Integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things

Abstract

This invention belongs to the field of energy efficiency management technology. It discloses an integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things (IoT). The system includes: real-time acquisition and fusion processing of parameter data through an IoT sensing layer to obtain a corresponding basic energy consumption dataset; generation of standardized power metering data using harmonic analysis and phase compensation algorithms; multi-scale pattern mining and load decomposition of the standardized power metering data to construct a power load characteristic model; analysis of the relationship between production status and energy consumption to establish an energy efficiency evaluation index system and energy consumption baseline; real-time evaluation and benchmarking analysis using group clustering and anomaly detection algorithms to form an energy efficiency optimization strategy knowledge base; output of intelligent control decision sequences through multi-objective optimization; execution of the intelligent control decision sequences and adoption of a closed-loop feedback mechanism to achieve adaptive and precise equipment control and collaborative energy consumption management, effectively solving the problems of traditional oil well power management.

Description

Technical Field

[0001] This invention relates to the field of energy efficiency management technology, and more specifically, to an integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things. Background Technology

[0002] In the oil extraction sector, oil wells are the core production units, and their electricity consumption accounts for a significant proportion of the total oil extraction cost. With the continuous development of the oil industry, the demands for oil well production efficiency and economic benefits are increasing, and traditional oil well electricity management models are gradually revealing numerous problems.

[0003] Compared with existing technologies, traditional oil well data acquisition relies on manual periodic inspections, which is inefficient and lacks real-time performance, failing to reflect changes in parameters during oil well operation in a timely manner. Moreover, the collected data is scattered and inconsistent in format, making it difficult to effectively integrate and analyze. Furthermore, due to a lack of scientific planning, it is difficult to balance accuracy and transmission efficiency, resulting in inconsistent data quality and failing to provide a reliable basis for subsequent analysis.

[0004] Traditional methods for assessing the power quality of oil wells are relatively simple, lacking precise power metering and standardized data processing. This makes it difficult to detect abnormal power parameters, potentially leading to the operation of oil well equipment in environments with poor power quality. This increases equipment wear and tear, reduces lifespan, and also affects production stability and safety. Furthermore, in studying power load characteristics, traditional methods cannot accurately grasp the power consumption patterns of oil wells under different times and operating conditions, making it difficult to allocate power reasonably for different load types, resulting in energy waste and increased production costs. They also cannot scientifically assess oil well energy efficiency. Finally, in terms of energy efficiency optimization, it is difficult to formulate effective optimization strategies, making it challenging to improve the overall energy efficiency of oil wells.

[0005] The rapid development of technologies such as the Internet of Things, big data, and artificial intelligence has provided new opportunities for solving the above problems;

[0006] In view of this, the present invention proposes an integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things to solve the above problems. Summary of the Invention

[0007] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution:

[0008] An integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things includes:

[0009] The data sensing module performs real-time monitoring and collection of multiple parameters in the oil well area based on a pre-built IoT sensing layer, and performs fusion processing on the collected data to obtain a structured basic dataset of oil well energy consumption.

[0010] The power quality analysis module, based on the obtained basic dataset of oil well energy consumption, and combined with harmonic analysis and phase compensation algorithms, performs in-depth analysis of power parameters and dynamic quality assessment, generating standardized power metering data with traceability.

[0011] The energy efficiency correlation module is based on the constructed electricity load characteristic model, and performs multi-dimensional correlation analysis on the relationship between production status and energy consumption in the target oil well area. Based on this, a corresponding energy efficiency evaluation index system and energy consumption baseline are constructed.

[0012] The dynamic evaluation module, based on the energy efficiency evaluation index system and the energy consumption baseline, uses group clustering and anomaly detection algorithms to perform real-time dynamic evaluation and benchmarking analysis of oil well power utilization efficiency, forming a hierarchical knowledge base of energy efficiency optimization strategies.

[0013] The decision generation module generates an energy efficiency improvement scheme based on the constructed energy efficiency optimization strategy knowledge base and multi-source real-time production parameters, and outputs a predictive intelligent control decision sequence.

[0014] The decision execution module, based on the obtained intelligent control decisions, performs adaptive and precise control and collaborative energy consumption management of oil well equipment through a closed-loop feedback mechanism.

[0015] Furthermore, intelligent sensing terminals and communication terminals are installed at oil well equipment such as oil well pump units, transformers, and distribution cabinets within the oil well area; the intelligent sensing terminals include, but are not limited to, temperature sensing terminals, current sensing terminals, and power factor sensing terminals; the communication terminals support multiple industrial communication protocols, such as MODBUS, OPCUA, or customized communication protocols.

[0016] A data acquisition gateway is constructed, which is used to perform preliminary processing on the data collected by the intelligent sensing terminal. The preliminary processing includes operations such as signal processing, filtering and analog-to-digital conversion, so that the sensing signals collected by the intelligent sensing terminal are converted into data.

[0017] Furthermore, a network connection is established between the intelligent sensing terminal and the data acquisition gateway based on the communication terminal, thereby obtaining the corresponding Internet of Things (IoT) sensing layer.

[0018] Furthermore, the process of acquiring the basic dataset of oil well energy consumption includes:

[0019] Based on the Internet of Things (IoT) sensing layer, multiple parameters of each oil well device in the oil well area are collected in real time to obtain the corresponding raw device parameter dataset. The raw device parameter dataset consists of several raw device parameter data, which include sensor ID, device ID, measurement parameter type, measurement value, timestamp, and geographical location information.

[0020] The collected raw equipment parameter dataset is cleaned based on preprocessing and outlier detection operations to obtain a cleaned raw equipment parameter dataset; then, the cleaned raw equipment parameter dataset is timestamped and fused to obtain time-series power data in a unified format.

[0021] Feature extraction is performed on the electrical parameters in the obtained time-series electrical energy data to obtain the corresponding basic electrical energy parameters and derived indices, and then they are converted into vector representations to obtain the corresponding feature vectors.

[0022] The obtained feature vectors are classified and integrated in multiple dimensions, and metadata is labeled based on the original equipment parameter dataset to obtain a structured basic dataset of oil well energy consumption.

[0023] Furthermore, the process of acquiring standardized electricity metering data includes:

[0024] Based on the basic dataset of oil well energy consumption, obtain the corresponding voltage and current waveform data, and obtain the corresponding basic power quality parameters.

[0025] Harmonic analysis is performed on the corresponding voltage and current waveform data based on the Fast Fourier Transform algorithm, and the harmonic analysis results corresponding to each harmonic are obtained.

[0026] The obtained basic power quality parameters and harmonic analysis results are integrated, and a power quality feature matrix containing multiple dimensions is constructed based on it.

[0027] Voltage fluctuation, three-phase imbalance and power factor are evaluated based on the power quality characteristic matrix, and a power quality scoring table containing scores for each power parameter is constructed based on it.

