A Deep Learning Based Data-Driven Thruster Fault Diagnosis Approach for Satellite Attitude Control System

Abstract. Problem. Speed control systems are used to ensure road safety and improve vehicle efficiency by controlling traffic speed. The main purpose of the speed control system is to ensure road safety, increase vehicle efficiency and reduce the negative impact of transport on the environment by controlling the speed of traffic. Reducing speed allows drivers to react in time to unforeseen situations, stop at traffic lights, and reduce the distance to other vehicles. In this paper, we have carried out mathematical modeling of a vehicle speed control system. Goal. As a result of the analysis, the purpose of the study was highlighted: to carry out mathematical modeling of the car speed control system. Job tasks: to model the speed control system using a proportional regulator and a PID controller. Methodology. Initially, we considered a vehicle speed control system using a proportional regulator. In the process of synthesis, it was found that the use of a P-controller provides insufficiently good quality of the vehicle speed control system. It was decided to use a PID controller to synthesize the speed control system. Results. The result of the study is: optimized settings of the PID controller provide a given control time tp≈40 s with practically no overshoot, which is a completely satisfactory quality of this system. Originality. The originality lies in the fact that a PID controller with an NCD block was used to determine the transient function of the system with optimal settings. Practical value. The use of the proposed results indicates the possibility of using a PID controller to ensure the set parameters.

Historically, in dipmeter analysis, depositional patterns are delineated for environmental, structural, and stratigraphic interpretations. The proposed method is a more fundamental approach, which uses raw data measurements from the dipmeter sonde to aid the geologist or log analyst in describing subsurface structures on a stratigraphic scale. Raw data are available at the well site, require only a basic understanding of sedimentary features and facies, and can be combined with computed results. A case study illustrates the reconstruction of sedimentary features from a raw data log recorded by a six-arm dipmeter. The dipmeter is a wireline tool with a series of evenly spaced focused electrodes applied to the circumference of the borehole wall. The raw data are presented as curves representing the electrode response and tool orientation. In outcrop, the geologist can often see an entire sedimentary feature in 3 dimensions relative to its depositional environment. Therefore, a large range of features can be resolved. However, in the borehole environment the perspective is reduced to the borehole diameter, thus reducing the range of recognizable features. In this study, a table was assembled that identifies the features distinguished by the proposed method as a function of borehole diameter. End_of_Record - Last_Page 163-------

CFI-LFENet: Infusing cross-domain fusion image and lightweight feature enhanced network for fault diagnosis

Problem. The article proposes a developed construction of a suspension – shock absorber, which made it possible to install a hydraulic hammer as a working equipment, simultaneously isolating it from vibrations.
 A mathematical model of the system was developed, the basis of which is a suspension – shock absorber for attaching a hydraulic hammer to an excavator, which includes modeling of its mechanical system. Goal. The goal is the development and research of a sub-axle - shock absorber for the attachment of hydraulic hammer equipment (hydraulic hammer) to an excavator. Methodology. The solution of the set problems involved the creation of a mathematical model of the vibration system and its implementation using the MathCAD application program. Originality. It is proposed to transform the differential equations of the mathematical model of the vibration system by the method of decreasing order and as a result obtain the displacements, velocities, and accelerations of individual elements and obtain the nature of the change in the disturbing force of the vibrating hammer. Using the MathCAD program, a study of the dynamics of the system, which includes a hydraulic ham a shock absorber and an excavator, was performed, as well as the frequencies of free oscillations of the system in question were determined. Practical value. The obtained results of scientific research on vibration protection of excavators, which are operated with attached shock devices (hydraulic hammers), with the use of the MathCAD mathematical program, can be successfully used in the development, as well as in the determination of dynamic loads of similar vibration protection systems used in industry.

According to principle of model reference adaptation, a model reference fault diagnosis approach for on-orbit satellite attitude control system was proposed based on measurement and calculation of environmental torques acted on satellite. With satellite kinematics and attitude dynamics, a linear model for satellite attitude control system is established. On the basis of system parameter and structural characteristics, satellite attitude control system reference model modified by measurement and calculation of environmental torques is built. With fault residual vector generated by comparing output of reference model with real system, sensor fault detection and isolation is accomplished. Extended state observer is designed to estimate system disturbance using augmented matrix method. According to disturbance estimation and environment torque calculation, actuator fault residual vector is obtained to detect and isolate actuator fault. The simulation experiment result demonstrates that the proposed approach is effective and efficient for real-time fault diagnosis of on-orbit satellite attitude control system.

