CN111783356B - Oil yield prediction method and device based on artificial intelligence - Google Patents
Oil yield prediction method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN111783356B CN111783356B CN202010604568.XA CN202010604568A CN111783356B CN 111783356 B CN111783356 B CN 111783356B CN 202010604568 A CN202010604568 A CN 202010604568A CN 111783356 B CN111783356 B CN 111783356B
- Authority
- CN
- China
- Prior art keywords
- yield
- time
- petroleum
- predicted value
- production
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims abstract description 51
- 239000003208 petroleum Substances 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000004519 manufacturing process Methods 0.000 claims description 55
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 32
- 239000012071 phase Substances 0.000 claims description 29
- 239000007791 liquid phase Substances 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 239000012530 fluid Substances 0.000 claims description 3
- 239000003921 oil Substances 0.000 description 16
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000006403 short-term memory Effects 0.000 description 4
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 3
- 239000010779 crude oil Substances 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 3
- 239000003129 oil well Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an artificial intelligence-based petroleum yield prediction method. The method comprises the following steps: inputting the petroleum yield related information of a plurality of historical time points into a trained time sequence prediction model, and sequentially outputting the petroleum yield related information of the next time point to obtain a time sequence predicted value; judging an abnormal event and a corresponding time point according to the time sequence predicted value, and calculating a predicted value of petroleum yield related information after the time point of the abnormal event by using a moving average model with the aim of reducing loss caused by abnormal fluctuation; and replacing the predicted value of the corresponding time point output by the time sequence model with the calculated predicted value of the petroleum yield related information to obtain a petroleum yield predicted result. According to the invention, the integral petroleum yield trend is predicted by training the time sequence prediction model, and when an abnormal point is encountered, the yield value of a period of time in the future is predicted by using the moving average, so that the prediction accuracy is improved.
Description
Technical Field
The invention relates to the technical field of petroleum yield prediction, in particular to an artificial intelligence-based petroleum yield prediction method and device.
Background
Petroleum is an important raw material in daily industrial production activities, the quantity of petroleum output has important significance for guiding enterprise production and enterprise planning operation activities, and meanwhile, the accurate prediction of petroleum output can enable petroleum enterprises to make reasonable production tasks and avoid blind decisions. The production change during oil exploitation is a dynamic process, and the oil production department needs to predict the future time measurement yield of the oil well so as to purposefully adjust the oil well production scheme, thereby realizing the stable production of the oil well. Currently, the main methods for predicting the single factor time series variable problem of the yield are regression, grey system prediction, fuzzy system prediction and the like, and for the time series prediction, if the linear relation is met, traditional modeling and prediction methods such as autoregressive (CAR), sliding average (MA) and mixed autoregressive sliding average (ARIMA) can be used for predicting the time series, namely, assuming that the future values of a group of time series are linearly related to the historical values of the time series, and if the linear relation is not met, a BP neural network can be used for prediction. But these predictions are relatively inaccurate. In recent years, there are other prediction methods that can reflect the internal structure of data to some extent and play a role in solving the problem of nonlinear and non-normal time series, but there are difficulties in realizing codes. In addition, none of the existing single well production predictions take into account the impact of an anomaly event on production predictions, especially where the prediction gap is large for a period of time after the occurrence of the anomaly event in the well. The yield is relatively well predicted if the time series of yields are relatively smooth when predicting yields for a single well, but when an abnormal event is encountered, a situation occurs in which the predicted value and the actual value differ greatly.
At present, in the actual oil field yield prediction stage, the whole oil field is usually predicted, or single well yield is predicted, for example, algorithms based on SSA and RBF, BP neural network, ARIMA, A RIMA-Kalman filter and the like are adopted to predict the single well yield. Because of the non-periodicity and non-linearity of the single well crude oil yield time sequence, the single well crude oil yield time sequence needs to be modeled and predicted by using a black box model, and multi-step prediction is carried out on the single well crude oil yield time sequence by combining singular spectrum analysis and a radial basis function neural network, the singular spectrum analysis method can effectively reduce error transmission in the multi-step prediction process, so that the reliability of the multi-step prediction is improved. BP neural network can not predict the yield in detail well, can only predict its overall trend. The ARIMA (autoregressive moving average) model is quite simple, requiring only endogenous variables and not other exogenous variables (what is called endogenous variable refers to should be dependent only on the data itself, unlike regression which requires other variables).