[0028] The power quality rating table and industry power quality standards are used to calculate parameter deviations and obtain the corresponding deviation calculation results. A mapping relationship between the deviation calculation results and the actual measured values ​​of power parameters is constructed, and calibration coefficients corresponding to the power parameters are generated based on it.

[0029] Based on the obtained calibration coefficients, a multinomial fitting algorithm is used to construct calibration models corresponding to different power parameters, and these models are combined to obtain the corresponding power parameter calibration models.

[0030] Based on the obtained power parameter calibration model, the time-series power data is corrected and standardized to obtain high-precision power metering data.

[0031] Statistical analysis and time-scale aggregation are performed on the obtained high-precision electricity metering data to obtain standardized electricity metering data at different time scales.

[0032] Furthermore, the process of obtaining the electricity load characteristic model includes:

[0033] The standardized electricity metering data obtained is decomposed into trend, seasonal and random components using time series analysis algorithms. The seasonal components are then periodically identified to obtain the multi-scale periodic characteristics of the standardized electricity data, including daily, weekly and seasonal periods.

[0034] By combining the trend term and seasonal term and the corresponding multi-scale periodic features, a time feature model corresponding to electricity consumption is constructed.

[0035] Based on the standardized electricity metering data, the corresponding load change curve is obtained and divided into several load curve segments;

[0036] Time-frequency domain features are extracted from the load curve segments to obtain the corresponding load statistical feature vectors;

[0037] Obtain the load statistical feature vector corresponding to each load curve segment, and construct a set of typical load patterns based on it;

[0038] Cluster analysis is performed on a set of typical load patterns to obtain the corresponding load type classification;

[0039] Representative samples are extracted based on the load type classification to obtain corresponding typical representative samples; and a load type identification rule base is constructed based on them.

[0040] Based on the load type identification rule base, feature extraction and type matching are performed on the real-time collected power data to obtain the load type of the current oil well area. Combined with the current oil well equipment status, the current total power is allocated to obtain the equipment-level load distribution map. The obtained load distribution map is then integrated with the constructed time characteristic model to build a three-dimensional power load characteristic model that includes time and space dimensions.

[0041] Furthermore, the process of obtaining the energy efficiency evaluation index system includes:

[0042] Configure a production acquisition unit and collect production parameters within the target oil well area based on it; integrate the collected production parameters with power consumption data to obtain the corresponding energy consumption-production correlation dataset;

[0043] Multivariate correlation analysis and causal relationship inference were performed based on the energy consumption-production related dataset to obtain the corresponding correlation matrix and causal relationship;

[0044] The obtained causal relationships are classified into key factors that directly affect oil well energy consumption and key factors that indirectly affect oil well energy consumption.

[0045] Based on the aforementioned correlation matrix and causal relationships, the key factors that directly affect oil well energy consumption are ranked to form a ranking table of key influencing factors.

[0046] Based on the ranking table of key influencing factors, an energy efficiency evaluation dimension and indicator hierarchy structure is constructed; and a preliminary energy efficiency evaluation indicator system is built based on it.

[0047] The Analytic Hierarchy Process (AHP) is used to assign weights to various electrical energy parameters and production parameters to obtain corresponding index weights. Based on pre-set scoring levels, the measured values ​​corresponding to each electrical energy parameter and production parameter are mapped to standardized scores. Based on the index weights and standardized scores, the corresponding initial energy efficiency evaluation index system is improved to obtain a complete energy efficiency evaluation index system.

[0048] Furthermore, the process of obtaining the energy consumption baseline includes:

[0049] Obtain production parameters and standardized electricity metering data corresponding to the historical optimal energy efficiency operating period; and group the data based on different oil well operating conditions to obtain corresponding operating condition group data;

[0050] Based on the energy efficiency evaluation index system, the data points with the highest energy efficiency in different working condition group data are obtained and used as reference data for energy efficiency benchmarks; and based on these, a mathematical relationship between energy consumption and key influencing factors is established to obtain energy consumption benchmarks under different oil well working conditions.

[0051] Furthermore, the process of acquiring the energy efficiency optimization strategy knowledge base includes:

[0052] The system acquires real-time production parameters and standardized electricity metering data under the current oil well operating conditions. Based on the constructed energy efficiency evaluation index system, it obtains the index scores of various data indicators within the corresponding production parameters and electricity metering data. The system then performs a weighted summation based on the obtained index weights to obtain the corresponding real-time energy efficiency evaluation results.

[0053] The obtained energy efficiency assessment results are compared with the energy consumption baseline under the corresponding oil well operating conditions, and the energy efficiency deviation value and energy efficiency compliance rate are obtained based on the comparison results.

[0054] Based on the energy efficiency deviation value and energy efficiency compliance rate, an energy efficiency gap assessment result is generated, which includes energy consumption gap and energy saving potential.

[0055] The oil wells in the oil well area are divided into several oil well groups, and the oil wells in the corresponding oil well groups are compared and analyzed based on the energy efficiency gap assessment results to obtain the corresponding horizontal comparison result matrix. The horizontal comparison result matrix includes the energy efficiency ranking, gap value and best practice case of the oil wells in each group.

[0056] The current operating mode of the oil well is obtained and compared with the corresponding best practice cases. Based on the comparison results, the differences between the two oil wells are obtained, and the main optimization directions are obtained accordingly, forming a preliminary set of optimization strategies for different energy efficiency problems.

[0057] An economic evaluation and feasibility analysis are conducted on the preliminary optimization strategy set. Based on the combined results of the economic evaluation and feasibility analysis, the optimization strategies within the preliminary optimization strategy set are prioritized to form a complete energy efficiency optimization strategy knowledge base.

[0058] Furthermore, the process of obtaining the intelligent control decision sequence includes:

[0059] Collect historical operating data of oil wells, including basic datasets of oil well energy consumption and key operating parameters;

[0060] Based on the oil well energy consumption basic dataset, obtain the electrical energy consumption data corresponding to the oil well area, construct the mapping relationship between it and key operating parameters, and construct a parameter-energy consumption response model based on it.

[0061] Based on the parameter-energy consumption response model and the energy efficiency optimization strategy knowledge base, parameter optimization objectives and constraints are set; a multi-objective optimization problem is constructed based on the parameter optimization objectives and constraints; and the multi-objective optimization problem is solved based on the particle swarm optimization algorithm.

[0062] A set of Pareto optimal solutions is obtained based on the solution results of the multi-objective optimization problem, and the optimal configuration scheme is selected according to decision preferences;

[0063] Construct a digital twin model of oil well operation, simulate the implementation of the optimal configuration scheme in a virtual environment, analyze the impact of parameter adjustments on the operating status, production and energy consumption of oil well equipment, assess the risks in the implementation of the optimal configuration scheme, and formulate a complete energy efficiency improvement implementation plan based on it;

[0064] Based on the energy efficiency improvement implementation plan and the current oil well status, an intelligent control decision sequence is generated.

[0065] Furthermore, the process of adaptive precision control and collaborative energy management includes:

[0066] The intelligent control decisions are converted into commands to obtain corresponding equipment-level control commands, which are then sent to the oil well equipment.

[0067] It also monitors the response of oil well equipment and the trend of parameter changes in real time, and determines whether the parameter adjustment process changes in the expected direction;

[0068] When the change does not proceed as expected, the corresponding expected deviation result is obtained, and closed-loop feedback adjustment is performed based on the expected deviation result;

[0069] Simultaneously, the energy consumption baseline after the command is executed is obtained and compared with the energy consumption baseline before the command is executed. The energy consumption change rate and cumulative energy saving are obtained for different time periods, and the energy saving effect is quantified. An energy saving effect evaluation report containing charts and analysis conclusions is generated to intuitively display the results of energy efficiency optimization.

[0070] The technical effects and advantages of the IoT-based integrated system for oil well power metering and energy efficiency analysis of this invention are as follows:

[0071] 1. By employing harmonic analysis and phase compensation algorithms, in-depth analysis and dynamic quality assessment of power parameters are performed. From acquiring voltage and current waveform data to constructing a power quality feature matrix, then to evaluating and calculating deviations and generating calibration coefficients, the final data correction and standardization process is achieved to obtain high-precision power metering data, which is then aggregated over time. This not only accurately grasps the power quality status but also provides a reliable basis for energy consumption analysis, reducing equipment losses caused by power quality issues and ensuring stable equipment operation.

[0072] 2. By employing algorithms such as time series analysis, multi-scale pattern mining and refined load decomposition are performed on standardized electricity metering data; a time feature model is constructed to describe the electricity consumption pattern, identify load abrupt change points, extract load statistical features, construct a set of typical load patterns and classify them; real-time discrimination and power allocation are performed through a load type identification rule base, and a three-dimensional electricity load feature model is constructed to provide strong support for optimizing electricity consumption strategies and rationally allocating electricity, effectively reducing energy waste and improving energy utilization efficiency. Attached Figure Description

[0073] Figure 1 This is a schematic diagram of the integrated oil well power metering and energy efficiency analysis system based on the Internet of Things of the present invention;

[0074] Figure 2 This is a schematic diagram of the integrated method for oil well power metering and energy efficiency analysis based on the Internet of Things of the present invention. Detailed Implementation

[0075] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] Example 1

[0077] Please see Figure 1 As shown in this embodiment, the integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things includes:

[0078] The data sensing module performs real-time monitoring and collection of multiple parameters in the oil well area based on a pre-built IoT sensing layer, and performs fusion processing on the collected data to obtain a structured basic dataset of oil well energy consumption.

[0079] It should be further explained that, in the specific implementation process, the acquisition of the basic dataset of oil well energy consumption includes:

[0080] Install intelligent sensing terminals and communication terminals at oil well equipment such as oil well pump units, transformers, and distribution cabinets within the oil well area; intelligent sensing terminals include, but are not limited to, temperature sensing terminals, current sensing terminals, and power factor sensing terminals; communication terminals support a variety of industrial communication protocols, such as MODBUS, OPCUA, or customized communication protocols.

[0081] A data acquisition gateway is constructed to perform preliminary processing on the data collected by the intelligent sensing terminal. The preliminary processing includes operations such as signal processing, filtering, and analog-to-digital conversion to convert the sensing signals collected by the intelligent sensing terminal into digital quantities.

[0082] Furthermore, a network connection is established between the intelligent sensing terminal and the data acquisition gateway based on the communication terminal; thus obtaining the corresponding Internet of Things sensing layer.

[0083] Based on the constructed IoT sensing layer, multiple parameters of each oil well device in the oil well area are collected in real time to obtain the corresponding raw device parameter dataset. The raw device parameter dataset consists of several raw device parameter data, including sensor ID, device ID, measurement parameter type, measurement value, timestamp, and geographical location information.

[0084] One embodiment of the present invention includes, for example, installing high-precision voltage sensing terminals, current sensing terminals, and power factor sensing terminals on electric pumping units, frequency converters, and control cabinets to measure electrical energy parameters such as three-phase voltage, current, power, and power factor; installing temperature sensing terminals, pressure sensing terminals, etc., at wellheads, pipelines, and storage tanks to monitor production process parameters; installing vibration sensing terminals, etc., on drive motors and mechanical devices to monitor equipment operating status; installing insulation monitoring devices and temperature sensors on transformers to monitor the status of power supply equipment; and integrating weather stations to collect external condition data such as ambient temperature, humidity, and wind speed.

[0085] It should be further explained that, in the specific implementation process, due to the differences between different types of data such as temperature, pressure, voltage and current, the corresponding acquisition frequency varies in the actual data acquisition process, in order to balance data accuracy and transmission efficiency.

[0086] The collected raw equipment parameter dataset is cleaned based on preprocessing and outlier detection operations to obtain a cleaned raw equipment parameter dataset. Preprocessing includes data deduplication, missing value handling, and formatting. Missing value handling refers to using different imputation strategies based on the data type in the collected raw equipment parameter dataset to achieve data filling. For example, linear interpolation can be used for forward imputation of continuous parameters such as voltage and current. Outlier detection uses the Laida criterion, combined with the rated parameters of the oil well equipment, to identify and mark potential outliers, and then handles them. For example, taking voltage parameters in the raw equipment parameter dataset as an example, the voltage time series corresponding to the voltage parameter is obtained, the collected value at a certain data point within the voltage time series is obtained, and outlier detection is performed; the corresponding outliers are obtained and marked as potential outliers. The outlier detection method includes... Criteria and pre-defined voltage limits; for example, if the acquired value corresponding to a certain data point does not meet the criteria. The range of values ​​defined by the criteria ( If the voltage is not within the specified range, the corresponding data point is a potential anomaly. and These represent the mean and standard deviation of the corresponding voltage time series, respectively.

[0087] Outlier handling refers to smoothing outliers at detected potential anomalies using a sliding window mid-range filtering algorithm. The size of the sliding window is dynamically adjusted based on the acquisition frequency corresponding to the measurement parameters at the potential anomaly. For example, for each detected potential anomaly, a corresponding sliding window length w is set based on its acquisition frequency, and the data within the window is recorded. The mathematical expression for the corresponding smoothing process is: In the formula, This represents the parameter value corresponding to the i-th potential outlier detected, and median{} represents the median filtering operation; and These represent the values ​​within the window centered on the i-th potential outlier. and The parameter values ​​corresponding to each data point; This represents the parameter value corresponding to the potential outlier after smoothing; however, since different devices have different sampling frequencies, the sliding window size varies depending on the device parameters.

[0088] Because different intelligent sensing terminals use different sampling frequencies and data upload times, the cleaned raw equipment parameter datasets undergo timestamp alignment and data fusion to obtain time-series energy data in a unified format. The data fusion process includes: local fusion of different energy parameters from the same oil well equipment, and global fusion of energy parameters from different oil well equipment. During this fusion process, original equipment parameter data such as device ID and measurement data type are added to each data point. Timestamp alignment refers to using the intelligent sensing terminal with the highest sampling frequency as a benchmark, and then using a linear interpolation algorithm to time-paste the data collected by intelligent sensing terminals at other sampling frequencies, bringing the data collected by intelligent sensing terminals at different sampling frequencies to the same time dimension. For example, assuming the equipment parameters with a low sampling frequency... The collected value at time Then the highest sampling frequency is obtained simultaneously. and The collected value at time and Among them, it is necessary to ensure The formula for expressing the data supplemented at the corresponding time is: ; Indicates that the time is filled in. The collected values ​​at any given time;

[0089] Furthermore, feature extraction is performed on the electrical parameters within the obtained time-series electrical energy data to obtain the corresponding basic electrical energy parameters and derived indices, which are then converted into vector representations to obtain the corresponding feature vectors. The basic electrical energy parameters include statistical features such as the average three-phase voltage, the average three-phase current, active power, reactive power, and power factor; the derived indices include power quality indices (such as voltage imbalance) and equipment operating status indices (such as load factor).

[0090] The obtained feature vectors are classified and integrated in multiple dimensions, and metadata is labeled based on the original equipment parameter dataset to obtain a structured basic dataset of oil well energy consumption. The multi-dimensional data classification and integration refers to classifying and integrating the obtained feature vectors based on multiple dimensions such as equipment type, parameter type, and time dimension. The classification and integration is to group the feature vectors according to different feature categories. Feature categories include basic electrical parameters, power quality indicators, load characteristics, etc.

[0091] The power quality analysis module, based on the obtained basic dataset of oil well energy consumption, and combined with harmonic analysis and phase compensation algorithms, performs in-depth analysis of power parameters and dynamic quality assessment, generating standardized power metering data with traceability.

[0092] It should be further explained that, in the specific implementation process, the acquisition of standardized electricity metering data includes:

[0093] Based on the basic dataset of oil well energy consumption, the corresponding voltage and current waveform data are obtained, and the corresponding basic power quality parameters are obtained. The basic power quality parameters include voltage deviation, current deviation, voltage fluctuation, current fluctuation, and voltage and current frequency deviation, etc.

[0094] Meanwhile, based on the Fast Fourier Transform algorithm, harmonic analysis is performed on the corresponding voltage and current waveform data, and the harmonic analysis results corresponding to each harmonic analysis are obtained. The harmonic analysis results include indicators such as harmonic content and harmonic distortion rate.

[0095] The obtained power quality basic parameters and harmonic analysis results are integrated, and a power quality feature matrix containing multiple dimensions is constructed based on it; the power quality feature matrix can be used to characterize power quality under different dimensions.

[0096] The evaluation of voltage fluctuation, three-phase imbalance, and power factor is based on the power quality characteristic matrix. The evaluation process involves constructing evaluation levels for power parameters related to voltage fluctuation, three-phase imbalance, and power factor using industry power quality standards, mapping the actual values ​​in the power quality characteristic matrix to the evaluation levels, and obtaining the corresponding evaluation results. The evaluation results include parameter scores for each power parameter; and a power quality scoring table containing the scores for each power parameter is constructed based on it.

[0097] Then, the power quality rating table and the industry power quality standard are used to calculate the parameter deviation. The parameter deviation calculation refers to the deviation between the actual value of the collected power parameters and the standard value of the power parameters specified by the industry power quality standard, so as to determine the degree of deviation of the corresponding power parameters.

[0098] Construct a mapping relationship between the deviation calculation results and the actual values, and generate calibration coefficients corresponding to the corresponding electrical energy parameters based on it;

[0099] The calibration coefficient is generated based on the parameter deviation calculation results of the corresponding electrical energy parameters. The greater the deviation of the electrical energy parameters, the larger the corresponding coefficient.

[0100] Based on the obtained calibration coefficients, a multinomial fitting algorithm is used to construct calibration models corresponding to different power parameters. These models are then combined to obtain corresponding power parameter calibration models. Based on the obtained power parameter calibration models, time-series power data is corrected and standardized to obtain high-precision power metering data. Data correction refers to correcting the values ​​of the measurement data within the time-series power data based on the obtained calibration coefficients to eliminate the influence caused by sensor terminal errors. Standardization refers to unifying data of different dimensions to the same scale to facilitate data comparison and analysis, thereby improving data accuracy and obtaining high-precision power metering data.

[0101] The obtained high-precision electricity metering data is statistically analyzed and aggregated over time scales to obtain standardized electricity metering data at different time scales. The statistical analysis includes calculating the mean, variance, maximum, minimum, and other statistical quantities of each parameter to comprehensively understand the data distribution characteristics. The time scale aggregation adopts a hierarchical aggregation strategy to generate electricity metering data at different time scales in sequence, and includes statistical characteristics such as mean, maximum, minimum, standard deviation, and percentiles for each time scale, providing multi-dimensional support for subsequent analysis. The time scales include minute, hour, day, month, and grade.

[0102] The load characteristic analysis module performs multi-scale pattern mining and refined load decomposition analysis on the oil well power consumption based on the obtained standardized power metering data, and obtains the corresponding power load characteristic model.

[0103] It should be further explained that, in the specific implementation process, the acquisition process of the electricity load characteristic model includes:

[0104] The standardized electricity metering data obtained was decomposed using a time series analysis algorithm into trend, seasonal, and random components. The formula for this data decomposition is as follows: In the formula, This represents the value of the standardized electrical energy metering data at time t; This is the trend term, used to represent the long-term trend of a time series. This is a seasonal term used to reflect the periodic changes in a time series. For random terms, used to represent random fluctuations in standardized electricity metering data that cannot be explained by trend and seasonal terms;

[0105] Furthermore, the decomposed seasonal terms are periodically identified to obtain the corresponding standardized power data in multiple scales, such as daily, weekly, and seasonal cycles. For example, the multi-scale cycle characteristics corresponding to the daily cycle can be used to identify the changes in power consumption patterns and patterns in the oil well area on that day.

[0106] By combining trend and seasonal terms and their corresponding multi-scale periodic characteristics, a time characteristic model for power consumption is constructed. This time characteristic model is used to describe the long-term trend and periodic variation of power consumption in oil wells.

[0107] The corresponding load change curve is obtained based on standardized electricity metering data, and abrupt change points are identified to obtain the transition points of the corresponding load states. The load change curve is then divided based on the transition points to obtain corresponding load curve segments. The abrupt change point identification uses a change point detection algorithm, such as the PELT algorithm, to identify significant abrupt change points in the curve.

[0108] Time-frequency domain features are extracted from the corresponding load curve segments to obtain the corresponding load statistical features, which include data statistical features and frequency domain features. These features are then converted into vector form for expression, resulting in the corresponding load statistical feature vector. This vector can comprehensively describe the characteristics of the load change curve. Data statistical features include mean, variance, peak value, peak-to-valley ratio, etc.; frequency domain features include spectral energy distribution, dominant frequency components, etc.

[0109] Obtain the load statistical feature vector corresponding to each load curve segment, and construct the corresponding typical load mode set based on it. The typical load mode set refers to the feature vector set used to describe various typical load modes. Typical load modes include normal operation mode, no-load mode and high-load operation mode, etc.

[0110] Cluster analysis is performed on a set of typical load patterns to obtain the corresponding load type classification. The cluster analysis uses the K-means clustering algorithm and combines it with a dynamic time warp distance metric.

[0111] Representative samples are extracted based on load type classification to obtain corresponding typical representative samples. Representative sample extraction involves selecting the sample that best represents the characteristics of each load type classification as the typical representative of that load type. For example, the sample closest to the cluster center can be selected or typical samples can be generated by combining multiple samples. A load type identification rule base is then constructed based on this rule base, which is used for real-time load type discrimination.

[0112] Based on a load type identification rule base, feature extraction and type matching are performed on real-time collected power data to obtain the load type of the current oil well area. Combined with the current oil well equipment status, power is allocated to the current total power to obtain an equipment-level load distribution map. This load distribution map is then integrated with a constructed time characteristic model to build a three-dimensional power load characteristic model containing time and spatial dimensions. This model reflects the power consumption characteristics and patterns of various oil well equipment within the target oil well area under different times and operating conditions. Power allocation distributes power consumption to different equipment or functional units based on load type and total power. During power allocation, pre-set constraints must be met simultaneously. These constraints aim to minimize the sum of the differences between the power allocated to each oil well equipment and its corresponding rated power (i.e., ensuring that the power allocated to each oil well equipment is as close as possible to its corresponding rated power) to reduce performance loss or failure risks caused by power mismatch.

[0113] The energy efficiency correlation module is based on the constructed electricity load characteristic model, and performs multi-dimensional correlation analysis on the relationship between production status and energy consumption in the target oil well area. Based on this, a corresponding energy efficiency evaluation index system and energy consumption baseline are constructed.

[0114] It should be further explained that, in the specific implementation process, the acquisition process of the energy efficiency evaluation index system and energy consumption baseline includes:

[0115] Configure a production acquisition unit, which consists of equipment terminals such as an oil well dynamic fluid level gauge, flow meter, and water cut meter, to collect data on production parameters in the target oil well area. Production parameters include oil well production, fluid level height, and water cut.

[0116] The collected production parameters and power consumption data are aligned with timestamps to eliminate the impact of time deviation; and the production parameters and power consumption data are integrated into a unified dataset to form a multidimensional data table containing time, energy consumption characteristics and production characteristics, which is recorded as the energy consumption-production related dataset.

[0117] Based on the energy consumption-production correlation dataset, multivariate correlation analysis and causal relationship inference are performed. Multivariate correlation analysis uses Pearson correlation coefficients to obtain the correlation strength between different energy consumption levels and various production parameters, converting it into a matrix form to obtain the corresponding correlation matrix. The correlation matrix can be used to intuitively reflect the correlation strength between different energy consumption levels and various production parameters. Causal relationship inference uses the Granger causality test to identify the causal relationship between energy consumption and production parameters. For example, higher liquid level corresponds to heavier load and increased pumping unit energy consumption; lower liquid level reduces pumping unit load and power consumption. The obtained causal relationships are classified into key factors that directly affect oil well energy consumption and key factors that indirectly affect oil well energy consumption. The Granger causality test is existing technology and will not be elaborated upon in this invention.

[0118] Based on the correlation matrix and causal relationship, the key factors that directly affect the energy consumption of oil wells are ranked to form a ranking table of key influencing factors.

[0119] Based on a ranking table of key influencing factors, an energy efficiency evaluation dimension and indicator hierarchy are constructed. The energy efficiency evaluation dimensions include multiple aspects such as energy consumption efficiency, production efficiency, and equipment operating status. The indicator hierarchy adopts a three-layer structure: the target layer (overall energy efficiency evaluation), the criterion layer (each energy efficiency evaluation dimension), and the indicator layer (specific evaluation indicators). Each energy efficiency evaluation dimension includes several specific evaluation indicators; for example, the energy consumption efficiency dimension may include indicators such as energy consumption per unit output and energy utilization rate. Based on the energy efficiency evaluation dimension and indicator hierarchy, and combined with industry standards and expert experience, a preliminary energy efficiency evaluation indicator system is constructed.

[0120] The Analytic Hierarchy Process (AHP) is used to assign weights to various electrical energy parameters and production parameters to obtain corresponding index weights. Based on pre-set scoring levels, the measured values ​​of each electrical energy parameter and production parameter are mapped to standardized scores. Based on the index weights and standardized scores, the initial energy efficiency evaluation index system is improved to obtain a complete energy efficiency evaluation index system. During the improvement process, the improved energy efficiency evaluation index system needs to be reviewed by experts based on their experience.

[0121] Obtain production parameters and standardized electricity metering data corresponding to the historical optimal energy efficiency operating period; and group the data based on different oil well operating conditions to obtain corresponding operating condition group data, including oil well operating conditions such as production range and water content range.

[0122] Based on the energy efficiency evaluation index system, the data points with the highest energy efficiency in different working condition group data are obtained and used as reference data for energy efficiency benchmarks. Regression analysis is used to establish the mathematical relationship between energy consumption and key influencing factors, obtain the energy consumption benchmark under different oil well working conditions, and use it as a reference standard for energy efficiency evaluation and optimization.

[0123] The dynamic evaluation module, based on the energy efficiency evaluation index system and energy consumption baseline, uses group clustering and anomaly detection algorithms to conduct real-time dynamic evaluation and benchmarking analysis of oil well power utilization efficiency, forming a hierarchical knowledge base of energy efficiency optimization strategies.

[0124] It should be further explained that, in the specific implementation process, the acquisition process of the energy efficiency optimization strategy knowledge base includes:

[0125] The system acquires real-time production parameters and standardized electricity metering data under the current oil well operating conditions. Based on the constructed energy efficiency evaluation index system, it obtains the index scores of each data index within the corresponding production parameters and electricity metering data. The system then performs a weighted summation based on the obtained index weights to obtain the corresponding real-time energy efficiency evaluation results. The real-time energy efficiency evaluation results include the total score, scores for each dimension, and scores for each index.

[0126] The obtained energy efficiency assessment results are compared with the energy consumption baseline under the corresponding oil well operating conditions, and the energy efficiency deviation value and energy efficiency compliance rate are obtained based on the comparison results. The energy efficiency deviation value refers to the difference between the actual energy consumption and the baseline energy consumption, and the energy efficiency compliance rate refers to the ratio between the actual energy consumption and the baseline energy consumption.

[0127] Energy efficiency gap assessment results are generated based on energy efficiency deviation values ​​and energy efficiency compliance rates. These results include energy consumption gaps and energy-saving potential. Node potential is the product of the expected energy savings after optimization and the unit price of energy. Furthermore, economic constraints must be considered during the acquisition of energy-saving potential; the mathematical expression for these constraints is as follows:

[0128] In the formula, It indicates that it can save energy. and These represent the actual energy consumption value and the baseline energy consumption value within the energy consumption baseline, respectively. The maximum energy efficiency is determined by professionals in the field based on their work experience.

[0129] Oil wells are grouped based on their characteristics, resulting in several oil well groups. These characteristics include geological conditions, oil production methods, and equipment configurations.

[0130] Furthermore, based on the energy efficiency gap assessment results, a benchmarking analysis is conducted on similar wells within the corresponding well groups to obtain a corresponding horizontal benchmarking result matrix. The benchmarking analysis refers to identifying the best and worst performing wells in terms of energy efficiency across different wells within the same well group, constructing a benchmarking system based on these differences, and obtaining the reasons for these differences. This allows for the construction of the corresponding horizontal benchmarking result matrix. The horizontal benchmarking result matrix includes information such as the energy efficiency ranking, gap value, and best practice cases for each well within each group. It can be used to demonstrate the benchmarking results and gaps between each well and the best performing well in each dimension. Best practice cases refer to the operating methods of the best performing well, including key parameter settings, maintenance strategies, and operating procedures.

[0131] The current operating mode of the oil wells is obtained and compared with corresponding best practice cases. Based on the comparison results, the differences between the two oil wells are identified, and the corresponding main optimization directions are determined, forming a preliminary set of optimization strategies for different energy efficiency problems. The main optimization directions include... set up The optimization strategy set includes parameter adjustment, operation mode optimization, equipment upgrade, or process improvement; each optimization direction corresponds to a type of optimization strategy; the initial optimization strategy set consists of several different categories of optimization strategies; it includes multiple possible optimization schemes and their expected effects;

[0132] An economic evaluation and feasibility analysis are conducted on the preliminary set of optimization strategies. The economic evaluation refers to estimating the costs and benefits of each optimization strategy, including initial investment costs, operating costs, and expected energy-saving benefits, and obtaining economic indicators such as investment payback period and return on investment. The feasibility analysis refers to assessing the technical feasibility, implementation difficulty, and risks of the optimization strategies, taking into account factors such as technology maturity, site conditions, and personnel capabilities.

[0133] Based on the comprehensive economic assessment and feasibility analysis results, the optimization strategies within the preliminary optimization strategy set are prioritized to form a complete energy efficiency optimization strategy knowledge base, providing a systematic reference for decision-making by calculating various cost factors such as implementation costs, operating costs, and maintenance costs.

[0134] The decision generation module generates an energy efficiency improvement scheme based on the constructed energy efficiency optimization strategy knowledge base and multi-source real-time production parameters, and outputs a predictive intelligent control decision sequence.

[0135] It should be further explained that, in the specific implementation process, the acquisition process of the intelligent control decision sequence includes:

[0136] Collect historical operating data of oil wells, including basic data sets of oil well energy consumption and key operating parameters, such as stroke count, stroke, balance and pump diameter.

[0137] Based on the basic dataset of oil well energy consumption, the electrical energy consumption data corresponding to the corresponding oil well area is obtained, and the mapping relationship between it and key operating parameters is constructed. The corresponding mapping relationship is learned by the neural network algorithm, and the corresponding parameter-energy consumption response model is constructed based on it. The construction process of the parameter-energy consumption response model is existing technology and will not be explained in detail in this invention.

[0138] Based on the parameter-energy consumption response model and the energy efficiency optimization strategy knowledge base, parameter optimization objectives and constraints are set. Optimization objectives include minimizing energy consumption, maximizing energy efficiency, or a combination of multiple objectives. For example, dual-objective optimization of minimizing energy consumption and maximizing output can be considered simultaneously. Constraints include parameter range constraints (e.g., upper and lower limits of electrical energy parameters), production target constraints (e.g., minimum output requirements), equipment safety constraints (e.g., maximum load limits), etc.

[0139] Furthermore, a multi-objective optimization problem in mathematical form is constructed based on the parameter optimization objective and constraints, and the decision variables, objective function, and constraint functions are clearly defined;

[0140] The problem size and complexity of the corresponding multi-objective optimization problem are obtained, and the algorithm parameters of the particle swarm optimization algorithm are adjusted accordingly. The multi-objective optimization problem is then solved based on the adjusted particle swarm optimization algorithm. The algorithm parameters include population size, number of generations, crossover rate, mutation rate, etc.

[0141] A set of Pareto optimal solutions is obtained based on the solution results of the multi-objective optimization problem. The Pareto optimal solution refers to the optimal parameter configuration scheme under different trade-offs. One of the schemes is selected as the final optimal configuration scheme according to decision preferences. The solution includes the set values ​​and adjustment steps of each key parameter.

[0142] A digital twin model of oil well operation is constructed to simulate the implementation of the optimal configuration scheme in a virtual environment. The impact of parameter adjustments on the operating status, production, and energy consumption of oil well equipment is analyzed to verify the effectiveness of the optimal configuration scheme. Potential risks during the implementation of the optimal configuration scheme, such as equipment overload and process instability, are assessed. Risk response plans are developed to ensure the safe and reliable implementation of the scheme. A complete energy efficiency improvement execution plan is formed, including parameter configuration, implementation steps, expected results, and risk control. The process of the digital twin model is existing technology and will not be elaborated upon in this invention.

[0143] Based on the energy efficiency improvement implementation plan and the current oil well status, an intelligent control decision sequence is generated. The decision generation needs to consider the gap between the current oil well equipment status and the target oil well equipment status, plan the status transition path, and determine the order and magnitude of parameter adjustment. For multi-parameter adjustment, the mutual influence and time dependence between parameters should be considered to avoid parameter conflicts and system instability.

[0144] It also determines the implementation order and priority of control decisions within each implementation step, forming an orderly execution sequence; and generates an intelligent control decision sequence that includes specific actions, execution order, priority, and expected effects.

[0145] The decision execution module, based on the obtained intelligent control decisions, performs adaptive and precise control and collaborative energy consumption management of oil well equipment through a closed-loop feedback mechanism;

[0146] It should be further explained that, in the specific implementation process, the process of adaptive precision control and collaborative energy consumption management includes:

[0147] The intelligent control decisions are converted into corresponding equipment-level control commands, which are then sent to the oil well equipment. Command conversion involves breaking down high-priority control decisions into commands that can be executed by specific equipment. For example, pump parameter adjustment decisions are converted into inverter setpoints, and water injection parameter adjustment decisions are converted into valve openings. During the corresponding command conversion process, equipment characteristics and control protocols must be considered to ensure that the command format is correct and the parameter range is appropriate.

[0148] Real-time monitoring of equipment response and parameter change trends; real-time monitoring of equipment operation data collected through the IoT sensing layer, including control parameters and status parameters;

[0149] Parameter change trend analysis uses time series analysis to evaluate the control effect and determine whether parameter adjustments are changing in the expected direction.

[0150] When the changes do not occur as expected, the corresponding expected deviation result is obtained, and closed-loop feedback adjustment is performed based on the expected deviation result. The closed-loop feedback adjustment refers to dynamically adjusting the control quantity based on the expected deviation result and the PID control principle to eliminate fluctuations and stabilize the system. During the adjustment process, attention should be paid to avoid over-adjustment and oscillation. A gradual adjustment strategy can be adopted to ensure that the system smoothly transitions to the target state.

[0151] Simultaneously, the energy consumption baseline after the command is executed is obtained and compared with the energy consumption baseline before the command is executed. The energy consumption change rate and cumulative energy saving are obtained for different time periods, and the energy saving effect is quantified. An energy saving effect evaluation report containing charts and analysis conclusions is generated to intuitively display the results of energy efficiency optimization.

[0152] This invention acquires basic energy consumption data for oil wells during operation through real-time multi-parameter monitoring and data acquisition of oil well equipment, providing a data foundation for subsequent energy efficiency analysis. Based on this basic energy consumption dataset, it performs electrical parameter analysis and quality assessment to ensure data accuracy and standardization, providing reliable data support for energy efficiency analysis. It also conducts time-series pattern mining and load analysis of oil well electrical energy consumption to gain a deeper understanding of electrical load characteristics and establish an electrical load characteristic model. Furthermore, it performs correlation analysis between oil well production status and energy consumption, constructing an energy efficiency evaluation index system and energy consumption benchmark, providing a scientific basis for energy efficiency assessment. Based on the established evaluation system and benchmark, it conducts dynamic evaluation and benchmarking analysis of oil well electrical energy utilization efficiency, generating an energy efficiency optimization strategy knowledge base. According to the optimization strategy library and real-time production parameters, it optimizes oil well operating parameters, generating energy efficiency improvement schemes and intelligent control decisions. Finally, based on the intelligent control decisions, it performs adaptive control and energy consumption management of oil well equipment, achieving continuous improvement and optimization of oil well electrical energy utilization efficiency.

[0153] Example 2

[0154] Please see Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description in Embodiment 1. An integrated method for oil well power metering and energy efficiency analysis based on the Internet of Things is provided, including:

[0155] Step 1: Based on the pre-built IoT sensing layer, perform real-time monitoring and collection of multiple parameters in the oil well area, and fuse the collected data to obtain a structured basic dataset of oil well energy consumption.

[0156] Step 2: Based on the obtained basic dataset of oil well energy consumption, and combined with harmonic analysis and phase compensation algorithms, perform in-depth analysis of electrical energy parameters and dynamic quality assessment to generate standardized electrical energy metering data with traceability;

[0157] Step 3: Based on the obtained standardized electricity metering data, perform multi-scale pattern mining and refined load decomposition analysis on the electricity consumption of oil wells to obtain the corresponding electricity load characteristic model;

[0158] Step 4: Based on the constructed electricity load characteristic model, and based on it, conduct a multi-dimensional correlation analysis of the production status and energy consumption relationship of the target oil well area, and based on it, construct a corresponding energy efficiency evaluation index system and energy consumption baseline.

[0159] Step 5: Based on the energy efficiency evaluation index system and the energy consumption baseline, use group clustering and anomaly detection algorithms to conduct real-time dynamic evaluation and benchmarking analysis of oil well power utilization efficiency, forming a hierarchical energy efficiency optimization strategy knowledge base;

[0160] Step Six: Based on the constructed energy efficiency optimization strategy knowledge base and multi-source real-time production parameters, generate an energy efficiency improvement scheme for multi-objective optimization of oil well operating parameters, and output a predictive intelligent control decision sequence;

[0161] Step 7: Based on the obtained intelligent control decisions, and through a closed-loop feedback mechanism, perform adaptive and precise control and collaborative energy consumption management of the oil well equipment.

[0162] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0163] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0164] In the description of this invention, it should be understood that the terms "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0165] In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0166] In the description of this invention, "several" means one or more, and "a large number" means two or more.

[0167] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0168] All formulas in this manual are dimensionless and calculated numerically. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0169] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. An oil well electric energy metering and energy efficiency analysis integrated system based on the Internet of Things, characterized in that, include: The data sensing module performs real-time monitoring and collection of multiple parameters in the oil well area based on a pre-built IoT sensing layer, and performs fusion processing on the collected data to obtain a basic dataset of oil well energy consumption. The power quality analysis module, based on the obtained basic dataset of oil well energy consumption, and combined with harmonic analysis and phase compensation algorithms, performs in-depth analysis of power parameters and dynamic quality assessment, generating standardized power metering data; The load characteristic analysis module performs multi-scale pattern mining and refined load decomposition analysis on the oil well power consumption based on the obtained standardized power metering data, and obtains the power load characteristic model. The process of obtaining the characteristic model of electricity load includes: Standardized electricity metering data is decomposed into trend, seasonal, and random components; the seasonal components are periodically identified to obtain multi-scale periodic features; and a time feature model is constructed by combining the trend, seasonal, and multi-scale periodic features. The load change curve is obtained based on the standardized electricity metering data, and then divided into several load curve segments. Time-frequency domain features are extracted from load curve segments to obtain load statistical feature vectors; and a set of typical load patterns is constructed based on the load statistical feature vectors corresponding to each load curve segment. Cluster analysis is performed on a set of typical load patterns to obtain a classification of load types; Representative samples are extracted based on the load type classification to obtain typical representative samples; and a load type identification rule base is constructed based on them. Based on the load type identification rule base, feature extraction and type matching are performed on real-time power data to obtain the load type of the current oil well area. Combined with the current oil well equipment status, the current total power is allocated to obtain the equipment-level load distribution map. The obtained load distribution map is then integrated with the constructed time feature model to obtain a three-dimensional power load feature model. The energy efficiency correlation module is based on the constructed electricity load characteristic model and performs multi-dimensional correlation analysis on the relationship between production status and energy consumption in the target oil well area. Based on the results of the multi-dimensional correlation analysis, an energy efficiency evaluation index system and energy consumption baseline are constructed. The dynamic evaluation module, based on the energy efficiency evaluation index system and energy consumption baseline, uses group clustering and anomaly detection algorithms to perform real-time dynamic evaluation and benchmarking analysis of oil well power utilization efficiency, and obtains an energy efficiency optimization strategy knowledge base. The decision generation module generates energy efficiency improvement schemes based on the constructed energy efficiency optimization strategy knowledge base and real-time production parameters, resulting in an intelligent control decision sequence. The decision execution module, based on the obtained intelligent control decisions, performs adaptive and precise control and collaborative energy consumption management of oil well equipment through a closed-loop feedback mechanism.

2. The IoT-based oil well electric energy metering and energy efficiency analysis integrated system according to claim 1, characterized in that, The IoT sensing layer consists of intelligent sensing terminals, communication terminals, and data acquisition gateways.

3. The integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things as described in claim 2, characterized in that, The process of acquiring the basic dataset of oil well energy consumption includes: Based on the Internet of Things (IoT) sensing layer, multiple parameters of each oil well device are collected in real time to obtain a raw device parameter dataset; the raw device parameter dataset consists of several raw device parameter data. The collected raw equipment parameter dataset is cleaned; and the cleaned raw equipment parameter dataset is timestamped and fused to obtain time-series power data. Feature extraction is performed on the electrical parameters in the time-series electrical energy data to obtain the basic electrical energy parameters and derived indices, and then they are converted into vector representations to obtain feature vectors. The obtained feature vectors are classified and integrated in multiple dimensions, and metadata is labeled based on the original equipment parameter dataset to obtain the basic dataset of oil well energy consumption.

4. The integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things as described in claim 3, characterized in that, The process of acquiring standardized electricity metering data includes: Based on the basic dataset of oil well energy consumption, obtain the corresponding voltage and current waveform data and the corresponding basic power quality parameters; Harmonic analysis was performed on the corresponding voltage and current waveform data to obtain the harmonic analysis results; The obtained basic power quality parameters and harmonic analysis results are integrated, and a power quality feature matrix is ​​constructed based on them; Voltage fluctuation, three-phase imbalance and power factor are evaluated based on the power quality characteristic matrix, and a power quality scoring table is constructed based on the evaluation results. The parameter deviations of the power quality rating table and industry power quality standards are calculated to obtain the deviation calculation results; a mapping relationship between the deviation calculation results and the actual measured values ​​of power parameters is constructed, and corresponding calibration coefficients are generated based on it. Based on the obtained calibration coefficients, a calibration model corresponding to different power parameters is constructed by using a polynomial fitting algorithm, and the models are combined to obtain the power parameter calibration model. Based on the obtained power parameter calibration model, the time-series power data is corrected and standardized to obtain high-precision power metering data; Statistical analysis and time-scale aggregation were performed on the obtained high-precision electricity metering data to obtain standardized electricity metering data.

5. The integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things as described in claim 1, characterized in that, The process of obtaining the energy efficiency evaluation index system includes: Data on production parameters within the target oil well area are collected; the collected production parameters are integrated with power consumption data to obtain an energy consumption-production correlation dataset. Multivariate correlation analysis and causal relationship inference were performed on the energy consumption-production related dataset to obtain the correlation matrix and causal relationship; The obtained causal relationships are classified into key factors that directly affect oil well energy consumption and key factors that indirectly affect oil well energy consumption; and the key factors that directly affect oil well energy consumption are ranked to form a key influencing factor ranking table. A preliminary energy efficiency evaluation index system was constructed based on the ranking table of key influencing factors; and weights were assigned to each electrical energy parameter and production parameter to obtain the index weights. Based on the pre-set rating levels, the measured values ​​corresponding to each electrical energy parameter and production parameter are mapped to standardized scores. Based on the index weights and standardized scores, the corresponding initial energy efficiency evaluation index system is improved to obtain the energy efficiency evaluation index system.

6. The integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things as described in claim 5, characterized in that, The process of obtaining the energy consumption baseline includes: Obtain production parameters and standardized electricity metering data corresponding to the historical optimal energy efficiency operating period; and group the data based on different oil well operating conditions to obtain operating condition grouping data; Based on the energy efficiency evaluation index system, the data points with the highest energy efficiency in different working condition group data are obtained; and based on these data, a mathematical relationship between energy consumption and key influencing factors is established to obtain the energy consumption baseline.

7. The integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things as described in claim 6, characterized in that, The process of acquiring the knowledge base for energy efficiency optimization strategies includes: Based on the constructed energy efficiency evaluation index system, the index scores of various data indicators in the real-time production parameters and standardized electricity metering data under the current oil well operating conditions are obtained, and the weighted summation is performed in combination with the obtained index weights to obtain the real-time energy efficiency evaluation results. The obtained energy efficiency assessment results are compared with the energy consumption baseline under the corresponding oil well operating conditions to obtain the energy efficiency deviation value and energy efficiency compliance rate; and the energy efficiency gap assessment results are generated based on the energy efficiency deviation value and energy efficiency compliance rate. The oil wells in the oil well area are divided into several oil well groups, and a benchmarking analysis is performed on each oil well based on the energy efficiency gap assessment results to obtain a horizontal benchmarking result matrix. The horizontal benchmarking result matrix includes the energy efficiency ranking, gap value and best practice case of oil wells in each group. Obtain the current operating mode of the oil well and compare it with the corresponding best practice case. Based on the comparison results, obtain the differences between the two oil wells, and obtain the main optimization directions based on the differences and construct the corresponding preliminary optimization strategy set. An economic evaluation and feasibility analysis are conducted on the preliminary optimization strategy set, and the optimization strategies within the preliminary optimization strategy set are prioritized based on the results of the economic evaluation and feasibility analysis, resulting in an energy efficiency optimization strategy knowledge base.

8. The integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things as described in claim 7, characterized in that, The process of obtaining the intelligent regulation decision sequence includes: Collect historical operating data of oil wells; and based on the collected historical operating data, obtain the mapping relationship between power consumption data and key operating parameters, and construct a parameter-energy consumption response model based on it; Based on the parameter-based energy consumption response model and the energy efficiency optimization strategy knowledge base, parameter optimization objectives and constraints are set; based on the parameter optimization objectives and constraints, a multi-objective optimization problem is constructed and solved; Based on the solution results, a set of Pareto optimal solutions are obtained, and the optimal configuration scheme is selected according to decision preferences; The selected optimal configuration scheme is simulated and implemented based on a pre-built digital twin model of oil well operation. The risks in the implementation of the optimal configuration scheme are evaluated and corrected based on the simulation results. An energy efficiency improvement execution scheme is obtained. Based on the energy efficiency improvement execution scheme and the current oil well status, an intelligent control decision sequence is generated.

9. The integrated system for oil well power metering and energy efficiency analysis based on the Internet of Things as described in claim 8, characterized in that, The process of adaptive precision control and collaborative energy management includes: The intelligent control decisions are converted into equipment-level control commands, which are then sent to the oil well equipment. Real-time monitoring of oil well equipment response and parameter change trends, and based on this, determining whether the parameter adjustment process is changing in the expected direction; When the change does not proceed as expected, the corresponding expected deviation result is obtained, and closed-loop feedback adjustment is performed based on the expected deviation result; at the same time, the energy consumption baseline after the instruction is executed is obtained and compared with the energy consumption baseline before the instruction is executed, the energy consumption change rate and cumulative energy saving in different time periods are obtained and the data is quantified to obtain an energy saving effect assessment report.

Images