A novel fault diagnostic method in power converters for wind power generation system

The numbers of hard disk drive heads manufactured in Thailand have increased rapidly in the past few years, and one of the most important components of the hard disk drive head is the hard disk drive arm. This component has been produced in large amounts and has been a major income source for a case study company. The manufacturing process of the hard disk drive arm, especially the machining process, is highly complicated and also a main factor of defining the usability of the final product. However, during dimension inspections, many defected parts were detected, resulting in an overall decrease in productivity, sales and profit. Normally, parts are randomly chosen from each CNC machine to be inspected. If there is a defective product, that machine would be shut down and the tool settings will be reset. If the machine that has been producing defective products is inspected late into the inspection shifts, it would result in a considerable amount of defective parts produced before any corrective actions can be made. Therefore, this study presents an application of the integration between Multiple Attribute Decision Making (MADM) and Data Mining (DM) to define the inspection order for tooling adjustment of which the machines with higher risk of producing defective parts can be inspected and corrected before those with lower risk. The methodology is as follows. First, raw measurement data from each machine was collected and noise elimination was performed using the anomaly clustering method. Secondly, K-means clustering, after a machine performance hypothesis test to confirm that the performance of each machine is not equal, was opted for dividing the raw data into three clusters, consisting of good, normal, and bad machines. Finally, a daily CNC machine priority assessment model (CNC-MPAM) is developed based on the Simple Additive Weight (SAW) technique, resulting in a machine performance score for optimal ordering of machine tooling adjustment. Experimental results suggested that this proposed method is capable of machine adjustment ordering so that defective prone machines can be serviced sooner, reducing defective parts produced and improving overall productivity.

There are many different uses for the data that comes from a measurement. With the advent of new testing methodologies, data has become finely granular—allowing for precise analysis of the properties and performance of materials, geometries, and even simulations. Raw measurement data can be retained and compared directly to the output of complex acoustic models for development, improvement, evaluation, and eventually a form of calibration. Advances in technology are rapidly removing the limitations of computational power needed to create accurate models of acoustic phenomena in a timely and efficient manner. This allows a progression from limited particle simulations on single workstations, to large scale wave-based simulations using cloud-based GPU computing clusters. Performance will be evaluated, comparing their output to laboratory measurements, with the goal of creating better tools for acoustic design, prediction, experimentation, and development.There are many different uses for the data that comes from a measurement. With the advent of new testing methodologies, data has become finely granular—allowing for precise analysis of the properties and performance of materials, geometries, and even simulations. Raw measurement data can be retained and compared directly to the output of complex acoustic models for development, improvement, evaluation, and eventually a form of calibration. Advances in technology are rapidly removing the limitations of computational power needed to create accurate models of acoustic phenomena in a timely and efficient manner. This allows a progression from limited particle simulations on single workstations, to large scale wave-based simulations using cloud-based GPU computing clusters. Performance will be evaluated, comparing their output to laboratory measurements, with the goal of creating better tools for acoustic design, prediction, experimentation, and development.

In order to meet the requirements of multi-parameter and real-time fault diagnosis of China VI vehicle emission standards diesel engine air system, this paper focuses on the research of the diesel engine air system fault detection and diagnosis method based on deep learning to improve the operational safety and fault diagnosis efficiency. In this paper, the air system fault detection and diagnosis are completed based on the AE model and the CNN model, combined with the actual operation of the diesel engine. Among them, the AE model successfully detected all real-time operation faults, and the false detection rate on the health data was 0.1162%; the CNN model obtained a 90.77% fault diagnosis accuracy rate on the test set of the real-time operation data set. The results show that the model has high accuracy in the diagnosis of diesel engine faults, which is of great significance to the application of deep learning based on big data processing.

The rolling bearing is a critical part of rotating machinery and its condition determines the performance of industrial equipment; it is necessary to detect rolling bearing faults as early as possible. The traditional methods of fault diagnosis are not efficient and are time-consuming. With the help of deep learning, the convolution neural network (CNN) plays a huge role in the data-driven methods of bearing fault diagnosis. However, the vibration signal is non-stationary, contains high noise, and is one-dimensional, which is difficult to analyze directly by the CNN model. Considering the multi-domain learning as an advantage of deep learning, this paper proposes a novel rolling bearing fault diagnosis approach using an improved one-dimensional (1D) and two-dimensional (2D) convolution neural network (CNN) of two-domain information learning. The constructed fault diagnosis model combining 1D and 2D CNN extracts the fault features from the two-domain information of bearing fault samples. The padding and dropout technology are utilized to fully extract features from the raw data and reduce over-fitting. To prove the validity of the proposed method, this paper performs two tests with two bearing datasets, the Case Western Reserve University (CWRU) bearing dataset and the Dalian University of Technology (DUT) vibration laboratory dataset. The experimental results show that our proposed method achieves high recognition accuracy of rolling bearing fault states via two-domain learning of monitoring data, and there is no manual experience necessary. Vibration data under strong noise were also used to test the method, and the results show the superiority and robustness of the proposed method.

