Experimental and numerical evaluation of the dust suppression efficiency of an innovative vortex pneumatic fog screen dust control device.

To effectively control the dust generated by coal mining operations, a new type of cyclonic pneumatic mist curtain dust control device was developed. Using CFD software, numerical simulations were conducted on the internal airflow velocity field, the exit velocity of the cyclonic pneumatic mist curtain, and the mist droplet particle field of the curtain. Experiments were carried out to measure the spray coverage, droplet size, and the dust control performance of the model device. The results indicate that when the water pump supply pressure is 8 MPa, the fan supply wind speed is 12 m/s, and the nozzle installation angle is 75 degrees, the cyclonic pneumatic mist curtain dust control device model operates under optimal conditions. The effective coverage of the cyclonic mist curtain is 380 × 3300 mm, fully suppressing dust generation on one side of the curtain. An optimal dust removal distance of about 90 cm was determined. After installing the cyclonic pneumatic mist curtain dust control device, the average dust reduction efficiency for respirable dust reached 91.07%, and the overall dust reduction efficiency achieved 93.34%.

Same job, same working conditions? A cross-sectional study to examine the similarities and differences of the working situation in ambulatory and residential youth welfare workers.

BACKGROUND: Employees in social work exhibit high rates of sick leave due to mental health issues. Additionally, work-related demands in youth welfare have increased in recent years. Particularly in light of the escalating shortage of skilled professionals in this field, this trend becomes especially critical. The aim of this study is to systematically examine health-relevant working conditions, coping strategies, and health indicators in youth welfare. A special focus is placed on a differentiated analysis of job-related characteristics in the context of outpatient and residential youth welfare. METHODS: Mean values, standard deviations and the reliability of scales are measured. In addition to descriptive statistics, t-tests for analyzing mean differences, as well as correlation analyses and odds ratios as measures of association, are computed. RESULTS: A total of N = 1044 employees in youth welfare participated in the online survey. Among them, 671 individuals belonged to the field of residential youth welfare, and 373 to outpatient youth welfare. The results indicate that, in youth welfare in general, a variety of emotional, social, qualitative, and quantitative demands exhibit high levels. The comparison between outpatient and residential youth welfare reveals differences in half of the demands. The significant differences are observed for social demands and aggression from clients, which are statistically significant higher in the residential setting. Regarding resources, the most significant difference is observed for autonomy, which is higher in the outpatient setting. Overall, the association patterns reveals more similarities than differences between outpatient and residential settings. In both settings working conditions seem to have deteriorated during the pandemic. CONCLUSIONS: In conclusion, the identified job-related characteristics in outpatient and residential youth welfare exhibit more similarities than differences. Nevertheless, the identified differences provide insights into the specific features of each work context, offering valuable starting points for targeted health promotion in practice. TRIAL REGISTRATION: This trial is recorded at the Hamburg University Ethics Committee (AZ 2022_027).

Multisource working condition recognition via nonlinear kernel learning and p-Laplacian manifold learning.

Effectively utilizing information from multiple sources and fewer labeled operating condition samples from a sucker-rod pumping system for oil production can improve the recognition effects and engineering practicability. Nevertheless, this is a challenging energy environment scientific application research subject, and therefore, this study proposes an operating state recognition scheme that relies on multisource nonlinear kernel learning and p-Laplacian high-order manifold regularization logistic regress. Specifically, three measured features are selected and extracted, i.e., wellhead temperature signal, electrical power signal, and ground dynamometer cards, based on mechanism analysis, expert experience, and prior knowledge. Finally, we establish the operating condition recognition model to recognize by the multisource p-Laplacian regularization kernel logistic regress algorithm. The experimental data are derived from 60 wells of a common high-pressure and low-permeability thin oil reservoir block of an oil field in China. The corresponding trials highlight that our scheme outperforms traditional recognition methods by exploiting single-source and multiple-feature data. In the context of fewer labeled samples, the proposed method has a greater recognition effect, engineering practicability, and better model robustness than the existing schemes based on other high-order manifold learning, verifying our method's effectiveness.

