For intelligent debugging management of offshore oil engineering with big data

Abstract

With the development of science and technology, in the field of oilfield commissioning, the requirements for process management are more and more standardized and scientific, and the requirements for decentralized equipment status detection and maintenance are also higher and higher. It is the hope of any manager to eliminate hidden dangers and prevent them in a timely manner. This paper introduces an intelligent debugging model based on big data. Based on the big data mechanism, the model is divided into different functions according to different functions and requirements. It can ensure the authenticity of debugging data, coordinate all big data work through the big data communication mechanism, and conduct scientific management of debugging data. The model is divided into three levels: data acquisition layer, data transmission layer and control management layer. The offshore oil intelligent debugging platform software based on big data technology is built. A new intelligent debugging method for offshore oil based on big data is presented to study the warning information, fault location and equipment health status of intelligent debugging. Development for Marine oil intelligent debugging applications, for business people to provide intelligent Marine oil intelligent debugging method, provide data support for management decision-making, implementation of the lean management data in the field of intelligent debugging, improving the capacity of intelligent debugging data analysis and mining, effective use of the existing intelligent debugging automation system and other related data in the system, solved the “huge amounts of data, information, the lack of a” awkward situation, improve intelligence debugging application function, meet the demand of intelligent debugging of each department, improve the efficiency of debugging and running reliability and intelligent management.

Keywords

Intelligent debugging offshore oil big data communication mechanism

1 Introduction

Existing offshore oil intelligent debugging system of evaluation and analysis of running status of equipment and lacking, will not be able to timely grasp and diagnostic equipment current status and predict possible future risk, need to build intelligent debugging equipment evaluation model, a secondary equipment of intelligent debugging jurisdiction of evaluation, analysis, and offshore oil intelligent debug vulnerabilities, help management and decision-making department to solve network frame reformation, construction investment, etc., improve the auxiliary decision-making ability, better to reduce the occurrence of failure, improve the ability of offshore oil debugging and stable power supply [1, 2]. In recent years, the development of information technology and communication technology, as well as the emergence and progress of big data, business intelligence, data mining and other new technologies have provided new technical means for solving these problems. Therefore can be integrated in intelligent debugging dispatching automation system of time series database, solve the problem of mass data storage, build offshore oil based on the technology of “big data” intelligent debugging diagnosis system software, to seek solutions to offshore oil intelligent debugging method of massive amounts of data, loss of information, data in the field of Marine oil intelligent debugging implement lean management, provide data analysis and display tools for business people, provide data support for management decisions.

This research mainly studies the intelligent debugging and diagnosis method of offshore oil based on big data technology from two aspects of warning information and offshore oil intelligent debugging equipment. In the aspect of alarm information, the paper mainly studies the intelligent clustering method of alarm information using data mining technology, the visualization technology, the identification and shielding method of the interference alarm information and the visualization of the alarm information. In the aspect of offshore oil intelligent commissioning equipment, it mainly analyzes the historical change process of the equipment alarm, excavates the correlation between the historical warning information, finds the weak links of offshore oil intelligent commissioning, gives early warning hints to the weak links of offshore oil through visualization technology, and puts forward corresponding auxiliary decisions. The intelligent commissioning mechanism model of oilfield is designed, which is composed of software of control management center and several commissioning instruments. The control management center receives the data sent by the debugger through the network, and undertakes the tasks of data management, designing the debugging process and work tasks of each debugger. Each debugger is scheduled to complete debugging by sending task instructions. On the one hand, the debugger downloads the debugging process and work tasks through the communication module. On the other hand, data is collected through automatic acquisition module and uploaded to control management center through communication module.