Dissolved gas analysis (DGA) approach is extensively applied to detect incipient faults of power transformers. This paper presents a novel DGA method for power transformer incipient fault diagnosis based on integrated adaptive neuro fuzzy inference system (ANFIS) and Dempster-Shafer Theory (DST). Four out of seven common conventional methods which are studied and compared for better consistency and accuracy, are used to develop new ANFIS based fault diagnosis models. To promote fault diagnostic performance further and make fault decision process more reliable and reasonable, an improved DST is introduced to integrate outputs of each ANFIS based model, and to provide comprehensive and convincing fault diagnosis results. The fault diagnosis capability of the proposed method is validated by a reported fault dataset and 10-fold cross validation experiment. The performance of the proposed method is compared with conventional approaches and ANFIS based models which demonstrate that the proposed method is superior to other methods and is more effective and stable for power transformer fault diagnosis with high accuracy and consistency.

In order to realize the condition monitoring of the motor ?anytime, anywhere?, improve the detection accuracy and shorten the detection time, the author proposes a fault signal processing and diagnosis system for the motor heat recovery system based on the IoT. That is, based on the IoT technology, a mobile terminal oriented motor remote monitoring and fault diagnosis system, the sensing layer of the system collects real-time motor operation status data, and the transmission layer realizes data transmission, cloud storage and response to data requests from the application layer, finally, at the mobile end, the motor running status and diagnosis results are displayed through charts and text, so as to realize remote monitoring and fault diagnosis of the motor. The experimental results show that the accuracy of fault diagnosis test of GA-SVM in mobile terminal is more than 90%, and the running time is less than 30 ms, and the running time is very short. It proves that the mobile terminal uses the fault detection method based on GA-SVM model with high accuracy and short detection time, that is, the fault signal processing and diagnosis accuracy of the motor heat recovery system of the IoT is high and the detection time is short.

This paper is concerned with the problem of predictive function control (PFC) for a class of hydraulic vibration servo control systems. Our aim is to design a new advanced control strategy such that the control system can track trajectory in a fast and accurate way. For this end, the mathematical model of the hydraulic vibration servo control system is firstly studied. By analyzing the nonlinear, time-varying, and model structure uncertainty features of the objects, the desired control strategy is presented based on PFC. Finally, the simulation results show that our proposed method is effective and can be used to improve the tracking speed, accuracy, and robustness.

Line structured light calibration establishes the relationship between the camera and the laser plane. Different from conventional calibration algorithms, the proposed method needs only one scan of the stair block, and then we can obtain the optimal laser plane function. We first demonstrate our line structured light system's mathematical model. Secondly, a constrained nonlinear multivariable function is constructed with the aid of the stair block. Finally, we can obtain the optimal laser plane function by solving the optimization function. In the experimental section, Our calibration method is proved with high accuracy and flexibility by several experiments.

BACKGROUND: To maintain the required temperature range of electrical components of electric vehicles, it is necessary to use thermostating systems. The developing mathematical model of the temperature control system allows, even at the design stage of the vehicle, to determine the necessary parameters of the temperature control system, select algorithms for controlling the system, and calibrate the developed algorithm to ensure the necessary heat removal from electrical components. AIMS: Creation of a mathematical model of the electric motorcycle thermostating system, aimed at determining the potential possibilities of optimizing the system by organizing the air flow through the radiator. METHODS: The mathematical model is implemented in the AVL Cruise software environment. The characteristics of the components included in the model were obtained as a result of laboratory studies and supplemented with power equilibrium equations at the inputs and outputs, taking into account their efficiency. RESULTS: Using the developed model of the radiator of the thermostating system, the temperature graphs of the electric motor and inverter of the electric motorcycle during the driving cycle were obtained. It is noted that the applied temperature control system allows to maintain the temperature of electric components in the specified range. CONCLUSIONS: The mathematical model of the radiator of the thermostating system proposed in this paper allows to carry out calculations of the system at the stage of design of electric vehicles. The model also allows for further development in order to more fully determine the parameters of the thermostating system, including the thermal efficiency.