Early Leak Detection Research Articles

Suggested Flowchart Through Integrated C-Reactive Protein and White Blood Cell Count Analysis for Screening for Early Complications After Gastric Bypass: a Single-Center Retrospective Study.

Early leakage detection following bariatric procedures is crucial, but a standardized evaluation method is lacking. The aim was to validate the potential benefits of postoperative day 1 (POD1) C-reactive protein (CRP) levels and white blood cell (WBC) counts in distinguishing at-risk patients following Roux-en-Y gastric bypass (RYGB) while considering the impact of obesity-related chronic inflammation. Retrospective analysis of 261 consecutive patients aged 18-65 years with a body mass index (BMI) of 32.5-50 kg/m2 who underwent primary RYGB between 2017 and 2022. Sequential changes in CRP levels and WBC counts measured 48 h preoperatively and on POD1 morning were collected and compared between patients with/without complications and in patients without complications stratified by preoperative CRP levels. Female patients and those with a higher BMI tended to have higher baseline CRP levels, which were positively related to postoperative CRP. Patients experiencing complications had higher WBC counts and a higher prevalence of WBC counts >14,000/μl (77.8% vs. 25.4%; p<0.001) than those without complications. Baseline CRP ≥ 0.3 mg/dl, a longer operative time, and blood loss >10 ml were significantly more common with WBC counts above 14,000/μl; a reasonable range of change in WBC count (∆WBC) derived from its positive correlation to postoperative WBC count (r=0.6695) may serve as a useful complementary indicator. An individualized CRP threshold setting and integrated interpretation of the WBC count can be more appropriate than using static criteria for differentiating at-risk patients after RYGB. Further studies are needed to validate these findings and determine their generalizability.

From Radio to In-Pipe Acoustic Communication for Smart Water Networks in Urban Environments: Design Challenges and Future Trends

The smart management of water resources is an increasingly important topic in today’s society. In this context, the paradigm of Smart Water Grids (SWGs) aims at a constant monitoring through a network of smart nodes deployed over the water distribution infrastructure. This facilitates a continuous assessment of water quality and the state of health of the pipeline infrastructure, enabling early detection of leaks and water contamination. Acoustic-wave-based technology has arisen as a viable communication technique among the nodes of the network. Such technology can be suitable for replacing traditional wireless networks in SWGs, as the acoustic channel is intrinsically embedded in the water supply network. However, the fluid-filled pipe is one of the most challenging media for data communication. Existing works proposing in-pipe acoustic communication systems are promising, but a comparison between the different implementations and their performance has not yet been reported. This paper reviews existing works dealing with acoustic-based communication networks in real large-scale urban water supply networks. For this purpose, an overview of the characteristics, trends and design challenges of existing works is provided in the present work as a guideline for future research.

An unsupervised leak detection method with aggregating prediction and reconstruction along projection pathway for natural gas gathering pipelines

Early detection of leaks in natural gas gathering pipelines makes proactive maintenance and corrective measures take place more effective, thus enhancing the safe and reliable operation of pipelines and mitigating serious threats to the environment and human life. The data-driven leak detection methods have become a natural choice owing to the extensive deployment of sensors in the pipeline network. However, the supervised and semi-supervised leak detection methods need to utilize a certain amount of leak data to train reliable classifiers, and labeled data usually difficult to obtain in real-world applications especially for the gas industry. Besides, most of data-driven methods today only consider the long-term or short-term patterns hidden in the multivariate time series rather than both, which may reduce their effectiveness since temporal data generated in the real-world applications often relates to a mixture of these two patterns. To settle this challenge, we propose a novel unsupervised leak detection method by utilizing a one-dimensional convolutional autoencoder (1D-CAE) to learn short-term dependency patterns from local time series and a long short-term memory (LSTM) to discover evolving trends about long-term patterns from entire temporal data. The proposed method not only calculates the difference between actual samples and their predictions but also compares the inputs and their reconstructions, where comparisons of reconstruction are further extended from input space to hidden spaces. The obtained deviations are then integrated through the developed integration strategy and employed to calculate their global leak scores. Specially, considering that the magnitudes of deviations integrated together are diverse or there may exist correlation among these deviations caused by correlated neurons across layers, the minimum covariance determinant (MCD) method is employed to scale deviations and eliminate correlations along the projection pathway. The effectiveness of the proposed method is verified on real datasets of natural gas gathering pipeline. In addition, analysis of experimental results demonstrates that the proposed method has good accuracy, and is conducive to operating in the context of uncontrolled long-term monitoring.