2 Related work

From offshore oil development strategy of science and technology and national science and technology development strategy, promote the comprehensive support technology in the development of offshore oil the basis of the fusion point of view, the national offshore oil company “need to use advanced computing and big data and technological achievements, to explore advanced computing system and the high performance computing technology, the power analysis of large data mining algorithm, optimization strategy and visual display technology, and power data simulation, test and evaluation technology; Typical applications of big data in various business fields for intelligent offshore oil “[3 –5]. By big data further improves the management level of the development and construction units should make full use of its advantages in offshore oil intellectualization, the surrounding sea oil development management work actively carry out large data application innovation practice, strengthen the data value mining, deepen the development of professional big data applications, auxiliary diagnosis, management, decision [6, 7]. To big data technology into the offshore oil intelligent debug program, set up offshore oil intelligent debugging based database planning, transformation of the mode of traditional artificial data acquisition [8, 9], integrated with adjustable camp through information and Marine oil real-time information, establish across different professional, department of Marine oil intelligent debugging scheme based data collaborative d mechanism, improve data access efficiency and precision. Mining the application value of intelligent commissioning big data, relying on the information platform and visual tools [10, 11], realizing the automatic generation and export of offshore oil intelligent commissioning planning business report, and improving the planning efficiency. Application scenarios is such as optimal sequencing of design and development planning projects, low-voltage monitoring analysis, identification of medium-voltage grid structure, etc. Cluster, correlation and other analysis methods are used to assist the intelligent debugging and diagnosis analysis of offshore oil, so as to improve the intelligent level of offshore oil intelligent debugging and planning [12, 13]. Establish a big database of power economy, and build a resource database of big data of power economy of industrial enterprises above the scale, covering intelligent debugging, output of major products, economic benefits and other data, realize statistical analysis of industry, region, time and other dimensions, and provide data support for production, operation and risk analysis. The abnormal fluctuation of enterprise growth rate is analyzed, and the deep-rooted factors of industry changes such as “high base effect caused by user type change” and “implementation of new standards in textile industry” are found, so as to grasp the changes of electricity market situation [14, 15]. Establish industrial intelligent commissioning forecasting models and industrial economic prosperity index models based on different industries, dig deeply into the value of intelligent commissioning data, predict the monthly growth rate of industrial intelligent commissioning, strengthen the identification and monitoring of industrial enterprise operating risk, and support the government to do a good job in economic operation regulation. Taking the unified data center of the whole business as the technical route, hubei company formulated the data linking and integration scheme [16, 17], and solved professional connection problems such as mismatching of schedule and ununified requirements in project management according to the actual management process of offshore oil investment projects. In combination with actual business needs such as statistical analysis, post-evaluation of projects, development diagnosis and planning topics, a full-life data center for offshore oil investment projects is established to realize functions such as automatic data collection, whole-process visual monitoring and intelligent auxiliary analysis, and apply big data to assist in making investment decisions for projects, so as to improve efficiency and benefits [18 –20]. Implement the big data strategy, organically combine traditional marketing services with the current hot big data technology, carry out the research and practice of digital development, and mine the value of big data in intelligent debugging, equipment operation and maintenance and other fields [21, 22]. On the basis of collecting and managing marketing data, a two-level working mechanism of open, Shared and innovative marketing big data is established to comprehensively promote the application research of big data. While improving the operation and maintenance level of offshore oil equipment, it also brings customers more convenient and comfortable intelligent debugging experience [23, 24]. In general, big data technology gradually permeates and forms a number of typical big data application scenarios. For local and county-level power enterprises, there are still great potentials in many aspects, such as the lean maintenance of offshore oil fault, the improvement of information acquisition capacity and governance. In various fields of production, the design of intelligent debugging system at home and abroad is relatively backward. In the past, most of the intelligent debugging device processors were 8-bit single-chip microcomputer of 51 series, and there were almost no intelligent debugging devices for petroleum and petrochemical production enterprises [25]. In recent years, with the popularization of the industrial application of 32-bit and 64-bit embedded processors such as ARM, intelligent debugging products with high-speed intelligence have appeared [26, 27]. But at present, there are few and few instruments suitable for intelligent debugging of petroleum and petrochemical production, and their functions are not complete. Most of them are only for the collection, monitoring and treatment of a certain attribute of the equipment. Especially in the total control management center, the function of equipment data analysis, diagnosis and decision support is relatively weak. With the progress of science and technology, intelligent debugging system is developing towards intelligence. Intelligent debugging devices tend to be light in size and easy to carry. Its function also will be more powerful, process data more quickly, fast. Background control management center has also strengthened the monitoring and management of intelligent debugging data [28, 29]. Therefore, the intelligent debugging system that can detect record, analyze and process various equipment parameters will become the mainstream of various intelligent debugging fields.

