|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
ABSTRACT The industry is facing significant challenges due to the recent downturn in oil prices, particularly for the development of tight reservoirs. It is more critical than ever to 1) identify the sweet spots with less uncertainty and 2) optimize the completion-design parameters. The overall objective of this study is to quantify and compare the effects of reservoir quality and completion intensity on well productivity. We developed a supervised fuzzy clustering (SFC) algorithm to rank reservoir quality and completion intensity, and analyze their relative impacts on wells' productivity. We collected reservoir properties and completion-design parameters of 1,784 horizontal oil and gas wells completed in the Western Canadian Sedimentary Basin. Then, we used SFC to classify 1) reservoir quality represented by porosity, hydrocarbon saturation, net pay thickness and initial reservoir pressure; and 2) completion-design intensity represented by proppant concentration, number of stages and injected water volume per stage. Finally, we investigated the relative impacts of reservoir quality and completion intensity on wells' productivity in terms of first year cumulative barrel of oil equivalent (BOE). The results show that in low-quality reservoirs, wells' productivity follows reservoir quality. However, in high-quality reservoirs, the role of completion-design becomes significant, and the productivity can be deterred by inefficient completion design. The results suggest that in low-quality reservoirs, the productivity can be enhanced with less intense completion design, while in high-quality reservoirs, a more intense completion significantly enhances the productivity. Keywords Reservoir quality; completion intensity; supervised fuzzy clustering, approximate reasoning,tight reservoirs development
Abstract Hydrogen Sulphide (H2S) is a colourless, flammable and highly toxic gas with a strong odour of rotten eggs that is found in many reservoir fluids and aquifers in the world. This gas is commonly a result of "reservoir souring" – a process which increases the H2S concentration. Increasing amounts of this gas pose serious health, safety and environmental concerns. This can result in significant costs associated with replacement of downhole and surface equipment and increased processing costs, but more lethally a potential loss of life. Many reservoirs particularly those undergoing waterflooding face increasing levels of hydrogen sulphide (H2S) production with time. H2S is a highly toxic gas that can be fatal even at low concentrations. Being able to predict the risk potential of a particular reservoir to increasing H2S production with time would be highly valuable. The objective is to determine apriori whether a reservoir would likely see dangerously high levels of H2S being produced during the lifetime of the reservoir, and if so, be a catalyst in supporting further investigation and mitigation of H2S early in the reservoir development. There is very little published field data with regards to reservoir souring, hence a purely data driven model would not be possible to create. However, we do have a good understanding of the reaction kinetics that goes into the biological process that generates H2S. To this end the best modelling paradigm that can assimilate sparse data with first principles dynamics is fuzzy logic. A fuzzy logic model has been built around the reaction kinetics and then conditioned to the published field data. The model created matches the published field data fairly well. It is now a ready tool that can be used by engineers to make a quick assessment of their reservoirs before going into full blown expensive sampling and laboratory analysis. The novel aspect of this paper is being able to use fuzzy logic to combine the first principles chemistry together with sparse data to produce a model that can be used practically. Fuzzy Logic has been out of the news of late as machine learning and neural networks are the current hot potatoes, however it is often overlooked that fuzzy logic can still be used in low dimensional cases where only sparse data is available.
Rate of penetration (ROP) modeling is one of the most important objectives of any drilling program. Penetration model depends on different criteria such as mud weight (MW), weight on bit (WOB), rotary speed (N), and so forth. It is a complex process, because of the high number of variables and uncertainties. Different mathematical models and evaluation methods were developed to solve this problem but they were unable to attain desirable accuracy. Adaptive neuro-fuzzy inference systems (ANFIS) could be used in these cases to predict the rate of penetration. ANFIS is a combination of neural networks and fuzzy logic networks and could be used to create a robust ROP model. The objective of this study is to apply the ANFIS method and compare the modeling results with conventional artificial neural network models. ANFIS trains the model using a set amount of data and then validates it against random data to measure the error. Drill bit record from a certain field has been taken as training data and testing data for the program. The selection process uses the Sugeno model for generating the fuzzy model and the backpropagation and gradient descent method for recognizing the patterns. The data was normalized and sorted out to remove the incomplete values. Tests were done by applying 2 and 3 membership functions to a 4 input interface and a 5 input interface. The accuracy of the results depends on the numbers of inputs and membership functions. Each input was tested with different membership functions to test the data. The output generated from the training process showed that sigmoid function and Gaussian function with grid partitioning and linear output function yielded the best results for 4 and 5 inputs using 2 and 3 membership functions each. The training error recorded was about 3 percent with a checking error of 20 percent for most cases.
