Self-diagnosis Method Research Articles

Sensor self-diagnosis method for a nickel top-blowing furnace based on graph interactive dynamic fusion

Abstract As modern industry gradually advances towards greater automation and intelligence, the scale of nickel top-blowing furnace smelting systems is continuously expanding, leading to an increasing need for sensor maintenance. Traditional periodic evaluations and manual maintenance methods are no longer sufficient to meet the development needs of intelligent sensors. To address this issue, this paper proposes a sensor self-diagnosis method based on graph interactive dynamic fusion, called DLGCN-GIDF. First, a combination of knowledge-driven and data-driven approaches is introduced. By constructing a dual-layer architecture based on a functional module graph network and a sensor graph network, a sensor correlation graph model for the nickel top-blowing furnace system is established. Next, with the aid of a GIDF module, the relative weights between functional modules and sensors are integrated to perform spatiotemporal correlation-based graph fusion. This enables the prediction of spatiotemporal data for sensors from a system perspective. Finally, the goal of sensor self-diagnosis is achieved using a standardised residual testing algorithm. Taking a nickel top-blowing furnace smelting system as an example, the feasibility and effectiveness of our method of sensor fault self-diagnosis are verified.

Research and application of self-diagnosis and automatic intervention functions for turbine regulating valve malfunctions in nuclear power plants

Abstract The inlet regulating valve of the turbine is very important to the control of the turbine. If the control is abnormal, it will create some uncontrollable safety risks, which may cause the turbine to trip, even to over-speed. The study of the structure and control mode of the turbine regulating valve shows some defects in the design of the turbine regulating valve in a nuclear power plant. In this paper, through the analysis of the fault mode, the method of fault self-diagnosis is studied, verified, and improved so that it has perfect self-diagnosis and intervention means, improves the reliability of turbine valve control, and eliminates the hidden danger of tripping.

SST: a snore shifted-window transformer method for potential obstructive sleep apnea patient diagnosis

Objective. Obstructive sleep apnea (OSA) is a high-incidence disease that is seriously harmful and potentially dangerous. The objective of this study was to develop a noncontact sleep audio signal-based method for diagnosing potential OSA patients, aiming to provide a more convenient diagnostic approach compared to the traditional polysomnography (PSG) testing. Approach. The study employed a shifted window transformer model to detect snoring audio signals from whole-night sleep audio. First, a snoring detection model was trained on large-scale audio datasets. Subsequently, the deep feature statistical metrics of the detected snore audio were used to train a random forest classifier for OSA patient diagnosis. Main results. Using a self-collected dataset of 305 potential OSA patients, the proposed snore shifted-window transformer method (SST) achieved an accuracy of 85.9%, a sensitivity of 85.3%, and a precision of 85.6% in OSA patient classification. These values surpassed the state-of-the-art method by 9.7%, 10.7%, and 7.9%, respectively. Significance. The experimental results demonstrated that SST significantly improved the noncontact audio-based OSA diagnosis performance. The study’s findings suggest a promising self-diagnosis method for potential OSA patients, potentially reducing the need for invasive and inconvenient diagnostic procedures.

Sensor self-diagnosis method based on a graph neural network

Many types of sensors are used in industrial processes, and their reliability is high. However, the traditional method of regularly detecting and evaluating their health status is time-consuming and laborious, and is not suitable for the development of intelligent sensors. In this work, the relative entropy method is first used to quantitatively evaluate the redundancy relationship between sensors, and a sensor graph network is established based on this relationship. Secondly, an unsupervised multi-sensor self-diagnosis model, called attention-based pruning graph convolutional network, is proposed. In order to capture the strong redundancy among sensors by the attention mechanism, multi-sensor timing prediction is realised using a graph convolutional neural network, and the health status of each sensor can be independently judged by the changes in redundancy among the sensors. Finally, a temperature measurement system in a nickel flash furnace is considered as a case study to verify the feasibility and effectiveness of the proposed method.

