A wellhead device fault prediction system based on narrowband internet of things

Abstract

The present application relates to oil and gas equipment intelligent operation and safety early warning technical field, specifically to a kind of wellhead device fault prediction system based on narrowband internet of things.It includes: data acquisition module, for obtaining the unstructured text data and structured time series data of target wellhead device;Factor quantification module, for determining working condition mutation factor;Dynamic weight module, for determining dynamic weight factor;Fault prediction module, for responding to dynamic weight factor, and determining direct failure probability;Uncertainty quantification module, for determining uncertainty index based on multiple prediction results of fault prediction module;Risk assessment module, for determining comprehensive risk index by combining direct failure probability and uncertainty index;Decision response module, for generating graded early warning instruction.The present application realizes the change from passive response to active foresight, significantly enhances the foresight, adaptability and timeliness of fault prediction, and realizes earlier warning.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance and safety early warning technology for oil and gas equipment, specifically a wellhead device fault prediction system based on narrowband Internet of Things. Background Technology

[0002] Wellhead equipment is a key piece of equipment in oil and gas extraction, and its operating status is directly related to production safety and efficiency. How to accurately predict its potential failures and realize the transformation from passive response to proactive predictive maintenance is the core technical challenge to ensure the safe and efficient operation of oil and gas fields.

[0003] Existing fault prediction technologies largely rely on structured sensor time-series data, making it difficult to integrate expert experience and forward-looking risk information contained in unstructured texts such as geological reports and work instructions. This results in incomplete information input for prediction models. Furthermore, traditional models are typically static and cannot dynamically adjust their prediction logic based on real-time changes in working conditions. When faced with sudden changes in the geological environment or adjustments to operations, their accuracy and robustness decrease significantly. In addition, existing methods often provide a single fault probability prediction value, lacking a quantitative assessment of the uncertainty of the prediction results themselves, making it difficult to support reliable decision-making in high-risk scenarios.

[0004] Therefore, there is an urgent need for a novel fault prediction scheme that can integrate multi-source heterogeneous data, achieve adaptive prediction, and quantify uncertainty.

[0005] The information disclosed in the background section above is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention discloses a wellhead device fault prediction system based on narrowband Internet of Things. Specifically, the technical solution of this invention includes:

[0007] The data acquisition module is used to acquire unstructured text data and structured time-series data of the target wellhead device;

[0008] The factor quantification module is used to determine the factors that cause sudden changes in operating conditions based on unstructured text data.

[0009] The dynamic weighting module is used to determine the dynamic weighting factor based on the sudden change factor of the operating condition;

[0010] The fault prediction module is used to determine the probability of direct failure in response to dynamic weighting factors and based on structured time series data.

[0011] The uncertainty quantification module is used to determine uncertainty indicators based on the multiple prediction results of the fault prediction module.

[0012] The risk assessment module is used to determine a comprehensive risk index by combining direct failure probability and uncertainty indicators;

[0013] The decision response module is used to generate tiered early warning instructions based on the comprehensive risk index and preset risk thresholds.

[0014] Furthermore, the factor quantification module is used to determine the operating condition mutation factor based on unstructured text data, including:

[0015] Unstructured text data is processed using pre-trained language models to extract key semantic units;

[0016] For key semantic units, obtain the corresponding baseline influence weight, confidence level, and intensity modifier score;

[0017] The operating condition mutation factor is calculated by combining the baseline impact weight, confidence level, and intensity modifier score.

[0018] Furthermore, the fault prediction module adopts a physical information neural network model, and the loss function of the physical information neural network model includes data-driven loss and physical information loss.

[0019] Furthermore, the dynamic weighting factor is used to adjust the weight of physical information loss in the loss function;

[0020] The dynamic weight module is specifically used for:

[0021] Call the operating condition mutation factor;

[0022] The dynamic weighting factor is calculated using a preset adaptive adjustment function.

