Energy exploration method, system and equipment based on distributed optical fiber sensing and medium

Abstract

The invention discloses an energy exploration method, system, device, equipment and medium based on distributed optical fiber sensing, and the method comprises the following steps: receiving a preliminary analysis result sent by a signal processing module, the preliminary analysis result is obtained by performing signal conversion and signal analysis on physical quantity data related to energy in an energy exploration area through a signal processing module; and inputting the preliminary analysis result into the optimized energy exploration prediction model for prediction to obtain an energy exploration prediction result. By collecting and processing distributed optical fiber data and utilizing the energy exploration prediction model to carry out energy exploration prediction, change characteristics of energy activities in different time and space scales can be comprehensively captured, energy distribution and reserves can be more accurately predicted, the overall efficiency of energy exploration is improved, and exploration errors are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of energy exploration, and particularly relates to an energy exploration method, system, device, equipment and medium based on distributed optical fiber sensing. Background Art

[0002] Distributed optical fiber sensing technology utilizes backward scattered light such as Rayleigh scattering, Brillouin scattering and Raman scattering in optical fibers, as well as forward transmitted light for sensing measurement, and can realize continuous distributed measurement of external parameters along the optical fiber. In energy exploration, this technology can monitor key parameters such as formation temperature and pressure in real time, providing strong support for accurately understanding the distribution and dynamic changes of underground energy resources. At present, remarkable achievements have been made in this technology in aspects such as oil and gas exploration and coal mine geological monitoring. For example, in oil and gas exploration, parameters such as formation pressure and temperature can be monitored in real time, providing key information for the positioning and exploitation of oil and gas resources; in coal mine geological monitoring, it can monitor the deformation of the strata in the goaf area to ensure the safe production of coal mines. However, distributed optical fiber sensing technology still faces many challenges in energy exploration applications. For example, the complexity of the technology leads to relatively high installation and maintenance costs; the measurement process may be interfered by external environmental factors, affecting the measurement accuracy, etc. Therefore, how to improve the measurement accuracy, expand the application scope, reduce the cost, etc. of distributed optical fiber sensing technology in energy exploration are urgent problems to be solved. In addition, the data collected by distributed optical fibers is huge and complex, containing various noise and interference information. How to effectively process these data to accurately obtain energy-related information is an important problem currently faced. When traditional data processing methods are used to process distributed optical fiber energy exploration data, it is often difficult to fully mine the spatio-temporal characteristics in the data, resulting in low accuracy of energy prediction and evaluation. Summary of the Invention

[0003] The purpose of the present invention is to provide an energy exploration method, system, device, equipment and medium based on distributed optical fiber sensing, which can effectively improve the accuracy and efficiency of energy exploration.

[0004] The present invention is realized through the following technical solutions:

[0005] In the first aspect, an energy exploration method based on distributed optical fiber sensing provided by the first embodiment of the present invention includes the following steps:

[0006] Receiving the preliminary analysis result sent by the signal processing module, where the preliminary analysis result is obtained by the signal processing module through signal conversion and signal analysis of the physical quantity data related to energy in the energy exploration area;

[0007] Inputting the preliminary analysis result into the optimized energy exploration prediction model for prediction to obtain the energy exploration prediction result.

[0008] Furthermore, the energy exploration prediction model is constructed using an Elman artificial neural network. The energy exploration prediction model includes an input layer, a hidden layer, an output layer, and a relevance unit. The input layer is used to receive the processed feature data set. The hidden layer uses an activation function to perform a non-linear transformation on the input data. The output layer outputs a prediction result related to energy. The relevance unit is used to store the information output by the neurons in the hidden layer at the previous moment and feedback the output information to the input layer.

[0009] Furthermore, the method further includes: after the energy exploration prediction model is constructed, training the energy exploration prediction model, specifically including:

[0010] Obtaining the raw data measured by the measurement module;

[0011] Preprocessing the collected raw data to obtain preprocessed data;

[0012] According to the energy activity law and the geological structure characteristics, dividing the collection time into multiple feature intervals, each interval corresponding to a different stage of energy activity, and combining the spatial position information, extracting the key feature data in each time-space unit to form a feature data set;

[0013] Inputting the feature data set into the energy exploration prediction model for training, enabling the energy exploration prediction model to learn the relationship between the change law of the physical quantity data related to energy in time-space and the energy distribution and reserves, and obtaining a trained energy exploration prediction model.

[0014] Furthermore, the method further includes: using two evaluation indexes, namely the root mean square error and the mean absolute percentage error, to evaluate the trained energy exploration model, specifically including:

[0015] Setting the root mean square error threshold and the mean absolute percentage error threshold according to the accuracy requirements of energy exploration,

[0016] Calculating the root mean square error and the mean absolute percentage error of the trained energy exploration prediction model respectively to obtain the root mean square error value and the mean absolute percentage error value;

[0017] If the obtained root mean square error value and mean absolute percentage error value are respectively lower than the root mean square error threshold and the mean absolute percentage error threshold, it is determined that the trained energy exploration prediction model meets the standard;

[0018] If the obtained root mean square error value and mean absolute percentage error value are respectively higher than the root mean square error threshold and the mean absolute percentage error threshold, optimizing and adjusting the trained energy exploration prediction model.

[0019] Furthermore, the optimization and adjustment of the trained energy exploration prediction model uses the zebra optimization algorithm to optimize the energy exploration prediction model. The specific method includes:

[0020] Coding and initialization: Encode the training parameters in the energy exploration prediction model as the position information of zebra individuals, randomly initialize the positions of the zebra population, and set the parameters of the algorithm.