Image Recognition Method for Micropores Inside Small Gas Pipelines

To address difficulties in the early detection of small gas pipeline leaks, a method is proposed for the image recognition of micropores inside small gas pipelines. First, we design a feature fusion network (Neck) for a small gas pipeline internal micropores identification network model, introducing BiFPN (bi-directional feature pyramid network) into the Neck, and enhancing the micropores feature fusion capability of the network model using cross-scale feature information fusion. Second, we design a classification prediction network (Head) for a small gas pipeline internal micropores identification network model, constructing a small target detection layer in the classification prediction network, and improving the microporosity detection rate of the network model by improving the detection capability for small leakages. Then, micropore datasets are fed into the network model separately to train the model. Finally, comparison and ablation experiments are used to verify the micropore recognition ability of the network model. The experimental results show that the precision of the image recognition method for micropores inside small gas pipelines is 94.7%, the detection rate is 96.6%, and the average precision is 95.5%, which can better realize the early detection of leakages in small gas pipelines.

A Novel Technique for Detecting Underground Water Pipeline Leakage Using the Internet of Things

Water-pipeline leakage is one of the most common problems that depletes water supplies. Countries like Jordan, which are really experiencing a water deficit, are particularly concerned about this issue. The lack of monitoring tools makes the underground water-pipeline leakage a challenge since the pipelines are invisible. Besides, reducing the amount of time needed to precisely detect and locate the leak is another challenge. If not reduced, the aforementioned element has an effect on cost. A small broken water distribution line costs $64,000 per year. In Jordan, water leakage costs $1.7 million. This expense can be significantly decreased using an effective early water leak detection system. In this paper, we proposed an efficient internet of things system for detecting water-pipeline leakage based on a shielded pipeline, a NodeMCU, a soil moisture sensor, and the Firebase database. We created a baseline system, and then we tested and evaluated the proposed system when various types of soil are used. Furthermore, this paper compared several strategies offered for detecting water-pipeline leaking including the proposed system. The results showed that the proposed system reduced the time required for detecting water-pipeline leakage by 70% and the system hardware cost by 83% compared with the earlier work. It was difficult to compare the total cost of the proposed system with the total cost of previous works since the total cost is not calculated in their systems. &amp;nbsp;Besides, in this paper, we proposed an IoT system for securing the underground water pipelines from adversaries.

EVALUASI KEAMANAN INFORMASI PADA SMAN 1 XYZ MENGGUNAKAN INDEKS KAMI VERSI 4.2

&#x0D; The importance of the process of evaluating information system security for a company, organization, or government agency whose goal is to carry out early detection of information leaks and even disruption of information systems. In this research conducted at SMAN 1 XYZ. The research being conducted was to determine the level of readiness and governance of information security based on ISO/IEC 27001:2013 standardization by using tools, namely the KAMI Information Security Index Version 4.2. In this research the method used to carry out the data collection process is to make direct observations on the objects used as research and questions and answers with the IT department that handles related information systems. Based on the research conducted, it was found that the maturity level of information security is that at the level of need for electronic devices, a score of 20 points is in line with the high KAMI index and is still Level I to Level II. Even though the result of the readiness assessment has a value of 245, this is a safety level of 1 which applies to SMAN 1 XYZ. To achieve a qualification level in accordance with the ISO/IEC 27001: 2013 standard, SMAN 1 XYZ must improve information security internally and externally, in this case external parties, and carry out security assessments on an ongoing and continuous basis.

