No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Identifying the Stages of Fire Development from Compartment Temperatures with GMM-HMMs: A Case Study of Room Fires
Abstract
It is essential for firefighters to identify the stages of fire development when conducting the fire emergency response operation. However, at present, the approaches for firefighters to identify the stages of fire development on the fireground mainly rely on subjective observation and judgment to the signs and symptoms changing on-site, which is highly unreliable and ambiguous. Therefore, to enhance firefighters’ situational awareness, a machine learning approach by using Gaussian Mixture Models and Hidden Markov Models (GMM-HMM) to automatically identify the stages of fire development from compartment temperatures is proposed in this paper. To provide enough data samples for unsupervised model training, the CFD-based fire simulation—Fire Dynamics Simulator (FDS)—is applied to generate a large volume of simulated training data. Taking the ISO 9705 fire test room as our case study environment, we collect simulation data under 100 fire scenarios within this room to formulate the recognition model. By using the difference between the fire growth time in terms of the model estimated value and the actual value from HRR to evaluate the accuracy of the recognition, we find that the recognition model indicates an average of 98% accuracy within the 2 min error range in cross-validation, and acceptable performance of recognition are also found from the case examined by the real experimental data.
ResearchGate has not been able to resolve any citations for this publication.
In England, there are no fixed requirements on the parameters adopted when considering residential design fires, and analyses undertaken are often deterministic with limited consideration given to probabilistic assessments and the sensitivity of parameters. The Home Office dwelling fires dataset has been analysed, considering the fire damage area and the time from ignition to fire and rescue service arrival. From this, lognormal distributions for the maximum heat release rate (HRR) and fire growth rate of residential fires have been approximated. The mean maximum HRR ranges from 900 kW to 1900 kW, with a standard deviation ranging from 2000 kW to 3700 kW, depending on property type and room of fire origin. The mean growth rate, assuming a t2 relationship, ranges from 0.0022 kW/s 2 to 0.0034 kW/s2 , with a standard deviation ranging from 0.0071 kW/s2 to 0.0132 kW/s2. When considering incidents which result in immediate fire and rescue service call out following ignition, the mean growth rate increases to a range of 0.0058 kW/s2 to 0.0088 kW/s2. As a result of the analyses, design fire distributions are provided which can be adopted for probabilistic assessments. For deterministic analyses, it is proposed that an approximate 95th percentile fire may be adopted, aligning with a medium growth rate of 0.0117 kW/s2 and a maximum fuel-limited HRR in the region of 3800 kW to 4400 kW, depending on whether the dwelling is a house or an apartment. A 95th percentile design fire broadly aligns with values already specified in guidance, helping to substantiate the existing recommendations.
In the recent past, a few fire warning and alarm systems have been presented based on a combination of a smoke sensor and an alarm device to design a life-safety system. However, such fire alarm systems are sometimes error-prone and can react to non-actual indicators of fire presence classified as false warnings. There is a need for high-quality and intelligent fire alarm systems that use multiple sensor values (such as a signal from a flame detector, humidity, heat, and smoke sensors, etc.) to detect true incidents of fire. An Adaptive neuro-fuzzy Inference System (ANFIS) is used in this paper to calculate the maximum likelihood of the true presence of fire and generate fire alert. The novel idea proposed in this paper is to use ANFIS for the identification of a true fire incident by using change rate of smoke, the change rate of temperature, and humidity in the presence of fire. The model consists of sensors to collect vital data from sensor nodes where Fuzzy logic converts the raw data in a linguistic variable which is trained in ANFIS to get the probability of fire occurrence. The proposed idea also generates alerts with a message sent directly to the user's smartphone. Our system uses small size, cost-effective sensors and ensures that this solution is reproducible. MATLAB-based simulation is used for the experiments and the results show a satisfactory output.
The detection of manmade disasters particularly fire is valuable because it causes many damages in terms of human lives. Research on fire detection using wireless sensor network and video-based methods is a very hot research topic. However, the WSN based detection model need fire happens and a lot of smoke and fire for detection. Similarly, video-based models also have some drawbacks because conventional algorithms need feature vectors and high rule-based models for detection. In this paper, we proposed a fire detection method which is based on powerful machine learning and deep learning algorithms. We used both sensors data as well as images data for fire prevention. Our proposed model has three main deep neural networks i.e. a hybrid model which consists of Adaboost and many MLP neural networks, Adaboost-LBP model and finally convolutional neural network. We used Adaboost-MLP model to predict the fire. After the prediction, we proposed two neural networks i.e. Adaboost-LBP model and convolutional neural network for detection of fire using the videos and images taken from the cameras installed for the surveillance. Adaboost-LBP model is to generate the ROIs from the image where emergencies exist Our proposed model results are quite good, and the accuracy is almost 99%. The false alarming rate is very low and can be reduced more using further training.
A fire detection system requires accurate and fast mechanisms to make the right decision in a fire situation. Since most commercial fire detection systems use a simple sensor, their fire recognition accuracy is deficient because of the limitations of the detection capability of the sensor. Existing proposals, which use rule-based algorithms or image-based machine learning can hardly adapt to the changes in the environment because of their static features. Since the legacy fire detection systems and network services do not guarantee data transfer latency, the required need for promptness is unmet. In this paper, we propose a new fire detection system with a multifunctional artificial intelligence framework and a data transfer delay minimization mechanism for the safety of smart cities. The framework includes a set of multiple machine learning algorithms and an adaptive fuzzy algorithm. In addition, Direct-MQTT based on SDN is introduced to solve the traffic concentration problems of the traditional MQTT. We verify the performance of the proposed system in terms of accuracy and delay time and found a fire detection accuracy of over 95%. The end-to-end delay, which comprises the transfer and decision delays, is reduced by an average of 72%.
Typical fire monitoring and warning systems use a single smoke detector that is connected to a fire management system to give early warnings before the fire spreads out up to a damaging level. However, it is found that only smoke detector-based fire monitoring systems are not efficient and intelligent since they generate false warnings in case of a person is smoking, etc. There is need of a multi-sensor based intelligent and smart fire monitoring system that employs various parameters, such as presence of flame, temperature of the room, smoke, etc. To achieve such a smart solution, a multi-sensor solution is required that can intelligently use the data of sensors and generate true warnings for further fire control and management. This paper presents an intelligent Fire Monitoring and Warning System (FMWS) that is based on Fuzzy Logic to identify the true existence of dangerous fire and send alert to Fire Management System (FMS). This paper discusses design and application of a Fuzzy Logic Fire Monitoring and Warning System that also sends an alert message using Global System for Mobile Communication (GSM) technology. The system is based on tiny, low cost, and very small in size sensors to ensure that the solution is reproduceable. Simulation work is done in MATLAB ver. 7.1 (The MathWorks, Natick, MA, USA) and the results of the experiments are satisfactory.
The recent advances in embedded processing have enabled the vision based systems to detect fire during surveillance using convolutional neural networks (CNNs). However, such methods generally need more computational time and memory, restricting its implementation in surveillance networks. In this research article, we propose a cost-effective fire detection CNN architecture for surveillance videos. The model is inspired from GoogleNet architecture, considering its reasonable computational complexity and suitability for the intended problem compared to other computationally expensive networks such as “AlexNet”. To balance the efficiency and accuracy, the model is fine-tuned considering the nature of the target problem and fire data. Experimental results on benchmark fire datasets reveal the effectiveness of the proposed framework and validate its suitability for fire detection in CCTV surveillance systems compared to state-of-the-art methods.
Methodologies for the empirical measurement of situation awareness are reviewed, including a discussion of the advantages and disadvantages of each method and the potential limitations of the measures from a theoretical and practical viewpoint. Two studies are presented that investigate questions of validity and intrusiveness regarding a query-based technique. This technique requires that a simulation of the operational tasks be momentarily interrupted in order to query operators on their situation awareness. The results of the two studies indicate that the query technique is not intrusive on normal subject behavior during the trial and does not suffer from limitations of human memory, which provides an indication of empirical validity. The results of other validity studies regarding the technique are discussed along with recommendations for its use in measuring situation awareness in varied settings.
Fire is a severe natural calamity that causes significant harm to human lives and the environment. Recent works have proposed the use of computer vision for developing a cost-effective automated fire detection system. This paper presents a custom framework for detecting fire using transfer learning with state-of-the-art CNNs trained over real-world fire breakout images. The framework also uses the Grad-CAM method for the visualization and localization of fire in the images. The model also uses an attention mechanism that has significantly assisted the network in achieving better performances. It was observed through Grad-CAM results that the proposed use of attention led the model towards better localization of fire in the images. Among the plethora of models explored, the EfficientNetB0 emerged as the best-suited network choice for the problem. For the selected real-world fire image dataset, a test accuracy of 95.40% strongly supports the model's efficiency in detecting fire from the presented image samples. Also, a very high recall of 97.61 highlights that the model has negligible false negatives, suggesting the network to be reliable for fire detection.
Dissolved gases analysis (DGA) provides widely-recognized practice for oil-immersed power transformers and it is mainly interpreted for fault diagnosis. In order to accurately estimate the health index state of power transformers and predict the incipient operation failure, a dynamic fault prediction technique based on Hidden Markov model (HMM) of DGA is proposed in this paper. Gaussian mixture model, as a soft clustering method, is used to extract the static features of different health states from a DGA dataset of 65 in-service power transformers with 1600 days operation. Especially, a sub-health state is introduced to enrich the health index and ageing stages of power transformers. The static features between health states and concentrations of dissolved gases are built and the effectiveness of clustering is cross validated. Furthermore, taking time sequence into consideration, transition probability of power transformer between different health states based on HMM model is calculated and analyzed. The effectiveness has been proved that dynamic early warning and incipient fault prediction in sub-health status of in-service power transformers. Moreover, the dynamic fault prediction is able to provide decision-making basis for practical condition-based operation and maintenances.
Fire safety regulations in many countries require Fire Risk Assessment to be carried out for buildings such as workplaces and houses in multiple occupation. This duty is imposed on a “Responsible Person” and also on any other persons having control of buildings in compliance with the requirements specified in the regulations.
The following techniques for uncertainty and sensitivity analysis are briefly summarized: Monte Carlo analysis, differential analysis, response surface methodology, Fourier amplitude sensitivity test, Sobol' variance decomposition, and fast probability integration. Desirable features of Monte Carlo analysis in conjunction with Latin hypercube sampling are described in discussions of the following topics: (i) properties of random, stratified and Latin hypercube sampling, (ii) comparisons of random and Latin hypercube sampling, (iii) operations involving Latin hypercube sampling (i.e. correlation control, reweighting of samples to incorporate changed distributions, replicated sampling to test reproducibility of results), (iv) uncertainty analysis (i.e. cumulative distribution functions, complementary cumulative distribution functions, box plots), (v) sensitivity analysis (i.e. scatterplots, regression analysis, correlation analysis, rank transformations, searches for nonrandom patterns), and (vi) analyses involving stochastic (i.e. aleatory) and subjective (i.e. epistemic) uncertainty.
Selecting design fires. Brandteknik och Riskhantering, Lunds tekniska högskola Lund Google Scholar
- L Staffansson
Experimental study of the effects of fuel type, fuel distribution, and vent size on full-scale underventilated compartment fires in an ISO 9705 room
- A Lock
- M Bundy
- E L Johnsson
- A Hamins
- G H Ko
- C Hwang
- P Fuss
- R Harris