Search results

To improve the speed and precise of online monitoring and diagnosis for satellite using satellite telemetry data.Design/methodology/approach – In monitoring system, a fuzzy range which gives the probability of alarm for telemetry channels using fuzzy reasoning is outlined. A failure confidence factor is presented to modify the traditional real‐time diagnosis algorithm based on multisignal model to describe the relative failure possibility for suspected components. According to the modified real‐time diagnosis algorithm based on multisignal model, it rapidly generates the states for all the components of the system such as good, bad, suspected and unknown. Then the failure probability for suspected components is obtained by Mamdani fuzzy reasoning algorithm.Findings – The experimental results reveal that the diagnosis system can not only improve diagnosis of speed but also can improve the diagnostic precision by giving failure probability for suspected fault components which may be potential failure components.Research limitations/implications – It requires the clear fault dependency relationship between components and tests.Practical implications – A very useful method for researchers and engineers who are engaged in satellite online monitoring and diagnosis.Originality/value – This paper presents a new method combining multisignal model and fuzzy theory to give the failure probability for suspected components which improves the speed and precision for fault diagnosis.

This paper focuses on organizational change through the business process management approach. While “business process modeling” permits understanding process activities and their activities with other participants, “current reality tree (CRT)” technique promotes the identification of process constraints. The purpose of this study is to compare the results from applying both diagnostic techniques, process modeling, using the business process modeling notation, and root cause analysis, using the CRT.

The comparison is made using a pre-experiment in which two teams conducted diagnoses concomitantly in the information technology management (ITM) process of one unit of the biggest and prestigious higher education institution (HEI) in Brazil.

The modeling technique and the CRT should be considered complementary techniques, since applying one does not diminish or exclude the importance of using the other. Results were compared analyzing which dimensions of the process each technique highlighted: strategy, organization, activity/information and resources.

A possible limitation of this research is that the experiment was conducted in a single process and the result cannot be generalized to other processes.

It may be noted that the main contribution of this study is the presentation of the steps of two techniques for process diagnosis. It is expected that with the reports on diagnoses outcomes, team's assessment and the perception of the managers presented here other improvement teams may use the results of this research as an inspiration to perform process diagnosis, and as basis for decision making to define which technique to use according to the specific needs of process improvement.

The paper stands out the comparison of the technique application's outcomes. This study offers valuable insights to the organizations that are interested in restructuring their processes. It delineates many important benefits of such a diagnosis techniques. It also identifies possible pitfalls and recommends guidelines for the successful conduction of process diagnoses initiatives.

This paper aims to improve the fault detection adaptive threshold of aircraft flap control system to make the system fault diagnosis more accurate.

According to the complex mechanical–electrical–hydraulic structure and the multiple fault modes of the aircraft flap control system, the advanced fault diagnosis method based on the bond graph (BG) model is presented, and based on the system diagnostic BG model, the parameter uncertainty intervals are estimated and a new adaptive threshold is constructed by linear fraction transformation.

To construct a more reasonable and accurate adaptive threshold range to more accurately detect system failures, some typical failure modes’ diagnosis process are selected and completed for verification; the simulation results show that the proposed method is effective and feasible for complex systems’ fault diagnosis.

This study can provide a theoretical guidance and technical support for fault diagnosis of complex systems, which avoid misdiagnosis and missed diagnosis.

This study enables more accurate fault detection and diagnosis of complex systems when considering factors such as parameter uncertainty.

The purpose of this study is to analyze the intelligent semisupervised fault diagnosis method of aeroengine.

A semisupervised fault diagnosis method based on denoising autoencoder (DAE) and deep belief network (DBN) is proposed for aeroengine. Multiple state parameters of aeroengine with long time series are processed to form high-dimensional fault samples and corresponding fault types are taken as sample labels. DAE is applied for unsupervised learning of fault samples, so as to achieve denoised dimension-reduction features. Subsequently, the extracted features and sample labels are put into DBN for supervised learning. Thus, the semisupervised fault diagnosis of aeroengine can be achieved by the combination of unsupervised learning and supervised learning.

