Development of an Automatic Tracking Camera System Integrating Image Processing and Machine Learning

This paper describes the development of a robust object tracking system that combines detection methods based on image processing and machine learning for automatic construction machine tracking cameras at unmanned construction sites. In recent years, unmanned construction technology has been developed to prevent secondary disasters from harming workers in hazardous areas. There are surveillance cameras on disaster sites that monitor the environment and movements of construction machines. By watching footage from the surveillance cameras, machine operators can control the construction machines from a safe remote site. However, to control surveillance cameras to follow the target machines, camera operators are also required to work next to machine operators. To improve efficiency, an automatic tracking camera system for construction machines is required. We propose a robust and scalable object tracking system and robust object detection algorithm, and present an accurate and robust tracking system for construction machines by integrating these two methods. Our proposed image-processing algorithm is able to continue tracking for a longer period than previous methods, and the proposed object detection method using machine learning detects machines robustly by focusing on their component parts of the target objects. Evaluations in real-world field scenarios demonstrate that our methods are more accurate and robust than existing off-the-shelf object tracking algorithms while maintaining practical real-time processing performance.

Theoretical studies of the “Workpiece-tool” system vibroacoustic dynamics of the turning group woodworking machines

In the woodworking industry, the issue of noise reduction is one of the fundamental ones. In most cases, it is an indicator of equipment and products quality, in addition, it negatively affects the performance and irritates the nervous system of machine operators. [1]. The cause of noise is the process of cutting tool interaction with wood and it also depends on the type of wood cutting tool. For wood manufacturing, the blade and abrasive cutting tools are used. The blade instrument has a specified number of fixed shape blades and is divided into disk, cylindrical, conical and plate-shaped ones according to the shape of the body. The abrasive cutting tool on the working surface contains an indefinite number of abrasive material particles. [2]. The edge of the cutter interacts with the surface under work, along the entire width, the cutting direction is perpendicular to the cutting edge. With a small cutting depth, this does not cause significant sound vibrations, but with intensive technological modes of the treated surface, this factor is of great importance in generating noise.There are a lot of works devoted to the study of different cutting tool dependence and noise characteristics [3-7]. For example, in [8] it was experimentally proved that the noise level increases by 1-5 dBA with an increase in the number of knives from 2 to 4. This article presents the results of the acoustic system theoretical studies “manufactured workpiece cutting tools” for cantilever fixing of the workpiece of turning group woodworking machines.

PRODUCT QUALITY CONTROL USING SIX SIGMA (DMAIC) METHODS TO MINIMIZE WAST IN BIMA MANDIRI CIGARETTE COMPANY REMBANG, PASURUAN REGENCY

Quality is a key to be able to compete in the industrial world [16. Quality control is needed to reduce the number of defective products produced by the company, thus reducing losses experienced by the company. The Bima Mandiri Rembang Pasuruan cigarette company is a company that produces cigarettes, one of which is INNO cigarettes. The number of defective products produced by the company so that the company must make an increase in quality by using a method to reduce the number of defects that occur. The number of defective products causes the company to suffer losses. For that, we need a method that can reduce cigarette defective products which in turn can improve the quality of the company's production[12]. Six Sigma with the DMAIC stage (Define, Measure, Analyze, Improve, Control) is a method used in this research. Based on these steps, defects that often occur are less dense cigarettes as many as 289 sticks with a percentage of 25%, tearing on the cigarettes as many as 227 cigarettes with a percentage of 20% and peeling cigarettes as many as 208 sticks with a percentage of 18%. Factors that cause defects include humans, machines, methods and materials. After calculating using the Six Sigma method, before the improvement, the DPMO value is 113988.1 and the Sigma Level value is 2.722. After the improvements were made, the DPMO value decreased to 76488.1 and the Sigma Level was 2.94715. To achieve the six sigma target, the company is expected to be able to carry out improvements with a focus on the factors that cause product defects and always carry out regular control to reduce product defects. The corrective steps taken in the Bima Mandiri Rembang Pasuruan Regency cigarette company are human: regular training for machine operators and employees; methods: inspection of raw materials, blending machines and glue residue in the teat; engine: inspection of engine components; material: reprocessing less refined raw materials and using better quality glue.

Multisensory Virtual Reality for delivering training content to machinery operators

The issue of training operators in the use of machinery is topical in the industrial field and in many other contexts, such as university laboratories. Training is about learning how to use machinery properly and safely. Beyond the possibility of studying manuals to learn how to use a machine, operators typically learn through on-the-job training. Indeed, learning by doing is in general more effective, tasks done practically are remembered more easily, and the training is more motivating and less tiresome. On the other hand, this training method has several negative factors. In particular, safety may be a major issue in some training situations. An approach that may contribute overcoming negative factors is using Virtual Reality and digital simulation techniques for operators training. The research work presented in this paper concerns the development of a multisensory Virtual Reality application for training operators to properly use machinery and Personal Protective Equipment (PPE). The context selected for the study is a university laboratory hosting manufacturing machinery. The application allows user to navigate the laboratory, to approach a machine and learn about how to operate it, and also to use proper PPE while operating a machine. Specifically, the paper describes the design and implementation of the application and presents the results of preliminary testing sessions.

Investigating Human-Machine Interfaces’ Efficiency in Industrial Machinery and Equipment: A Kenyan Context

The twenty-first century has seen a vast technological revolution characterized by the development of cyber-physical systems, integration of things, and new and computationally improved machines and systems. However, there have been seemingly little strides in the development of user interfaces, specifically for industrial machines and equipment. The aim of this study was to assess the efficiency of the human-machine interfaces in the Kenyan context in providing a consistent and reliable working environment for industrial machine operators. The researcher employed a convenient purposive sampling to select 15 participants who had at least two years of hands-on experience in machines operation, control, or instrumentation. The results of the study are herein presented, including the recommendations to enhance workforce productivity and efficiency.