In the prior art, the following problems exist with using time series to predict future production over time:
1) The current various models have certain problem of low prediction precision, for example, a BP neural network can predict the trend of the whole yield, but an average value is worth predicting for more areas; ARIMA adopts an ARIMA model to predict time sequence data, the time sequence data must be stable, if the data is unstable, the data cannot be captured regularly, and in essence, only linear relations can be captured, but nonlinear relations cannot be captured, and when the data fluctuation is large, the accuracy is low.
2) The current models all consider predictions under ideal conditions, but do not consider predictions after abnormal events, especially those after abnormal conditions, where the actual value may not agree with the trend of the original predicted value, resulting in a significant bias in the predicted value from the true value.
3) The calculation for the latter period of the abnormal event is too ambiguous, not predicted from the actual abnormal situation, but rather the whole is input into the model without considering the effect of the abnormal event on the whole prediction.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an artificial intelligence-based petroleum yield prediction method and device, which can improve the accuracy of petroleum yield related information prediction by considering the influence of abnormal events on prediction.
The invention provides an artificial intelligence-based petroleum yield prediction method. The method comprises the following steps:
inputting the petroleum yield related information of a plurality of historical time points into a trained time sequence prediction model, and sequentially outputting the petroleum yield related information of the next time point to obtain a time sequence predicted value;
judging an abnormal event and a corresponding time point according to the time sequence predicted value, and calculating a predicted value of petroleum yield related information after the time point of the abnormal event by using a moving average model with the aim of reducing loss caused by abnormal fluctuation;
and replacing the predicted value of the corresponding time point output by the time sequence model with the calculated predicted value of the petroleum yield related information to obtain a petroleum yield predicted result.
In one embodiment, determining an exception event and corresponding point in time comprises:
acquiring venturi data measured by a multiphase flowmeter;
acquiring the proportion of the change of the petroleum yield related data at the abnormal time point by utilizing the Venturi data;
if the current output at time t and the output change amplitude at time t-1 exceed the set threshold and the Venturi data change, determining that an abnormal event occurs and determining a corresponding time point.
In one embodiment, the predicted value of the petroleum production related information subsequent to the abnormal event time point is calculated according to the following steps:
let k=x L+1 /X L ，X L+1 X is information related to oil yield after the time point of an abnormal event L Information related to oil production prior to the time point of the abnormal event;
computing X using a moving average model L+1 The predicted value of the petroleum production related information is expressed as
In one embodiment, the time series prediction model is a long-short term memory network, and the training process includes: calculating the output value of the cells of the long-short time memory network according to a forward calculation method; reversely calculating error items of cells of each long-short-time memory network; calculating the gradient of each weight according to the corresponding error term; the weights are updated using a gradient-based optimization algorithm.
In one embodiment, the time series prediction model is a long and short term memory network, and the prediction process includes:
inputting the gas phase yield, liquid phase yield, water content and single well oil yield data measured by the multiphase flow meter into a first LSTM neural network unit, outputting as the current cell state C and hidden state H, and obtaining a predicted value
Will predict the valueAnd the corresponding values of the previous time points are input to the cells of LSTM and combined with the last cell state C and hidden state H to obtain the predicted value +.>And obtaining the time sequence predicted value.
In one embodiment, in training the time series prediction model, the sample data includes: fluid operating pressure, pre-venturi differential pressure, post-venturi differential pressure, temperature, water cut, mass instantaneous flow, volumetric instantaneous flow, mass instantaneous flow, and cumulative gas phase production, liquid phase production, water cut, and single well production per minute.
In one embodiment, the petroleum production related information includes one or more of gas phase production, liquid phase production, water content, and petroleum production.