Transfer Prediction Method of Bearing Remaining Useful Life Based on Deep Feature Evaluation under Different Working Conditions.

In the existing bearing remaining useful life (RUL)-prediction model based on deep learning, the advantages and disadvantages of the extracted features are evaluated by the prediction accuracy; thus, the analytical ability of the features is poor. At the same time, the change of working conditions has a great influence on prediction accuracy. To overcome these limitations, a prediction method of bearing RUL based on feature evaluation and deep transfer learning is proposed. The proposed model can solve the above problems: (1) a method of feature evaluation and selection for bearing life prediction based on trend consistency index was designed. (2) In this study, a domain adversarial transfer model based on feature condition mapping is proposed to overcome the second limitation. Experimental results show that this method is superior to the existing bearing evaluation and prediction methods.

Differences in the Effects of Work Environment on Health Problems and Satisfaction of Working Condition by Gender: The 6th Korean Working Conditions Survey.

This study investigated gender differences in exposure to hazardous factors, health problems, and work environment satisfaction and identified the effects of such differences on farmworkers in Korea. Through the 6th Korean Working Conditions Survey (KWCS) conducted by the Occupational Safety and Health Research Institute (OSHRI), the raw data on 2347 farmworkers were analyzed to present descriptive statistics for demographic characteristics, exposure to hazardous factors, health problems, and work environment satisfaction. We compared genders using chi-squared tests and investigated the effects of gender-specific working conditions on work-related health problems and work environment satisfaction using multivariate logistic analysis. The results were presented as an odds ratio (OR) with 95% confidence interval. Job position predicted work-related health problems in male farmworkers and work environment satisfaction in female farmworkers. Furthermore, female farmworkers perceived themselves to have more health problems than male farmworkers. Nevertheless, female farmworkers received less health and safety information and had lower work environment satisfaction compared to male farmworkers. The findings may improve the occupational welfare of farmworkers through continuous enhancement of the agricultural labor environment.

A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions.

The diagnosis of bearing faults is an important guarantee for the healthy operation of mechanical equipment. Due to the time-varying working conditions of mechanical equipment, it is necessary to achieve bearing fault diagnosis under time-varying working conditions. However, the superposition of the two-dimensional working conditions of speed and acceleration brings great difficulties to diagnosis via data-driven models. The long short-term memory (LSTM) model based on the infinitesimal method is an effective method to solve this problem, but its performance still has certain limitations. On this basis, this article proposes a model for fault diagnosis under time-varying operating conditions that combines a residual network model (ResNet) and a gate recurrent unit (model) (GRU). Firstly, the samples were segmented, and feature extraction was performed using ResNet. We then used GRU to process the information. Finally, the classification results were output through the output network. This model could ignore the influence of acceleration and achieve high fault diagnosis accuracy under time-varying working conditions. In addition, we used t-SNE to reduce the dimensionality of the features and analyzed the role of each layer in the model. Experiments showed that this method had a better performance compared with existing bearing fault diagnosis methods.

Metric Learning-Guided Semi-Supervised Path-Interaction Fault Diagnosis Method for Extremely Limited Labeled Samples under Variable Working Conditions.

The lack of labeled data and variable working conditions brings challenges to the application of intelligent fault diagnosis. Given this, extracting labeled information and learning distribution-invariant representation provides a feasible and promising way. Enlightened by metric learning and semi-supervised architecture, a triplet-guided path-interaction ladder network (Tri-CLAN) is proposed based on the aspects of algorithm structure and feature space. An encoder-decoder structure with path interaction is built to utilize the unlabeled data with fewer parameters, and the network structure is simplified by CNN and an element additive combination activation function. Metric learning is introduced to the feature space of the established algorithm structure, which enables the mining of hard samples from extremely limited labeled data and the learning of working condition-independent representations. The generalization and applicability of Tri-CLAN are proved by experiments, and the contribution of the algorithm structure and the metric learning in the feature space are discussed.