A New Pressure-Based Modeling Approach for Early Leak Detection in Gas Processing Plants Using Machine Learning

Natural gas is composed mostly of methane, the simplest hydrocarbon molecule, with only one carbon atom. But most gas at the wellhead contains other hydrocarbon molecules known as Natural Gas Liquids (NGL). Heavier gaseous hydrocarbons such as propane (C3H8), normal butane (n-C4H10), isobutane (i- C4H10) and pentanes, may also be processed in gas plants and exported as Liquified Natural Gas (LNG). During operational services in gas plant from inlet to outlet piping, gas leaks tend to occur undetected at some points in the facility. Apart from loss of gas resources, leaks and venting at natural gas processing plants release other pollutants besides methane (e.g., benzene, hexane, hydrogen sulfide) that can threaten air quality and public health. Hence, the need for early detection of gas leaks by using appropriate Machine Learning (ML) models. Insight from existing general flow equations was used to develop a new modelling approach for Machine Learning, in a test case: Gas Plant JK – 52. Input gas pressure data is calibrated and evaluated for consistency in real-time. The data is then corrected for lag-time and used to compute tolerance. Indicated time of alarm is checked against events such as residual gas, supply, pumping, etc. Where alarm is eventless, leak is suspected and eventually confirmed, suggesting that action should be taken to mitigate against the leakage. Following the input of a split training dataset, different types of regressions were used for the machine learning before automating the system for real-time evaluation and detection. Linear regression provided a 39% test accuracy, which was considered too low. This led to the use of random forest regression, which provided a 95% test accuracy and was considered excellent. It is hoped that with continuing data acquisition in gas plants employing this algorithm, further modelling will become more predictive as machine learns from experience.

The Early Detection of LPG Gas Cylinder Leaks in Households Based on the Internet of Things with SMS Message Notifications

Almost all residences, places of business, and restaurants use LPG gas cylinders for daily cooking. We can see nowadays the many problems caused by these gas cylinders, one of which is a fire caused by a leak in the gas cylinder. Therefore we need an appropriate technology to overcome this problem, namely a tool to detect gas leaks using sensors and provide notifications to owners to reduce the impact of fires caused by gas leaks so that people can be safe. In this study, the microcontroller was ATMega 328 Arduino Uno, sim 900a, to provide danger notifications in the form of SMS and MQ-2 gas sensors (LPG, Natural Gas, Coal Gas) with an LPG gas leak detector with hazard notifications via SMS on the impact of a fire. Caused by a gas leak can be detected early so that a fire does not occur in the household.

Case Study of the Use of a Digital Twin for Leak Detection and Quantification in Underground Gas Storage Wells

Summary Underground gas storage (UGS) wells are essential components in energy security. However, UGS wells present a complicated and delicate combination of elements where ensuring safe and secure functionality over long periods is paramount. This paper showcases how a digital twin is used to evaluate and forecast the link between leaks and temperature and pressure trends in a UGS well, allowing the identification and quantification of defects and, subsequently, well barrier integrity. The digital twin used for this application presents advantages compared with other solutions present on the market with regard to the simplified configuration; that is, with minimal input data, the system can produce an accurate and useful output, which is then used in the well integrity decision-making process. UGS wells present additional criticalities with respect to normal production wells due to their longer life span and the repetitive production and injection cycles. This makes early and accurate leak detection essential for the safe management of the well barriers. The proposed digital twin simulates the trends of pressure and temperature within each annulus and compares results with data from the field, allowing the identification of the position and size of leaks. A genetic algorithm is applied to optimize the placement of leaks on their specific barriers. Once a leak is identified, a risk assessment is conducted to evaluate the overall integrity of the well. If the status of the well is found to be critical enough, an intervention may be planned. The studies presented show how the digital twin has been used on two wells with similar problems. At first, it has confirmed the necessity to put the well out of service as opposed to planning maintenance, thereby saving both time and cost. In the second case, it allowed the validation of a solution that led to a 60% reduction in failure consequence, allowing the well to continue operating without major costs or risks. The errors of the resulting simulations were always confined within the 0.5 bar limit highlighting its accuracy. The system has been in use for over a year and has shown great potential in accurate and efficient identification of leaks. This has accelerated the process of well integrity evaluation and allowed timely interventions on wells that required it. On the other hand, the process has highlighted cases where previous assumptions about leak location and size were corrected using the digital twin, therefore reducing the costs of interventions. Finally, the model showcases a clear readiness for predictive capabilities aimed to select, plan, and design fit for purpose mitigating actions.