Compared with the prior art, the method has the advantages that the abnormal event is judged according to the yield data measured by the multiphase flowmeter, the characteristics of venturi original differential pressure measurement data are applied, the integral petroleum yield trend is predicted by combining a time sequence yield training time sequence prediction model, and when abnormal points are encountered, a running average is used for predicting yield values in a future period of time so as to obtain higher accurate values.
Other features of the present invention and its advantages will become apparent from the following detailed description of exemplary embodiments of the invention, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow chart of an artificial intelligence based oil production prediction method according to one embodiment of the invention;
FIG. 2 is a schematic diagram of a training and prediction process for a long and short term memory network according to one embodiment of the invention;
FIG. 3 is an overall process schematic of an artificial intelligence based petroleum production prediction method according to one embodiment of the invention;
FIG. 4 is a graph showing predicted oil production results using a single long and short term memory network in the prior art;
figure 5 is a graphical illustration of the results of prediction using a long and short time memory network and a moving average, according to one embodiment of the invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
The invention provides an artificial intelligence-based petroleum production prediction method, which uses a trained time series model to predict petroleum production related information, including but not limited to gas phase production, liquid phase production, water content, single well production and the like. In the following description, the prediction process will be described taking a long short-term memory network (LSTM) as an example.
The petroleum yield prediction method based on artificial intelligence provided by the invention needs to train a time sequence prediction model, and is shown in fig. 1, and the model prediction process comprises the following steps:
step S110, a model sample is constructed.
Specifically, the data sources for the model building sample process are the three-phase flowmeter device measuring the fluid operating pressure, pre-venturi differential pressure, post-venturi differential pressure, temperature, water cut, mass instantaneous flow (oil), volume instantaneous flow (gas), mass instantaneous flow (water), and cumulative gas phase production, liquid phase production, water cut, and single well production per minute.
Further, the result data may be processed into average data per hour or average data per day.
Step S120, smoothing the data.
When a model sample is constructed, certain smoothing processing is needed after all data are obtained, so that unnecessary abnormal points are eliminated, and prediction errors caused by data acquisition or calculation are avoided.
Step S130, training a time sequence model to obtain a predicted value of the petroleum yield related information, and replacing the predicted value after the abnormal event by using a moving average.
The integral model is constructed by adopting the current time point and N-1 single well yield values before the current time point, and predicting the next moment. And then the predicted gas phase yield, liquid phase yield, water content and single well yield and the gas phase yield, liquid phase yield, water content and single well yield of the previous period are taken as common input to predict the gas phase yield, liquid phase yield, water content and single well yield of the next time point.
For example, taking a long-short-term memory network as an example, the gas phase yield, the liquid phase yield, the water content and the oil yield are input for N time points, and the gas phase yield, the liquid phase yield, the water content and the oil yield are output for the time point of the next time point. MA (moving average) is then used to replace the predicted value after the abnormal event.
Referring to fig. 2, the LSTM model includes an input gate, a hidden layer, and an output gate, where the hidden layer includes a plurality of LSTM units (labeled LSTM1, LSTM2, etc.), and includes an input gate i, a forgetting gate f, an output gate o, C is a state of the whole memory cell, x is an input vector, and h is an output vector of the hidden layer. The calculation formula of the input gate, the output gate and the forgetting gate in the whole cell is expressed as follows:
c t ＝f t *c t-1 +i t *tanh(W xc x t +W hc h t-1 +b c ) (4)
h t ＝o t *tanh(c t ) (5)
wherein, for the time t: i.e t Is the input gate output, W xi ,E hi ,b i Input gate weights, hidden state weights and biases are respectively input correspondingly; f (f) t Is output by forgetting gate, W xf ,W hf ,b f Respectively corresponding to forgetting gate weight, hidden state weight and bias; o (o) t Is the output gate output, W xo ,W ho ,b o The hidden state weight and the bias are respectively and correspondingly output the gate weight; c t Is the LSTM cell state, h t Is LSTM hidden state, W c b C Is the bias of the weights of the cell states.