The JT9D aeroengine data set and simulated aeroengine data set are applied to test the effectiveness of the proposed method. The result shows that the semisupervised fault diagnosis method of aeroengine based on DAE and DBN has great robustness and can maintain high accuracy of fault diagnosis under noise interference. Compared with other traditional models and separate deep learning model, the proposed method also has lower error and higher accuracy of fault diagnosis.

Multiple state parameters with long time series are processed to form high-dimensional fault samples. As a typical unsupervised learning, DAE is used to denoise the fault samples and extract dimension-reduction features for future deep learning. Based on supervised learning, DBN is applied to process the extracted features and fault diagnosis of aeroengine with multiple state parameters can be achieved through the pretraining and reverse fine-tuning of restricted Boltzmann machines.

The purpose is using generative adversarial network (GAN) to solve the problem of sample augmentation in the case of imbalanced bearing fault data sets and improving residual network is used to improve the diagnostic accuracy of the bearing fault intelligent diagnosis model in the environment of high signal noise.

A bearing vibration data generation model based on conditional GAN (CGAN) framework is proposed. The method generates data based on the adversarial mechanism of GANs and uses a small number of real samples to generate data, thereby effectively expanding imbalanced data sets. Combined with the data augmentation method based on CGAN, a fault diagnosis model of rolling bearing under the condition of data imbalance based on CGAN and improved residual network with attention mechanism is proposed.

The method proposed in this paper is verified by the western reserve data set and the truck bearing test bench data set, proving that the CGAN-based data generation method can form a high-quality augmented data set, while the CGAN-based and improved residual with attention mechanism. The diagnostic model of the network has better diagnostic accuracy under low signal-to-noise ratio samples.

A bearing vibration data generation model based on CGAN framework is proposed. The method generates data based on the adversarial mechanism of GAN and uses a small number of real samples to generate data, thereby effectively expanding imbalanced data sets. Combined with the data augmentation method based on CGAN, a fault diagnosis model of rolling bearing under the condition of data imbalance based on CGAN and improved residual network with attention mechanism is proposed.

The purpose of this paper is to describe the delivery of a mainstreaming model within a public sector, mental health (National Health Service (NHS)) organisation. The model promotes the inclusivity of a spectrum of presentations from co-existing moderate anxiety and depression to severe mental disorder (psychosis) and problematic substance and alcohol use.

This paper introduces the delivery of three collective approaches, termed the “three essential elements” to support a mainstreaming treatment model, facilitated by a “Dual Diagnosis Lead”. The model encompasses; a “direct access” referral pathway, joint collaboration with practitioners and the delivery of a “Dual Diagnosis” training programme. An independent evaluation was commissioned to explore eight mental health and substance misuse practitioners’ views and experiences in relation to the impact of the mainstreaming model. This paper also considers feedback from 230 course participants attending a one day “Dual Diagnosis” training programme.

This paper suggests that practitioners may benefit from the implementation of the mainstreaming approach and the delivery of this approach could be moving “Dual Diagnosis” interventions closer to mainstream practice.

The limitations of the mainstreaming model are acknowledged in relation to the generalisation of practitioners’ views and reported experiences.

This paper offers a description of the delivery of a mainstreaming model involving the “three essential elements”. The model provides a useful insight and demonstrates the possibilities which may be achieved when attempting to implement a mainstreaming treatment approach within mainstream mental health and drug and alcohol services.

Intelligent diagnosis of equipment faults can effectively avoid the shutdown caused by equipment faults and improve the safety of the equipment. At present, the diagnosis of various kinds of bearing fault information, such as the occurrence, location and degree of fault, can be carried out by machine learning and deep learning and realized through the multiclassification method. However, the multiclassification method is not perfect in distinguishing similar fault categories and visual representation of fault information. To improve the above shortcomings, an end-to-end fault multilabel classification model is proposed for bearing fault diagnosis.

In this model, the labels of each bearing are binarized by using the binary relevance method. Then, the integrated convolutional neural network and gated recurrent unit (CNN-GRU) is employed to classify faults. Different from the general CNN networks, the CNN-GRU network adds multiple GRU layers after the convolutional layers and the pool layers.