A Multiscale Recursive Attention Gate Federation Method for Multiple Working Conditions Fault Diagnosis.

Federated learning (FL) is an effective method when a single client cannot provide enough samples for multiple condition fault diagnosis of bearings since it can combine the information provided by multiple clients. However, some of the client's working conditions are different; for example, different clients are in different stages of the whole life cycle, and different clients have different loads. At this point, the status of each client is not equal, and the traditional FL approach will lead to some clients' useful information being ignored. The purpose of this paper is to investigate a multiscale recursive FL framework that makes the server more focused on the useful information provided by the clients to ensure the effectiveness of FL. The proposed FL method can build reliable multiple working condition fault diagnosis models due to the increased focus on useful information in the FL process and the full utilization of server information through local multiscale feature fusion. The validity of the proposed method was verified with the Case Western Reserve University benchmark dataset. With less local client training data and complex fault types, the proposed method improves the accuracy of fault diagnosis by 23.21% over the existing FL fault diagnosis.

Benefits of Working from Home During the COVID-19 Pandemic for Undiagnosed Workers with Attention-Deficit/Hyperactivity Disorder Symptoms.

Purpose: Our previous study suggested that working conditions might impact work productivity amid the COVID-19 pandemic. This study aimed to investigate the association between working from home (WFH) and depressive symptoms, work productivity, and quality of life (QOL), in undiagnosed workers with attention-deficit/hyperactivity disorder (ADHD) symptoms during the COVID-19 pandemic. Methods: During the pandemic, the survey was conducted among eligible workers with (N = 904) and without (N = 900) ADHD symptoms based on the Adult ADHD Self-Report Scale [ASRS]. Each group was further stratified by working conditions (full working on-site [FWOS], hybrid, full WFH [FWFH]). Two-way ANOVA was performed to investigate the impact of WFH on depressive symptoms (Patient Health Questionnaire [PHQ-9] score), work productivity (Work Productivity and Activity Impairment scale [WPAI] scores), and QOL (EuroQol 5-Dimensions 5-Levels [EQ-5D-5L] score). The Tukey-Kramer test was used to assess differences between the stratified subgroups. Poisson and multiple regression analyses were also performed to assess the factors associated with these outcomes. Results: Other than PHQ-9 score between FWOS and hybrid work in workers with ADHD symptoms (p < 0.05), no significant differences were observed in outcomes among the working condition subgroups in both workers with and without ADHD symptoms. In workers with ADHD symptoms, hybrid work and FWFH were significantly associated with a lower PHQ-9 score (hybrid, p < 0.001; FWFH, p < 0.05) but neither were significantly associated with WPAI score nor EQ-5D-5L. Annual income and discretionary work were significantly associated with a lower PHQ-9 score and a higher EQ-5D-5L score in workers with ADHD symptoms. Job type (manufacture/construction) was significantly associated with a lower presenteeism score. Conclusion: WFH (hybrid and FWFH) may be associated with lower depressive symptoms compared with FWOS in undiagnosed workers with ADHD symptoms. The findings may be useful when considering suitable working environments for workers especially with ADHD symptoms.

Employment conditions and leisure-time physical activity among korean workers: a longitudinal study (2009-2019).

BACKGROUND: Employment conditions may affect individuals' leisure-time physical activity (LTPA). We aimed to examine the relationship between changes in working and employment conditions and LTPA among working-age populations in South Korea from 2009 to 2019. METHODS: A cohort of 6,553 men and 5,124 women aged 19-64 years was analyzed using linear individual-level fixed-effects regressions to examine changes in working and employment conditions with changes in LTPA. RESULTS: Reduced working hours, labor union membership, and part-time work were associated with increased LTPA for both sexes. Manual labor and self-reported precarious work were associated with reduced LTPA. The longitudinal relationship between employment conditions and LTPA was clear in men, but less apparent in women. CONCLUSIONS: Changes in working and employment conditions had longitudinal associations with changes in LTPA among working-age Koreans. Future research should examine changing employment conditions and their effect on LTPA, particularly among women and manual/precarious workers. These results could inform effective planning and interventions to increase LTPA.