[0021] Fitness evaluation: According to the encoded position information of zebra individuals, construct the corresponding energy exploration prediction model, calculate the root mean square error or mean absolute percentage error of the model on the validation set, and use the root mean square error or mean absolute percentage error as the fitness value of the individual.

[0022] Leader selection and population update: Select the zebra individual with the smallest fitness value as the leader, and the remaining individuals update their positions according to the leader's position and the update rules in the algorithm.

[0023] Iteration and convergence judgment: Repeat the fitness evaluation and leader selection and population update steps until the maximum number of iterations is reached or the convergence condition is satisfied, and obtain the optimal position of the zebra individual as the optimized model parameters.

[0024] Evaluation and application of the optimized model: Use the optimized model parameters to reconstruct the energy exploration prediction model, calculate the root mean square error and mean absolute percentage error on the test set, and evaluate whether the model performance has been improved. If the expected effect is not achieved, adjust the parameters of the zebra optimization algorithm and then optimize again to obtain the optimized energy exploration prediction model.

[0025] In the second aspect, an energy exploration system based on distributed optical fiber sensing provided by another embodiment of the present invention includes: a receiving module and a prediction module;

[0026] The receiving module is configured to receive the preliminary analysis result sent by the signal processing module, and the preliminary analysis result is obtained by the signal processing module performing signal conversion and signal analysis on the physical quantity data related to energy in the energy exploration area.

[0027] The prediction module is configured to input the preliminary analysis result into the optimized energy exploration prediction model for prediction to obtain the energy exploration prediction result.

[0028] Further, it also includes a model construction module. The model construction module uses an Elman artificial neural network to construct an energy exploration prediction model. The energy exploration prediction model includes an input layer, a hidden layer, an output layer, and a correlation unit. The input layer is used to receive the processed feature data set. The hidden layer uses an activation function to perform non-linear transformation on the input data. The output layer outputs a prediction result related to energy. The correlation unit is used to store the information output by the hidden layer neurons at the previous moment and feedback the output information to the input layer.

[0029] The system also includes a model training module. The model training module is configured to obtain the original data measured by the measurement module, preprocess the collected original data to obtain preprocessed data, divide the acquisition time into multiple feature intervals according to the energy activity law and geological structure characteristics. Each interval corresponds to a different stage of energy activity. Combining the spatial position information, extract the key feature data within each time-space unit to form a feature data set, and input the feature data set into the energy exploration prediction model for training, so that the energy exploration prediction model learns the relationship between the change law of the physical quantity data related to energy in time-space and the energy distribution and reserves, and obtains a trained energy exploration prediction model.

[0030] The system also includes a model optimization module. The model optimization module is configured to optimize the trained energy exploration prediction model using the zebra optimization algorithm. The model optimization module includes an encoding and initialization unit, a fitness evaluation unit, an update unit, an iteration unit, and an evaluation unit.

[0031] The encoding and initialization unit is configured to encode the training parameters in the energy exploration prediction model as the position information of zebra individuals, randomly initialize the positions of the zebra population, and set the parameters of the algorithm.

[0032] The fitness evaluation unit is configured to construct a corresponding energy exploration prediction model according to the encoded position information of zebra individuals, calculate the root mean square error or mean absolute percentage error of the model on the validation set, and use the root mean square error or mean absolute percentage error as the fitness value of the individual.

[0033] The update unit is configured to select the zebra individual with the smallest fitness value as the leader, and the remaining individuals update their positions according to the leader's position and the update rules in the algorithm.

[0034] The iteration unit is configured to repeat the fitness evaluation and leader selection and population update steps until the maximum iteration number is reached or the convergence condition is met, and obtain the optimal position of the zebra individual as the optimized model parameters.

[0035] The evaluation unit is configured to reconstruct the energy exploration prediction model using the optimized model parameters, calculate the root mean square error and the mean absolute percentage error on the test set, evaluate whether the model performance is improved. If the expected effect is not achieved, the parameters of the zebra optimization algorithm are adjusted and then optimized again.

[0036] Thirdly, an energy exploration device based on distributed optical fiber sensing provided by another embodiment of the present invention includes: a light source module, a measurement module, a signal processing module and a processor. The light source module includes a light source generator and an optical isolator. The light source generator is used to generate a broadband light source;

[0037] The optical isolator is connected to the light source generator and is used to filter the broadband light source;

[0038] The measurement module includes an optical coupler, a polarization controller, a phase modulator and a distributed optical fiber sensor. The optical coupler is used to divide the input target light source into two paths according to a preset ratio and output them to the polarization controller and the phase modulator respectively;

[0039] The polarization controller is used to compensate the polarization state of the optical signal;

[0040] The phase modulator is used to perform phase modulation on the optical signal;

[0041] The distributed optical fiber sensor is arranged underground and is used to measure the physical quantity data related to energy;

[0042] The signal processing module includes a photoelectric converter and a spectrum analyzer. The photoelectric converter is used to convert the received optical signal into a voltage signal;

[0043] The spectrum analyzer receives the voltage signal from the photoelectric converter, analyzes the voltage signal to obtain the frequency, amplitude and power spectral density, and sends the preliminary analysis result to the processor;

[0044] The processor executes the energy exploration method based on distributed optical fiber sensing described in the above embodiments.