The current paper presents the use of adaptive neuro fuzzy inference systems as a suitable tool employed for the prediction of stability status in an open pit. The determination of the non-linear behaviour and associated uncertainty of such a multivariate dynamic system is often challenging and demanding. Thus, the combined use of fuzzy logic and artificial neural networks, allows for modelling complexity and uncertainty of the problem. The model is trained with an extensive database of 141 worldwide case studies. The inputs refer to the values of eighteen variables suggesting key influencing factors namely: overall environment, mean annual precipitation, intact rock quality, rock mass properties, tectonic conditions and in-situ stress, hydraulic conditions, discontinuity properties, pit wall geometry, blasting method, and history of instability. The reliability of the predictive capability is computed through performance indices such as the root mean square error (RMSE) and further validated through a receiver operating characteristic curve and showed 98% prediction capability. Slope stability status through adaptive neuro fuzzy inference system produces fast convergence giving reliable predictions, and thus being an objective, unbiased, cost effective tool that can be used at the preliminary and at further design stage of a project.
Adaptive Neuro Fuzzy Inference System (ANFIS) is fast gaining popularity in the area of geotechnical engineering and geomechanics. Applications are predominantly focused in the estimation of pile bearing capacity, (Harandizadeh et al., 2019, Ghorbani et al., 2019), in optical cost of design of underground gas storage facility, (Jelušič et al., 2018). Rock slopes in open-pit mining environments continue to expand, with production rates increasing over the last 100 years (Franz, 2009). In order for mining industry to make full use of the mineral recourse, the final slope is generally designed to be as steep as possible (Sjöberg, 1999). A change in slope angle by as little as 2° – 3° can be measured in hundreds of millions of dollars in project revenue (Lilly, 2002). Nonetheless, at the heart of all mining project is the associated risk which encompasses both safety and economics. Petley and Froude, (2018), highlighted the increasing levels of global loss from mining and quarrying related landslides.
Xue, Y. (Key Laboratory of Geotechnical and Underground Engineering (Tongji University) / Tongji University) | Dong, H. (Key Laboratory of Geotechnical and Underground Engineering (Tongji University) / Tongji University) | Li, X. (Key Laboratory of Geotechnical and Underground Engineering (Tongji University) / Tongji University) | Zhao, F. (China Station Construction Silkroad Construction Investment Group CO., LTD.)
Tunnel boring machines (TBM) are widely used in the excavation of tunnels built in hard rock, and the proper operational parameters plays an important role in obtaining high tunnelling efficiency. However, the selection of operational parameters depends on the drivers' subjective perception of tunnelling status, which may lead to misjudgement and untimely adjustment. A comprehensive assessment of TBM tunnelling status need to be introduced.
In this paper, fuzzy comprehensive evaluation method is adopted to assess the tunnelling status while tunnelling. Taking the penetration rate, advance rate, utilization, tunnelling energy and disc cutter wearing into account, an evaluating set was established, and each factor was weighted and their membership function was established. Thus a complete procedure of tunnelling status was formed. Based on the statistical of tunnelling data collected from Yinhanjiwei project in China, this established method was verified.
The evaluating results from field data shows the reasonability and feasibility of the established evaluating method. The tunnelling status of TBM are classified into four classes, and in certain class of rock mass (BQ classification), the tunnelling status of TBM varies from good to bad, which means operational parameters may not be set properly, to obtain better TBM performance, operational parameters should be adjusted according to geological conditions.
This method established considers factors in aspects of tunnelling efficiency and economic, so that it can be a good way to assess the comprehensive tunnelling status of TBM, furthermore it could be a good reference for TBM drivers to decide whether some adjustment should be made. What's more, this method can also be used in the TBM design phase to predict tunnelling status, for proper planning of project.
Last decades have seen a great increase in the exploitation and utilization of underground space. Tunnels crossing rock or soil are under construction all around the world to meet huge demand of transportation and resources supplement. TBM (Tunnel Boring Machine), a highly mechanized method that specialized in hard rock tunnelling, is more and more selected rather than traditional DBM (Drilling and Blasting). Despite the advantages of high advance rate and safety, several problems still exist in the TBM construction. For example, TBM has poor performance in terms of stratum adaptability, which means that some unfavourable geological conditions may result in the low-efficiency or even breakdown of TBM. In this context, on one hand, TBM manufacture should guarantee adequate capacity to excavate the stratum along the tunnelling line, and on the other hand, the operational parameters should be selected properly according to geological conditions and tunnelling state. Selection of TBM operational parameters would make a great difference to advance rate, tunnelling efficiency and disc cutter (installed in the front of TBM to break rock) wearing. However, the selection of operational parameters depends mostly on experiences of TBM driving crews. As far as we know, there are barely some methods established for the crews to evaluate the TBM tunnelling status, so, establishing a comprehensive evaluation method is quite necessary.