Assessment of selected psychosocial risk factors: stress, job burnout, and bullying in the case of medical staff as part of workplace ergonomics during the COVID-19 pandemic-A prospective pilot study.

Background: The purpose of the pilot study conducted by the authors was to assess occupational risk in selected areas of psychosocial risk factors among health professions in a pilot study. Medical staff working in the healthcare sector experience stress, job burnout and bullying on a daily basis. Monitoring occupational risks in the above areas provides an opportunity to take appropriate preventive measures. Methods: The prospective online survey included 143 health care workers from various professional groups. Eighteen participants did not complete the survey, and the results of 125 participants were eventually included in the analysis. The study used health and safety questionnaires in the healthcare sector, which are not widely used as screening tools in Poland. Results: The following statistical methods were performed in the study: the Mann-Whitney test, Kruskal-Wallis test, Dunn's test. In addition, multivariate analysis was performed. The results obtained in the study indicate that the questionnaires used in the study can be widely used by employers or occupational medicine as screening tools. Conclusions: Our findings show that level of education attainment in healthcare is correlated with higher chance of experiencing stress and burnout. Among the surveyed professions, nurses reported a higher amount of stress and burnout. Paramedics reported the highest chance of being bullied at work. This can be explained by their nature of work which requires directly interacting with patients and their families. In addition, it should be noted that the tools used can be successfully applied in workplaces as elements of workplace ergonomics assessment in the context of cognitive ergonomics.

Factors related to a successful professional development for specialist nurses in surgical care: a cross-sectional study.

BACKGROUND: A high level of competence among staff is necessary for providing patient-safe surgical care. Knowledge regarding what factors contribute to the professional development of specialist nurses in surgical care and why they choose to remain in the workplace despite high work requirements is needed. To investigate and describe the organizational and social work environment of specialist nurses in surgical care as part of studying factors that impact on professional development. METHOD: This was a cross-sectional study with a strategic convenience sampling procedure that recruited 73 specialist nurses in surgical care in Sweden between October to December 2021. The study was guided by STROBE Statement and checklist of cross-sectional studies. The validated Copenhagen Psychosocial Questionnaire was used, and additional demographic data. Descriptive statistics were performed and the comparison to the population benchmarks was presented as the mean with a 95% confidence interval. To study potential differences among the demographic and professional characteristics, pairwise t tests were used with Bonferroni adjustment for multiple comparisons with a significance level of 5%. RESULTS: Five domains were identified as factors related to success, as they received higher scores in relation to population benchmarks: quality of leadership, variation of work, meaning of work and work engagement as well as job insecurity. There was also a significant association between a having a manager with low nursing education and job insecurity (p = 0.021). CONCLUSIONS: Quality of leadership is important for the professional development of specialist nurses in surgical care. Strategic work seems to include managers with a higher nursing education level to prevent insecure professional working conditions.

Current career situations of Chinese pharmacovigilance professionals working for pharmaceutical companies: an exploratory survey.