The Paderborn University bearing dataset is utilized to demonstrate the practicability of the model. The experimental results show that the average accuracy in test set is 99.7%, and the proposed network is better than multilayer perceptron and CNN in fault diagnosis of bearing, and the multilabel classification method is superior to the multiclassification method. Consequently, the model can intuitively classify faults with higher accuracy.

The fault labels of each bearing are labeled according to the failure or not, the fault location, the damage mode and the damage degree, and then the binary value is obtained. The multilabel problem is transformed into a binary classification problem of each fault label by the binary relevance method, and the predicted probability value of each fault label is directly output in the output layer, which visually distinguishes different fault conditions.

Risk‐adjustment is designed to predict healthcare costs to align capitated payments with an individual's expected healthcare costs. This can have the consequence of reducing overpayments and incentives to under treat or reject high cost individuals. This paper seeks to review recent studies presenting risk‐adjustment models.

This paper presents a brief discussion of two commonly reported statistics used for evaluating the accuracy of risk adjustment models and concludes with recommendations for increasing the predictive accuracy and usefulness of risk‐adjustment models in the context of predicting future healthcare costs.

Over the last decade, many advances in risk‐adjustment methodology have been made. There has been a focus on the part of researchers to transition away from including only demographic data in their risk‐adjustment models to incorporating patient data that are more predictive of healthcare costs. This transition has resulted in more accurate risk‐adjustment models and models that can better identify high cost patients with chronic medical conditions.

The paper shows that the transition has resulted in more accurate risk‐adjustment models and models that can better identify high cost patients with chronic medical conditions.

In gearbox fault diagnosis, identifying the fault type and severity simultaneously, as well as the compound fault containing multiple faults, is necessary.

To diagnose multiple faults simultaneously, this paper proposes a multichannel and multi-task convolutional neural network (MCMT-CNN) model.

Experiments were conducted on a bearing dataset containing different fault types and severities and a gearbox compound fault dataset. The experimental results show that MCMT-CNN can effectively extract features of different tasks from vibration signals, with a diagnosis accuracy of more than 97%.

Vibration signals at different positions and in different directions are taken as the MC inputs to ensure the integrity of the fault features. Fault labels are established to retain and distinguish the unique features of different tasks. In MCMT-CNN, multiple task branches can connect and share all neurons in the hidden layer, thus enabling multiple tasks to share information.

The purpose of this paper is to investigate the extent to which organizational level of functionality is affected by its leadership, its staff, the way task is performed in the organization (culture), and the structural and governance makeup of organizations. This study also determined the direct and indirect impacts of these variables on organizational functionality in general and drawing lessons to educational organizations in specific.

This is a quantitative study. Data from 185 participants were analyzed using SPSS software version 24. The data analysis procedure for this study followed various steps. First, multiple factor analysis was conducted to narrow the long list of items and to create a manageable list of construct variables for analyses. Then path analysis, using a series of multiple regression, was conducted to identify the degree of relationship between the independent and dependent variables. Finally, a path model coefficient diagram was created.

Using path analysis, a new model that depicts the level of interactions among the proposed variables and the extent and direction of influence of each variable on organizational level of functionality has been created. In addition, a path diagram that illustrates the model is provided and explained. This study also determined the direct and indirect impacts of these variables on organizational functionality. Finally, conclusions and implications of the study for educational organizations were presented.

It should be noted that path analysis studies, by nature, are based on assumptions provided by the researchers. Hence, future studies using different variables and different assumption may not necessarily generate the same result. In addition, this study looked at a broader view of organizations rather than a specific type.

This study expanded the use of organizational diagnosis frameworks, beyond studying organizational performance, to study organizational level of functionality which can be used to diagnose the level of function (or dysfunction) of organizations in a holistic manner.

The present study contributes to the body of literature in organizational diagnosis in various ways; chief of which is the creation of a new path model which shows the direct and indirect effects of specific variables in numeric terms.

Unlike previous studies on the topic, this study suggests that organizational level of functionality should be studied using variables internal to the organization, because any two organizations of similar purpose and capacity, located in similar environment, could function differently due to factors internal to the organizations. Investigating organizational level of functionality using variables internal to the organization is assumed to provide a deeper diagnosis and self-assessment as it minimizes the noises created by variables external to the organization. All the variables in this study are therefore carefully selected to be internal to organizations.