman users. Insights gained from these design approaches were then combined with the conceptual design method to generate design proposals. At the end of the study, the developed manual washing machine design performed improved RULA analysis scores and biomechanical loading outcomes compared to hand washing.

Experimental Investigation of the Surface Roughness for Aluminum Alloy AA6061 in Milling Operation by Taguchi Method with the ANOVA Technique

The surface roughness of the machined parts is the most important parameter to predict the performance of mechanical components. Moreover, predicting the optimal machining parameters conditions is the preferable method for cost reduction and achieving the desired surface quality of the product. This study investigates three cutting parameters, such as depth of cut, spindle speed, and feed for the milling aluminium alloy AA6061, to predict the surface roughness quality. The experimental work utilized a manual milling machine with a coated carbide cutter. Furthermore, the experiments were arranged using the Taguchi L9 orthogonal array (OA) method. The average surface roughness (Ra) was measured and converted to signal-to-noise (S/N) ratio and then analyzed in the statistical method of analysis of variance (ANOVA). Finally, the optimal combination set speed, feed, and depth of cut was 2400 rpm, 30 mm/min, and 0.5 mm, respectively. Also, according to the ANOVA test, the most influential parameter was the spindle speed among the selected parameters, with the highest P value of (66.42%). In comparison, the lowest P value is a depth of cut (5.34%). Furthermore, spindle speed was the only significant factor statistically. By selecting a high spindle speed (2400 rpm), surface quality was enhanced, but the preferable level was low for depth of cut and feed.

Detection of bruises on red apples using deep learning models

The detection and sorting of bruised apples after harvest play a crucial role in improving their economic value by eliminating surface defects. This also reduces the risk of contamination of infected apples during transport and storage. It can be done by using manual detection or machine vision techniques in red, green, and blue (RGB) colors to detect bruises on apples of various skin colors; however, in the early stages of bruising, it is challenging. Therefore, the main purpose of this study is determin of the effectiveness of Deep Learning models combined with the Near Infrared (NIR) imaging system for naturally bruised Super Chief red apples immediately after harvest. In total, 1000 images for the healthy class and 500 images for the bruised class were acquired from 500 apples. After the images were acquired with the RGB and NIR cameras, the data sets were divided into training (70 %), validation (15 %), and testing (15 %) sets. The Alexnet, the Inceptipon-V3, and the VGG16 network structures were trained using the training and validation data sets, and the trained network was evaluated using the test dataset. The VGG16 model achieved the highest test accuracy (86 %) when trained on the RGB data set, while the AlexNet model exhibited the lowest test accuracy (74.6 %). When the models were trained and tested with NIR datasets, 99.33 %, 100 % and 100 % accuracy rates were obtained for AlexNet, Inception V3, and VGG16, respectively. During the experiments, the VGG16 model trained with the NIR dataset achieved the lowest loss rate of 0.0002, whereas when trained and tested with the RGB dataset, the same VGG16 model also recorded the lowest loss rate of 0.353.These findings indicate that the deep learning models, particularly when trained with NIR data, demonstrate high accuracy rates in classifying apples as healthy or bruised, making them suitable for industrial classification applications. Therefore, the NIR data set is recommended for precise and reliable apple classification in industrial settings.

Significantly better precision with new machine learning versus manual image registration software in processing images from single-plane fluoroscopy to determine tibiofemoral kinematics following total knee replacement.

One common method to determine tibiofemoral kinematics following total knee replacement (TKR) is to capture single-plane fluoroscopic images of a patient activity and determine anterior-posterior (AP) positions of the femoral condyles and internal-external (IE) tibial rotation. Although JointTrack is widely used to analyze such images, precision (i.e. repeatability) in determining AP positions and IE tibial rotations using the two publicly available programs has never been quantified. The objectives were to determine the precision and reproducibility of results using both programs. Fluoroscopic images of 16 patients who performed a weight-bearing deep knee bend following TKR were analyzed. JointTrack Manual (JTM) and JointTrack Machine Learning (JTML) were used to perform 3D model-to-2D image registration after which AP positions of the femoral condyles and IE tibial rotations were determined. Precision in AP positions and IE rotations was quantified. Intraclass correlation coefficients (ICCs) for both repeatability (i.e. intraobserver) and reproducibility (i.e. interobserver) also were determined. Precision using JTM was worse than JTML for AP positions of the medial and lateral femoral condyles (1.0 mm and 0.9 mm vs 0.3 mm and 0.4 mm, respectively; p < 0.001 for both). For IE tibial rotation, precision also was worse using JTM versus JTML (1.1º vs 0.9°, p = 0.010). ICC values for JTML indicated good to excellent agreement (range: 0.82-0.98) whereas ICC values for JTM indicated only moderate to good agreement (range: 0.58-0.88). JTML has better precision and reproducibility than JTM and also is more efficient to use. Therefore, use of JTML over JTM is strongly recommended.

Performance Evaluation of Manual Seeder Machine for Precision Farming

Proper placement of seeds in the field is the most important operation to obtain an optimum yield of the crop. In India, about 75% of the landholders are small and have marginal land-holding capacity. Considering the limitations due to costly seed, the traditional method of manual dibbling, labor shortage, and small marginal land holding pattern there is a need for small manual planters for small and marginal landholders. Cotton, the white gold, is the king of textile, fibers and it is an important worldwide cash crop. The sowing of cotton is labor intensive as its planting requires 3-4 man-days/ha. Because of the above, the manual seeder was tested in the laboratory as well as in the field as per IS code: 6316-1993 with specific objectives. Laboratory analysis of manual seeder as seed rate (2.85 kg/ha and 2.88 kg/ha), seed damage (7.84% and 7.74%), and seed uniformity (62 cm and 64 cm) of cotton and castor crop respectively. Field analysis of manual seeder as coefficient of uniformity (91.63% and 93.23%), depth of seed placement (5.7 cm and 5.9 cm), speed of operation (1.82 km/h 1.84 km/h), theoretical field capacity (0.93 ha/h and 0.93 ha/h), effective field capacity (0.166 ha/h 0.171 ha/h), field efficiency (86.01% and 88.60%), draft (9.54 kgf and 10.46 kgf), energy consumption (10.93 MJ/ha and 10.04 MJ/ha) and cost of operation (440 Rs/ha and 445 Rs/ha) of cotton and castor crop respectively.