Spoofing Attack Detection Method for UAV Navigation System

An implementation of methods for protecting unmanned aerial vehicles (UAVs) from spoofing attacks of the global positioning system (GPS) to ensure safe navigation is discussed in this paper. The Global Navigation Satellite System (GNSS) is widely used to locate UAVs and is by far the most popular navigation solution. This is due to the simplicity and relatively low cost of this technology, as well as the accuracy of the transmitted coordinates. However, there are many security threats to GPS navigation. Primarily this is due to the nature of the GPS signal, the signal is transmitted in the clear, so an attacker can block or tamper with it. This study analyzes the existing GPS protection methods. As part of the study, an experimental stand and scenarios of attacks on the UAV GPS system were developed. Data from the UAV flight logbook was collected and an analysis of cyber-physical parameters was carried out to see an effect of the attack on the on-board sensors readings. Based on this, a new method for detecting UAV anomalies was proposed, based on an analysis of changes in UAV internal parameters. This self-diagnosis method allows the UAV to independently assess the presence of changes in its subsystems and identify signs of a cyberattack. To detect an attack, the UAV collects data on changes in cyber-physical parameters over a certain period of time, then updates this data. As a result it is necessary for the UAV to determine the degree of difference between the two time series of the collected data. The greater the degree of difference between the updated data and the previous ones, the more likely the UAV is under attack.

Insights on the environmental management system of the European port sector

This research focusses on assessing the environmental performance of European Ports based on a wide representation of EcoPorts members. The data is extracted from the Self-Diagnosis Method (SDM), a concise checklist against which port managers can self-assess the environmental management of their port in relation to the performance of the EcoPorts membership. A total number of 97 ports from 18 different European Maritime States contributed to this evaluation. They have answered questions related to the main components of internationally recognized Environmental Management System (EMS) standards. Similar periodic assessments have been carried out since 2013, allowing for the identification of benchmark performance. The geographical representation and characteristics of the participating ports are given along with the perceived ranking of priority environmental issues based on regular reviews. Air quality has been the top environmental priority for many years, followed by climate change, which has risen rapidly to the second position. Most of the ports have an environmental policy in place (96%) and a compilation of an inventory of significant environmental aspects (92%). Transparency is also very important to ports, with 91% of ports communicating their environmental policy to stakeholders, and 86% of ports making it publicly available on their website.Around 80% of ports have set up an environmental monitoring program, with port waste being the most monitored issue.With regard to services to shipping, more than half of the responding ports are offering on shore power supply (OPS), and one third of them have made LNG bunkering available. In parallel, an increasing number of ports compared with previous exercises (57%) provide differentiated dues for ships that go beyond regulatory standards, with air emissions, waste and climate change being the main target of these discounts. In general, trends over the years have shown a clear improvement of the environmental port performance.

Self-Detection and Self-Diagnosis Methods for Sensors in Intelligent Integrated Sensing System

Intelligent integrated sensing systems possess capabilities such as perceiving external information, data processing. It has a wide range of applications in Internet of Things (IOT), smart manufacturing, and other fields. However, if the information is acquired incorrectly, it will definitely affect the correctness of data processing. Though there have been many researches about sensor data processing, only a few focused on how to self-detect and self-diagnosis the working status of the sensors themselves. Based on the above, this paper proposes to evaluate the accuracy and reliability of sensor output by predicting the sensor’s real-time output with multi-sensor fusion. The proposed system can perform self-diagnosis to find out the cause or type of the error when failure occurs. Furthermore, this system can also perform real-time fault-tolerant conveniently. Experimental results show that this method has high recognition accuracy with small amount of calculation complexity. The intelligent integrated sensing system can be more reliable with the proposed self-diagnosis technologies for the smart sensors.