Feasibility of a TDR-based technique for fluid hydrocarbon leak detection

Undetected leakage of fluid hydrocarbons from pipelines or underground storage tanks into the subsurface environment are environmental and public health hazards. It is evident that there is a need for efficient, effective and accurate technology to detect these leaks rapidly and non-destructively, so as to make the process safe, to make quantitative risk assessment, and to provide effective preventive measures. There are unsurmountable limitations in many existing leak detection techniques. Moreover, early detection of leakage would allow rapid remediation at source to significantly reduce the remediation costs, and more importantly the environmental impact. The results of an experimental investigation for the technical feasibility and practicality of a technique for detection and location of fluid hydrocarbon leaks in underground pipelines and storage tanks based on the principles of time-domain reflectometry (TDR) are presented in this paper. The measurement sensitivity of the technique was evaluated for 3 different types of cables, 2 cable configurations (parallel-wires or coaxial), 2 leaking fluids (tap water or petrol), a single leak or double leaks, and 2 backfill materials (fine sand or gravel) by a series of field-scale model tests. The testing parameters were varied systematically. The experimental results indicate that TDR is a technically feasible technique for the detection of fluid hydrocarbon leaks from pipelines and underground storage tanks when the setup configuration is appropriate.

Predictive factors and diagnostic significance of CT findings for anastomotic leak after gastric cancer surgery: A retrospective analysis

AbstractBackgroundAnastomotic leak following radical gastrectomy poses a significant risk to patients. Despite previous studies, effective methods for diagnosing anastomotic leaks after gastric cancer surgery remain elusive. In this study, we aimed to assess the overall burden of anastomotic leaks and investigate diagnostic factors, particularly radiological signs on postoperative computed tomography (CT), that may facilitate early detection.MethodsWe included a total of 70 gastric cancer patients who underwent curative gastrectomy and underwent CT examination post‐surgery. Among them, 35 patients with anastomotic leak were matched with 35 patients without anastomotic leak. We compared the rates of various types of postoperative complications between the two groups and conducted univariate and multivariate analyses to identify predictive variables for postoperative diagnosis.ResultsPatients with anastomotic leaks experienced significantly longer postoperative hospital stays and higher overall expenditures (p &lt; 0.001). Logistic regression analysis revealed that extraluminal gas at the anastomosis site, fever (T ≥ 38.5°C), and neutrophilia (NE ≥ 78%) on postoperative days 4–7 were independent diagnostic factors for anastomotic leaks (p &lt; 0.05).ConclusionsThe diagnostic factors identified in this study offer valuable insights into early detection of anastomotic leaks. We recommend early CT examination for patients exhibiting consistent fever and neutrophilia between postoperative days 4 and 7 following gastric cancer surgery.