Modern trends in the formation of occupational pathology when working on mobile agricultural machinery

Introduction. There are currently several works in the scientific literature devoted to studying the influence of working conditions on mobile agricultural machinery on the occupational morbidity of workers on the example of individual regions. Still, Russian Federation did not conduct such studies before. The study aims to analyze working conditions and current trends in the formation of occupational pathology when working on mobile agricultural machinery in the Russian Federation. Materials and methods. The paper uses the results of long-term sanitary-hygienic and ergonomic studies of working conditions when working on mobile agricultural machinery and data on the level of occupational morbidity (PZ) of farmworkers of the Russian Federation in 2011-2017. Results. Microclimatic discomfort, dustiness and gas contamination of the working area air, industrial noise, general and local vibration, physical overload, forming harmful operating conditions (classes 3.2-3.4), occupational risk categories from medium to very high characterize working on mobile agriculture machinery. From 2011 to 2017, researchers have identified 960 agricultural machine operators with 1052 occupational diseases in the Russian Federation, formed mainly under the influence of physical factors and physical overloads. In the nosological structure of occupational diseases (OD), the first place is occupied by vibration disease (VD), the second by radiculopathy (RP), and the third by sensorineural hearing loss. Researchers characterize the current trends in the nosological structure by a significant increase in the prevalence of radiculopathy against the background of a decrease in diagnosis cases of vibration disease. Conclusions. Working conditions when working on mobile agricultural machinery remain harmful and pose a high risk of developing occupational radiculopathy, vibration disease and sensorineural hearing loss. It should be taken into account when developing measures to prevent occupational pathology for agricultural machine operators.

Multisensory VR for Delivering Training Content to Machinery Operators

The issue of training operators in the use of machinery is topical in the industrial field and in many other contexts, such as university laboratories. Training is about learning how to use machinery properly and safely. Beyond the possibility of studying manuals to learn how to use a machine, operators typically learn through on-the-job training. Indeed, learning by doing is in general more effective, tasks done practically are remembered more easily, and the training is more motivating and less tiresome. On the other hand, this training method has several negative factors. In particular, safety may be a major issue in some training situations. An approach that may contribute overcoming negative factors is using Virtual Reality and digital simulations techniques for operators training. The research work presented in this paper concerns the development of a multisensory Virtual Reality environment for training operators to properly use machinery and Personal Protective Equipment (PPE). The context selected for the study is a university laboratory hosting manufacturing machinery. It has been developed an application that allows user to navigate the laboratory, to approach a machine and learn about how to operate it and also what PPE to use while operating. Specifically, the paper describes the design and implementation of the application.

Correlation of yarn feeding to the dimensional and elastic parameters of tubular knitted fabric

The yarn feeding for a loop formation is a critical factor in determining the size and elasticity of highly elastic knitted fabrics. Currently, the prevalent production processes rely on experienced machine operators to set up the optimal feed rate by trial and error. To improve production efficiency and reduce the reliance on the operator’s skill, we attempt to create a structure model of tubular knitted fabric that could correlate the size as well as elasticity of fabric with the loop geometry parameters (wale spacing, course spacing) of the yarn feeding. The experimental tensile test of the elastic fabric verified that the model is able to deduce the yarn feeding parameters from the elasticity and dimensional requirements of the fabric to be knitted. It is also illustrated that the yarn feeding is a key factor in controlling the elasticity of knitted fabrics.

Anthropometric Analysis of Selected Body Dimensions and Comparison with the Design Approach for Forestry and Agricultural Machine Operators

The aim of the study was to conduct an analysis of selected anthropometric measurements of sitting posture of the adult male population and to compare the results to the workplace of earthmoving machine operators. Research into this problem is important in several respects, particularly the design approaches taken for the current and future machines, and their impact on the health and safety of operators. The anthropometric analysis was based on dimension measurements of the adult male population gathered in the years 2002–2019. The sample consisted of 1702 subjects aged 18 to 25. Thirteen body dimensions were selected and evaluated according to the European Standard of International Organization for Standardization (EN ISO) Nr. 3411. Anthropometric analysis of individual dimensions was evaluated using descriptive statistics and frequency histograms. The results of the analysis were compared to values recommended in the EN ISO 3411 standard. Results confirmed the growing trend of specific human dimensions within the adult population. In eight of the 13 analyzed body dimensions, descriptive statistics showed above-average values in the analyzed population compared to the values given in the standard. The long-term trend commonly observed in the adult population of developed countries was also confirmed.

Subjective hearing sensation of process variations at a milling machine. How reliable will chatter marks be detected?

Intuition enables experienced machine operators to detect production errors and to identify their specific sources. A prominent example in machining are chatter marks caused by machining vibrations. The operator's assessment, if the process runs stable or not, is not exclusively based on technical parameters such as rotation frequency, tool diameter, or the number of teeth. Because the human ear is a powerful feature extraction and classification device, this study investigates to what degree the hearing sensation influences the operators decision making. A steel machining process with a design of experiments (DOE)-based variation of process parameters was conducted on a milling machine. Microphone and acceleration sensors recorded machining vibrations and machine operators documented their hearing sensation via survey sheet. In order to obtain the optimal dataset for calculating various psychoacoustic characteristics, a principle component analysis was conducted. The subsequent correlation analysis of all sensor data and the operator information suggest that psychoacoustic characteristics such as tonality and loudness are very good indicators of the process quality perceived by the operator. The results support the application of psychoacoustic technology for machine and process monitoring.