BACKGROUND: Pharmacovigilance in China has experienced rapid development in the past 30 years. The implementation of Good Pharmacovigilance Practice in China since the end of 2021 heralds a new era of pharmacovigilance affairs, which puts forward higher requirements for the quantity and quality of pharmacovigilance personnel. This study aimed to preliminarily explore the current career situations of pharmacovigilance professionals working in China for pharmaceutical companies. METHODS: A questionnaire was adapted from research in the USA and Europe with the help of several pharmacovigilance experts. Snowball sampling was used to conduct an exploratory survey to obtain the frequency of basic demographic information, work status, and career expectations of pharmacovigilance professionals working for pharmaceutical companies. RESULTS: The personnel engaged in pharmacovigilance work for pharmaceutical companies were mainly medical or pharmaceutical undergraduates within 3 years of graduation. Their work intensity and pressure were relatively high. The training provided by their universities and enterprises could not well meet their needs to improve their job competence. Although they were optimistic about pharmacovigilance and will not change their career, most of them were planning to change their employers. CONCLUSION: There was a gap between the demand and supply of pharmacovigilance personnel. Relevant regulatory authorities and industry associations should guide higher education institutions to collaborate with pharmacovigilance specialists to strengthen pharmacovigilance education for medical or pharmaceutical students, on the basis of which pharmacovigilance certification courses and continuing education courses can be developed. Meanwhile, pharmaceutical enterprises should consider reasonably adjusting work intensity and income to avoid a high turnover rate.

Vocal Health, Working Conditions and Their Implications on the Occupational Health of Telemarketers: An Integrative Review.

OBJECTIVE: To analyze the national and international literature on vocal health, working conditions and occupational health of telemarketers. METHODS: A literature review was conducted using the LILACS, PubMed and SciELO databases. The term "telemarketing" was used for all searches, along with the following descriptors: voice, vocal disorders, work condition and occupational health. Articles published in English, Portuguese or Spanish from 2009- 2019 were included. The variables selected for organizing the data were authors, region, first author's education, affiliation, journal, objective, sample, design, and result. RESULTS: A total of 540 publications were identified in the databases, and after applying the eligibility criteria, 14 articles were included in the final analysis. DISCUSSION: Of the articles selected for final analysis, there was a concentration of studies in 2014, with a new peak of resumption of research in 2019. Regarding Brazilian studies, there was a concentration of studies from the Southeast region, mostly developed by speech therapists. CONCLUSION: In the analyzed articles, it was possible to verify the interference of telemarketers' working conditions in their vocal and occupational health.

Magnitude da qualidade de vida relacionada ao trabalho entre profissionais atuantes em unidades de urgência e emergência / Magnitude of work-related quality of life among professionals working in urgency and emergency units / Magnitud de la calidad de vida relacionada con el trabajo entre profesionales que trabajan en unidades de urgencia y emergencia

O objetivo deste estudo foi investigar a qualidade de vida dos profissionais de saúde nas emergências no município de Vitoria de Santo Antão ­ PE. Trata-se de um estudo transversal, descritivo com abordagem quantitativa do tipo survey. Foi realizado com 70 profissionais de saúde (médicos, enfermeiros e técnicos de enfermagem), aplicando os questionários: epidemiológico direcionado ao trabalho, QAFH (questionário de atividade física habitual) e QWLQ-bref (Quality of Working Life Questionnaire ­ Bref). Na análise foram empregadas técnicas estatísticas descritivas e multivariadas. A prevalência de 21,4% (IC95%: 13,4 ­ 32,4) de profissionais não satisfeitos com a qualidade de vida no trabalho. As medianas nos domínios pessoal, profissional e QVT total do QWLQ-bref foram mais elevadas entre os médicos (p < 0,05). O alto índice de funcionários não satisfeitos no emprego impõe a adoção de estratégias visando à melhoria na qualidade de vida e no trabalho.

The objective of this study was to investigate the quality of life of health professionals in emergencies in the city of Vitoria de Santo Antão - PE. This is a cross- sectional, descriptive study with a quantitative approach of the survey type. It was carried out with 70 health professionals (doctors, nurses and nursing technicians), applying the questionnaires: epidemiological work-oriented, QAFH (habitual physical activity questionnaire) and QWLQ-bref (Quality of Working Life Questionnaire ­ Bref). In the analysis, descriptive and multivariate statistical techniques were used. The prevalence of 21.4% (95%CI: 13.4 ­ 32.4) of professionals not satisfied with the quality of life at work. The medians in the personal, professional and total QWL domains of the QWLQ-bref were higher among physicians (p < 0.05). The high rate of dissatisfied employees at work requires the adoption of strategies aimed at improving quality of life and work.