[0045] Fourthly, an electronic device provided by another embodiment of the present invention includes a processor, an input device, an output device and a memory. The processor is respectively connected to the input device, the output device and the memory. The memory is used to store a computer program. The computer program includes program instructions. The processor is configured to call the program instructions to execute the method described in the above embodiments.

[0046] In a fifth aspect, another computer-readable storage medium provided by an embodiment of the present invention stores a computer program, and the computer program includes program instructions that, when executed by a processor, cause the processor to execute the method described in the above embodiments.

[0047] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0048] A method, system, device, equipment, and medium for energy exploration based on distributed optical fiber sensing provided by an embodiment of the present invention have the following advantages:

[0049] (1) Improve the accuracy of energy exploration: By collecting data through a measurement module, processing data through a signal processing module, and predicting energy exploration using an energy exploration prediction model, the energy distribution and reserves can be predicted more accurately, reducing exploration errors.

[0050] (2) Fully exploit spatio-temporal characteristics: The spatio-temporal feature extraction and processing can comprehensively capture the change characteristics of energy activities at different time and space scales, providing rich information for accurate energy assessment.

[0051] (3) Strong adaptability: The constructed energy exploration prediction model can adapt to the exploration needs of different types of energy and complex geological structures, and can be self-optimized and updated according to the actual situation, improving the generality and practicality of the method.

[0052] (4) Improve exploration efficiency: Accurate prediction results help optimize the exploration plan, reduce unnecessary exploration workload, and thus improve the overall efficiency of energy exploration. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0054] Figure 1 It is a structural block diagram of an energy exploration device based on distributed optical fiber sensing provided by the first embodiment of the present invention;

[0055] Figure 2 It is a flowchart of an energy exploration method based on distributed optical fiber sensing provided by the second embodiment of the present invention;

[0056] Figure 3 It is a structural block diagram of an energy exploration system based on distributed optical fiber sensing provided by the third embodiment of the present invention. Detailed implementation mode

[0057] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with embodiments and drawings. The illustrative implementation modes of the present invention and their descriptions are only used to explain the present invention and are not used to limit the present invention.

[0058] Embodiment 1

[0059] As Figure 1 shown, the structural block diagram of an energy exploration device based on distributed optical fiber sensing provided by the first embodiment of the present invention. The device includes a light source module, a measurement module, a signal processing module, and a processor.

[0060] Among them, the light source module includes a light source generator and an optical isolator. The light source generator is used to generate a broadband light source; the optical isolator is connected to the light source generator and is used to filter the broadband light source to filter out noise and reflected light and output a target light source.

[0061] The light source generator uses the amplified spontaneous emission (ASE) broadband light source generated by a high-power erbium-doped fiber amplifier (EDFA). The broadband light source uses a semiconductor laser as a pump light source to excite erbium ions from a low energy level to a high energy level, causing an inverted population distribution of particles inside the erbium-doped fiber. Then, with the spontaneous emission of high-energy-level particles, they transition back to the low energy level, and the released energy can cause the particles in the high energy level to undergo stimulated emission, thereby transitioning back to the low energy level and emitting the energy of two photons. Then, with the help of the energy of the photons, the stimulated emission action continues to obtain a high-power light source output. When the light source uses a linearly polarized semiconductor laser, if a part of the output laser has feedback, the operation of active optical devices such as lasers or optical amplifiers will tend to be unstable, its spectrum will become chaotic, and noise will also be generated due to interference in the communication system. To avoid the occurrence of the above-mentioned optical return phenomenon, this embodiment uses an optical isolator to prevent the light from returning and make the light propagate in a single direction.

[0062] The measurement module includes an optical coupler, a polarization controller, a phase modulator, and a distributed optical fiber sensor. The optical coupler is used to divide the input target light source into two paths according to a preset ratio and output them to the polarization controller and the phase modulator respectively; the polarization controller is used to compensate the polarization state of the optical signal; the phase modulator is used to perform phase modulation on the optical signal; the distributed optical fiber sensor deployed underground is used to measure physical quantity data related to energy.

[0063] The function of an optical coupler is to act as a beam splitter that divides the optical power in the required ratio, or as a beam mixer that mixes optical signals from different paths. An optical coupler with two output ports, whose coupling ratio can be 1:1 or 1:n, is called a beam splitter or a T-coupler. For an optical coupler in the beam splitting form, its input power is distributed by the two output ports according to the coupling ratio. The optical coupler in this embodiment is a 2×2 optical coupler that splits the input optical signal according to a preset ratio and outputs two optical signals.

[0064] The polarization controller is used to improve the signal fading caused by polarization in the propagating optical signal. When an optical signal propagates in a single-mode fiber, its polarization state is easily affected by the birefringence characteristics of the fiber itself or changes due to external environmental disturbances, resulting in a change in the polarization state of the guided light. The intensity of the interference signal varies with the change of the polarization state of the light wave, thereby affecting the observation of the sensing result. In severe cases, the interference signal cannot even be measured at all, thus causing signal fading. Therefore, this embodiment uses a polarization controller to overcome the above problems to improve the measurement accuracy.

[0065] The distributed optical fiber sensor in this embodiment can adopt a coated fiber sensor. A coated fiber sensor is to coat a thin film on a fiber, couple the pressure wave into the fiber, and make the fiber phase deform as the pressure changes. The coated fiber sensor is suitable for distributed sensors.