The LSTM model training process can adopt a BPTT algorithm similar to the classical counter propagation algorithm principle, and the whole process can be divided into four steps, namely, calculating the output value of the LSTM cells according to a forward calculation method; reversely calculating an error term of each LSTM cell, wherein the error term comprises two reverse propagation directions of time and network level; calculating the gradient of each weight according to the corresponding error term; the weights are updated using a gradient-based optimization algorithm. There are various types of gradient-based optimization algorithms, such as random gradient descent (SGD), adaGrad, RMSProp, etc. The present invention preferably employs an adaptive momentum estimation algorithm (Adam). The Adam algorithm is an effective random optimization method based on gradients, integrates the advantages of the AdaGrad algorithm and the RMSProp algorithm, can calculate adaptive learning rates for different parameters, and occupies less storage resources. Compared with other random optimization methods, the Adam method has better overall performance in practical application.
Other time series prediction models, such as GRU, may be used to predict the petroleum production-related information.
For a further understanding of the present invention, the overall process of the artificial intelligence based oil production prediction method of the present invention is specifically described below in conjunction with FIG. 3, including the steps of:
step S210, processing the venturi data gas phase yield, liquid phase yield, water content and single well oil yield data measured by the multiphase flow meter, respectively performing standard processing on all the result data, and changing the data into a format required by the model, for example, the input format is:
(X N-6 ，X N-5 ，X N-4 ，X N-3 ，X N-2 ，X N-1 ，X N ) The output is X N+1 。
Step S220, inputting the formatted data into the LSTM model, outputting the formatted data into the current cell state C and the hidden state H after passing through the first LSTM neural network unit, and obtaining the predicted data
Step S230, the process is againIs taken into the cell and combined with the last C and H, and output as +.>And so on until output +.>Wherein->To->Is a predicted value.
Step S240, comparing the predicted value with the original value, and training the whole LSTM model according to the loss function.
Step S250, predicting petroleum production related information by using the trained LSTM model, and obtaining time series predicted values of gas phase production, liquid phase production, water content, single well oil production and the like at different moments.
Step S260, for obtaining the time-series predicted value, determining an abnormal event and an abnormal time point.
For example, according to abnormal changes of differential pressure, temperature and pressure signals measured by the multiphase flow meter, when the upper measuring signal deviates from the average value greatly and the output instantaneous data exceeds 20% of the average range of the average output data, the abnormal output fluctuation point is determined, and a corresponding time point when an abnormal event occurs is found. That is, it is judged that the abnormal event is that the variation amplitude of the yield exceeds 20% according to the current time t and the time t-1, and that the data is changed in the original venturi data, it is considered that the abnormality is occurred.
For simple calculation, the type of the abnormal event and the yield change ratio K of the abnormal event relative to the normal condition are judged according to the current data when the abnormal event occurs, namely the K value represents the ratio of the yield at the time t to the yield at the time t-1 after the abnormal event occurs.
In step S270, the gas phase yield, liquid phase yield, water content, and yield prediction values after the abnormal point are calculated using a moving average Method (MA), and the calculated prediction values are used instead of the predicted values among LSTM.
For example, if at X L An abnormal event occurs at the corresponding moment, and the original LSTM predicted value is still inaccurate. The MA predicted value is therefore used instead of the LSTM predicted value after the abnormal point in time.
Specifically, let k=x L+1 /X L (optionally, eight data obtained from multiphase flow meter, X) L+1 For gas phase production, liquid phase production, water content and single well production after an abnormal time point, X L For gas phase production, liquid phase production, water content, and single well production before the anomaly time point), and then X is calculated using MA L+1 The predicted value thereafter, e.g. expressed asX can be obtained according to the calculation formula L+3 、X L+4 、X L+5 … X calculated by MA L+2 And the subsequent values replace the yield values predicted by the original LSTM, and finally the required gas phase yield, liquid phase yield, water content and single well yield predicted values are obtained.
The whole model prediction process is completed, wherein the gas phase yield, the liquid phase yield, the water content and the yield are predicted based on Venturi differential pressure, temperature and pressure data measured by multiphase flow meters to judge abnormal time points, the gas phase yield, the liquid phase yield, the water content and the yield result data of each minute are combined, after data processing, the whole data are input into a model to be trained, a basic LSTM prediction model is obtained, then the gas phase yield, the liquid phase yield, the water content and the yield after the abnormal points are calculated by using an MA algorithm and multiplied by a proportionality coefficient K, and the LSTM prediction gas phase yield, the liquid phase yield, the water content and the single well yield at the corresponding time points are replaced.