Highly sensitive and wrappable room temperature wireless gasochromic and chemiresistive dual-response H2 sensors using spray coating

Developing highly reliable, sensitive and room temperature operation hydrogen (H2) sensors is essential to adapt successfully to the H2 economy. Despite the development of various H2 sensors, detecting leaks and pinpointing their precise location remains challenging because of the highly diffusive nature of H2 and environmental factors such as the wind direction. This study reports the development of room temperature, wireless, dual-signal, wrappable, chemiresistive, and eye-readable gasochromic H2 sensors using solution-based and low temperature annealed SnO2/WO3 films on polyimide substrate. These sensors can be wrapped around any point source, such as flanges, rendering the early detection and pinpointing of H2 leaks. An optimized spray-coated gasochromic WO3 film achieves a color change value (ΔE) of 11 with a 6 s response time at 4% H2 and low eye detectable limit of 0.2%. Simultaneously, because a patterned spray-coated gasochromic layer does not interfere with the active area of a SnO2-based chemiresistive sensor, the resistance value of the sensor changes by more than 11,000 times at 1% H2 with a wide concentration range from 0.005% to 2% of H2 at room temperature. Such a sensor can be easily applied to various nonplanar surfaces, while the Bluetooth system integration enables wireless monitoring via smartphones. Our study provides a simple strategy to develop wrappable dual-signal wireless sensors for reliable detection and monitoring of H2 leaks at room temperature.

Continuous pH monitoring using a sensor for the early detection of anastomotic leaks.

Anastomotic leaks (AL) and staple line leaks are a serious post-operative complication that can develop following bariatric surgery. The delay in the onset of symptoms following a leak usually results in reactive diagnostics and treatment, leading to increased patient morbidity and mortality, and a clinical and economic burden on both the patient and the hospital. Despite support in literature for pH as a biomarker for early detection of AL, the current methods of pH detection require significant clinician involvement and resources. Presented here is a polyaniline (PANI)-based pH sensor that can be connected inline to surgical drains to continuously monitor peritoneal secretion in real time for homeostatic changes in pH. During this study, the baseline peritoneal fluid pH was measured in two pigs using the PANI sensor and verified using a benchtop pH probe. The PANI sensor was then utilized to continuously monitor the changes in the pH of peritoneal effluent, as a gastric leak was simulated. The inline sensors were able to detect the resulting local changes in drainage pH within 10 min of leak induction. The successful implementation of this sensor in clinical practice can both enable high efficiency continuous monitoring of patient status and drastically decrease the time required to detect AL, thus potentially decreasing the clinical and economic burden incurred by gastric leaks.

Batteryless Sensor Devices for Underground Infrastructure—A Long-Term Experiment on Urban Water Pipes

Drinking water is becoming increasingly scarce as the world’s population grows and climate change continues. However, there is great potential to improve drinking water pipelines, as 30% of fresh water is lost between the supplier and consumer. While systematic process monitoring could play a crucial role in the early detection and repair of leaks, current practice requires manual inspection, which is both time-consuming and costly. This project envisages maintenance-free measurements at numerous locations within the underground infrastructure, a goal that is to be achieved through the use of a harvesting device mounted on the water pipe. This device extracts energy from the temperature difference between the water pipe and the soil using a TEG (thermoelectric generator), takes sensor measurements, processes the data and transmits it wirelessly via LoRaWAN. We built 16 harvesting devices, installed them in four locations and continuously evaluated their performance throughout the project. In this paper, we focus on two devices of a particular type. The data for a full year show that enough energy was available on 94% of the days, on average, to take measurements and transmit data. This study demonstrates that it is possible to power highly constrained sensing devices with energy harvesting in underground environments.

Machine Learning Approach Based on Smart Ball COMSOL Multiphysics Simulation for Pipe Leak Detection

Due to the changing flow conditions during the pipeline’s operation, several locations of erosion, damage, and failure occur. Leak prevention and early leak detection techniques are the best pipeline risk mitigation measures. To reduce detection time, pipeline models that can simulate these breaches are essential. In this study, numerical modeling using COMSOL Multiphysics is suggested for different fluid types, velocities, pressure distributions, and temperature distributions. The system consists of 12 meters of 8-inch pipe. A movable ball with a diameter of 5 inches is placed within. The findings show that dead zones happen more often in oil than in gas. Pipe insulation is facilitated by the gas phase’s thermal inefficiency (thermal conductivity). The fluid mixing is improved by 2.5 m/s when the temperature is the lowest. More than water and gas, oil viscosity and dead zones lower maximum pressure. Pressure decreases with maximum velocity and vice versa. The acquired oil data set is utilized to calibrate the Support Vector Machine and Decision Tree techniques using MATLAB R2021a, ensuring the precision of the measurement. The classification result reveals that the Support Vector Machine (SVM) and Decision Tree (DT) models have the best average accuracy, which is 98.8%, and 99.87 %, respectively.