He, Huacheng (Shanghai Jiao Tong University) | Wang, Lei (Shanghai Jiao Tong University) | Xu, Shengwen (Shanghai Jiao Tong University) | Li, Bo (Shanghai Jiao Tong University) | Zhang, Jian (School of Naval Architecture and Ocean Engineering / Jiangsu University of Science and Technology)
For dynamic positioning systems, a three degree-of-freedom motion control in the horizontal plane has usually been regarded as adequate for practical applications. However, for marine structures with small water-plane area and low metacentric height, an unintentional coupling phenomena between the vertical plane and the horizontal plane will be induced by the thruster actions. In order to effectively mitigate the thruster induced roll and pitch motion, a fixed damping controller is first applied for the dynamic positioning of a semi-submersible platform in head seas. Then a novel adaptive fuzzy damping controller is further proposed to improve the pitch mitigating effects. The fuzzy controller takes the low-frequency pitch angle and pitch rate as input, and outputs the time varying damping control coefficient through fuzzy inference. Comparisons are made between the fixed damping controller and the proposed fuzzy damping controller. The simulation results reveal that the adaptive damping controller has outstanding performance in both horizontal and vertical motions.
The increasing demand for oil and gas in recent years has led to marine operations in harsher and deeper waters. As a result, marine vessels are usually required to be positioned at a special location with high accuracy, which leads to the widespread use of dynamic positioning system (DPS). A dynamically positioned (DP) vessel is defined as a vessel that maintains its position and heading (fixed location or pre-determined track) exclusively by means of active thrusters (Sprensen, 2011).
In the traditional design of dynamic positioning systems, it has been adequate to only consider the three degree-of-freedom (DOF) motion in the horizontal plane (surge, sway and yaw). However, for certain marine structures with a small water-plane area and low metacentric height, which results in relatively low hydrostatic restoring force compared to the inertia forces, an unintentional coupling phenomenon between the vertical plane and the horizontal plane through the thruster action can be invoked. This is usually found in semi-submersible platforms, which typically have natural periods in roll and pitch in the range of 35-65s (Sørensen and Strand, 1998). The thruster induced roll and pitch motion may lead to limited operating condition and discomfort of the crew. Therefore, special control strategy should be derived to suppress the unintentional coupling effects.
The fuzzy set theory is applied in the Geological strength index (GSI) determination following the Mamdani fuzzy algorithm. The fundamental parameters (block volume and joint condition factor) which were used in Cai’s quantitative GSI chart (Cai et al., 2004) are used as two input membership functions in the determination of GSI after setting 22 ”if-then” rules.
Beforehand, the joint condition factor was determined by the first fuzzy algorithm using total 210 “if-then” rules from three input functions namely joint waviness, small-scale smoothness and joint alteration factors proposed by Palmstrom, 1995.
GSI for sedimentary rock masses in Singapore was determined by Mamdani fuzzy algorithm, and it was observed that the results are comparable with quantitative GSI (Cai’s 2004 approach) and field-assessed qualitative GSI (Hoek et al., 1995).
1. Fuzzy inference algorithm
The first step in the fuzzy modeling process is the fuzzification in which the numeric values are converted into the fuzzy values after applying appropriate membership functions. The most commonly used is the linear type, trapezoidal and triangular (den Hartog et al., 1996; Alvarez Grima, 2000). In the second step of the fuzzy modeling process, the fuzzy conditional rules are to be formulated. Those conditional rules describe the input-output relationship. A fuzzy conditional rule is generally composed of a statement and a consequent (IF statement, THEN consequent). For example, “if x is good then y is valuable” in which the terms good and valuable can be represented by fuzzy sets or more specifically by membership functions. The third step in the fuzzy modeling process is to adopt a representative fuzzy inference system (FIS) to aggregate ”if-then” rules (Zadeh 1973). The FIS process is to extract the end results from the applied rules used with input parameters and their membership functions. In the final step, the required output of numerical (crisp) value is to be obtained from a fuzzy set. The process is termed as ”Defuzzification.” Among several defuzzification methods for instance centroid of area (COA), mean of the maximum and smallest of maximum, the COA is applied in this study as it is the most commonly used method (Alvarez Grima, 2000).
Unconfined compressive strength (UCS) of rocks is one of the most important parameters in rock engineering, engineering geology, and mining projects. The accuracy of laboratory test results relies highly on the quality of specimens. In some situations, obtaining good quality specimens is difficult, time-consuming and expensive. In view of this, research on the development of predictive models to determine the UCS of rocks has been carried out for more than three decades. In this paper, an intelligent approach applying the Mamdani fuzzy model was performed to predict the UCS of sedimentary rocks from a Singapore underground excavation project. For the prediction of UCS, parameters including bulk density, porosity and point load test results obtained by laboratory tests on rock cores were used as input parameters. Those predicted UCS results were compared with the results of statistical models using determination of the coefficient of correlation (R2) and root mean square error (RMSE). The comparison reveals that the performance of the fuzzy model is better than the statistical models. This approach is recommended to provide preliminary estimates of UCS for similar sedimentary rocks in other parts of Singapore. As it is the first attempt of such with limited data, it is advisable to update the current model when additional UCS results are available in local civil and mining engineering projects.