3 Offshore oil commissioning analysis under the influence of dynamic factors of big data

3.1 Dynamic environmental analysis model for offshore petroleum

From the perspective of the development history of the oil industry, the oil price has experienced three cycles of violent oscillations. Current prices after a round of the cycle, to begin to enter the fourth round of oscillation downward interval, for the global oil and gas industry and Marine engineering affected the business chain across the board, using the model under the background of the offshore market environment dynamic analysis is as follows: the global oil and gas market characteristic of periodic oscillation is obvious from a macro point of view, the main factors influencing oil price fluctuations package global macroeconomic, geopolitics, etc., the behavior of the main oil-producing countries, other market speculators also has a significant influence on oil prices. From the perspective of the development of global oil and gas industry, global oil prices in the above three factors, under the joint action of global oil prices experienced three big oscillation, their common characteristic is rapid decline after oil prices reached a record high point, after a steady rise sharply rising after a rapid decline in a cycle, and slowly return to a steady state, and the previous steady state after a period of oscillation at higher prices. The dynamic analysis of the variation characteristics of international oil prices is shown in Fig. 1.

Fig.1

Dynamic analysis model of Marine engineering market environment.

Market segmentation refers to the process in which an enterprise divides the overall market into several market segments based on the similarities and differences between the market and the overall customers and on the basis of some factors affecting customer demand. There are many ways to segment a market, but not all of them make practical sense to an enterprise. The implementation of market segmentation should follow some basic principle, market segmentation can play its role. The basis for market segmentation is shown in Fig. 2.

Fig.2

Market segmentation model.

Under the condition of market segmentation, the selected enterprise’s sub-market needs to have a certain scale and demand, so as to ensure that the enterprise can obtain sufficient economic benefits after entering the market. It is inappropriate to delimit too large or too small market segments. In addition, when selecting market segments, enterprises should also pay attention to the development potential of sub-markets. In the market segmentation, the target market selected by enterprises must be the market that enterprises are likely to enter and occupy a certain share. If you want to enter the market without sufficient ability or you can’t compete with many competitors, you will only waste your resources. In addition, it should also be noted that some markets are restricted by natural laws and legal ethics, so that enterprises cannot enter and participate in the competition. Such factors cannot be used as the basis for the selection of market segmentation, let alone as the target market.

3.2 Capability evaluation system of offshore oil intelligent commissioning equipment

Offshore petroleum engineering equipment manufacturing industry is a globally competitive industry with high technology content as its basic feature. For platform construction enterprises, whether they can deliver products in line with market demand is the value of their existence. Therefore, technical ability can be defined as the ability to deliver products according to customer requirements. The realization process of offshore platform products is a large-scale complex system engineering, which involves the matrix management of large projects across multiple functions and the cooperation between multiple technical capabilities. In offshore oil engineering equipment manufacturing enterprise product final delivery ability namely overall technical ability as the main line, analysis of market segmentation and customer demand as the foundation, through on-the-spot investigation, expert interview and the study of relevant literature, to the Marine petroleum engineering equipment manufacturing enterprise’s technological innovation capability of all kinds of indexes are classified and formed about offshore oil engineering equipment manufacturing enterprise technological innovation ability evaluation index system, as shown in Table 1.

