{"title":"Hybrid Deep Neural Network for Data Driven Missile Guidance with Maneuvering Target","authors":"Junaid Farooq, Mohammad Abid Bazaz","doi":"10.14429/dsj.73.18481","DOIUrl":"https://doi.org/10.14429/dsj.73.18481","url":null,"abstract":"Missile guidance, owing to highly complex and non-linear relative movement between the missile and its target, is a challenging problem. This is further aggravated in case of a maneuvering target which changes its own flight path while attempting to escape the incoming missile. In this study, to achieve computationally superior and accurate missile guidance, a deep learning is employed to propose a self-tuning technique for a fractional-order proportional integral derivative (FOPID) controller of a radar-guided missile chasing an intelligently maneuvering target. A multi-layer two-dimensional architecture is proposed for a deep neural network that combines the prediction feature of recurrent neural networks and estimation feature of feed-forward artificial neural networks. The proposed deep learning based missile guidance scheme is non-intrusive, data-based, and model-free wherein the parameters are optimized on-the-run while predicting the target’s maneuvering tactics to correct for processing time and loop delays of the system. Using deep learning for online optimization with minimal computational burden is the core feature of the proposed technique. Dual-core parallel simulations of missile-target dynamics and the control system were performed to demonstrate superiority of the proposed scheme in feasibility, adaptability, and the ability to effectively minimize the miss-distance in comparison with traditional and neural offline-tuned PID and FOPID based techniques. Compared to state-of-the-art offline-tuned neural control, the miss-distance was reduced by 68.42% for randomly maneuvering targets. Furthermore, a minimum miss-distance of 0.97 m was achieved for intelligently maneuvering targets for which the state-of-the-art method failed to hit the target. Overall, the proposed technique offers a novel approach for addressing the challenges of missile guidance in a computationally efficient and effective manner.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136037037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Novel Dual Band Frequency Selective Surface and its Applications on the Gain Improvements of Compact UWB Monopole Antenna","authors":"Vikas Kumar Rai, Mithilesh Kumar","doi":"10.14429/dsj.73.18684","DOIUrl":"https://doi.org/10.14429/dsj.73.18684","url":null,"abstract":"In this work, a highly directional ultra-wideband (UWB) microstrip patch antenna as a single-element is suggested. The proposed antenna’s gain is enhanced with a novel dual-band frequency selective surface (FSS) placed beneath it. The FSS design has a hexagonal structure with meander line inductances and a capacitance-like structure connecting all of the corners to the middle. There is no metallic layer on the other side of the substrate, which shows transmission zeros at 4.95 GHz and 12.7 GHz, and a modified U-shaped monopole antenna is developed. First, the performance characteristics of the antenna and FSS are analyzed from the simulation results, and they are validated experimentally after fabrication, followed by measurement. The compact configuration comprises an antenna loaded with the proposed FSS results S11 less than -10 dB from 3.15 GHz to 22.65 GHz, covering the UWB band together with the X, Ku-band with a bandwidth of 19.5 GHz (151.16% FBW). The antenna’s overall physical dimensions would be 38.8 mm×38.8 mm×25.2 mm (0.407λo×0.407λo×0.265λo), with λo denoting the lowest frequency’s free-space wavelength. The FSS loading results in a 9.9 dBi maximum gain at 10 GHz. The antenna’s small size increases bandwidth, and its high peak gain makes it ideal for use in real-time applications.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136036890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Gait Parameter Tuning Using Bayesian Optimization for an Alligator Inspired Amphibious Robot","authors":"Atul Thakur","doi":"10.14429/dsj.73.18315","DOIUrl":"https://doi.org/10.14429/dsj.73.18315","url":null,"abstract":"This paper reports a sample-efficient Bayesian optimization approach for tuning the locomotion parameters of an in-house developed twelve degrees of freedom alligator-inspired amphibious robot. An optimization framework is used wherein the objective is to maximize the mean robot speed obtained via physical experiments performed on terrains with varying friction and inclinations and in the aquatic environment for swimming locomotion. We obtained an improvement in the mean robot speed by a factor of up to 6.38 using the developed approach over randomly generated locomotion parameters in 15 iterations. 