Air Quality Detection and Notification using Arduino IDE

Abstract: Truck drivers typically work long hours and occasionally in highly polluted settings like mines. Accident prevention at the workplace relies heavily on the health and alertness of the driver. The cabin's air quality can sometimes get worse, which can make drivers tired. A gas detector is a piece of equipment that works as part of a safety system to tell you if there are gases in a certain area. This type of project can communicate with the control system to automatically switch off process and is used to detect gas leaks and other emissions. There are numerous gases that can be harmful to organic life, such as humans or animals, which is why this kind of device is important. Oxygen depletion and combustible, flammable, and toxic gases can be detected with gas detectors. This kind of device is used a lot in industry and can be found monitoring manufacturing processes in places like oil rigs. Gas leak detection is the process of using sensors to find gas leaks that could be dangerous. When a hazardous gas is detected, these sensors typically emit an audible alarm. Early detection of gas leaks, when they occur, is one way to cut losses caused by leaks. One of the many technologies that helps stop gas leaks from harming people even more is the mobile sensor. Another approach to overcoming losses from both material and non-material sources is the creation of mobile sensors. It is anticipated that it will eventually be overcome using a gas sensor MQ-2 as a detector before it has a wider impact. MQ-2 is chosen due to inexpensive and long lifespan. The Arduino IDE is used to implement the C language, which is used to calibrate and configure MQ-2. With a distance of about 0-10 cm between the gas sensor and the point of leakage, it is anticipated that the results will be accurate to 80 percent after the gas sensor has been configured.

Early Postoperative Small Bowel Obstruction: Can We Blame the Drain?

Abdominal drains are frequently used in both elective and emergency laparotomies, in order to prevent formation of postoperative collections in gravity-dependent positions or as means of early detection of postoperative hemorrhage and anastomotic leaks. Despite the benefits of their use, rare drain-related complications have been reported in the literature, including adhesional band formation and intestinal erosion. Herein, we present an extremely rare case of early, non-resolving postoperative small bowel obstruction after abdominoperineal resection for low rectal cancer, which was induced from firm extrinsic compression of the distal ileum by a corrugated pelvic drain.

Modular stimuli-responsive hydrogel sealants for early gastrointestinal leak detection and containment

Millions of patients every year undergo gastrointestinal surgery. While often lifesaving, sutured and stapled reconnections leak in around 10% of cases. Currently, surgeons rely on the monitoring of surrogate markers and clinical symptoms, which often lack sensitivity and specificity, hence only offering late-stage detection of fully developed leaks. Here, we present a holistic solution in the form of a modular, intelligent suture support sealant patch capable of containing and detecting leaks early. The pH and/or enzyme-responsive triggerable sensing elements can be read out by point-of-need ultrasound imaging. We demonstrate reliable detection of the breaching of sutures, in as little as 3 hours in intestinal leak scenarios and 15 minutes in gastric leak conditions. This technology paves the way for next-generation suture support materials that seal and offer disambiguation in cases of anastomotic leaks based on point-of-need monitoring, without reliance on complex electronics or bulky (bio)electronic implantables.

Early detection of anastomotic leak with C-reactive protein increases the chances of anastomotic salvage.

Anastomotic leak results in increased morbidity and affects functional and oncological outcomes after colectomy. Measurement of C-reactive protein (CRP) allows early detection of anastomotic leaks. The aim of this study was to evaluate the benefit to the patient of earlier diagnosis and management of anastomotic leaks, namely avoiding takedown of the anastomosis. Patients with an anastomotic fistula after elective colorectal surgery from 2010 to 2020 were included. Three periods were defined according to progressive adherence to the CRP protocol in our department. A comparison was made between the periods 'before' (2010-2013) and 'after' (2016-2020) in terms of morbidity, mortality, anastomotic salvage, days spent in hospital within the first postoperative month, timely adjuvant chemotherapy and anastomotic stenosis. Out of 2655 elective colorectal operations, 171 patients presented with an anastomotic leak and 123 patients were included in the study. In univariate analysis, patients in the 'after' group had fewer severe complications (Clavien-Dindo Grade III to IV, 66.7% vs. 56.9; p= 0.017); the difference did not reach significance regarding timely postoperative chemotherapy (p= 0.058) and anastomotic stenosis (p= 0.682). In both, univariate and multivariate analysis, the 'after' period increased the chances of preserving the anastomosis (OR=2.37 [1.08-5.17]) and increased the number of days out of hospital (p= 0.0002). A CRP-based protocol for the screening of anastomotic leaks after colorectal surgery was related to increased anastomotic conservation, a decreased impact and severity of the leak and a shorter length of hospital stay.

Video-Based Time-Series Feature Extraction Image Encoding Methods for Enhanced Colorimetric Gas Concentration Estimation

Early detection and intervention of gas leaks can reduce industrial risks. Numerous early detection methods have been developed and applied in the industrial field, but they require professional analysis technology, long analysis time, and relatively expensive equipment. Strategies to reduce industrial gas hazards constantly require the development of new, efficient and reliable devices.In the past few decades, various types of gas sensors have been developed based on semiconductors, optical fibers, acoustic waves and other technologies. A significant amount of work has been done in recent years to make sensors smaller, more sensitive, more visually responsive, more manageable, more personal, and more wearable. However, these functions require expensive equipment, complex skills, and large amounts of power. In this regard, colorimetric sensors are of great interest due to their simplicity, ease of manufacture, low cost, visual response, and ease of interpretation without power consumption. However, current colorimetric sensors have some limitations to overcome, such as sensitivity, high cost, early detection and accuracy for use in industrial safety systems. Conventional colorimetric sensor studies use algorithms to compare discoloration with the naked eye, estimate gas concentrations with simple statistical methods, or estimate simple discoloration information using machine learning algorithms to estimate time-series data. Algorithms are trained on measured images or time series data extracted from images. Signal processing focuses on denoising done by scaling time series data. These studies using machine learning and deep learning-based analytics for colorimetric sensor studies did not give sufficient consideration to data coding. Machine learning of time series data is performed using a time series decomposition method that separates time dependencies. I am trying to analyze time-series data through image encoding.In this study, a time series data analysis technique using CNN (Convolutional Neural Network) including multidimensional image encoding was applied to improve the gas concentration estimation accuracy. The estimation accuracy obtained in this study was higher than the estimation accuracy obtained by applying existing statistical methods such as Auto-Regressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS) and machine learning techniques such as Multi-layer Perceptron (MLP).We focused on estimating gas concentrations using a time-series-based colorimetric analysis method developed based on colorimetric fabric detection data. Time series data obtained through gas experiments were encoded into images to classify the color value change trend of gas concentration. Image encoding improves the efficiency of specifying gas-exposed sections and estimating gas concentrations within the entire section. Compared to the concentration estimation accuracy of the existing data classification method, MLP was improved by more than 2.5%. In addition, the accuracy was improved by applying a CNN that learned multidimensional processing of sensor data through image encoding. As a result, it was confirmed that the estimation accuracy was improved by 6.1% compared to the basic estimation technique. Although this method has limited data form and application fields, it is effective for subjects such as ours. The proposed technology can be applied to the next-generation smart industrial safety system. Figure 1