Table 1
Evaluation index system of technological innovation ability of offshore oil intelligent commissioning Equipment

Overall technical capability First-level technical capability

R&d and design capability R&d investment intensity (%)

Composition of R&D personnel (%)

Research and development mechanism compliance

R&d success rate

Average New Product Development Cycle (year)

R&d expenses (ten thousand yuan)

The number of patents

Production and construction capacity Technical Level of production equipment and facilities (%)

Ratio of Technical personnel to Total production personnel (%)

Innovation management level The innovation desire of enterprise management

The incentive mechanism of technological innovation

Technology innovation risk management

Technical cooperation with foreign countries

Intensity of innovation resource input Intensity of acquisition of external science and technology funds

Input intensity of means of production

Innovation activity personnel input intensity

Product innovation capability Intensity of investment in new product development

Market competitiveness of new products

New product team capability

New product market share

Innovative return capability Financial risk bearing capacity

Access to technology innovation funding capacity

Technology Innovation Investment Recovery Cycle (year)

Rate of Return on Technological Innovation (%)

Contribution rate of technological innovation output (%)

Overall technical capability	First-level technical capability
R&d and design capability	R&d investment intensity (%)
	Composition of R&D personnel (%)
	Research and development mechanism compliance
	R&d success rate
	Average New Product Development Cycle (year)
	R&d expenses (ten thousand yuan)
	The number of patents
Production and construction capacity	Technical Level of production equipment and facilities (%)
	Ratio of Technical personnel to Total production personnel (%)
Innovation management level	The innovation desire of enterprise management
	The incentive mechanism of technological innovation
	Technology innovation risk management
	Technical cooperation with foreign countries
Intensity of innovation resource input	Intensity of acquisition of external science and technology funds
	Input intensity of means of production
	Innovation activity personnel input intensity
Product innovation capability	Intensity of investment in new product development
	Market competitiveness of new products
	New product team capability
	New product market share
Innovative return capability	Financial risk bearing capacity
	Access to technology innovation funding capacity
	Technology Innovation Investment Recovery Cycle (year)
	Rate of Return on Technological Innovation (%)
	Contribution rate of technological innovation output (%)

The basic idea of the close value evaluation method is to determine the “best advantage” and “worst disadvantage” of each evaluation index of the evaluation object, and then calculate the distance between each evaluation index of the object to be evaluated and “best advantage” and “worst disadvantage", so as to obtain the close value C, the detailed calculation method is as follows:

(1) Establish evaluation index matrix and standardization

Set of evaluation index A_i(I = 1, 2... M) in the index S_j(j = 1, 2... The evaluation index matrix A = (b_ij)_mn is obtained. Because there are many evaluation indexes and various interrelations among them, there are positive indexes (the higher the value is, the stronger the ability is) and negative indexes (the higher the value is, the weaker the ability is), and the dimensions of each index are not the same. In order to facilitate the analysis and comparison, the established index matrix should be normalized. To: $y_{ij} = {\begin{matrix} \frac{b_{ij}}{\sqrt{\sum_{i = 1}^{m} b_{ij}^{2}}} \\ \frac{- b_{ij}}{\sqrt{\sum_{i = 1}^{m} b_{ij}^{2}}} \end{matrix}$ (1)

Standardized evaluation index matrix is obtained: $Y = (y_{ij})_{m \times n}$ (2)

(2) Determine the most advantage and the most handicap of the evaluation index $\begin{matrix} y_{j}^{+} = max (y_{ij}) \\ y_{j}^{-} = min (y_{ij}) \end{matrix}$ (3)

(3) Calculate the affinity value of each evaluation object $C_{i} = \frac{y_{j}^{+}}{y_{j}^{-}}$ (4)

4 Intelligent commissioning operation and management of offshore oil based on big data

4.1 Construction of offshore oil intelligent commissioning structure

Offshore oil debugging and running control and intelligent management system combining the reality of offshore oil intelligent debugging operation management, intelligent debugging for offshore oil scheduling, shipment inspection and automatic operation maintenance personnel, test and operation support offshore oil intelligent monitoring, operation management and so on daily with the needs of the business, to adapt to the large capacity data acquisition, the application of the new technology such as network DSCADA; Improve the feeder automation security, multi-fault processing and new energy collaborative control capabilities, so that the intelligent debugging automation application software analysis response time, practicality and other indicators to reach the international advanced; Based on the idea of component-based service-oriented architecture, it provides unified exchange service, model service, data service, graphic service and application service, builds application-oriented, highly open, flexible and extensible resource sharing platform, and supports the business management requirements of offshore oil intelligent commissioning and scheduling, production command and so on.