[0023] Furthermore, the loss of physical information is calculated by substituting the prediction results of the fault prediction module into a preset standard erosion model that describes the erosion and wear process of the target wellhead device, so as to quantify the degree of deviation of the prediction results from the standard erosion model.

[0024] Furthermore, the uncertainty quantification module is used to determine uncertainty indicators based on multiple prediction results from the fault prediction module, including:

[0025] During the inference phase, the Dropout layer in the fault prediction module is used multiple times and forward propagation is performed to obtain a set of prediction results.

[0026] Based on the sample variance of the prediction result set, normalization is performed to generate an uncertainty index.

[0027] Furthermore, the risk assessment module is used to determine a comprehensive risk index by combining the direct failure probability and uncertainty indicators, including:

[0028] Invoke the direct failure probability, uncertainty index, and preset uncertainty amplification factor;

[0029] The direct failure probability is weighted and amplified based on the product of the uncertainty index and the uncertainty amplification factor.

[0030] The weighted and amplified result is output as a comprehensive risk index.

[0031] Furthermore, the decision response module is specifically used for:

[0032] The comprehensive risk index is compared with the preset first risk threshold and second risk threshold.

[0033] When the comprehensive risk index is lower than the first risk threshold, a first-level warning instruction is issued;

[0034] When the comprehensive risk index is between the first risk threshold and the second risk threshold, a second-level early warning instruction is output.

[0035] When the comprehensive risk index is higher than the second risk threshold, a third-level warning instruction is issued.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] 1. This invention innovatively integrates unstructured text containing expert experience with sensor time-series data. Through a factor quantification module, instructions or geological information in the text that predict future changes are quantified into operational condition mutation factors, which are then used to dynamically adjust the prediction model. This design enables the system to detect potential risks not yet manifested in sensor data, achieving a shift from passive response to proactive anticipation. This significantly enhances the foresight, adaptability, and timeliness of fault prediction, enabling earlier warnings.

[0038] 2. This invention employs a physical information neural network as the core of prediction and incorporates text quantization factors into its loss function weight adjustment. When the text information indicates stable operating conditions, the model focuses on learning historical data patterns; when it indicates drastic changes, it automatically switches to relying more on universal physical laws for constraints and predictions. This dynamic balancing mechanism ensures that the model can still make reasonable predictions under extreme conditions with sparse training data, significantly improving the model's robustness and generalization ability.

[0039] 3. This invention introduces an uncertainty quantification module, which uses the Monte Carlo Dropout method to evaluate the confidence level of the model's own prediction results. It not only outputs a single failure probability but also provides an uncertainty index to characterize the reliability of the current prediction. When the system faces unseen or critical conditions, even if the output failure probability is not high, the abnormally high uncertainty index can effectively alert maintenance personnel, thereby avoiding misjudgments caused by over-reliance on the model's single-point prediction and improving the safety of the decision-making process.

[0040] 4. This invention constructs a comprehensive risk assessment model that integrates the direct failure probability with the uncertainty index of the predicted results to generate a comprehensive risk index. This index can more comprehensively reflect the real risks, effectively distinguishing between different risk scenarios such as low probability with high uncertainty and medium probability with high certainty, overcoming the limitations of a single probability index. Early warning instructions generated based on this index and tiered thresholds achieve automation and standardization of decision-making responses, making operation and maintenance decisions more accurate, reasonable, and efficient. Attached Figure Description

[0041] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0042] Figure 1 This is a system structure diagram of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0044] Example 1:

[0045] Please see Figure 1 A wellhead device fault prediction system based on narrowband Internet of Things, comprising:

[0046] The data acquisition module is used to acquire unstructured text data and structured time-series data of the target wellhead device;

[0047] The factor quantification module is used to determine the factors that cause sudden changes in operating conditions based on unstructured text data.

[0048] The dynamic weighting module is used to determine the dynamic weighting factor based on the sudden change factor of the operating condition;

[0049] The fault prediction module is used to determine the probability of direct failure in response to dynamic weighting factors and based on structured time series data.

