Equipment Malfunction Research Articles

Fabric surface defect classification and systematic analysis using a cuckoo search optimized deep residual network

Fabric defects can significantly impact the quality of a textile product. By analyzing the types and frequencies of defects, manufacturers can identify process inefficiencies, equipment malfunctions, or operator errors. Although deep learning networks are accurate in classification applications, some defects may be subtle and difficult to detect, while others may have complex patterns or occlusions. CNNs may struggle to capture a wide range of defect variations and generalize well to unseen defects. Discriminating between genuine defects and benign variations requires sophisticated feature extraction and modeling techniques. This paper proposes a residual network-based CNN model to enhance the classification of fabric defects. A pretrained residual network, ResNet50, is fine-tuned to classify fabric defects into four categories: holes, objects, oil spots, and thread errors on the fabric surface. The fine-tuned network is further optimized via cuckoo search optimization using classification error as a fitness function. The network is systematically analyzed at different layers, and the investigation of classification results are reported using a confusion matrix and classification accuracy for each class. The experimental results confirm that the proposed model achieved superior performance with 95.36% accuracy and a 95.35% F1 score for multiclass classification. In addition, the proposed model achieved higher accuracy with similar or fewer trainable parameters than traditional deep CNN networks.

327 Sustained Improvement in Compliance With Use of Sequential Compression Devices in a Neurosurgery Patient Population of a Safety-Net Hospital

INTRODUCTION: Sequential Compression Devices (SCDs) are utilized in perioperative patients given increased risks of deep venous thrombosis from mobility reductions and post-operative inflammatory responses. Additionally, mechanical prophylaxis is crucial in patients where chemical prophylaxis is contraindicated. Previous work has found SCD compliance far less than expected. METHODS: Across a 9-month period (August-April), we tracked which neurosurgical patients in stepdown units had SCDs on and properly functioning. When not on or properly functioning, we documented the missing element. Compliance was calculated daily as the percentage of patients who were SCD compliant out of all patients with SCD orders, then averaged over the month, for each month. Most common barriers to compliance were identified. Together with nursing management, we designed and implemented a best practice alert to facilitate nursing education and supply chain management, at month 3. The impact was tracked over the next six months, with a 4-months break from November-February. RESULTS: Compliance averaged 19.7% (n = 95) during August, and 38.4% (n = 131) in September. After implementation of the best practice nursing alert and supply chain upgrades, compliance was 48.8% (n = 150) in October, 41.2% (n = 104) in March, and 45.9% (n = 76) in April. Residual barriers to compliance included patient behavior and equipment issues. Compliance was significantly increased from baseline in August to October (z = 5.042). The significant difference was sustained through March (z = 3.402) and April (z = 3.730). CONCLUSIONS: While initial improvement was attributed to a Hawthorne effect, implementation of the best practice nursing alert likely facilitated the sustained improvement in SCD compliance despite the break in surveillance. SCD compliance nonetheless remained below 50%. Further study is warranted to address the remaining barriers, such as improving patient engagement and minimizing equipment malfunction.

Predictive maintenance in oil and gas facilities, leveraging ai for asset integrity management

This paper explores the application of AI in predictive maintenance within oil and gas facilities, discussing its benefits, challenges, and future prospects. Through the integration of AI-driven analytics and real-time data monitoring, oil and gas companies can enhance their asset integrity management practices, ultimately driving cost savings and operational excellence. Predictive maintenance has become indispensable in the oil and gas industry, serving as a pivotal strategy to uphold operational efficiency and preserve asset integrity. This paper delves into the profound impact of artificial intelligence (AI) technologies on predictive maintenance, ushering in a new era of proactive equipment management. By harnessing AI capabilities, oil and gas companies can preempt equipment failures, curtail downtime, and refine maintenance protocols, thereby optimizing overall operational performance. The integration of AI in predictive maintenance marks a paradigm shift, offering a proactive approach to asset management. Leveraging AI-driven analytics and real-time data monitoring, oil and gas facilities can fortify their asset integrity management practices. Through predictive algorithms and machine learning models, these technologies empower companies to forecast equipment malfunctions with unprecedented accuracy, allowing for timely interventions and mitigating potential risks the benefits of AI-powered predictive maintenance in the oil and gas sector are multifaceted the future of predictive maintenance in the oil and gas industry is brimming with promise. As AI technologies continue to evolve, we can anticipate further advancements in predictive analytics, fault detection, and decision support systems. By embracing innovation and collaboration, oil and gas companies can harness the full potential of AI-driven predictive maintenance, cementing their position as industry leaders in asset management and operational efficiency.