Based on the unified support platform technical support to realize the application across the security area (production control area and information management area), that is to support the integrated operation of intelligent debugging and operation monitoring, intelligent debugging and analysis application, and intelligent debugging and operation management application, that is, the system’s “one supporting platform, three application systems” architecture system. The basic platform of the new generation of intelligent scheduling technical support system ADAPTS to the requirements of the five-level scheduling control system in the “big operation” system, realizes the functions of “remote retrieval, alarm direct transmission, horizontal transversal and vertical management", and has completely independent intellectual property rights. Flexible system architecture should be able to adapt itself to the requirements of the application of the dispatch center at all levels and the requirement of the system construction goal, follow the SOA thought, has the vitality, using mature effective IT technology, build an open to use, safe and reliable, standard, resource sharing, ease of integration, to use and easy to use, maintenance, minimize the technical support system. See Fig. 3.

Fig.3

Offshore Oil Intelligent commissioning structure diagram.

4.2 Offshore oil intelligent commissioning under big data technology

In order to meet the storage requirements and query performance of a large number of data, the intelligent analysis system provides a set of time series database management system to provide efficient access to real-time history data. The real-time history database management system realizes distributed data access by integrating bus layer. General database management capability; Can manage the real-time data of whole basin distribution to ensure the consistency of whole basin data. With a perfect interactive environment database entry, maintenance, retrieval tools and a good user interface.

In order to meet the storage requirements and query performance of a large number of data, the intelligent analysis system provides a set of time series database management system to provide efficient access to real-time history data. The real-time history database management system realizes distributed data access by integrating bus layer. General database management capability; Can manage the real-time data of whole basin distribution to ensure the consistency of whole basin data. Database entry, maintenance, retrieval tools and a good user interface with a complete interactive environment, as shown in Fig. 4.

Fig.4

Visualization of big data.

In order to distinguish users of different intelligent debugging devices, k-means algorithm is selected in this paper. The specific implementation process of the algorithm is as follows:

Input: k, data [n].

Select k initial center points, such as C [0] = data[0], C[K-1] = data[K-1];

For the data [0]... Data [n], respectively with C [0].. C [K-1], assuming the least difference from C [I], is denoted as I;

For all points marked as I, recalculate c[I] = sum of all data[j] marked as I number marked as I;

Repeat (2) (3) until the change of all C[I] values is less than the given threshold.

Figure 5 is a detailed schematic diagram of k-means intelligent debugging equipment clustering algorithm when k value is set to 3.

Fig.5

K-means clustering of intelligent debugging equipment.

Through the text of key extraction, characteristic value and subject extraction technology, such as the classification, clustering algorithms such as model, and based on similarity relation and based on the frequent degree of correlation analysis and other information for real-time alarm correlation analysis and correlation analysis of the history of the alarm information, building characteristics and the interference of association rules based on the alarm information identification model and classification model; Through the built model, combined with data analysis, the elimination and filtering of non-critical alarms such as debugging and listing, the combined display of frequent faults, the display of jitter signals, the shield of fault derived alarms and the intelligent classification display of alarm information are completed. Taking circuits as an example, cluster analysis is first conducted according to the current characteristics, regions or voltage levels, and different weights and scores are adopted for the status evaluation of different types of circuits, so as to diagnose, analyze and evaluate the health status of the circuits. See Table 2.