[0066] The signal processing module includes a photoelectric converter and a spectrum analyzer. The photoelectric converter is used to convert the received optical signal into a voltage signal; the spectrum analyzer receives the voltage signal from the photoelectric converter, analyzes the voltage signal to obtain the frequency, amplitude, and power spectral density, and sends the analysis result to the processor.

[0067] The photoelectric converter is used to receive the optical signal and convert it into an electrical signal. It usually uses semiconductor-based photodiodes, such as P-N junction diodes, P-I-N diodes, or avalanche diodes; and uses a transimpedance amplifier and a limiting amplifier to process the converted photocurrent. The transimpedance amplifier and the limiting amplifier can convert the photocurrent into a voltage signal with a smaller amplitude, and then convert it into a digital signal through the subsequent comparator circuit. For a high-speed optical fiber communication system, the signal often shows a relatively serious attenuation. To avoid serious distortion of the output signal, a clock recovery circuit (CDR) and a phase-lock loop circuit (PLL) are usually added at the backend of the receiver circuit to process the signal before output.

[0068] The main function of a spectrum analyzer is to analyze the frequency composition and intensity of a signal, and it is used for signal display and analysis of a measurement system. Its input signal is the voltage signal output by an optoelectronic converter, and through this instrument, the power spectral density of each frequency of this input signal can be observed.

[0069] In this embodiment, the processor can be a host computer. The host computer is connected to the spectrum analyzer and is used to receive the preliminary analysis result from the spectrum analyzer, input the preliminary analysis result into the energy exploration prediction model, output the energy exploration prediction result, and upload it to the cloud management platform. The main role of the host computer is to receive the preliminary analysis result from the spectrum analyzer and call the energy exploration prediction model for in-depth analysis. Among them, the energy exploration prediction model is trained by the cloud management platform by calling cloud computing resources according to the historical energy exploration prediction results in the database. The cloud management platform receives the energy exploration prediction result from the host computer, stores it in the database and updates the database, and synchronizes the updated model to the host computer. The host computer can also forward the preliminary analysis result to the cloud management platform for in-depth analysis, which can reduce the computing burden of the host computer and enable the host computer to be realized in a lightweight manner.

[0070] A method for energy exploration by an energy exploration device based on distributed optical fiber sensing includes the following steps:

[0071] Step 1: After receiving the measurement instruction sent by the host computer, the light source generator generates a broadband light source, and sends the broadband light source signal to the optical isolator through the optical fiber. The optical isolator filters the broadband light source signal to filter out noise and reflected light, and obtains the target light source signal;

[0072] Step 2: The optical coupler receives the target light source signal from the optical isolator and divides the target light source signal into two optical signals according to a preset ratio. Among them, the first optical signal is input into the polarization controller, and the second optical signal is input into the phase modulator;

[0073] Step 3: The polarization controller compensates the polarization state of the input first optical signal, and after the phase modulator performs phase modulation on the input second optical signal, the above two optical signals are respectively output to the distributed optical fiber sensor;

[0074] Step 4: According to the above two optical signals, the distributed optical fiber sensor measures and obtains physical quantity data related to energy, including the first optical measurement signal corresponding to the first optical signal and the second optical measurement signal corresponding to the second optical signal. The first optical measurement signal is input into the phase modulator, and the second optical measurement signal is input into the polarization controller, and is sent to the optoelectronic converter through the coupler;

[0075] Step 5: The optoelectronic converter converts the received optical signal into a voltage signal and sends the converted voltage signal to the spectrum analyzer; the spectrum analyzer analyzes the voltage signal to obtain the frequency, amplitude, and power spectral density, and sends the frequency, amplitude, and power spectral density to the host computer as the preliminary analysis result;

[0076] Step 6: The host computer receives the preliminary analysis result from the spectrum analyzer, inputs the preliminary analysis result into the energy exploration prediction model, outputs the energy exploration prediction result as the final analysis result, and uploads it to the cloud management platform;

[0077] Step 7: The cloud management platform receives the energy exploration prediction result from the host computer and stores it in the database; updates the energy exploration prediction model and synchronizes the updated model to the host computer.

[0078] An energy exploration device based on distributed optical fiber sensing in this embodiment generates a target light source through the light source module, the measurement module measures the physical quantity data related to energy according to the target light source, the signal processing module converts the optical signal into an electrical signal and analyzes it, and the host computer finally obtains the analysis result through the energy exploration prediction model, realizing accurate energy exploration according to the acquisition and analysis of underground sound waves and being able to perform accurate energy exploration according to the measurement signal, improving the efficiency and accuracy. In addition, this embodiment uses two optical signals for measurement and uses the measurement data of the two optical signals as the analysis data, which can further improve the accuracy of the analysis result to improve the accuracy of energy exploration.

[0079] Embodiment 2

[0080] As Figure 2 shown, a method for energy exploration based on distributed optical fiber sensing provided by the second embodiment of the present invention, the execution subject of this method is a processor, and includes the following steps:

[0081] Receive the preliminary analysis result sent by the signal processing module, where the preliminary analysis result is obtained by the signal processing module performing signal conversion and signal analysis on the physical quantity data related to energy in the energy exploration area;

[0082] Input the preliminary analysis result into the optimized energy exploration prediction model for prediction to obtain the energy exploration prediction result.

[0083] Among them, the energy exploration prediction model is constructed using an Elman artificial neural network. This Elman artificial neural network has an input layer, a hidden layer, an output layer, and a relevance unit. The relevance unit is used to store the information output by the hidden layer neurons at the previous moment and feedback it into the network, enabling the network to learn the differences caused by the sequence of system inputs over time. Set the connection weights between the input layer and the hidden layer and the connection weights between the hidden layer and the output layer. When the network propagates forward, calculate the outputs of each layer. Use the feature dataset to train the model so that the model learns the relationship between the variation law of energy-related physical quantity data in time-space and energy distribution and reserves.

[0084] The constructed energy exploration prediction model includes an input layer, a hidden layer, an output layer, and a relevance unit. The input layer receives the time-space feature data after feature extraction. The hidden layer performs a non-linear transformation on the input data using an appropriate activation function (such as the sigmoid function or the tanh function). The output layer outputs prediction results related to energy, such as energy reserve estimates, energy extraction potential assessment values, etc. The relevance unit is used to store the information output by the hidden layer neurons at the previous moment and feedback it to the input layer, enabling the network to learn the differences caused by the sequence of system inputs over time, so as to better capture the dynamic characteristics of energy activities. Use the feature dataset to train the model. By adjusting the connection weight matrix and other neural network parameters (such as the learning rate, the number of iterations, etc.), make the model learn the relationship between the variation law of energy-related physical quantity data in time-space and energy distribution and reserves, and minimize the error between the prediction result and the actual energy parameters.

[0085] The method also includes: after the energy exploration prediction model is constructed, training the energy exploration prediction model, specifically including:

[0086] Obtain the original data measured by the measurement module. Specifically: collect energy-related physical quantity data at multiple location points in the energy exploration area at different times through a distributed fiber optic sensor. The collection time range covers at least one complete energy activity cycle to ensure that the collected data covers different geological structures and energy states. Use the distributed fiber optic sensor to arrange multiple measurement points in the energy exploration area according to a predetermined spatial layout to ensure comprehensive coverage of the entire exploration area. The distributed fiber optic sensor continuously collects energy-related physical quantity data, such as temperature, strain, vibration, etc. The collection frequency is set according to the dynamic characteristics of energy activities to ensure that the subtle changes in energy activities can be captured. The collection time span covers at least one complete energy activity cycle, such as a complete oil and gas extraction cycle or a heat exchange cycle of geothermal energy, etc., to obtain the data characteristics of energy states in different stages.

[0087] Preprocess the collected raw data to obtain preprocessed data. Specifically: clean the collected raw data to remove outliers and noise interference, and then normalize the data to make data of different physical quantities have a unified dimension and numerical range, facilitating subsequent analysis. Data cleaning: Use methods based on statistical analysis and physical model constraints to identify and remove outliers. For example, for temperature data, if the temperature value at a certain measurement point deviates from the temperature values of surrounding measurement points by more than a certain threshold and does not conform to the temperature change range corresponding to the energy activity law and geological structure characteristics, it is determined as an outlier and corrected or deleted. At the same time, use signal processing algorithms to remove noise interference, such as using wavelet transform and other methods to separate and filter noise signals from the raw data. Normalization processing: Normalize data of different physical quantities to make them have a unified dimension and numerical range. For example, temperature data may be between 0 - 100 degrees Celsius, and strain data may be between -1 and 1. Through normalization, they are mapped to a specific interval, such as the 0 - 1 interval, for subsequent data analysis and model training.

[0088] Time - space feature extraction step: According to the energy activity law and geological structure characteristics, divide the collection time into multiple feature intervals, each interval corresponding to a different stage of energy activity. Combining spatial position information, extract key feature data within each time - space unit to form a feature dataset; According to the energy type (such as oil and gas, geothermal, coal, etc.) and the geological structure characteristics of the exploration area (such as formation structure, rock type, etc.), divide the collection time into multiple feature intervals with physical significance. For example, in oil and gas exploration, it can be divided into intervals such as the reservoir pressure rising period, stable production period, and depletion period; In geothermal energy exploration, it can be divided into intervals such as the heat reservoir heating period, stable heat exchange period, and cooling period. Combining spatial position information, for each time - space unit (i.e., a specific spatial area within a specific time interval), extract key feature data that can reflect the energy state and geological characteristics. For example, calculate statistical features such as the average value, variance, and gradient of physical quantity data within the spatial area, as well as the correlation features between different physical quantities, to form a feature dataset that can comprehensively describe the distribution and change of energy in time and space. Among them, the number and range of the divided feature intervals are dynamically adjusted according to the energy type and geological structure characteristics to accurately capture the change characteristics of energy activity in time - space.

[0089] Input the feature dataset into the energy exploration prediction model for training, enabling the energy exploration prediction model to learn the relationship between the change law of energy - related physical quantity data in time - space and the energy distribution and reserves, and obtaining a trained energy exploration prediction model.

[0090] The method further includes: evaluating the trained energy exploration model using two evaluation metrics, namely the root mean square error (RMSE) and the mean absolute percentage error (MAPE). The calculation formula for RMSE is:

[0091]

[0092] where a i is the actual energy parameter value, p i is the predicted energy parameter value, and q is the number of prediction samples.

[0093] The calculation formula for MAPE is:

[0094]

[0095] Set the thresholds of RMSE and MAPE according to the accuracy requirements of energy exploration. When the model evaluation metrics are lower than the thresholds, it is determined that the trained energy exploration model meets the standard. If the model evaluation metrics are higher than the thresholds, optimize and adjust the trained energy exploration prediction model. The optimization measures include increasing the amount of training data, such as collecting data at more time points or spatial positions; adjusting the neural network parameters, such as reducing the learning rate to improve the convergence stability of the model and increasing the number of neurons in the hidden layer to enhance the expression ability of the model, until the model meets the requirements. In this embodiment, the zebra optimization algorithm (ZOA) is used to optimize the trained energy exploration prediction model. After the model evaluation meets the standard, it is applied to energy prediction in the distributed fiber optic energy exploration area.

[0096] Use the zebra optimization algorithm (ZOA) to optimize the trained energy exploration prediction model. The specific steps include:

[0097] Coding and initialization: Encode the training parameters in the energy exploration prediction model as the position information of zebra individuals. The training parameters at least include the connection weights between the input layer and the hidden layer, the connection weights between the hidden layer and the output layer, and the number of neurons in the hidden layer in the Elman artificial neural network. Randomly initialize the positions of the zebra population and set the parameters of the algorithm, including the population size and the maximum number of iterations;

[0098] Fitness evaluation: According to the encoded positions of zebra individuals, construct the corresponding energy exploration prediction model, and calculate the RMSE or MAPE of the model on the validation set as the fitness value of the individual. The smaller the fitness value, the better the model performance;

[0099] Leader Selection and Group Update: Select the zebra individual with the minimum fitness value as the leader, and the remaining individuals update their positions according to the leader's position and the update rules in the algorithm. The update rules include foraging and defense strategies to explore the new parameter space and ensure that the new positions meet the constraint conditions, where the constraint conditions at least include the thresholds of the root mean square error (RMSE) and the mean absolute percentage error (MAPE).

[0100] Iteration and Convergence Judgment: Repeat the above steps of fitness evaluation, leader selection, and group update until the maximum number of iterations is reached or the convergence condition is met. At this time, the position of the optimal zebra individual obtained is the optimized model parameter.

[0101] Evaluation and Application of the Optimized Model: Reconstruct the energy exploration prediction model using the optimized model parameters, calculate the RMSE and MAPE on the test set, and evaluate whether the model performance has been improved. If the expected effect is not achieved, adjust the parameters of the ZOA algorithm and optimize again to obtain the optimized energy exploration prediction model.

[0102] When the model meets the evaluation requirements, apply it to the energy prediction of unknown positions in the distributed optical fiber energy exploration area. During the application process, the model can self-optimize and update according to the newly collected real-time data. For example, when the geological structure in the exploration area changes (such as formation fractures, rock deformations, etc.) or the energy state changes dynamically (such as changes in reservoir pressure caused by oil and gas extraction, changes in heat exchange efficiency caused by geothermal energy extraction, etc.), the model can automatically adjust its internal parameters to adapt to the new situation and continuously provide accurate energy exploration prediction results.

[0103] An energy exploration method based on distributed optical fiber sensing provided by an embodiment of the present invention can comprehensively capture the change characteristics of energy activities at different time and space scales through the collection and processing of distributed optical fiber data and the use of an energy exploration prediction model, can more accurately predict the energy distribution and reserves, improve the overall efficiency of energy exploration, and reduce exploration errors. The energy exploration prediction model can adapt to the exploration requirements of different types of energy and complex geological structures, and can self-optimize and update according to the actual situation.

[0104] Example 3:

[0105] As Figure 3As shown in the figure, an energy exploration system based on distributed optical fiber sensing provided by the third embodiment of the present invention is used to implement an energy exploration method based on distributed optical fiber sensing described in the second embodiment. The system includes: a receiving module and a prediction module; the receiving module is configured to receive the preliminary analysis result sent by the signal processing module, and the preliminary analysis result is obtained by the signal processing module through signal conversion and signal analysis of the physical quantity data related to energy in the energy exploration area. The prediction module is configured to input the preliminary analysis result into the optimized energy exploration prediction model for prediction to obtain the energy exploration prediction result.

[0106] The energy exploration system based on distributed optical fiber sensing further includes a model construction module. The model construction module uses an Elman artificial neural network to construct an energy exploration prediction model. The energy exploration prediction model includes an input layer, a hidden layer, an output layer, and a correlation unit. The input layer is used to receive the processed feature data set. The hidden layer uses an activation function to perform a non-linear transformation on the input data. The output layer outputs a prediction result related to energy. The correlation unit is used to store the information output by the hidden layer neurons at the previous moment and feedback the output information to the input layer.

[0107] The system further includes a model training module. The model training module is configured to obtain the original data measured by the measurement module, preprocess the collected original data to obtain the preprocessed data, divide the acquisition time into multiple feature intervals according to the energy activity law and geological structure characteristics, each interval corresponding to a different stage of energy activity, combine the spatial position information, extract the key feature data in each time-space unit to form a feature data set, and input the feature data set into the energy exploration prediction model for training, so that the energy exploration prediction model learns the relationship between the change law of the physical quantity data related to energy in time-space and energy distribution and reserves, and obtains the trained energy exploration prediction model.

[0108] The system further includes a model optimization module. The model optimization module is configured to optimize the trained energy exploration prediction model using the zebra optimization algorithm. The model optimization module includes an encoding and initialization unit, a fitness evaluation unit, an update unit, an iteration unit, and an evaluation unit.

[0109] The encoding and initialization unit is configured to encode the training parameters in the energy exploration prediction model as the position information of zebra individuals, randomly initialize the positions of the zebra population, and set the parameters of the algorithm.

[0110] The fitness evaluation unit is configured to construct a corresponding energy exploration prediction model according to the encoded position information of zebra individuals, calculate the root mean square error or mean absolute percentage error of the model on the validation set, and use the root mean square error or mean absolute percentage error as the fitness value of the individual.

[0111] The update unit is configured to select the zebra individual with the minimum fitness value as the leader, and the remaining individuals update their positions according to the leader's position and the update rules in the algorithm.

[0112] The iteration unit is configured to repeat the fitness evaluation, leader selection, and population update steps until the maximum number of iterations is reached or the convergence condition is satisfied, and the optimal position of the zebra individual is obtained as the optimized model parameters.

[0113] The evaluation unit is configured to reconstruct the energy exploration prediction model using the optimized model parameters, calculate the root mean square error and mean absolute percentage error on the test set, evaluate whether the model performance has been improved. If the expected effect is not achieved, the parameters of the zebra optimization algorithm are adjusted and then optimized again.

[0114] An energy exploration system based on distributed optical fiber sensing provided by an embodiment of the present invention can comprehensively capture the change characteristics of energy activities at different time and space scales, can more accurately predict energy distribution and reserves, improve the overall efficiency of energy exploration, and reduce exploration errors by collecting, processing distributed optical fiber data and using an energy exploration prediction model for energy exploration prediction. The energy exploration prediction model can adapt to the exploration requirements of different types of energy and complex geological structures, and can be self-optimized and updated according to the actual situation.

[0115] Embodiment 4

[0116] An electronic device provided by the fourth embodiment of the present invention includes a processor, an input device, an output device, and a memory. The processor is respectively connected to the input device, the output device, and the memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions to execute the method described in the second embodiment above.

[0117] It should be understood that in the embodiments of the present invention, the so-called processor may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0118] The input device may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device may include a display (such as an LCD), a speaker, etc.

[0119] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0120] In a specific implementation, the processor, the input device, and the output device described in the embodiments of the present invention may implement the implementation manners described in the method embodiments provided by the embodiments of the present invention, and may also implement the implementation manners of the system embodiments described in the embodiments of the present invention, which will not be elaborated herein.

[0121] Embodiment 5

[0122] In the fifth embodiment of the present invention, there is also provided an embodiment of a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor is caused to execute the method described in the second embodiment above.

[0123] The computer-readable storage medium may be an internal storage unit of the terminal described in the foregoing embodiments, such as the hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk equipped on the terminal, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the terminal. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or will be output.

[0124] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0125] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described terminals and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0126] In several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces, devices or units, and can also be electrical, mechanical or other forms of connection.

[0127] The specific implementation manners described above further elaborate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only the specific implementation manners of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An energy exploration method based on distributed optical fiber sensing, characterized in that, Including the following steps: Receiving the preliminary analysis result sent by the signal processing module, where the preliminary analysis result is obtained by the signal processing module through signal conversion and analysis of the energy-related physical quantity data in the exploration area; Inputting the preliminary analysis result into the optimized energy exploration prediction model for prediction to obtain the energy exploration prediction result.

2. The energy exploration method based on distributed optical fiber sensing according to claim 1, wherein The energy exploration prediction model is constructed using an Elman artificial neural network. The energy exploration prediction model includes an input layer, a hidden layer, an output layer, and a relevance unit. The input layer is used to receive the processed feature dataset. The hidden layer uses an activation function to perform non-linear transformation on the input data. The output layer outputs the prediction result related to energy. The relevance unit is used to store the information output by the hidden layer neurons at the previous moment and feedback the output information to the input layer.

3. The energy exploration method based on distributed optical fiber sensing according to claim 2, characterized in that The method further includes: after the energy exploration prediction model is constructed, training the energy exploration prediction model, specifically including: Obtaining the original data measured by the measurement module; Preprocessing the collected original data to obtain the preprocessed data; According to the energy activity law and geological structure characteristics, dividing the acquisition time into multiple feature intervals, each interval corresponding to a different stage of energy activity, and combining the spatial position information to extract the key feature data in each time-space unit to form a feature dataset; Inputting the feature dataset into the energy exploration prediction model for training, enabling the energy exploration prediction model to learn the relationship between the change law of energy-related physical quantity data in time-space and energy distribution and reserves, to obtain the trained energy exploration prediction model.

4. The energy exploration method based on distributed optical fiber sensing according to claim 3, wherein, The method further includes: using two evaluation indicators, root mean square error and mean absolute percentage error, to evaluate the trained energy exploration model, specifically including: Setting the root mean square error threshold and mean absolute percentage error threshold according to the accuracy requirements of energy exploration; Calculating the root mean square error and mean absolute percentage error of the trained energy exploration prediction model respectively to obtain the root mean square error value and mean absolute percentage error value; If the obtained root mean square error value and mean absolute percentage error value are respectively lower than the root mean square error threshold and mean absolute percentage error threshold, it is determined that the trained energy exploration prediction model meets the standard; If the obtained root mean square error value and mean absolute percentage error value are respectively higher than the root mean square error threshold and mean absolute percentage error threshold, optimizing and adjusting the trained energy exploration prediction model.

5. The energy exploration method based on distributed optical fiber sensing according to claim 4, characterized in that, The optimization and adjustment of the trained energy exploration prediction model uses the zebra optimization algorithm to optimize the energy exploration prediction model. The specific method includes: Coding and initialization: Coding the training parameters in the energy exploration prediction model as the position information of zebra individuals, randomly initializing the positions of the zebra population, and setting the parameters of the algorithm; Fitness evaluation: According to the coded position information of zebra individuals, constructing the corresponding energy exploration prediction model, calculating the root mean square error or mean absolute percentage error of the model on the validation set, and taking the root mean square error or mean absolute percentage error as the fitness value of the individual; Leader selection and population update: Select the zebra individual with the minimum fitness value as the leader, and the remaining individuals update their positions according to the leader's position and the update rules in the algorithm; Iteration and convergence judgment: Repeat the fitness evaluation and leader selection and population update steps until the maximum number of iterations is reached or the convergence condition is satisfied, and the optimal position of the zebra individual is obtained as the optimized model parameters; Evaluation and application of the optimized model: Use the optimized model parameters to reconstruct the energy exploration prediction model, calculate the root mean square error and mean absolute percentage error on the test set, and evaluate whether the model performance is improved. If the expected effect is not achieved, adjust the parameters of the zebra optimization algorithm and then optimize again to obtain the optimized energy exploration prediction model.

6. An energy exploration system based on distributed optical fiber sensing, characterized in that, Including: A receiving module and a prediction module; The receiving module is configured to receive the preliminary analysis result sent by the signal processing module, and the preliminary analysis result is obtained by the signal processing module performing signal conversion and signal analysis on the physical quantity data related to energy in the energy exploration area; The prediction module is configured to input the preliminary analysis result into the optimized energy exploration prediction model for prediction to obtain the energy exploration prediction result.

7. The energy exploration system based on distributed optical fiber sensing according to claim 6, characterized in that, The system further includes a model construction module, and the model construction module uses an Elman artificial neural network to construct an energy exploration prediction model. The energy exploration prediction model includes an input layer, a hidden layer, an output layer, and a correlation unit. The input layer is used to receive the passed feature data set. The hidden layer performs a non-linear transformation on the input data using an activation function. The output layer outputs the prediction result related to energy, and the correlation unit is used to store the information output by the hidden layer neurons at the previous moment and feedback the output information to the input layer; The system further includes a model training module, and the model training module is configured to obtain the original data measured by the measurement module, preprocess the collected original data to obtain the preprocessed data, divide the acquisition time into multiple feature intervals according to the energy activity law and geological structure characteristics, each interval corresponding to a different stage of energy activity, combine the spatial position information, extract the key feature data in each time-space unit to form a feature data set, and input the feature data set into the energy exploration prediction model for training, so that the energy exploration prediction model learns the relationship between the change law of the physical quantity data related to energy in time-space and the energy distribution and reserves, and obtains the trained energy exploration prediction model; The system further includes a model optimization module, and the model optimization module is configured to optimize the trained energy exploration prediction model using the zebra optimization algorithm. The model optimization module includes an encoding and initialization unit, a fitness evaluation unit, an update unit, an iteration unit, and an evaluation unit; The encoding and initialization unit is configured to encode the training parameters in the energy exploration prediction model as the position information of the zebra individuals, randomly initialize the positions of the zebra population, and set the parameters of the algorithm; The fitness evaluation unit is configured to construct a corresponding energy exploration prediction model according to the encoded position information of zebra individuals, calculate the root mean square error or mean absolute percentage error of the model on the validation set, and use the root mean square error or mean absolute percentage error as the fitness value of the individual; The update unit is configured to select the zebra individual with the smallest fitness value as the leader, and the remaining individuals update their positions according to the leader's position and the update rules in the algorithm; The iteration unit is configured to repeat the fitness evaluation and leader selection and population update steps until the maximum number of iterations is reached or the convergence condition is satisfied, and obtain the optimal position of the zebra individual as the optimized model parameters; The evaluation unit is configured to reconstruct the energy exploration prediction model using the optimized model parameters, calculate the root mean square error and mean absolute percentage error on the test set, and evaluate whether the model performance has been improved. If the expected effect is not achieved, the parameters of the zebra optimization algorithm are adjusted and then optimized again.

8. An energy exploration device based on distributed optical fiber sensing, characterized in that, Including: A light source module, a measurement module, a signal processing module and a processor. The light source module includes a light source generator and an optical isolator, and the light source generator is used to generate a broadband light source; The optical isolator is connected to the light source generator and is used to filter the broadband light source; The measurement module includes an optical coupler, a polarization controller, a phase modulator and a distributed optical fiber sensor. The optical coupler is used to divide the input target light source into two paths according to a preset ratio and output them to the polarization controller and the phase modulator respectively; The polarization controller is used to compensate the polarization state of the optical signal; The phase modulator is used to perform phase modulation on the optical signal; The distributed optical fiber sensor is arranged underground and is used to measure the physical quantity data related to energy; The signal processing module includes a photoelectric converter and a spectrum analyzer. The photoelectric converter is used to convert the received optical signal into a voltage signal; The spectrum analyzer receives the voltage signal from the photoelectric converter, analyzes the voltage signal to obtain the frequency, amplitude and power spectral density, and sends the preliminary analysis result to the processor; The processor executes the energy exploration method based on distributed optical fiber sensing according to any one of claims 1-5.

9. An electronic device, comprising a processor, an input device, an output device and a memory, the processor being respectively connected to the input device, the output device and the memory, the memory being used for storing a computer program, the computer program comprising program instructions, characterized in that, The processor is configured to call the program instructions and execute the method according to any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by the processor, the processor is caused to execute the method according to any one of claims 1-5.

Images