IMPROVING THE QUALITY OF MAINTENANCE AND REPAIR OF TRACTION SUBSTATIONS EQUIPMENT

The article deals with maintenance and repair of traction substations. The general problem of improving the maintenance and repair system of traction substations of electrified railways is described. An analysis of methods and means of maintenance and repair of substation equipment was carried out. The causes of malfunctions of the traction substations equipment are analyzed/ The distribution of malfunctions of TP equipment by types of equipment was analyzed. The results of transformer inspections are presented.

Совершенствование технологии эксплуатации инженерных систем жилых зданий на основе использования организационно-технологического моделирования

The author has proposed a model for the technical operation of residential buildings, which considers two main functions for maintaining the housing stock: scheduled preventive inspection and repair of technical facilities, as well as the elimination of sudden malfunctions of technical equipment, in particular emergency ones. It is believed that the work team can begin scheduled preventive maintenance and inspection only when all requests for sudden malfunctions have been satisfied.
 To conduct the study, the theory of queuing is used - one of the probabilistic methods.
 The main parameters of the model are: the average time between the occurrence of equipment malfunctions, the average time for eliminating such malfunctions, the average time for preventive inspection and repair of one technical object. Based on the methods of queuing theory, the characteristics of the system are determined that determine the quality of its work, as well as the boundaries of changes in parameters at which the system copes with the work from the standpoint of one or another criterion.

A differential equation for inverse point kinetics

The reactivity that represents the percentage departure of a nuclear reactor from its criticality condition is perhaps the most important individual property since it is directly related to the nuclear reactor’s safe operation. Control systems are used to limit the rate of increase in reactivity. The development of systems for monitoring the reactivity, from the nuclear power data acquired from the plant's onboard electronics, requires a constant improvement of the nuclear kinetic models.The transient situations that emerge in nuclear reactors can be predicted from the changes in the neutron flux and, therefore, it is possible to make a sufficiently accurate prediction about the consequences of the disturbances relating to the magnitude of the neutron flux, which varies over time, by using the integral parameters that represent the nuclear reactor core. The point kinetic equations relate these parameters and, in this way, allow the transient situations that can occur in a nuclear reactor to be studied.The reactivity is usually determined by solving the inverse point kinetic equation, which is an integral equation that depends on the nuclear power variation history. In this paper, we present a method to calculate the reactivity through the solution of an ordinary differential equation that does not depend on the nuclear power variation history, then allows the prompt recovery of the reactimeter in case of loss of the nuclear power data acquisition or malfunction of such equipment (Zarei, 2022; Ansari, 1991).The presented paper is organized as follows: Section 1 contains the basic concepts of point kinetics equations and the integral formalism for the reactivity calculation. The mathematical formalism that leads to the differential equation for the reactivity is presented in Section 2. The prompt recovery of the reactivity using the proposed method is discussed in Section 3. The results are shown in Section 4 and the conclusion is presented in Section 5.

RHEOLOGICAL AND COLLOID-STRUCTURAL BEHAVIOUR OF HIGH-VISCOSITY CRUDE OIL AND EMULSION AFTER WAVE ACTION

One of the main problems in oil production is the formation of stable oil-water emulsions that cause corrosion of pipelines, malfunction of pumping equipment, and poisoning of catalysts at refineries. The features of the viscosity-temperature behaviour of high-viscosity resinous crude oil from the Russkoye field (Yamal-Nenets autonomous district) and its 30 wt% emulsion after exposure to electromagnetic and low-frequency acoustic fields are investigated. Electromagnetic treatment of crude oil leads to a decrease in the phase transition temperature and the yield strength coefficient. Low-frequency acoustic processing of the emulsion is accompanied by a decrease in the effective viscosity and the yield strength coefficient. After a complex wave action, the viscosity-temperature characteristics of crude oil continue to fall, and the stability of the formed emulsions decreases due to the intense coalescence of water-phase droplets. It is shown that the amount of released asphaltenes in oil-containing systems decreases after wave treatment. On the contrary, after a complex impact, their content in crude oil increases, while in the emulsion it continues to decrease. This is likely to occur due to the release of hydrocarbons occluded in the asphaltene structure into the liquid oil phase.