","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136036893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"RCS Modeling and Validation of Full Scale Launch Vehicle for its Real Time Dynamic Trajectory","authors":"Surender Veerabathini, Sudhakara Reddy Penubolu, Ramana Reddy Penubolu","doi":"10.14429/dsj.73.18193","DOIUrl":"https://doi.org/10.14429/dsj.73.18193","url":null,"abstract":"Radar Cross Section (RCS) plays a significant role in detecting and tracking the space-based objects such as launch vehicles, missiles, aircrafts etc. In space applications, Radar systems are used to track and provide real-time trajectory information of the satellite launch vehicles after the lift off from the launch pad for range safety purpose. RCS is a critical key parameter that determines tracking performance of the Radar and it is highly dependent on both Radar operating parameters and the target characteristics. For space-based applications, a good quantity of RCS is required for quick detection by the Radar for continuous tracking. In order to choose the best Radar tracking configuration for real time tracking of the launch vehicle, it is required to model and simulate the launch vehicle’s RCS fluctuations prior to launch in order to predict the real time Signal to Noise Ratio (SNR) for its complete dynamic trajectory. This modeling and simulation methodology will help to choose the optimum Radar configuration for obtaining a good quantity SNR in the real-time launch. This study also provides good guidance to Radar operators for the effective Radar operation during real time space object tracking. This paper demonstrates, the real-time RCS fluctuations of a typical ISRO launch vehicle through simulation for its dynamic trajectory using physical optics based EM software prior to launch. Furthermore, the simulation results are validated with real time monostatic Radar tracking data, which showed good agreement.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136037032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Simulation Model for Studying the Effect of Function Distribution on the Evaluation of Building Damage Caused by Missile Attack","authors":"Chenglin Zhai, Xiaowei Chen","doi":"10.14429/dsj.73.18317","DOIUrl":"https://doi.org/10.14429/dsj.73.18317","url":null,"abstract":"When a building is hit by a missile, the most important parts are usually destroyed first to achieve maximum damage to the functions of the building. To accurately quantify the damage to a building, a function distribution density is constructed to describe the importance of different parts, and is applied to the probability damage calculation of a building under a missile strike. Based on the objective characteristics, the building is divided into several modules. The importance of the different modules is calculated using the damage tree. The distribution densities of the physical and system functions are constructed separately and combined into the function distribution density of the building. Meanwhile, the landing points of the missile are simulated using the Monte Carlo method, and depending on whether the function distribution density is considered, a probability damage calculation is performed. In comparison, the calculation results considering the function distribution density have a larger irregular shape, which can describe the damage to the building more accurately. This study can provide support for improving the physical protection of buildings and ensuring the operational reliability of their functions.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136037033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Deep Learning Techniques in Radar Emitter Identification","authors":"Preeti Gupta, Pooja Jain, O G Kakde","doi":"10.14429/dsj.73.18319","DOIUrl":"https://doi.org/10.14429/dsj.73.18319","url":null,"abstract":"In the field of electronic warfare (EW), one of the crucial roles of electronic intelligence is the identification of radar signals. In an operational environment, it is very essential to identify radar emitters whether friend or foe so that appropriate radar countermeasures can be taken against them. With the electromagnetic environment becoming increasingly complex and the diversity of signal features, radar emitter identification with high recognition accuracy has become a significantly challenging task. Traditional radar identification methods have shown some limitations in this complex electromagnetic scenario. Several radar classification and identification methods based on artificial neural networks have emerged with the emergence of artificial neural networks, notably deep learning approaches. Machine learning and deep learning algorithms are now frequently utilized to extract various types of information from radar signals more accurately and robustly. This paper illustrates the use of Deep Neural Networks (DNN) in radar applications for emitter classification and identification. Since deep learning approaches are capable of accurately classifying complicated patterns in radar signals, they have demonstrated significant promise for identifying radar emitters. By offering a thorough literature analysis of deep learning-based methodologies, the study intends to assist researchers and practitioners in better understanding the application of deep learning techniques to challenges related to the classification and identification of radar emitters. The study demonstrates that DNN can be used successfully in applications for radar classification and identification.
 
","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136037034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sambhav Kumar Jain, Tapan K. Jain, Saumya Shanker, Srikant Srivastava
{"title":"Rapid and Accurate INS Transfer Alignment for Air Launched Tactical Missile Using Kalman Filter","authors":"Sambhav Kumar Jain, Tapan K. Jain, Saumya Shanker, Srikant Srivastava","doi":"10.14429/dsj.73.18435","DOIUrl":"https://doi.org/10.14429/dsj.73.18435","url":null,"abstract":"An Inertial Navigation System (INS) independently measures the Position, Velocity, and Attitude (PVA) of thevehicle to navigate it towards the target. Since INS is a dead-reckoning system, it requires accurate initialization toprovide the navigation (PVA) solution. In the case of an air-launched tactical missile, the aircraft navigation system(Master INS) information is used to initialize accurately the missile INS (Slave INS). Rapid transfer alignment isneeded in today’s combat operation to converge slave INS initialization in the shortest possible time using aircraftnavigation information. The transfer alignment consists of first initializing the missile INS and establishing anavigation solution (PVA) using the missile IMU rates and accelerations, then a Kalman filter is used to, estimatethe errors between the Slave INS and Master INS. The proposed method’s simulation results show that a tacticalmissile INS can be aligned to an acceptable accuracy in a very short time based on the aircraft’s attitude information and with natural maneuvers experienced during aircraft take-off.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"22 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139360375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A A New Approach in Realisation of DGS Microstrip Patch Antennas With Fractal Geometry","authors":"R. H. Prasad, D. Vakula, M. Chakravarthy","doi":"10.14429/dsj.73.18561","DOIUrl":"https://doi.org/10.14429/dsj.73.18561","url":null,"abstract":"A new approach in realization of Defected Ground Structure Microstrip Patch antennas with Fractal Slots cutin the ground plane has been presented. The presented approach resulted in miniaturization of radiating patches and avoidance of multiple resonances which are prime considerations in antennas for Wi-Fi applications. A rectangular Microstrip patch is taken as a basic radiating patch. In the ground plane, square and circular slots following Sierpinski Carpet Fractal Geometry are cut resulting in Defected Ground Structure (DGS) Microstrip Patch antenna. The antenna is designed to operate at 2.4 GHz and the performance characteristics have been simulated using HFSS software. The proto-type DGS Microstrip patch antenna with square fractal slots is fabricated and tested. The measured results are in good agreement with the simulation studies. The technique has also resulted in size reduction of radiating patch compared to the standard microstrip patch antenna operating at the same frequency.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"370 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139360475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Nagendranath, Sanjay Anandrao Khalane, Rajesh Kumar Gupta, Lakshmana Rao C
{"title":"Delamination Buckling of Composite Conical Shells Under External Pressure","authors":"A. Nagendranath, Sanjay Anandrao Khalane, Rajesh Kumar Gupta, Lakshmana Rao C","doi":"10.14429/dsj.73.18174","DOIUrl":"https://doi.org/10.14429/dsj.73.18174","url":null,"abstract":"Airframe construction in conical form is the most desired shape of flight hardware due to their low drag profileand are located at the fore-end region of flight vehicles encountering high drag loads. Owing to their tailoringcapability, materials with orthotropic mechanical properties are preferred choice. Delamination defects formed inthem while manufacturing or when subjected to loads would unfavorably influence the mechanical performanceof the orthotropic airframe. In the current work, FE simulation of delamination which is embedded in orthotropiccone shaped shells under external pressure load is performed as per the method cited in published literature. A layer wise element based on shell theory has been used and the effect of delamination size and its through the thickness position on the mechanical performance of the cone shaped shell is investigated. Circumferential and rectangular shapes of defects have been simulated. The investigation is performed for metal and composite materials with 3 types of stacking sequences generally used in practical designs. Verification of the procedure is carried out by equating with the procedure cited in published studies on shells of thin orthotropic cylinders. The eigen value of the first mode is taken as the critical buckling factor under external pressure. The buckling factor of the delaminated cone is normalized with the buckling factor of the ideal cone. The normalized buckling factor is showed graphically with the normalised defect size. Global, as well as local buckling and also symmetric as well as asymmetric buckling shapes, are observed in the results of the simulation. Shift from global mode to local mode of buckling is also observed in certain cases. Drastic reduction in buckling capability with the local mode is observed when the defect location is close to the surface and more prominent for an outer surface case.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"32 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139360626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Life Saving Aspects of Pilot for Escape Aid Explosive (EAX) System Applications Some Considerations","authors":"B. Parate","doi":"10.14429/dsj.73.18331","DOIUrl":"https://doi.org/10.14429/dsj.73.18331","url":null,"abstract":"This manuscript deals with life saving aspects of the pilot for escape aid explosive (EAX) system applicationsunder emergency situation. During the ejection from the aircraft, the pilot is subjected to the various forces suchas linear, angular and transverse accelerations, decelerations, wind drag accelerations, wind blast, dynamic forces,aerodynamic forces, spinning and tumbling. Linear accelerations (decelerations) of major interest in aviation arethose of a high magnitude and a short duration that occur in emergency ejection from the aircraft or occasionallyin a high altitude at high-speed parachute opening, as they tend to exceed the strength limitations of the skeletalstructure of the pilot body. The human body is a heterogeneous mass that is made up of solid, liquid and viscoelastic components. The effects of these forces on the pilot’s body are crucial in nature and significant pertains toan injury. This article is described with some considerations of ballistics, kinematics with different forces and theireffects on the pilot body for aircraft applications during an entire flight trajectory. In conclusion, this kind of studyis very essential considering the pilots safety and its performance at low and high altitudes during an emergency.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":"49 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139360288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}