To further demonstrate the technical effects of the present invention, a comparative experiment was performed, taking as an example yield (productions) predictions, wherein fig. 4 is the result of the prior art prediction using a single LSTM, and fig. 5 is the result of the prediction using the lstm+ma combination of the present invention. It can be seen that the fitting effect of the prediction result (prediction) and the True value (True) of the present invention is better than that of the prior art.
In summary, the invention can predict the gas phase yield, the liquid phase yield, the water content and the petroleum yield for a long time based on the Venturi data measured by the multiphase flowmeter and by using the LSTM time series model, and has high prediction accuracy, and only corresponding yield result data is needed in the prediction process without combining other data. In addition, the invention utilizes the original Venturi data and the gas phase yield, liquid phase yield, water content and yield result data to obtain the ratio of the gas phase yield, liquid phase yield, water content and yield change at each abnormal time point, further uses a moving average model to predict the gas phase yield, liquid phase yield, water content and single well yield after an abnormal event, multiplies the ratio K after the abnormal event, replaces the gas phase yield, liquid phase yield, water content and single well yield predicted at the corresponding time point LSTM, and further ensures that the prediction result is more accurate.
The present invention may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information for computer readable program instructions, which can execute the computer readable program instructions.
Various aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.
The foregoing description of embodiments of the invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvements in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.
Claims (7)
1. An artificial intelligence-based petroleum production prediction method comprises the following steps:
inputting the petroleum yield related information of a plurality of historical time points into a trained time sequence prediction model, and sequentially outputting the petroleum yield related information of the next time point to obtain a time sequence predicted value;
judging an abnormal event and a corresponding time point according to the time sequence predicted value, and calculating a predicted value of petroleum yield related information after the time point of the abnormal event by using a moving average model with the aim of reducing loss caused by abnormal fluctuation;
replacing the predicted value of the corresponding time point output by the time sequence model with the calculated predicted value of the petroleum yield related information to obtain a petroleum yield predicted result;
wherein the predicted value of the petroleum production related information subsequent to the abnormal event time point is calculated according to the following steps:
let k=x L+1 /X L ，X L+1 X is information related to oil yield after the time point of an abnormal event L Information related to oil production prior to the time point of the abnormal event;
computing X using a moving average model L+1 The predicted value of the petroleum production related information is expressed as
Wherein in training the time series prediction model, the sample data includes: fluid operating pressure, pre-venturi differential pressure, post-venturi differential pressure, temperature, water cut, mass instantaneous flow, volumetric instantaneous flow, mass instantaneous flow, and cumulative gas phase production, liquid phase production, water cut, and single well production per minute.
2. The method of claim 1, wherein determining an exception event and a corresponding point in time comprises:
acquiring venturi data measured by a multiphase flowmeter;
acquiring the proportion of the change of the petroleum yield related data at the abnormal time point by utilizing the Venturi data;
if the current output at time t and the output change amplitude at time t-1 exceed the set threshold and the Venturi data change, determining that an abnormal event occurs and determining a corresponding time point.
3. The method of claim 1, wherein the time series prediction model is a long-short-term memory network, and the training process comprises: calculating the output value of the cells of the long-short time memory network according to a forward calculation method; reversely calculating error items of cells of each long-short-time memory network; calculating the gradient of each weight according to the corresponding error term; the weights are updated using a gradient-based optimization algorithm.
4. The method of claim 1, wherein the time series prediction model is a long-short-term memory network, the prediction process comprising:
inputting the gas phase yield, liquid phase yield, water content and single well oil yield data measured by the multiphase flow meter into a first LSTM neural network unit, outputting as the current cell state C and hidden state H, and obtaining a predicted value
Will predict the valueAnd the corresponding values of the previous time points are input to the cells of LSTM and combined with the last cell state C and hidden state H to obtain the predicted value +.>And obtaining the time sequence predicted value.