The stability of any excavated structure in rock mining project depends on many geomechanical properties of intact and rock mass such as unconfined compressive strength (UCS) and tensile strength. Bieniawski (1974) concluded that UCS is required more often than any other rock properties since this parameter is essential for the stability of underground excavations, access tunnels, roadways, etc.
There are standard procedures for measuring the UCS of rock specimens (ISRM, 2014 and ASTM D7012, 2014). These conventional procedures included the fundamental laboratory tests and correlated index tests. In the fundamental laboratory test, the deformation of a rock specimen is measured while the unconfined compressive force is increased. The stress at which the specimen failure occurs is taken as the peak strength. The second approach uses index tests to calculate the UCS instead of directly measuring it. The main advantages of the use of index tests are low costs involved and the measuring equipment is portable (Meulenkamp and Alvarez, 1999). However, in order to carry out these standard tests, good quality specimens such as cylindrical core or block specimens are necessary to be prepared with high accuracy. However, it is sometimes impossible to obtain good quality specimens in the weak or highly fractured rock mass (Alber and Kahraman, 2009).
Abstract The development of an offshore oil field is a complex and risky project. One core problem in this task is the selection of a production system that maximizes oil recovery and minimizes investments and operational costs while meeting external, economic, environmental, societal and technological demands in a scenario of uncertainties. Several studies address this problem in the literature; however, they do not consider uncertainties in the initial data neither justify objectively the chosen alternative among other feasible ones. We propose to select an offshore production system using an intelligent system that considers input uncertainties and chooses the best alternative in a rational manner. By comparing the results obtained with previous studies and real scenarios, we conclude that our methodology can obtain the optimal solution in situations where other methods cannot.
Li, Ben (Huazhong University of Science and Technology) | Wang, Guanxue (Huazhong University of Science and Technology) | Xu, Guohua (Huazhong University of Science and Technology) | Zhang, Xin (Huazhong University of Science and Technology) | Xu, Han (University of Southern California)
When an autonomous underwater vehicle (AUV) is operating in an unknown environment, a reliable obstacle avoidance system (OAS) is essential, especially for a large scale under-actuated AUV. This paper introduces an (OAS) for large-scale AUV in a 3D environment based on navigation sensors. For the OAS, reacting behavior given by fuzzy planner and predefined behavior are carried out to achieve the collision avoidance in both horizontal and vertical plane. Meanwhile, the speed of the AUV is simultaneously controlled by speed fuzzy planner to reach a desirable value. Finally, computer simulations in the 3D virtual environment are carried out to prove the effectiveness of the OAS.
The path planning of AUV can be divided into two tasks including global path planning and local path planning. The global path planning is to find an optimal path without obstacles from the start point to the goal point based on the known information and gives a series of waypoints that must be arrived. Obstacle avoidance can be considered as part of the local path planning task. When obstacles are detected, the vehicle will take collision avoidance behaviors. After avoiding the obstacles, the AUV will manage to get back to the originally planned path. So, a reliable OAS is essential for the safety of the vehicle and the success of the mission. Numerous algorithms have been created to design an OAS. Including geometric constraint, virtual force field, vector field histogram, potential field and fuzzy logic inference. Zhang, Wille and Knoll (1996) proposed that classical robot control architecture need to employ the Sensing-Modelling-Planning-Action (SMPA) strategy. However, in this way, there is a time delay between the perception of the obstacles and taking actions to avoid the obstacles, due to the complexity of the algorithms used for modeling and planning. Besides, this method requires high quality of computers and sonars to compute and sense, which is undesirable. Fuzzy logic was developed based on the relative importance of precision and allows a system to make inferences based on the uncertain or incomplete information gathered. It is also noted that (Zhao, Lu, and Anvar, 2010) Fuzzy logic relies on heuristic knowledge which is subject to the designer’s experience and interpretation of the system. A fuzzy system deals with the nonlinear match of input and output data. For large scale AUV, because of the high speed and large inertia, it is crucial for the AUV to respond in time to avoid the collisions when encountering obstacles. Therefore, the fuzzy logic algorithm is more suitable for OAS to cope with the obstacles in time based on sonar information. Xu and Feng (2009) proposed an AUV fuzzy obstacle avoidance method under event feedback supervision but did not discuss the details of the fuzzy planner. Abbasi, Danesh and Ghayour (2010) proposed a path fuzzy planner for AUV to avoid moving unknown obstacles in the horizontal plane. This paper designed an OAS for large-scale AUV in 3D space based on navigation sensors. Collision avoiding was achieved by making behaviors given by fuzzy planner along with the predefined behavior.