Evaluation of risk factors affecting the safety of coal mine construction projects using an integrated DEMATEL-ISM approach

Purpose The purpose is to identify and evaluate the safety risk factors in the coal mine construction process.Design/methodology/approach The text mining technique was applied in the stage of safety risk factor identification. The association rules method was used to obtain associations with safety risk factors. Decision-Making Trial and Evaluation Laboratory (DEMATEL) and Interpretative Structural Modeling (ISM) were utilized to evaluate safety risk factors.Findings The results show that 18 safety risk factors are divided into 6 levels. There are 12 risk transmission paths in total. Meanwhile, unsafe behavior and equipment malfunction failure are the direct causes of accidents, and inadequate management system is the basic factor that determines the safety risk status.Research limitations/implications Due to the limitation of the computational matrix workload, this article only categorizes numerous lexical items into 18 factors. Then, the workshop relied on a limited number of experts; thus, the findings may be potentially biased. Next, the accident report lacks a universal standard for compilation, and the use of text mining technique may be further optimized. Finally, since the data are all from China, subsequent cross-country studies should be considered.Social implications The results can help China coal mine project managers to have a clear understanding of safety risks, efficiently carry out risk hazard identification work and take timely measures to cut off the path of transmission with risks identified in this study. This helps reduce the economic losses of coal mining enterprises, thus improving the safety standards of the entire coal mining industry and the national standards for coal mine safety policy formulation.Originality/value Coal mine construction projects are characterized by complexity and difficulties in construction. Current research on the identification and assessment of safety risk factors in coal mine construction is insufficient. This study combines objective and systematic research approaches. The findings contribute to the safety risk management of China coal mine construction projects by providing a basis for the development of safety measures.

Perception of power quality disturbances using Fourier, Short-Time Fourier, continuous and discrete wavelet transforms

Electric power utilities must ensure a consistent and undisturbed supply of power, with the voltage levels adhering to specified ranges. Any deviation from these supply specifications can lead to malfunctions in equipment. Monitoring the quality of supplied power is crucial to minimize the impact of fluctuations in voltage. Variations in voltage or current from their ideal values are referred to as "power quality (PQ) disturbances," highlighting the need for vigilant monitoring and management. Signal processing methods are widely used for power system applications which include understanding of voltage disturbance signals and used for retrieval of signal information from the signals Different signal processing methods are used for extracting information about a signal. The method of Fourier analysis involves application of Fourier transform giving frequency information. The method of Short-Time Fourier analysis involves application of Short-Time Fourier transform (STFT) giving time–frequency information. The method of continuous wavelet analysis involves application of Continuous Wavelet transform (CWT) giving signal information in terms of scale and time where frequency is inversely related to scale. The method of discrete wavelet analysis involves application of Discrete Wavelet transform (DWT) giving signal information in terms of approximations and details where approximations and details are low and high frequency representation of original signal. In this paper, an attempt is made to perceive power quality disturbances in MATLAB using Fourier, Short-Time Fourier, Continuous Wavelet and Discrete Wavelet Transforms. Proper understanding of the signals can be possible by transforming the signals into different domains. An emphasis on application of signal processing techniques can be laid for power quality studies. The paper compares the results of each transform using MATLAB-based visualizations. The discussion covers the advantages and disadvantages of each technique, providing valuable insights into the interpretation of power quality disturbances. As the paper delves into the complexities of each method, it takes the reader on a journey of signal processing complexities, culminating in a nuanced understanding of power quality disturbances and their representations across various domains. The outcomes of this research, elucidated through energy values, 3D plots, and comparative analyses, contribute to a comprehensive understanding of power quality disturbances. The findings not only traverse theoretical domains but also find practical utility in real-world scenarios.

When a Critically Ill Child is Oceans Away From a PICU: A Military Pediatric CCAT Mission.

A 4-year-old former 26-week premature male presented to the U.S. Naval Hospital Guam emergency department in respiratory failure secondary to human metapneumovirus requiring urgent intubation. His condition was complicated by a bradycardic arrest requiring 15 minutes of resuscitation before the return of circulation. He was admitted to the adult intensive care unit and was managed via pediatric telecritical care from San Diego. He developed acute respiratory distress syndrome, acute renal failure, hypotension requiring multiple pressors, and fluid overload necessitating bilateral chest tubes and two peritoneal drains. A pediatric critical care air transport team departed San Antonio within 36 hours of activation and transported the patient via C-17 to Hawaii, performing a tail swap to a KC-135. Before takeoff, mechanical delays caused prolonged ground time and lack of temperature control resulted in patient's hyperthermia to reach 104.2°F despite the ice packing. The ambient temperature caused equipment malfunction (suction, handheld blood analyzer, and ventilator), necessitating manual bagging. Despite initial temperature challenges, the team removed 700 mL of peritoneal fluid and substantially reduced the patient's ventilator settings. After 22 hours of care, the team arrived with the patient to a civilian pediatric intensive care unit in CA, USA. Over several weeks, the patient made a full recovery. This pediatric critical care air transport mission highlights the complications intrinsic to air transport. Missions of this severity and length benefit from utilization of pediatric specialists to minimize morbidity and mortality. Highlighting the challenges related to preparation, air frame, and equipment malfunction should help others prepare for future pediatric air transports.