[0050] The uncertainty quantification module is used to determine uncertainty indicators based on the multiple prediction results of the fault prediction module.

[0051] The risk assessment module is used to determine a comprehensive risk index by combining direct failure probability and uncertainty indicators;

[0052] The decision response module is used to generate tiered early warning instructions based on the comprehensive risk index and preset risk thresholds;

[0053] This invention provides a wellhead device fault prediction system based on narrowband Internet of Things, which aims to integrate multi-source heterogeneous information to achieve forward-looking and adaptive prediction and early warning of wellhead device performance degradation; the system constructs a technical closed loop from data acquisition, risk quantification, dynamic prediction to decision response;

[0054] In a specific implementation scenario, the system includes:

[0055] The data acquisition module acquires unstructured text data and structured time-series data of the target wellhead equipment in parallel through industrial IoT interfaces and database interfaces. The unstructured text data refers to real-time generated geological analysis reports, drilling operation daily reports, and other text information, used to capture expert opinions and operational instructions that may predict future changes in operating conditions. The structured time-series data refers to pressure data continuously collected by the wellhead sensor array. ,temperature Physical quantities such as flow velocity v are used to characterize the current operating status of the equipment. This module adopts an NB-IoT module to transmit the structured time-series data of the wellhead device (such as pressure, temperature, flow velocity, etc.) to the subsequent processing module in a long distance and with low power consumption through the NB-IoT network.

[0056] The factor quantization module receives text data acquired by the data acquisition module and determines a condition mutation factor based on this unstructured text data. This factor serves as the core driving input for subsequent dynamic adaptive correction of the model.

[0057] The dynamic weighting module determines the operating condition mutation factors in real time based on the factor quantification module. Determine a dynamic weighting factor This is used to weigh the degree to which the predictive model depends on historical data experience and universal physical laws;

[0058] The fault prediction module, which is a neural network model that integrates physical information, responds to the dynamic weight factors output by the dynamic weight module. Based on the structured time-series data acquired by the data acquisition module, a direct failure probability is determined. ;

[0059] The uncertainty quantification module determines an uncertainty index based on the consistency of the multiple prediction results obtained by performing multiple random inferences on the fault prediction module. ;

[0060] The risk assessment module uses a risk fusion model to convert the direct failure probability output by the failure prediction module. Uncertainty index output by the uncertainty quantification module Combined, a comprehensive risk index is determined. ;

[0061] The decision response module is based on the comprehensive risk index determined by the risk assessment module. Compare with preset risk thresholds to generate and output tiered early warning instructions;

[0062] This embodiment constructs an end-to-end intelligent fault prediction system through the collaborative work of the above modules. It not only utilizes easily quantifiable structured sensor data, but also innovatively quantifies the expert experience and early warning information contained in unstructured text, and uses them as key factors for dynamically adjusting the prediction model. This design enables the system to perceive potential risks brought about by changes in operating instructions or geological environment in advance, realizing the transformation from passive response to proactive prediction, significantly improving the accuracy, robustness and timeliness of fault prediction, and ultimately forming a closed-loop, forward-looking intelligent operation and maintenance decision-making system.

[0063] Example 2:

[0064] The factor quantification module is used to determine the factors that cause sudden changes in operating conditions based on unstructured text data, including:

[0065] Unstructured text data is processed using pre-trained language models to extract key semantic units;

[0066] For key semantic units, obtain the corresponding baseline influence weight, confidence level, and intensity modifier score;

[0067] The working condition mutation factor is calculated by combining the baseline impact weight, confidence level, and intensity modifier score.

[0068] This embodiment is a specific implementation of the factor quantification module based on Embodiment 1; its underlying logic lies in designing a method for mathematically quantifying risk descriptions in natural language text.

[0069] The factor quantization module processes unstructured text data through a pre-trained language model to extract key semantic units. This pre-trained language model is a deep learning model that has been pre-trained on massive amounts of text in this field, enabling it to have contextual understanding and semantic feature extraction capabilities. The model receives texts such as geological analysis reports and work instructions, identifies and extracts key semantic units related to equipment risks, such as the detection of high-pressure gas layers or plans to carry out acidizing operations.

[0070] For each extracted key semantic unit, obtain its corresponding baseline influence weight, confidence score, and intensity modifier score; baseline influence weight It refers to the first The inherent risk level of an event corresponding to a semantic unit; it is defined as a dimensionless normalized risk coefficient that is pre-calibrated by domain experts or obtained through statistical analysis of historical data, with a value range between [0,1], used to characterize the degree of objective impact of such events on the failure rate;

[0071] Confidence This refers to the ability of a pre-trained language model to recognize the first... The degree of certainty for each semantic unit is the probability value directly output by the model when performing semantic recognition tasks, and is a dimensionless value in the interval [0,1]; intensity modifier score It refers to the quantitative scoring of words that modify the severity of semantic units. It is determined based on a modifier-score mapping table pre-built by domain experts based on an experience knowledge base, and is a dimensionless value.

[0072] To integrate the above multi-dimensional information, this embodiment uses the following heuristic risk assessment model to calculate the operating condition mutation factor. , It is the total number of key semantic units identified in a single text analysis; the formula is as follows:

[0073]

[0074] The total risk in a single analysis of a text is the sum of the risks contributed by all identified key risk events; the risk of each event is determined by its inherent impact. The certainty of the model's recognition and the severity described in the text These three factors jointly determine the final operating condition mutation factor. It is a dimensionless scalar;

[0075] It should be noted that the linear accumulation model used in this embodiment is... This is a simple and effective implementation method; in other implementation methods, nonlinear functions or attention mechanisms can also be used to fuse multiple risk events in order to capture the complex coupling effects that may exist between them.

[0076] Compared to traditional methods that rely solely on structured data, this embodiment enables the system to capture potential or impending risks that are not yet reflected in sensor data by deeply mining information in unstructured text. This method enhances the system's foresight and adaptability to sudden operating conditions, achieving earlier warnings of risks.

[0077] Example 3:

[0078] The fault prediction module adopts a physical information neural network model. The loss function of the physical information neural network model includes data-driven loss and physical information loss.

[0079] The dynamic weighting factor is used to adjust the weight of physical information loss in the loss function;

[0080] The dynamic weight module is specifically used for:

[0081] Call the operating condition mutation factor;

[0082] The dynamic weighting factor is calculated using a preset adaptive adjustment function;

[0083] Physical information loss is calculated by substituting the prediction results of the fault prediction module into a preset standard erosion model that describes the erosion and wear process of the target wellhead device, so as to quantify the degree of deviation of the prediction results from the standard erosion model.

[0084] This embodiment is based on Embodiment 1 and is a collaborative implementation of the fault prediction module, the dynamic weight module and their interaction. Its core lies in constructing a physical information neural network that is controlled in real time by external text information, thereby achieving a dynamic balance between the flexibility of data-driven approaches and the universality of physical laws.

[0085] The fault prediction module employs a physical information neural network model. This model incorporates partial differential equations describing the physical process as regularization terms into the loss function, thereby constraining the model's solution space. In this embodiment, the model uses a long short-term memory network as its infrastructure to learn the wellhead pressure. ,temperature Dynamic patterns in structured time-series data directly predict instantaneous material loss rates. ;

[0086] To obtain the final direct failure probability This module further analyzes the predicted instantaneous material loss rate. In the future, within a predetermined time window The total predicted material loss is obtained by integrating and accumulating the components. The total material loss is obtained. Material wear limit thresholds are preset based on equipment design specifications or industry safety standards. By using an S-shaped reliability function, such as a logic function, the reliability can be... Mapped to the probability of direct failure within a specific future time window For example ,in The constant is related to the slope of the function; the total loss function of this model. It consists of two parts:

[0087]

[0088] The optimization objective of the model is not only to minimize the data-driven loss. At the same time, it is also necessary to minimize the loss of physical information. ; Defined as the instantaneous material loss rate predicted by the model. The reference instantaneous loss rate is indirectly calculated or calibrated using high-frequency sensor data. The mean square error between them is expressed in units of mass / time (mass / time). This represents the model's pursuit of historical fidelity;

[0089] The core task of the dynamic weighting module is to calculate the dynamic weighting factors. This factor is used to adjust the weight of physical information loss in the total loss function; this module calls the operating condition mutation factor calculated by the factor quantization module. And calculate the dynamic weighting factor through a preset adaptive adjustment function; the function is:

[0090]

[0091] It is the baseline physical loss weight, a dimensionless hyperparameter whose value is determined during the model development phase by performing grid search optimization on the data validation set under stable operating conditions. It is a dimensionless sensitivity coefficient, also a hyperparameter, used to control... Follow The degree of change; introducing the hyperbolic tangent function. This is to smooth out the adjustment process and... The effect is applied in a bounded manner. superior;

[0092] Physical information loss The calculation aims to quantify the degree of deviation of the prediction results from physical laws; the loss of physical information is calculated by substituting the prediction results of the fault prediction module into a preset standard erosion model that describes the erosion and wear process of the target wellhead device; the specific formula is as follows:

[0093]

[0094] in, It is the predicted value directly output by the fault prediction module; It is a standard erosion model describing the rate of material loss and is the authoritative standard in the field of materials science. It is based on real-time fluid pressure obtained by a data acquisition module. Flow rate and the inherent material properties obtained by consulting material handbooks or experimental measurements. The function, for example, the model can take a specific form such as ,in and It is related to material properties Relevant empirical coefficients; The calculation results are also in units of mass / time, thus ensuring... The internal dimensions are consistent, making its final dimension mass-time (mass / time). ,and The dimensions are completely unified;

[0095] This collaborative design introduces physical information loss. This ensures that the prediction model's results do not deviate from basic physical laws even in extreme operating conditions where training data is sparse, thus improving the model's robustness and generalization ability; by introducing a factor derived from sudden changes in operating conditions... Driven dynamic weighting factor This makes the model adaptive; when the text information indicates that the working conditions are stable, the model trusts historical data patterns more; when it indicates that drastic changes are about to occur, the model automatically switches to making predictions that rely more on universal physical laws.

[0096] Example 4:

[0097] The uncertainty quantification module is used to determine uncertainty indicators based on multiple prediction results from the fault prediction module, including:

[0098] During the inference phase, the Dropout layer in the fault prediction module is used multiple times and forward propagation is performed to obtain a set of prediction results.

[0099] Based on the sample variance of the prediction result set, normalization is performed to generate an uncertainty index.

[0100] This embodiment is a specific implementation of the uncertainty quantification module based on embodiment 1. Its purpose is to provide the model with confidence in its own prediction results for the final decision of the system.

[0101] The uncertainty quantification module employs the Monte Carlo Dropout method; during the inference phase, the Dropout layer in the fault prediction module is enabled multiple times and forward propagation is performed to obtain a set of prediction results; in conventional neural network inference, the Dropout layer is disabled; however, in this embodiment, even during the inference phase, it is forcibly and repeatedly enabled, for example... The Dropout layer in the network is enabled for the second time; for the input data in the same step, through... The forward propagation is performed on each different subnetwork to obtain a set containing A set of prediction results for different predicted values ,in It is the first The direct failure probability obtained from the first forward propagation;

[0102] Based on the sample variance of the prediction result set, normalization is performed to generate an uncertainty index. To transform the original variance into a relative index with business meaning and easy comparison, this embodiment uses the following formula for calculation:

[0103]

[0104] in, yes The mean of the prediction results; It is the dimensionless uncertainty index of the final output; in the denominator It is the preset reference variance, which is the statistical average of the model output variance under a large number of historical stable operating conditions, used to scale the original variance to a relative scale with clear business meaning;

[0105] This embodiment introduces uncertainty quantification to add self-evaluation capabilities to the fault prediction system; when the system faces an unseen or critical operating condition, even if it might output a seemingly normal low failure probability, the uncertainty index... It may rise abnormally; this can effectively remind operations and maintenance personnel that the current prediction results are unreliable, thereby avoiding misjudgments caused by over-reliance on single-point predictions of the model and improving the security of the entire operations and maintenance decision-making process.

[0106] Example 5:

[0107] The risk assessment module is used to determine a comprehensive risk index by combining direct failure probability and uncertainty indicators, including:

[0108] Invoke the direct failure probability, uncertainty index, and preset uncertainty amplification factor;

[0109] The direct failure probability is weighted and amplified based on the product of the uncertainty index and the uncertainty amplification factor.

[0110] The weighted and amplified result is output as a comprehensive risk index.

[0111] This embodiment is a specific implementation of the risk assessment module based on embodiment 1. Its purpose is to build a comprehensive risk assessment model that is more comprehensive than a single failure probability and closer to the actual operation and maintenance decision-making logic.

[0112] The risk assessment module combines direct failure probability and uncertainty indicators to determine a comprehensive risk index; it calls upon three key inputs: the direct failure probability output by the failure prediction module. Uncertainty index calculated by the uncertainty quantification module And a preset uncertainty amplification factor. Uncertainty amplification factor It is a dimensionless, adjustable parameter that is set by the operations and maintenance management department based on its risk tolerance.

[0113] The direct failure probability is weighted and amplified based on the product of the uncertainty index and the uncertainty amplification factor; this is achieved through a risk fusion model, the calculation formula of which is as follows:

[0114]

[0115] Overall Risk Index Direct failure probability Based on this, and through an amplification factor driven by uncertainty. Adjust it; when the prediction is very certain. Approaching 0, the amplification factor is close to 1. Approximately equal to When the uncertainty of the forecast increases significantly Increasing the amplification factor will make it greater than 1, thus adjusting the original failure probability upwards;

[0116] The weighted and amplified result is output as the comprehensive risk index; the calculated comprehensive risk index It is a dimensionless value that incorporates the probability of an event occurring. and the certainty of the perception of this possibility The linear scaling model here It is an intuitive and easy-to-explain risk fusion strategy;

[0117] It should be noted that, although the direct failure probability The range of values ​​is However, the overall risk index Theoretically, there is no upper limit; when A value greater than 1 indicates that the model has extremely low certainty regarding the prediction result, even if the base probability is low. Even if the risk level is not high, its overall risk should still be considered extremely high and should immediately attract the highest level of attention from operations and maintenance personnel. This design ensures that highly uncertain prediction signals are not ignored. In other implementations, nonlinear fusion models such as exponential or piecewise functions can also be designed according to specific risk preferences.

[0118] This embodiment achieves a deeper understanding of risk assessment; a low-probability but highly uncertain prediction may pose a greater potential risk than a moderate-probability but highly certain prediction; this embodiment calculates a comprehensive risk index. This allows for accurate quantification and differentiation of these differences, making subsequent early warning and operation and maintenance decisions more precise and reasonable.

[0119] Example 6:

[0120] The decision response module is specifically used for:

[0121] The comprehensive risk index is compared with the preset first risk threshold and second risk threshold.

[0122] When the comprehensive risk index is lower than the first risk threshold, a first-level warning instruction is issued;

[0123] When the comprehensive risk index is between the first risk threshold and the second risk threshold, a second-level early warning instruction is output.

[0124] When the comprehensive risk index is higher than the second risk threshold, a third-level warning instruction is issued.

[0125] This embodiment is a specific implementation of the decision response module based on Embodiment 1; its purpose is to convert the continuous and quantitative comprehensive risk index calculated by the upstream module into a more comprehensive and quantitative one. This is transformed into discrete, explicit, and directly operational hierarchical early warning instructions;

[0126] The decision response module will output the comprehensive risk index from the risk assessment module. Compared with the preset first risk threshold Second risk threshold The two thresholds were determined through statistical methods such as receiver operation characteristic curve analysis on a large amount of historical data. The technical principle behind their setting is to achieve a balance between false alarm rate and false negative rate that meets specific operation and maintenance requirements.

[0127] Based on the comparison results, the system automatically triggers different levels of response strategies:

[0128] When the comprehensive risk index Below the first risk threshold When this occurs, a Level 1 warning instruction is issued; in practice, this instruction may correspond to maintaining routine monitoring.

[0129] When the comprehensive risk index Between the first risk threshold With the second risk threshold During this period, a second-level warning instruction is issued; this instruction may correspond to increasing the data collection frequency or suggesting that attention be paid to this issue.

[0130] When the comprehensive risk index Above the second risk threshold When this occurs, a Level 3 warning instruction will be issued; this instruction is the highest level of alarm, which may correspond to triggering a high-risk alarm and recommends a special inspection.

[0131] This embodiment achieves automation, standardization, and differentiation of decision-making response by establishing clear, data-driven hierarchical thresholds. It can match the corresponding level of operation and maintenance resources according to the actual severity of the risk, which not only avoids the waste of resources caused by excessive alarms, but also ensures that the highest priority and most timely response can be given to truly high-risk signals.

[0132] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention; any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A wellhead device fault prediction system based on narrowband Internet of Things, characterized in that, include: The data acquisition module is used to acquire unstructured text data and structured time-series data of the target wellhead device; The factor quantification module is used to determine the factors causing sudden changes in operating conditions based on unstructured text data. Specifically, this includes: processing unstructured text data through a pre-trained language model to extract key semantic units; for each key semantic unit, obtaining the corresponding baseline influence weights, confidence levels, and intensity modifier scores; and combining the baseline influence weights, confidence levels, and intensity modifier scores to calculate the working condition mutation factor. ; The dynamic weighting module is used to adjust the weights based on the operating condition mutation factor. Determine the dynamic weighting factor Adjusting the weight of physical information loss in the loss function; the dynamic weight module is specifically used to: call the operating condition mutation factor ; Calculate the dynamic weighting factor using a preset adaptive adjustment function. The adaptive adjustment function is specifically as follows: ;in, The preset baseline physical loss weights, The preset sensitivity coefficient, It is the hyperbolic tangent function; The fault prediction module is used to determine the probability of direct failure in response to dynamic weighting factors and based on structured time series data. The uncertainty quantification module is used to determine uncertainty indicators based on multiple prediction results from the fault prediction module. This includes: enabling the Dropout layer in the fault prediction module multiple times during the inference phase and performing forward propagation to obtain a set of prediction results; and performing normalization processing based on the sample variance of the prediction result set to generate uncertainty indicators. The risk assessment module is used to determine a comprehensive risk index by combining the direct failure probability and uncertainty indicators. This includes: calling the direct failure probability, uncertainty indicators, and a preset uncertainty amplification coefficient; weighting and amplifying the direct failure probability based on the product of the uncertainty indicators and the uncertainty amplification coefficient; and outputting the weighted and amplified result as the comprehensive risk index. The decision response module is used to generate tiered early warning instructions based on the comprehensive risk index and preset risk thresholds; The fault prediction module adopts a physical information neural network model, and the loss function of the physical information neural network model includes data-driven loss and physical information loss. The loss of physical information is calculated by substituting the prediction results of the fault prediction module into a preset standard erosion model that describes the erosion and wear process of the target wellhead device, so as to quantify the degree of deviation of the prediction results from the standard erosion model.

2. The wellhead device fault prediction system based on narrowband Internet of Things according to claim 1, characterized in that, The decision response module is specifically used for: The comprehensive risk index is compared with the preset first risk threshold and second risk threshold. When the comprehensive risk index is lower than the first risk threshold, a first-level warning instruction is issued; When the comprehensive risk index is between the first risk threshold and the second risk threshold, a second-level early warning instruction is output. When the comprehensive risk index is higher than the second risk threshold, a third-level warning instruction is issued.

Images