Table 2

Score of each analysis factor of line equipment health

Analysis of the factors	Fault level	Normal state	Pay attention state	Abnormal state	Serious condition
Overloading rate	25	1.1	0.8	0.45	0.28
Overload rate	25	1.2	0.7	0.53	0.38
Frequent action of telemetry	15	2	0.9	0.45	0.18
Terminal line rate	15	2	0.85	0.56	0.19
Correct rate of teleconferencing	20	2	0.75	0.58	0.23

5 Experimental analysis

The data samples are from the aggregate statistics of intelligent commissioning flow in different time periods between May 1, 2017, solstice, 2017 and June 15, 2017 of a municipal offshore petroleum project. In this paper, the intelligent commissioning flow statistics instrument is adopted as the intelligent commissioning flow collection method, which is divided into half an hour period to collect the intelligent commissioning flow fluctuation of offshore oil projects in real time. Because of input factors is adjacent to the first 3 weeks, on May 21, so the solstice on May 1, only as a intelligent forecast the training sample, and in accordance with the requirements for the output of 23 days after finishing the complete sample, in which the May 22 to June 14 until 22 days of data as the training sample, also used to predict the last day is June 15, intelligent debug data, on June 15, and use the real intelligent debugging data to evaluate the result of the forecast. The training samples at a certain moment are shown in Table 3.

Table 3
Sample table of intelligent debugging prediction training at a certain moment

Data 5.22 5.23 5.24

Input Adjacent cycle debugging 443 479 551

398 694 732

526 586 874

Adjacent day debugging 652 644 667

746 786 563

527 481 613

Adjacent time debugging 475 858 616

292 334 542

323 515 386

Target output 481 631 534

Data		5.22	5.23	5.24
Input	Adjacent cycle debugging	443	479	551
		398	694	732
		526	586	874
	Adjacent day debugging	652	644	667
		746	786	563
		527	481	613
	Adjacent time debugging	475	858	616
		292	334	542
		323	515	386
Target output		481	631	534

Use Matlab2016 software implement traffic forecast analysis, Matlab2016 itself with the Neural network toolbox, click on the application of Neural Net Fitting toolbox, select the input data (Inputs) and the target data (Targets), and select the training data, calibration data and test data, set the number of hidden layer, click on the “train” button for training, model predicted results is shown in Fig. 6. Among them, the intelligent commissioning working time of offshore petroleum Engineering is from 6am to 20pm, divided into half an hour, and the predicted value is compared with the actual value on June 15. The error is large in the peak period, because the commissioning flow fluctuates greatly during the peak period.

Fig.6

Schematic diagram of prediction results.

The intelligent debugging clustering algorithm minimizes the “total deviation” of all sample points from the hyperplane by seeking the optimal hyperplane through a class of sample points. In this case, the sample points are all between the two boundary lines, so finding the optimal regression hyperplane is also equivalent to finding the maximum interval, as shown in Fig. 7.

Fig.7

Intelligent debugging cluster prediction diagram.

In order to more clearly reflect the relationship between the predicted result and the true value, it is represented as a graph, as shown in Fig. 8. In the figure, the abscissa is the device number, the ordinate is the intelligent debugging time of the corresponding device, the dashed line is the predicted value to debugging time, and the solid line is the real value to intelligent debugging time. It can be seen from the comparison figure that the error between the predicted intelligent debugging time in the previous time and the actual intelligent debugging time is small, and the error of the predicted time after six times is larger. There are two reasons for this. First, the intelligent debugging time from the next time is calculated based on the predicted value of the previous time, so the error will accumulate with the increase of debugging times. Moreover, according to the above research on the prediction model of intelligent debugging time prediction, the farther the location of the predicted target debugging and the current equipment is, the lower the prediction accuracy will be.

Fig.8

Intelligent debugging prediction result diagram.