5. The method of claim 1, wherein the petroleum production-related information includes one or more of gas phase production, liquid phase production, water content, and petroleum production.
6. A computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor realizes the steps of the method according to any of claims 1 to 5.
7. A computer device comprising a memory and a processor, on which memory a computer program is stored which can be run on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 5 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010604568.XA CN111783356B (en) | 2020-06-29 | 2020-06-29 | Oil yield prediction method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010604568.XA CN111783356B (en) | 2020-06-29 | 2020-06-29 | Oil yield prediction method and device based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111783356A CN111783356A (en) | 2020-10-16 |
| CN111783356B true CN111783356B (en) | 2024-03-29 |
Family
ID=72760081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010604568.XA Active CN111783356B (en) | 2020-06-29 | 2020-06-29 | Oil yield prediction method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783356B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112360399A (en) * | 2020-11-30 | 2021-02-12 | 中国石油大学(北京) | Method, device and equipment for predicting yield of coal bed gas |
| CN112560238A (en) * | 2020-12-03 | 2021-03-26 | 中国石油天然气股份有限公司 | Oil yield prediction method and device based on Starkeberg game model |
| CN113537592B (en) * | 2021-07-15 | 2023-09-15 | 中国石油大学(北京) | Oil and gas reservoir yield prediction method and device based on long-short-term memory network |
| CN115204533A (en) * | 2022-09-16 | 2022-10-18 | 中国地质大学（北京） | Oil-gas yield prediction method and system based on multivariable weighted combination model |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156473A (en) * | 2014-08-25 | 2014-11-19 | 哈尔滨工业大学 | LS-SVM-based method for detecting anomaly slot of sensor detection data |
| CN105205570A (en) * | 2015-10-16 | 2015-12-30 | 国网重庆铜梁区供电有限责任公司 | Power grid power sale quantity prediction method based on season time sequence analysis |
| CN106651001A (en) * | 2016-11-08 | 2017-05-10 | 浙江理工大学 | Needle mushroom yield prediction method based on improved neural network and implementation system |
| CN107346464A (en) * | 2016-05-06 | 2017-11-14 | 腾讯科技（深圳）有限公司 | Operational indicator Forecasting Methodology and device |
| CN107478280A (en) * | 2017-08-17 | 2017-12-15 | 合肥工业大学 | A kind of water-coal-slurry electromagnetic flowmeter signal processing method based on the analysis of excitation frequency higher hamonic wave |
| CN110119845A (en) * | 2019-05-11 | 2019-08-13 | 北京京投亿雅捷交通科技有限公司 | A kind of application method of track traffic for passenger flow prediction |
| CN110264352A (en) * | 2019-05-16 | 2019-09-20 | 福建江夏学院 | Stock index prediction method and device based on neural network model and time series |
| CN110284872A (en) * | 2019-06-10 | 2019-09-27 | 中国石油大学(北京) | The virtual flow rate calculation method and system of the underwater acquisition system of offshore gas field group |
| CN110516890A (en) * | 2019-09-04 | 2019-11-29 | 重庆邮电大学 | A kind of crop yield monitoring system based on Grey Combinatorial Model Method |
| CN110621846A (en) * | 2017-05-04 | 2019-12-27 | 解决方案探寻有限公司 | Recording data from a streaming network |
| CN111163092A (en) * | 2019-12-30 | 2020-05-15 | 深信服科技股份有限公司 | Flow abnormity detection method, device, equipment and storage medium |
| CN111279050A (en) * | 2017-09-11 | 2020-06-12 | 吉奥奎斯特系统公司 | Well planning system |
-
2020
- 2020-06-29 CN CN202010604568.XA patent/CN111783356B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156473A (en) * | 2014-08-25 | 2014-11-19 | 哈尔滨工业大学 | LS-SVM-based method for detecting anomaly slot of sensor detection data |
| CN105205570A (en) * | 2015-10-16 | 2015-12-30 | 国网重庆铜梁区供电有限责任公司 | Power grid power sale quantity prediction method based on season time sequence analysis |
| CN107346464A (en) * | 2016-05-06 | 2017-11-14 | 腾讯科技（深圳）有限公司 | Operational indicator Forecasting Methodology and device |