DenMerD: a feature enhanced approach to radar beam blockage correction with edge-cloud computing

AbstractIn the field of meteorology, the global radar network is indispensable for detecting weather phenomena and offering early warning services. Nevertheless, radar data frequently exhibit anomalies, including gaps and clutter, arising from atmospheric refraction, equipment malfunctions, and other factors, resulting in diminished data quality. Traditional radar blockage correction methods, such as employing approximate radial information interpolation and supplementing missing data, often fail to effectively exploit potential patterns in massive radar data, for the large volume of data precludes a thorough analysis and understanding of the inherent complex patterns and dependencies through simple interpolation or supplementation techniques. Fortunately, edge computing possesses certain data processing capabilities and cloud center boasts substantial computational power, which together can collaboratively offer timely computation and storage for the correction of radar beam blockage. To this end, an edge-cloud collaborative driven deep learning model named DenMerD is proposed in this paper, which includes dense connection module and merge distribution (MD) unit. Compared to existing models such as RC-FCN, DenseNet, and VGG, this model greatly improves key performance metrics, with 30.7$$\%$$ % improvement in Critical Success Index (CSI), 30.1$$\%$$ % improvement in Probability of Detection (POD), and 3.1$$\%$$ % improvement in False Alarm Rate (FAR). It also performs well in the Structure Similarity Index Measure (SSIM) metrics compared to its counterparts. These findings underscore the efficacy of the design in improving feature propagation and beam blockage accuracy, and also highlights the potential and value of mobile edge computing in processing large-scale meteorological data.

Analysis of the Influence of Gas Leakage in The Dipleg of Cyclone Separators on Particle Properties

The FCC unit uses a cyclone separator for gas-solid separation of catalysts from flue gas or oil and gas. When the cyclone separator experiences a gas leakage fault, it directly affects its separation performance, causing excessive catalyst emissions and leading to the occurrence of catalyst running faults. However, there is currently a lack of diagnostic technology for cyclone separator equipment malfunction and gas leakage. Therefore, the influence of the dipleg of the cyclone separator on the particle loss rate under different gas leakage velocities was investigated experimentally. Experiments show that under normal conditions, particles are subject to multiple cycle separation, and fewer particles randomly enter the riser with the upward rotating flow to escape, which is mainly determined by the structure size and inlet velocity of the cyclone separator. When gas leakage occurs in the dipleg, the higher the gas leakage velocity, the higher the particle loss rate. As the number of particle cycles increases, the loss rate gradually decreases. For this purpose, the cyclone separator inside the FCC unit in the industrial site is taken as the object. In response to multiple cyclone separator loss faults, the changes in process parameters and collected catalyst particle properties of the cyclone separator are analyzed, and the changes in the running dose inside the device during operation are analyzed. Based on the analysis results, the operation of the unit is optimized and adjusted to avoid unplanned shutdown and maintenance. Therefore, based on this, a fault diagnosis technology for catalyst loss in FCC unit cyclone separators based on particle property parameters has been created, which has the characteristics of accuracy and reliability and can be applied to the analysis and diagnosis of catalyst loss faults in FCC unit.

Medical images under tampering

Attacks on deep learning models are a constant threat in the world today. As more deep learning models and artificial intelligence (AI) are being implemented across different industries, the likelihood of them being attacked increases dramatically. In this context, the medical domain is of the greatest concern because an erroneous decision made by AI could have a catastrophic outcome and even lead to death. Therefore, a systematic procedure is built in this study to determine how well these medical images can resist a specific adversarial attack, i.e. a one-pixel attack. This may not be the strongest attack, but it is simple and effective, and it could occur by accident or an equipment malfunction. The results of the experiment show that it is difficult for medical images to survive a one-pixel attack.