As shown in Fig. 9, strain monitoring time-history diagram is drawn by selecting the strain data at 16.17 m, 23.50, 62.166 and 69.80 m of the optical fiber at the measuring section of intelligent debugging pipe head after temperature decoupling respectively. It can be found from the figure that the strain variation also accords with the periodic law basically. However, as can be seen from the comparison of the strain amplitude of the anchorage segment and ITD in the figure, the variation amplitude of the anchorage segment is about 260US, while that of the ITD is about 720US. There is a significant difference between the two, indicating that the strain variation of the ITD is very obvious during the intelligent commissioning period due to the fact that the compensator connected at one end can allow it to expand in a small range.

Fig.9

Time history of bending strain at intelligent debugging position.

6 Conclusion

The data required for the operation and management of offshore petroleum engineering are broad in scope and large in quantity, so users need a large amount of offshore petroleum engineering information for decision support when conducting business analysis such as alarm information analysis, fault diagnosis and user service. Different statistics, analysis and presentation of the same data are required. There is a lack of tools for analyzing data association and data law, and information presentation is simple. Therefore, new data analysis, mining and presentation tools are needed to improve the efficiency of extracting knowledge hidden in data. In this paper, we study how to extract knowledge from a large amount of information, discover the operation rules of offshore petroleum engineering, and find new tools and methods. Set and processing speed. In the aspect of control management, an intelligent debugging management system platform is designed, which analyzes, diagnoses and processes the real-time data sent by the intelligent debugging instrument, and gives warning hints. The model has been proved in oilfield sewage monitoring system. The real-time acquisition and transmission function of intelligent debugging device ensures the accuracy and timeliness of intelligent debugging data. The management software of the control management center strengthens the real-time monitoring, analysis and processing of intelligent debugging data, and the management of early warning and prompt. The proposed model solves the problems such as large data error, low efficiency of intelligent debugging and weak backstage data processing ability in the field of intelligent debugging. At the same time, it satisfies the managers’ management requirements for the whole intelligent commissioning process, makes the equipment in a visible and knowable transparent management state, solves the deficiency of decentralized equipment in maintenance and management in an efficient and low-cost way, improves the management level of intelligent commissioning in engineering, and makes it more intelligent and scientific.

References

Yun

and Wenxue

, Strategies of Chinese Offshore Oil Engineering Companies to Go Global[J], China Oil & Gas 22(88.4) (2015), 17–22.

Son

B.Y.

, Lee

E.B.

and Using

Energies.

, Text Mining to Estimate Schedule Delay Risk of 13 Offshore Oil and Gas EPC Case Studies During the Bidding Process[J], Energies 12(10) (2019), 1956–1962.

Pedersen

, Durdevic

and Yang

, Review of Slug Detection, Modeling and Control Techniques for Offshore Oil & Gas Production Processes[J], IFAC Papers On Line 48(6) (2015), 89–96.

Serrano

X.M.

, Baums

I.B.

and Smith

T.B.

, Long distance dispersal and vertical gene flow in the Caribbean brooding coral Porites astreoides[J], Entific Reports 6(1) (2016), 21619–21626.

Hardisty

P.E.

, Michaela

and Cooper

K.E.

, The role of marine science in managing environmental risk offshore[J], The APPEA Journal 58(2) (2018), 562–571.

Ferguson

, Oil and gas companies need to adapt to attract digital natives[J], Offshore 78(2) (2018), 64–64.

Hawkins

A.D.

, Pembroke

A.E.

and Popper

A.N.

, Information gaps in understanding the effects of noise on fishes and invertebrates[J], Reviews in Fish Biology & Fisheries 25(1) (2015), 39–64.

Joly

, Rocha

and Sousa

L.C.F.

, The strategic importance of teaching Operations Research for achieving high performance in the petroleum refining business[J], Education for Chemical Engineers 10 (2015), 1–19.

Islam

and Sun

A.Y.

, Quantification of CO2 masses trapped through free convection process in isothermal brine saturated reservoir[J], International Journal of Heat and Mass Transfer 87(8.) (2015), 128–137.

10.