| CN106651001A (en) * | 2016-11-08 | 2017-05-10 | 浙江理工大学 | Needle mushroom yield prediction method based on improved neural network and implementation system |
| CN110621846A (en) * | 2017-05-04 | 2019-12-27 | 解决方案探寻有限公司 | Recording data from a streaming network |
| CN107478280A (en) * | 2017-08-17 | 2017-12-15 | 合肥工业大学 | A kind of water-coal-slurry electromagnetic flowmeter signal processing method based on the analysis of excitation frequency higher hamonic wave |
| CN111279050A (en) * | 2017-09-11 | 2020-06-12 | 吉奥奎斯特系统公司 | Well planning system |
| CN110119845A (en) * | 2019-05-11 | 2019-08-13 | 北京京投亿雅捷交通科技有限公司 | A kind of application method of track traffic for passenger flow prediction |
| CN110264352A (en) * | 2019-05-16 | 2019-09-20 | 福建江夏学院 | Stock index prediction method and device based on neural network model and time series |
| CN110284872A (en) * | 2019-06-10 | 2019-09-27 | 中国石油大学(北京) | The virtual flow rate calculation method and system of the underwater acquisition system of offshore gas field group |
| CN110516890A (en) * | 2019-09-04 | 2019-11-29 | 重庆邮电大学 | A kind of crop yield monitoring system based on Grey Combinatorial Model Method |
| CN111163092A (en) * | 2019-12-30 | 2020-05-15 | 深信服科技股份有限公司 | Flow abnormity detection method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| "基于机器学习方法的油井日产油量预测";刘巍 等;《石油钻采工艺》;第42卷(第02期);第70-75页 * |
| "面向产品生命周期的ARMA销售预测模型设计与实现";石鹤群;《硕士电子期刊》;第2016卷(第03期);第5章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111783356A (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111783356B (en) | Oil yield prediction method and device based on artificial intelligence | |
| US20210110313A1 (en) | Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models | |
| Hu et al. | Time series prediction method based on variant LSTM recurrent neural network | |
| US20190303755A1 (en) | Water quality prediction | |
| JP7206874B2 (en) | Control device, control method and program | |
| CN111143989B (en) | Frequency adjustment amount calculation method, module, system, storage medium, and device | |
| Hall | Uncertainty-based sensitivity indices for imprecise probability distributions | |
| WO2020188328A1 (en) | Method of performing a process and optimizing control signals used in the process | |
| US8874409B2 (en) | Multi-step time series prediction in complex instrumented domains | |
| US20220277232A1 (en) | Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models | |
| US20160314409A1 (en) | Method and system for real time production optimization based on equipment life | |
| CN110874616A (en) | Transformer operation prediction method based on LSTM network and Markov chain correction error | |
| Cheng et al. | Short-interval dynamic forecasting for actual S-curve in the construction phase | |
| WO2020075019A1 (en) | Prediction model enhancement | |
| US20200050982A1 (en) | Method and System for Predictive Modeling for Dynamically Scheduling Resource Allocation | |
| Zhu et al. | Novel causal network modeling method integrating process knowledge with modified transfer entropy: a case study of complex chemical processes | |
| CN116028315A (en) | Operation early warning method, device, medium and electronic equipment | |
| CN116502774B (en) | Time sequence prediction method based on time sequence decomposition and Legend projection | |
| US20210142208A1 (en) | Cumulative reward predictor training | |
| Durnyak et al. | Simulation of a combined robust system with a P-fuzzy controller | |
| Shen et al. | Sensitivity Analysis of Wavelet Neural Network Model for Short‐Term Traffic Volume Prediction | |
| Liu et al. | Identification of non-uniformly sampled Wiener systems with dead-zone non-linearities | |
| CN114118676A (en) | Data analysis method and device based on multi-type sensing equipment and readable medium | |
| JP2022163293A (en) | Operation support device, operation support method and program | |
| CN116362300B (en) | Regional power grid abnormal disturbance quantity prediction method, device, medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |