Machine Learning Microservice for Identification of Accident Predecessors

Drilling accidents prediction is the important task in well construction. Drilling support software allows observing the drilling parameters for multiple wells at the same time and artificial intelligence helps detecting the drilling accident predecessor ahead the emergency situation. We present machine learning (ML) algorithm for prediction of such accidents as stuck, mud loss, fluid show, washout, break of drill string and shale collar. The model for forecasting the drilling accidents is based on the "Bag-of-features" approach, which implies the use of distributions of the directly recorded data as the main features. Bag-of-features implies the labeling of small parts of data by the particular symbol, named codeword. Building histograms of symbols for the data segment, one could use the histogram as an input for the machine learning algorithm. Fragments of real-time mud log data were used to create the model. We define more than 1000 drilling accident predecessors for more than 60 real accidents and about 2500 normal drilling cases as a training set for ML model. The developed model analyzes real-time mud log data and calculates the probability of accident. The result is presented as a probability curve for each type of accident; if the critical probability value is exceeded, the user is notified of the risk of an accident. The Bag-of-features model shows high performance by validation both on historical data and in real time. The prediction quality does not vary field to field and could be used in different fields without additional training of the ML model. The software utilizing the ML model has microservice architecture and is integrated with the WITSML data server. It is capable of real-time accidents forecasting without human intervention. As a result, the system notifies the user in all cases when the situation in the well becomes similar to the pre-accident one, and the engineer has enough time to take the necessary actions to prevent an accident.

The calculation of maximum elevation due to storm surge by using joint probability method

In the present paper the maximum storm surge elevations with certain return years were calculated by using a joint probability method. Based on the analyses of the typhoons which, affected coastal zone of Guangdong Province in history, a group of model typhoons was established. A number of parameters, which described the typhoons, were selected. The data of each parameter I was graded into a few sub-groups according to their values, and this was done in accordance with the historical observations. The probability of each value of the parameters was calculated based on the historical records. The probability of a typhoon with a group of values of parameters could be calculated. Simulation results of the storm surges caused by the above model typhoons with their probabilities were analysed statistically. Thus an accumulated probability curve and maximum elevations with certain return years were obtained. A number of spots was selected. At some of the spots there are tidal stations and at the others there are none. The maximum elevations with certain return years at the spots were calculated and the results were found satisfactory. By using this method all the meteorological and hydrological data, which were available, can be fully utilized. This method is most suitable for calculating the maximum elevations at a place where there is no tidal station or at many places simultaneously.

Risk Decision-Making Technology in Gas Reservoir Development at Sichuan Basin

During the development of complex gas reservoirs, the risk decision-making problem often emerges. Thus, the study on risk assessment is an important tool used to identify potential hazards and create appropriate avoidance measures accordingly. Based on the analysis of seven types of risk factors in gas reservoir development planning, this paper aims to clarify the logical relationship between the risk factors in the strategic planning of natural gas development. The comprehensive research on target risks in the gas reservoir development planning based on stochastic simulation was carried out. The “probability curve scanning method” was used to evaluate objective risk factors, while the decision-making risk factors were evaluated using the “probability curve displacement method.” According to the realization probability and dispersion degree of the planned target combined with the risk grade evaluation matrix, the planning target evaluation risk grade was implemented. Moreover, the planning unit risk grade evaluation was obtained at different stages. Regarding the specific production capacity conditions in gas wells (horizontal and vertical wells) and gas reservoir water invasion, the probability method with Monte Carlo stochastic simulation was used to calculate the production and water invasion volumes. The established decision-making risk technology for gas reservoir development, along with the associated supporting procedures, can be used to evaluate the risks of reservoir development planning, production, and water invasion.

Influencing Factors on the Accuracy of Soil Calibration Models by EDG

Compaction is an important standard in evaluating the quality of earth filling work. The EDG, an electrical density gauge, is a new type of fast and nondestructive compaction detection equipment. It is used to test the dry density and water content of the soil by establishing a soil calibration model while the accuracy of measurement is mainly based on the precision of equation of calibration model. In this paper, the factors affecting the accuracy of the soil calibration model were studied by an indoor calibration test, and soil samples were prepared to verify the accuracy of the soil calibration model. The test results showed that the dry density range, water content range, and sample quantity 13 samples of soil had a significant influence on the correlation coefficient (R2) of the equation of the soil calibration model. In addition, when using the calibration model with different sample numbers and sample combinations but similar correlation coefficients to test multiple groups of density and moisture content, there are also differences in the expected value and standard deviation of the error probability curve of the test results. In the engineering practice, the reasonable sample quantity was determined by the applicable range of dry density and water content obtained from the measurement error analysis of the soil calibration model.

Risk Control of Manufacturing Enterprise Short-term Financial Investment Based on COSO-ERM and Industry 4.0

In this paper, firstly, the risk management and control process of related enterprises after COSO-ERM framework is introduced and the risk assessment and control methods of related investment strategies are introduced emphatically by studying the short-term financial investment business of manufacturing enterprises.Then, the risk probability method for measuring the risk size and the possibility of achieving the expected goals is introduced. Next, the differences between the risk curve and the risk probability curve are further compared. Finally, in Industry 4.0, it is concluded that the introduction of COSO-ERM framework into manufacturing enterprise risk management will not only help to grasp the implementation of enterprise strategic objectives through effective internal control, but also help to effectively assess the risks of strategic objectives and the possibility of achieving strategic objectives.

Risk Decision-making Technology in Gas Reservoir Development at Sichuan Basin

During the development of complex gas reservoirs, the risk decision-making problem often emerges. Thus, the study on risk assessment is an important tool used to identify potential hazards and create appropriate avoidance measures accordingly. Based on the analysis of seven types of risk factors in gas reservoir development planning, this paper aims to clarify the logical relationship between the risk factors in the strategic planning of natural gas development. The comprehensive research on target risks in the gas reservoir development planning based on stochastic simulation was carried out. The “probability curve scanning method” was used to evaluate objective risk factors, while the decision-making risk factors were evaluated using the “probability curve displacement method”. According to the realization probability and dispersion degree of the planned target combined with the risk grade evaluation matrix, the planning target evaluation risk grade was implemented. Moreover, the planning unit risk grade evaluation was obtained at different stages. Regarding the specific production capacity conditions in gas wells (horizontal and vertical wells) and gas reservoir water invasion – the probability method with Monte Carlo stochastic simulation was used to calculate the production and water invasion volumes. The established decision-making risk technology for gas reservoir development, along with the associated supporting procedures can be used to evaluate the risks of reservoir development planning, production, and water invasion.

Efficacy and Safety of Pyrotinib Versus T-DM1 in HER2+ Metastatic Breast Cancer Patients Pre-Treated With Trastuzumab and a Taxane: A Bayesian Network Meta-Analysis

PurposeTo compare the efficacy and safety between pyrotinib (Pyr) and trastuzumab emtansine (T-DM1) in pre-treated human epidermal growth factor receptor 2-positive (HER2+) metastatic breast cancer (MBC) patients.MethodsA comprehensive literature search of the PubMed, EMBASE, and Web of Science was performed in August 2020. Randomized clinical trials comparing the efficacy and safety between different anti-HER2 regimens in patients pre-treated with trastuzumab (Tra) and a taxane in metastatic settings (≤second-line treatment) were included. A fixed effects network meta-analysis based on the Bayesian inferential framework was conducted for progression-free survival (PFS), overall survival (OS), overall response rate (ORR), and grade ≥3 adverse events (AEs). Values of surface under cumulative ranking probability curve (SUCRA) were calculated to offer a ranking of all regimens.ResultsTwelve studies with 4,353 subjects were identified. Nine regimens were included into the network: T-DM1, lapatinib-capecitabine (Lap-Cap), Tra-Cap, Cap, neratinib (Ner), pertuzumab (Per)-Tra-Cap, Pyr-Cap, atezolizumab (Ate)-T-DM1, and Ner-Cap. For PFS, Pyr-Cap was more favorable than T-DM1 (hazard ratio, 95% confidence interval: 0.77, 0.70–0.86), Lap-Cap (0.64, 0.59–0.69), Tra-Cap (0.63, 0.56–0.70), Cap (0.50, 0.45–0.56), Ner (0.59, 0.51–0.69), Per-Tra-Cap (0.68, 0.59–0.79), and Ner-Cap (0.72, 0.64–0.81). For OS, Pyr-Cap showed further improvement than Lap-Cap (hazard ratio, 95% confidence interval: 0.71, 0.52–0.99), Cap (0.68, 0.49–0.96), and Ner (0.65, 0.45–0.94). For ORR, Pyr-Cap was significantly superior than Cap (odds ratio, 95% confidence interval: 7.87, 1.22–56.51). No significant difference was observed in grade ≥3 AEs among all the regimens. Pyr-Cap ranked in the highest in PFS, OS, ORR, and grade ≥3 AEs (SUCRA = 99.4, 89.7, 86.4, and 89.3%).ConclusionsThese results indicate that Pyr may be more effective than T-DM1 in HER2+ MBC patients pre-treated with Tra and a taxane. However, it may be associated with more grade ≥3 AEs.

Analysis of Time-Series Trends and ARIMA models to Forecast COVID – 19 cases

COVID-19 a novel corona virus originated from Wuhan China. It turned into a pandemic resulting in a large number of deaths and loss of livelihood. It is vital to determine the manner in which the number of cases propagates so that future pandemics can be tackled scientifically. However the pandemic can be controlled systematically using efficient health care systems. It is difficult to predict the pandemic propagation over a large period of time due to various factors. In this paper an analysis is made for short periods using statistical tools like predicting the probability curve, probability density function. Forecasting of Covid-19 cases is done using time series trend analysis and ARIMA models. The test of hypothesis for difference of means and standard deviations of the actual and forecasted values with 99% CI showed no significant difference between them.

Paleo-earthquake Evidence and Earthquake Recurrence for Düzce Fault, Turkey

Paleoseismological trenching was performed along the Düzce fault providing some preliminary insight about its seismogenic behavior. Dating was based on radiocarbon analysis of peat samples collected from the trenches and suggested seven earthquakes have occurred since 1740 BC. Integrating date constraints of events exposed in the trenches suggests a periodical earthquake recurrence model. According to a linear sequential event serial that has minimum misfit determined by considering the probability curve limits of the sample dates, the earthquake recurrence interval is between 384 and 460 years (or possibly between AD 394 and 400). A probability curve was also calculated for the date of the last earthquake (1999 Düzce earthquake) considering the probability distributions of sample dates based on the same event serial. This probability-distribution-based method, similarly, predicted that the 1999 Düzce earthquake occurred between 1933–2005 (± 36 years) with a 68 % probability. After this verification. Using this method, it was estimated that the next earthquake along the Düzce fault has a 68 % probability of occurring between 2328–2392. According to this calculation, the earthquake recurrence interval is about 391 ± 34 years with a 68 % probability and the AD 967 historical earthquake likely ruptured the Düzce fault. Assuming an average slip of 350 cm (the average slip of the 1999 earthquake), the slip rate was estimated to be between 8.7–11.2 mm/a.