Polyester Reçine Üretim Tesisinde Fonksiyonel Rezonans Analiz Yöntemi (FRAM) ile Risk Analizi

There are various hazards and risks in the workflow processes in polyester resin production facilities. The most important of these dangers and risks are; It is related to chemical processes, fire and explosion, equipment malfunctions and storage processes of the products obtained. This study aims to analyze the potential hazards and risks that may be encountered in a polyester resin production facility in the Marmara region, from the arrival of the raw material to the facility, to its processing and storage of the resulting products, with the Functional Resonance Analysis Method (FRAM) and to identify the stages that prevent the processes from being optimized. It has been prepared to make suggestions both for improving workflow processes and reducing risks in the process.

Hot Strip Mill Gearbox Monitoring and Diagnosis Based on Convolutional Neural Networks Using the Pseudo-Labeling Method

The steel industry is typical process manufacturing, and the quality and cost of the products can be improved by efficient operation of equipment. This paper proposes an efficient diagnosis and monitoring method for the gearbox, which is a key piece of mechanical equipment in steel manufacturing. In particular, an equipment maintenance plan for stable operation is essential. Therefore, equipment monitoring and diagnosis to prevent unplanned plant shutdowns are important to operate the equipment efficiently and economically. Most plant data collected on-site have no precise information about equipment malfunctions. Therefore, it is difficult to directly apply supervised learning algorithms to diagnose and monitor the equipment with the operational data collected. The purpose of this paper is to propose a pseudo-label method to enable supervised learning for equipment data without labels. Pseudo-normal (PN) and pseudo-abnormal (PA) vibration datasets are defined and labeled to apply classification analysis algorithms to unlabeled equipment data. To find an anomalous state in the equipment based on vibration data, the initial PN vibration dataset is compared with a PA vibration dataset collected over time, and the equipment is monitored for potential failure. Continuous wavelet transform (CWT) is applied to the vibration signals collected to obtain an image dataset, which is then entered into a convolutional neural network (an image classifier) to determine classification accuracy and detect equipment abnormalities. As a result of Steps 1 to 4, abnormal signals have already been detected in the dataset, and alarms and warnings have already been generated. The classification accuracy was over 0.95 at d=4, confirming quantitatively that the status of the equipment had changed significantly. In this way, a catastrophic failure can be avoided by performing a detailed equipment inspection in advance. Lastly, a catastrophic failure occurred in Step 9, and the classification accuracy ranged from 0.95 to 1.0. It was possible to prevent secondary equipment damage, such as motors connected to gearboxes, by identifying catastrophic failures promptly. This case study shows that the proposed procedure gives good results in detecting operation abnormalities of key unit equipment. In the conclusion, further promising topics are discussed.

A Dual-Task Learning Approach for Bearing Anomaly Detection and State Evaluation of Safe Region

Predictive maintenance has emerged as an effective tool for curbing maintenance costs, yet prevailing research predominantly concentrates on the abnormal phases. Within the ostensibly stable healthy phase, the reliance on anomaly detection to preempt equipment malfunctions faces the challenge of sudden anomaly discernment. To address this challenge, this paper proposes a dual-task learning approach for bearing anomaly detection and state evaluation of safe regions. The proposed method transforms the execution of the two tasks into an optimization issue of the hypersphere center. By leveraging the monotonicity and distinguishability pertinent to the tasks as the foundation for optimization, it reconstructs the SVDD model to ensure equilibrium in the model's performance across the two tasks. Subsequent experiments verify the proposed method's effectiveness, which is interpreted from the perspectives of parameter adjustment and enveloping trade-offs. In the meantime, experimental results also show two deficiencies in anomaly detection accuracy and state evaluation metrics. Their theoretical analysis inspires us to focus on feature extraction and data collection to achieve improvements. The proposed method lays the foundation for realizing predictive maintenance in a healthy stage by improving condition awareness in safe regions.

General value functions for fault detection in multivariate time series data.

One of the greatest challenges to the automated production of goods is equipment malfunction. Ideally, machines should be able to automatically predict and detect operational faults in order to minimize downtime and plan for timely maintenance. While traditional condition-based maintenance (CBM) involves costly sensor additions and engineering, machine learning approaches offer the potential to learn from already existing sensors. Implementations of data-driven CBM typically use supervised and semi-supervised learning to classify faults. In addition to a large collection of operation data, records of faulty operation are also necessary, which are often costly to obtain. Instead of classifying faults, we use an approach to detect abnormal behaviour within the machine's operation. This approach is analogous to semi-supervised anomaly detection in machine learning (ML), with important distinctions in experimental design and evaluation specific to the problem of industrial fault detection. We present a novel method of machine fault detection using temporal-difference learning and General Value Functions (GVFs). Using GVFs, we form a predictive model of sensor data to detect faulty behaviour. As sensor data from machines is not i.i.d. but closer to Markovian sampling, temporal-difference learning methods should be well suited for this data. We compare our GVF outlier detection (GVFOD) algorithm to a broad selection of multivariate and temporal outlier detection methods, using datasets collected from a tabletop robot emulating the movement of an industrial actuator. We find that not only does GVFOD achieve the same recall score as other multivariate OD algorithms, it attains significantly higher precision. Furthermore, GVFOD has intuitive hyperparameters which can be selected based upon expert knowledge of the application. Together, these findings allow for a more reliable detection of abnormal machine behaviour to allow ideal timing of maintenance; saving resources, time and cost.

Source Current Harmonic Cancellation in Distribution System by Using ANFIS Controller

Ensuring a reliable and stable power supply to consumers is of utmost importance in modern distribution systems. Many power quality issues, such as voltage fluctuations, harmonic distortions, transient events, load forecasting, and voltage sag/swell compensation, can lead to operational inefficiencies and compromise the performance of sensitive electronic equipment. The main causes of power quality problems are short circuits and overloads, reactive power imbalance, transients, equipment malfunctions, and ground issues. The ANFIS model leverages the strengths of both neural networks and fuzzy logic to effectively address power quality challenges. Thus, by using the ANFIS model for power quality improvement, we reduce the supply current harmonics by maintaining IEEE 519 standards. The stimulation results are implemented using MATLAB Simulink software. The simulation results are verified source current, load current and supply voltage, The THD value of source current.

Towards Resilient Energy Forecasting: A Robust Optimization Approach

Energy forecasting models deployed in industrial applications face uncertainty w.r.t. data availability, due to network latency, equipment malfunctions or data-integrity attacks. In particular, the case when a subset of features that has been used for model training becomes unavailable when the model is used operationally poses a major challenge to forecasting performance. Ad-hoc solutions, e.g., retraining without the missing features, may work for a small number of features, but they soon become impractical, as the number of models grows exponentially with the number of features. In this work, we present a principled approach to introducing resilience against missing features in energy forecasting applications via robust optimization. Specifically, we formulate a robust regression model that is optimally resilient against missing features at test time, considering both point and probabilistic forecasting. We develop three solution methods for the proposed robust formulation, all leading to Linear Programming problems, with varying degrees of tractability and conservativeness. We provide an extensive empirical validation of the proposed methods in prevalent applications, namely, electricity price, load, wind production, and solar production, forecasting, and we further compare against well-established benchmark models and methods of dealing with missing features, i.e., imputation and retraining. Our results demonstrate that the proposed robust optimization approach outperforms imputation-based models and exhibits similar performance to retraining without the missing features, while also maintaining computational practicality. To the best of our knowledge, this is the first work that introduces resilience against missing features into energy forecasting.

Measuring methane destruction efficiency in gas flares with dual comb spectroscopy

Gas flaring is used as an alternative to venting when waste gases cannot be captured from industrial processes such as oil and natural gas production, chemical processing, and waste management. In the oil and natural gas production sector alone, an estimated 3.5 % of total global natural gas production is flared. Survey studies have shown that the methane destruction efficiency (DE) of flares is lower than expected due to real-world conditions (weather and equipment malfunction) and estimate that improving flare efficiency is a 0.5 Tg/yr methane emissions reduction opportunity. Continuous monitoring of flare DE would provide the opportunity for feedback to lower emissions; however, there are currently no technologies used at scale that can provide such a measurement. Here we present a method for measuring the operational methane DE from flares by monitoring methane levels in flares using dual-frequency comb spectroscopy. This method leverages the temperature-dependent absorption fingerprint of methane to differentiate heated and ambient methane. We assess the capabilities of this technique through a set of laboratory-based experiments utilizing a partially premixed methane flame. We estimate the limit of detection (LOD) and sensitivity of the measurements for directly monitoring a flame, and monitoring a flame from a distance of 1 km in the presence of ambient methane. For our configuration, a targeted monitoring scenario (direct flame measurement) results in the ability to distinguish methane DE up to 99.9 %; whereas in the presence of a 1 km background methane signal, the approach is able to quantify methane DE to 97.5 %. These performance metrics could be improved through an updated high-temperature spectral absorption database for methane, however the current estimated performance could already substantially impact flare emissions by closing the gap between the flare design specifications and what research studies estimate from actual in-field performance.