El objetivo de este estudio fue investigar la calidad de vida de los profesionales de la salud en emergencias en la ciudad de Vitoria de Santo Antão - PE. Se trata de un estudio descriptivo transversal con enfoque cuantitativo del tipo survey. Se realizó con 70 profesionales de la salud (médicos, enfermeros y técnicos de enfermería), aplicándose los cuestionarios: epidemiológico orientado al trabajo, QAFH (cuestionario de actividad física habitual) y QWLQ-bref (Cuestionario de Calidad de Vida Laboral ­ Bref). En el análisis se utilizaron técnicas estadísticas descriptivas y multivariadas. Prevalencia del 21,4% (IC95%: 13,4 ­ 32,4) de profesionales insatisfechos con la calidad de vida en el trabajo. Las medianas en los dominios de CVL personal, profesional y total del QWLQ-bref fueron mayores entre los médicos (p < 0,05). El alto índice de empleados insatisfechos en el trabajo exige la adopción de estrategias encaminadas a mejorar la calidad de vida y de trabajo.

Working Condition and Job Satisfaction of Nurses as Predicting Factors of the Prevalence of Health care-associated Infections among Elderly Inpatients.

Background: Health care-Associated Infections (HCAIs) are among the most common adverse events (AEs) that can negatively affect both patients and health systems. The elderly is among patients at high risk for infections. Some controllable risk factors have received less attention in research. Therefore, this study aims to investigate the relationship between prevalence of HCAIs among elderly inpatients, job satisfaction of nurses, and working condition. Materials and Methods: This cross-sectional study was conducted on 211 nurses working in hospitals affiliated with Iran University of Medical Sciences, Tehran, in 2021. The data were collected from HCAIs reports by the Nosocomial Infection Control Committee, a demographic questionnaire, the Practice Environment Scale of the Nursing Work Index (PES-NWI), and the Minnesota Satisfaction Questionnaire (MSQ). The data were statistically analyzed using Pearson correlation coefficient, ANOVA, t-test, and multiple linear regression (MLR) in SPSS 26. Results: The results showed that there was a significant relationship between the PES-NWI and MSQ (r = 0.68, p < 0.00). The MLR results indicated that staffing and resource adequacy, nurse participation in hospital affairs, job satisfaction, nursing manager's leadership, and nursing foundations for quality of care are predictive factors that these could explain 78% of the changes in the prevalence of HCAIs and the goodness of fit of the regression model was acceptable [F6.210 = 129.47, p < 0.001]. Conclusions: Since job satisfaction and the work condition could predict HCAIs among the elderly patients, healthcare administers are recommended to consider these two variables in the development of HCAIs prevention and control programs.

[Questionnaire Survey of Japanese Medical Physicists on Working Conditions in 2020].

The questionnaire survey was conducted in 2020 to investigate the working conditions of qualified medical physicists in Japan. We developed a web-based system for administering the questionnaire and surveyed 1,228 qualified medical physicists. The number of received responses was 405. We summarized the results of the survey by job category. The obtained results showed that most of the people working as certified medical physicists met the following conditions: (1) position of healthcare occupation, (2) direct supervisor is a medical doctor or a medical physicist, (3) licensed or passed an examination for a Class I Radiation Protection Supervisor, (4) without the license of professional radiotherapy technologist, (5) master's or doctor's degree, (6) being assigned to the section that is different from the radiological technologist section. The average annual salary was approximately 600,000 yen higher for those employed as medical physicists than for those employed as radiotherapy technologists. The percentage of work performed by a certified medical physicist in radiation therapy greatly varies depending on whether the physicist is dedicated to treatment planning and equipment quality control. Alternatively, the proportion of the true duties of medical physicists in charge of radiation therapy, as considered by qualified medical physicists in radiation therapy, was the same regardless of whether they were working full-time or not. The results of this survey updated the working status of certified medical physicists in Japan. We will continue to conduct the survey periodically and update the information to contribute to the improvement of the working conditions of medical physicists and policy recommendations.

Workplace Mistreatment and Health Conditions Prior and during the COVID-19 in South Korea: A Cross-Sectional Study.

BACKGROUND: This study examined the relationship between workplace mistreatment, including discrimination, abuse, and overworking, and health problems among full-time workers prior to and during the coronavirus disease (COVID-19) outbreak in South Korea. METHODS: We analyzed data from the 2017 and 2020-2021 Korean Working Conditions Surveys, including the final sample of 44,425 participants. Multiple logistic regression was used to examine the relationship between workplace mistreatment and health problems among workers by gender. Interaction analysis was conducted to establish the association between the COVID-19 pandemic and health problems related to mistreatment. The occupational, demographic, and socioeconomic backgrounds were adjusted. RESULTS: We found a significant association between workplace mistreatment and health problems, including headaches, eyestrain, and anxiety. The association increased after the COVID-19 pandemic: "discrimination" (men (OR 2.26, 95% CI 1.93-2.65), women (OR 2.73, 95% CI 2.36-3.17)); abuse (men (OR 5.42, 95% CI 2.87-10.23), women (OR 4.70, 95% CI 3.12-7.08)); and overworking: men (OR 2.36, 95% CI 2.01-2.77), women (OR 3.52, 95% CI 2.68-4.61). The interaction indicates an increased incidence of people having health problems due to workplace mistreatment (OR 1.03, 95% CI 1.00-1.06) during the COVID-19 pandemic. CONCLUSION: Statistically, employees who experience workplace mistreatment have worse health conditions. The COVID-19 pandemic has affected the job environment and increased the association between workplace mistreatment and health problems. To eliminate the health problems related to workplace mistreatment, it is necessary to address the impact of the COVID-19 pandemic on work and employee health conditions.

Working Condition Recognition Based on Transfer Learning and Attention Mechanism for a Rotary Kiln.

It is difficult to identify the working conditions of the rotary kilns due to the harsh environment in the kilns. The flame images of the firing zone in the kilns contain a lot of working condition information, but the flame image data sample size is too small to be used to fully extract the key features. In order to solve this problem, a method combining transfer learning and attention mechanism is proposed to extract key features of flame images, in which the deep residual network is used as the backbone network, the coordinate attention module is introduced to capture the position information and channel information on the branch of feature graphs, and the features of flame images obtained are further screened to improve the extraction ability. At the same time, migration learning is performed by the pre-trained ImageNet data set, and feature migration and parameter sharing are realized to cope with the training difficulty of a small sample data size. Moreover, an activation function Mish is introduced to reduce the loss of effective information. The experimental results show that, compared with traditional methods, the working condition recognition accuracy of rotary kilns is improved by about 5% with the proposed method.

Aeroengine Working Condition Recognition Based on MsCNN-BiLSTM.

Aeroengine working condition recognition is a pivotal step in engine fault diagnosis. Currently, most research on aeroengine condition recognition focuses on the stable condition. To identify the aeroengine working conditions including transition conditions and better achieve the fault diagnosis of engines, a recognition method based on the combination of multi-scale convolutional neural networks (MsCNNs) and bidirectional long short-term memory neural networks (BiLSTM) is proposed. Firstly, the MsCNN is used to extract the multi-scale features from the flight data. Subsequently, the spatial and channel weights are corrected using the weight adaptive correction module. Then, the BiLSTM is used to extract the temporal dependencies in the data. The Focal Loss is used as the loss function to improve the recognition ability of the model for confusable samples. L2 regularization and DropOut strategies are employed to prevent overfitting. Finally, the established model is used to identify the working conditions of an engine sortie, and the recognition results of different models are compared. The overall recognition accuracy of the proposed model reaches over 97%, and the recognition accuracy of transition conditions reaches 94%. The results show that the method based on MsCNN-BiLSTM can effectively identify the aeroengine working conditions including transition conditions accurately.