Shen

and Ritter

, Forecasting volatility of wind power production[J], Applied Energy 176(8.15) (2016), 295–308.

11.

Pedersen

, Mai

and Hansen

, Online Slug Detection in Multi-phase Transportation Pipelines Using Electrical Tomography[J], IFAC-Papers On Line 48(6) (2015), 159–164.

12.

Yikai

, Trend of Digital Transformation Promotion Among Petroleum Enterprises[J], China Oil & Gas 26(01) (2019), 23–30.

13.

Chen

, Zhang

and Chen

, Study on pressure interval of near-miscible flooding by production gas Re-injection in QHD offshore oilfield[J], Journal of Petroleum ence and Engineering 157 (2017), 340–348.

14.

White

, Now is the time to digitalize, embrace new technologies[J], Offshore 77(6) (2017), 64–74.

15.

Ahmed

, Are cyber security risks deterring digitalization[J], Offshore Engineer 41(5) (2016), 82–83.

16.

Hussin

M.H.

, Rahim

A.A.

and Ibrahim

M.N.M.

, BU prepares to sound on on world stage[J], Measurement 78(2016) (2015), 90–103.

17.

Rassenfoss

, SPE Technical Directors Working Outside the Lines[J], Journal of Petroleum Technology 67(01) (2015), 53–57.

18.

Kovski

, Final Rule for Control of Offshore Drilling Issued With Changes on Flexibility, Deadlines[J], Environment Reporter 47(16) (2016), 1177–1178.

19.

Legare

, Kneebone

and Deangelis

, The spatiotemporal dynamics of habitat use by blacktip (Carcharhinus limbatus) and lemon (Negaprion brevirostris) sharks in nurseries of St. John, United States Virgin Islands[J], Marine Biology 162(3) (2015), 699–716.

20.

Prokof’ev , Yu

and Pek

A.A.

, Problems in estimation of the formation depth of hydrothermal deposits by data on pressure of mineralizing fluids[J], Geology of Ore Deposits 57(1) (2015), 1–20.

21.

Schmoor

K.A.

, Achmus

and Foglia

, Reliability of design approaches for axially loaded offshore piles and its consequences with respect to the North Sea[J], Journal of Rock Mechanics & Geotechnical Engineering 10(06) (2018), 108–117.

22.

Shujie

, Xiangqian

and Hua

, Upgrading, Transforming, and Standardizing of Offshore Oil Drilling Equipment in China[J], China Oil & Gas 23(03) (2016), 31–37.

23.

Zou

and Lei

, The Cauchy problem for compressible Navier–Stokes equations with shear viscosity and large data[J], Ztschrift Für Angewandte Mathematik Und Physik 66(5) (2015), 2305–2341.

24.

Evangelista

and Filippo

S.D.M.

, Some Limits in the Use of the MASW Technique in Soils with Inclined Layers[J], Geotechnical & Geological Engineering 33(3) (2015), 701–711.

25.

Fang

, Yu

Q.H.

and Xu

, The Underwater Project Management in ‘Dong Fang’ Offshore Oil Engineering[J], Applied Mechanics and Materials 508 (2014), 125–128.

26.

Bouejla

, Chaze

and Guarnieri

, A Bayesian network to manage risks of maritime piracy against offshore oil fields[J], Safety ence 68 (2014), 222–230.

27.

Noroozi

, Abbassi

and Mackinnon

, Effects of Cold Environments on Human Reliability Assessment in Offshore Oil and Gas Facilities[J], Human Factors 56(5) (2014), 825–834.

28.

Kim

I.H.

, Dan

and Kim

, Simulation-Based Optimization of Multistage Separation Process in Offshore Oil and Gas Production Facilities[J], Industrial & Engineering Chemistry Research 53(21) (2014), 8810–8820.

29.

Rochette

, International regulation of offshore oil and gas activities: time to head over the parapet[J], Cancer Genetics & Cytogenetics 73(2) (2014), 103–108.