A Study on Self-Diagnosis Method to Prevent the Spread of COVID-19 Based on SVM

In this paper, a study was conducted to find a self-diagnosis method to prevent the spread of COVID-19 based on machine learning. COVID-19 is an infectious disease caused by a newly discovered coronavirus. According to WHO(World Health Organization)’s situation report published on May 18th, 2020, COVID-19 has already affected 4,600,000 cases and 310,000 deaths globally and still increasing. The most severe problem of COVID-19 virus is that it spreads primarily through droplets of saliva or discharge from the nose when an infected person coughs or sneezes, which occurs in everyday life. And also, at this time, there are no specific vaccines or treatments for COVID-19.Because of the secure diffusion method and the absence of a vaccine, it is essential to self-diagnose or do a self-diagnosis questionnaire whenever possible. But self-diagnosing has too many questions, and ambiguous standards also take time. Therefore, in this study, using SVM(Support Vector Machine), Decision Tree and correlation analysis found two vital factors to predict the infection of the COVID-19 virus with an accuracy of 80%. Applying the result proposed in this paper, people can self-diagnose quickly to prevent COVID-19 and further prevent the spread of COVID-19.

A Self-Diagnosis Method for Detecting UAV Cyber Attacks Based on Analysis of Parameter Changes.

We consider how to protect Unmanned Aerial Vehicles (UAVs) from Global Positioning System (GPS) spoofing attacks to provide safe navigation. The Global Navigation Satellite System (GNSS) is widely used for locating drones and is by far the most popular navigation solution. This is because of the simplicity and relatively low cost of this technology, as well as the accuracy of the transmitted coordinates. Nevertheless, there are many security threats to GPS navigation. These are primarily related to the nature of the GPS signal, as an intruder can jam and spoof the GPS signal. We discuss methods of protection against this type of attack and have developed an experimental stand and conducted scenarios of attacks on a drone’s GPS system. Data from the UAV’s flight log were collected and analyzed in order to see the attack’s impact on sensor readings. From this we identify a new method for detecting UAV anomalies by analyzing changes in internal parameters of the UAV. This self-diagnosis method allows a UAV to independently assess the presence of changes in its own subsystems indicative of cyber attacks.

Performance trends of environmental management in European ports

This paper presents the current status and trends over time in the environmental situation of European ports, based on the results of a wide representation of EcoPorts members (90 ports). All the information presented in this research comes from the Self-Diagnosis Method (SDM), a concise checklist managed by European Sea Ports Organisation (ESPO), against which ports can self-assess their environmental management. The results provide data on a total number of 54 indicators, being the existence of an inventory of environmental legislation the indicator with the highest implementation (96,7%), followed by the existence of an environmental policy (95,7%). Waste is the environmental issue that is being more monitored by ports. Air quality continues as the top environmental priority, followed by energy consumption and noise. It is interesting to highlight the growing awareness of Climate change among ports as well as the increasing implementation of green initiatives in ports.

A Study on Methods to Prevent the Spread of COVID-19 Based on Machine Learning

In this paper, a study was conducted to find a self-diagnosis method to prevent the spread of COVID-19 based on machine learning. COVID-19 is an infectious disease caused by a newly discovered coronavirus. According to WHO(World Health Organization)'s situation report published on May 18th, 2020, COVID-19 has already affected 4,600,000 cases and 310,000 deaths globally and still increasing. The most severe problem of COVID-19 virus is that it spreads primarily through droplets of saliva or discharge from the nose when an infected person coughs or sneezes, which occurs in everyday life. And also, at this time, there are no specific vaccines or treatments for COVID-19. Because of the secure diffusion method and the absence of a vaccine, it is essential to self-diagnose or do a self-diagnosis questionnaire whenever possible. But self-diagnosing has too many questions, and ambiguous standards also take time. Therefore, in this study, using SVM(Support Vector Machine), Decision Tree and correlation analysis found two vital factors to predict the infection of the COVID-19 virus with an accuracy of 80%. Applying the result proposed in this paper, people can self-diagnose quickly to prevent COVID-19 and further prevent the spread of COVID-19.

Covid-19 Diagnosis by Artificial Intelligence Based on Vibraimage Measurement of Behavioral Parameters

The hypothesis of behavioral parameters dependence measured from person’s head movements in quasi-stationary state on COVID-19 disease is discussed. Method for determining the dependence of vestibular-emotional reflex parameters on COVID-19, various diseases and pathologies are proposed. Micro-movements of a head for representatives of the control group (with a confirmed absence of COVID-19 disease) and a group of patients with a confirmed diagnosis of COVID-19 were studied using vibraimage technology. Parameters and criteria for the diagnosis of COVID-19 for training artificial intelligence (AI) on the control group and the patient group are proposed. 3-layer (one hidden layer) feedforward neural network (40 + 20 + 1 sigmoid neurons) was developed for AI training. AI was firstly trained on the primary sample of patients and a control group. Study of a random sample of people with trained AI was carried out and the possibility of detecting COVID-19 using the proposed method was proved a week before the onset of clinical symptoms of the disease. Number of COVID-19 diagnostic parameters was increased to 26 and AI was trained on a sample of 536 measurements, 268 patient measurement results and 268 measurement results in the control group. The achieved diagnostic accuracy was more than 99%, 4 errors per 536 measurements (2 false positive and 2 false negative), specificity 99.25% and sensitivity 99.25%. The issues of improving the accuracy and reliability of the proposed method for diagnosing COVID-19 are discussed. Further ways to improve the characteristics and applicability of the proposed method of diagnosis and self-diagnosis of COVID-19 are outlined.

Concepts of green port operations – one kind of self-diagnosis method to the port of Santos - Brazil

This paper aims to evaluate the sustainable performance within the concept of Green Port in the logistics operations. Through literature review about green port implementation in different ports worldwide, as well as the studies of various technologies and methods that aim to make the port environment more sustainable, this study will go through different levels, from the shipping loading and unloading, passing through all sectors and actors related to the movement of cargo inside the port, which may on the sustainable performance of the environment, to the inland transportation. The study focus on the reduction of emissions of pollutant gases such as sulfur oxides (Sox), oxides of nitrogen (NOx), atmospheric particulate matter (PM) and Carbon dioxide (CO2). The work addresses the possible innovations in the logistics operations inherent in the transportation, storage, and handling of goods, involving the analysis, types, and operations of the resources used in the port management of the largest port in Brazil, Port of Santos.

Steakholders’ diagnostic of oil and gas enterprises

The research was carried out to identify the main groups of stakeholders of NGC and their interests. It has been established that certain stakeholder groups are not limited to those that are grouped. These may include other interested parties, which are determined by the enterprise depending on the change in its activities. The need to identify groups of stakeholders and the study of their interests is explained by the fact that the interests of different groups have a different vector of direction and their ignorance can lead to conflict. It is proposed to analyze the stakeholders of NGCs by means of estimating the level of attraction of the stewards to the activity of the oil and gas company, is proposed to use the method of self-diagnostics of an enterprise that is easy to use. When evaluating each stakeholder, the oil and gas company sets "+" if the answer is positive and "-" if the answer is negative, which allows you to quickly acknowledge which components of the cooperation are executed at a high level and where it is necessary to make adjustments. The method of self-diagnosis of the level of attraction of stakeholders in the NDP activity allows to identify weaknesses in cooperation with stakeholders, but any cooperation should be effective for both parties. In the express assessment of the distinguished: mandatory and desirable. Observance of mandatory conditions is market, and such conditions are reduced to the availability of competitive advantages at the price, market opportunity to provide income for the enterprise and the principle of break-even activity. Compliance with the desired conditions ensures the possibility of generating profits from the company's activities on the market. Express-rating reflects the principle profitability of the local market for the oil and gas company in case of its release, or the absence of such profitability. To use the methodology for assessing the effectiveness of cooperation between stakeholders and oil and gas companies, it is expedient to use a group of experts, which will allow to conduct an express evaluation.

Integrated impedance and Lamb wave–based structural health monitoring strategy for long-term cycle-loaded composite structure

Impedance of a sensor is sensitivity to small structural damage which surrounds the sensor. Lamb wave propagation provides higher damage detection efficiency in the range of large area. Both methods have been widely developed for structural health monitoring. This article presents integrated impedance and Lamb wave–based structural health monitoring strategy for composite pressure vessels. The output of the presented structural health monitoring strategy includes distribution and classification of damage and health condition of sensor network under varying internal pressure loading environments. In the strategy, a novel damage index adjusting method for Lamb wave damage detection is developed based on the signal features of real and imaginary parts of the sensor impedance. First, the potential structural damage is pre-warned by monitoring the impedance variation of the piezoelectric transducer sensor network. Then, the health condition of sensor network under the working condition is assessed by impedance-based self-diagnosis method; subsequently, the Lamb wave damage index is adjusted based on the result of sensor self-diagnosis. Finally, on the basis of sensor self-diagnosis and damage index adjustment result, damage identification and classification are performed. Practical efficacy of the structural health monitoring approach is tested by the damage monitoring experiment on loaded composite structure.

Benchmark dynamics in the environmental performance of ports

This paper analyses the 2016 environmental benchmark performance of the port sector, based on a wide representation of EcoPorts members. This is the fifth time that this study has been conducted as an initiative of the European Sea Ports Organisation (ESPO). The data and results are derived from the Self-Diagnosis Method (SDM), a concise checklist against which port managers can self-assess the environmental management of their port in relation to the performance of the EcoPorts membership. The SDM tool was developed in the framework of the ECOPORTS project (2002–2005) and it is managed by ESPO. A total number of 91 ports from 20 different European Maritime States contributed to this evaluation. The main results are that air quality remains as the top environmental priority of the respondent ports, followed by energy consumption and noise.In terms of environmental management, the study confirms that key components are commonly implemented in the majority of European ports. 94% of contributing ports have a designated environmental manager, 92% own an environmental policy and 82% implement an environmental monitoring program. Waste is identified as the most monitored issue in ports (80%), followed by energy consumption (73%) and water quality (70%).

Research and Application of a Fault Self-Diagnosis Method for Roots Flowmeter Based on WSN Node

In order to diagnose whether the photoelectric encoder of Roots flow meter is working well in assuring the wireless sensor networks (WSN) work properly, this paper discusses the features of Roots flow meter and proposes an on-line fault self-diagnosis method. First, a flexible fault sensing circuit is designed as a state detection module on WSN node. Second, a fault self-diagnosis method is proposed. The fault diagnosis method is based on the vibration frequency of Roots flow meter. The failure is diagnosed by whether the relationship between the measurement of instantaneous flow and the vibration frequency is correct. Experiment results demonstrate the fault self-diagnosis method is suit to the application in WSN nodes and the WSN nodes have been successfully applied to the oil tank trucks.

UNIVERSITY CORPORATE CULTURE TRANSFORMATION: SOCIOLOGOCAL AND LINGUISTICS DIAGNOSIS METHODS

The purpose of the research article described the experience of sociological and linguistic studies of the National Research Tomsk State University corporate culture transformation during the 5-100 program (2013-2016) is to diagnose the current state and dynamics of the university corporate culture transformation, providing analytical support for changes. The novelty of the research is provided by using a complex of sociological and linguistic methods. This allows us to identify the value orientations and preferences of employees in relation to the current image of the university and its desired image, which are revealed by the results of a sociological survey and according to the content analysis of the discursive practices of the university. For the first time, qualitative-quantitative sociological methods were verified by phenomenological data obtained due to analyzing the corporate discourse of the university. The relevance of the study caused by the fact that the corporate culture of the university and the corporate discourse as the exponent of the ideology and organization of core values serve as a strategic management tool to guide the divisions of the university community on common goals, to strengthen the vision of a world-class university, to ensure loyalty of employees, students, university partners, to facilitate communication within the university environment. The sociological approach to the diagnosis of the configuration of TSU corporate culture used to relying on complex techniques: 1) self-diagnosis method «Metaphor» (by A. I. Prigozhin); 2) the construction of the frame structure of competing values based on the university staff survey «OCAI» (by K. Cameron and R. Quinn); 3) research of public opinion during the analytical data focus groups with representatives of the university community (supervisor: V. Kashpur, co-host - LA Dmitrieva, N. Gulius). The main objective was to identify the type of the dominant culture, its potential problem areas and gaps, as well as the dynamics of the changes under the influence of competing values. Changes in the organization language (2005-2016) were analyzed on the material on three groups of text documents: 1) documents regulating the TSU ethical rules and corporate culture norms - «Regulations on the corporate culture of Tomsk State University» (2005) and «Code of Ethics of the Tomsk State University» (2015); 2) Rector ‘treatment to the university community (2005-2016); 3) decoding of oral interviews with employees on the theme of the University changes (2014-2015). The analysis method included: 1) determination of the tokens number by the automatic processing of the analyzed texts by the program “Content analysis 1 Pro», 2) sample keywords of the corporate discourse and performance of their frequency; 3) formation of the ratings of keywords frequency in certain chronological and thematic groups of the analyzed texts 4) conceptual, semantic, contextual keyword analysis; 5) a comparative analysis of the composition and frequency of keywords in the text groups related to specific thematic groups and chronological periods; 6) changes in fixation; 7) interpretation. TSU diagnostics revealed a mixed picture: stretching between clan culture and the market. The University discourse translates values mostly of the clan culture, although management practices are focused on the strict implementation of “market” indicators of world-class university. It was identified the orientation to rigid implementation of the goals and the achievement of results planned by the top-managers, but in respect of staff the “human” strategy of maximum involvement of the staff and the minimum number of dismissals has been selected. Keyword analysis confirms this transformation vector: the elements of the high pathetic rhetoric focused on the enthusiasm of employees are disappeared, it was found the increasing modality of negation and duty; strengthening the opposition of “our” and «them». The axiological dominant picture of the world is shifting from progressive and positive, inspiring to work together - to the tense and antagonistic calling to mobilize in a situation of fierce competition, the polarization and the erosion of values. The required invariant of the dominant clan culture is the university’s corporate culture as a culture of cooperation, serving the people, education, science, real interaction between professors and students. In conclusion, practical recommendations for the control period of the organization transformation are offered.

Sherlock Is Around: Detecting Network Failures with Local Evidence Fusion

Traditional approaches for wireless sensor network diagnosis are mainly sink-based. They actively collect global evidences from sensor nodes to the sink so as to conduct centralized analysis at the powerful back-end. On the one hand, long distance proactive information retrieval incurs huge transmission overhead; On the other hand, due to the coupling effect between diagnosis component and the application itself, sink often fails to obtain complete and precise evidences from the network, especially for the problematic or critical parts. To avoid large overhead in evidence collection process, self-diagnosis injects fault inference modules into sensor nodes and let them make local decisions. Diagnosis results from single nodes, however, are generally inaccurate due to the narrow scope of system performances. Besides, existing self-diagnosis methods usually lead to inconsistent results from different inference processes. How to balance the workload among the sensor nodes in a diagnosis task is a critical issue. In this work, we present a new in-network diagnosis approach named Local-Diagnosis (LD2), which conducts the diagnosis process in a local area. LD2 achieves diagnosis decision through distributed evidence fusion operations. Each sensor node provides its own judgements and the evidences are fused within a local area based on the Dempster-Shafer theory, resulting in the consensus diagnosis report. We implement LD2 on TinyOS 2.1 and examine the performance on a 50 nodes indoor testbed.

Self-diagnosis method as an assessment tool for environmental management of Brazilian ports

This study aimed to provide an alternative approach for the use of a situational diagnosis to evaluate the environmental management systems of the main Brazilian ports. Through this diagnosis, both the enabling factors and barriers to the implementation of an effective environmental management system were identified. The study design was based on Self- Diagnosis Method (SDM) developed by EcoPorts, with the application of a survey on issues involving the various aspects of environmental management scenarios. The responses to the surveys were analyzed using the SWOT matrix in order to identify the strengths, opportunities, weaknesses and threats to the environmental management of the ports under study. Then, gap analysis was performed in order to determine the actions that should be taken for management to evolve from an unsatisfactory status to a desired status. Analysis of the questionnaires revealed a tendency of respondents to minimize the negative aspects of environmental management, and to emphasize the positive aspects. There was also an inconsistency between the responses to the questionnaire and the actions that have actually been taken by the port authorities. This disparity suggests that managers are not willing to confront their problems publicly. The results demonstrated that there is a need for an adoption of the conceptual pillars of Environmental Management in the management of Brazilian ports, as well as for the awareness among all stakeholders involved in the activities, from workers to senior management.