A big data processing oil drilling equipment risk assessment method and system

Abstract

The application discloses a kind of big data processing's oil drilling equipment risk assessment method and system, it is related to oil drilling technical field, its technical scheme key points include the following steps: obtaining the full life cycle data of target drilling operation equipment and operation environment dynamic data;Comprehensive correlation intensity judgment result and analysis are carried out to expansion data set to obtain second risk grade result set, third risk grade result set, second spread speed result set and third spread speed result set;First risk condition result set, first loss degree result set, second risk grade result set, second spread speed result set, third risk grade result set and third spread speed result set are combined, and the running risk of oil drilling equipment is evaluated, and risk assessment early warning instruction is output, effect is through quantitative comparison threshold after triggering mechanism to realize early warning.

Description

Technical Field

[0001] This invention relates to the field of oil drilling technology, and more specifically, to a method and system for risk assessment of oil drilling equipment using big data processing. Background Technology

[0002] In the oil drilling industry, the safe and stable operation of drilling equipment directly affects operational efficiency, production costs, and personnel safety. Traditional risk assessment methods for oil drilling equipment have many limitations and are insufficient to meet the safety requirements under complex operating conditions. Traditional assessment methods mostly rely on single-dimensional data, such as collecting only real-time operating parameters or manual inspection records, lacking the integration of data across the entire equipment lifecycle and dynamic data from the external environment. This singular data dimension prevents the assessment from comprehensively reflecting the full picture of equipment risks. For example, judging the drill string status solely based on rig torque data while ignoring key information such as geological changes and historical maintenance records can easily lead to misjudgments or omissions. Traditional methods lack sufficient data preprocessing capabilities and standardization and verification processes. Due to the diverse data acquisition equipment and complex environment at drilling sites, data often suffers from inconsistent formats, inconsistencies in units, and a high number of outliers. Directly using this unprocessed data for risk analysis will reduce the reliability of the assessment results. The lack of exploration into the correlation between risk triggering factors and equipment operating status makes it impossible to predict the spread rate of drill string stuck risks in advance, resulting in delayed early warnings and difficulty in taking timely countermeasures. Summary of the Invention

[0003] To address the shortcomings of existing technologies, the present invention aims to provide a method and system for risk assessment of oil drilling equipment using big data processing.

[0004] To achieve the above objectives, the present invention provides the following technical solution: A risk assessment method for oil drilling equipment using big data processing, comprising the following steps: Acquire full lifecycle data of the target drilling equipment and dynamic data of the operating environment; The full lifecycle data and dynamic operational environment data are classified and integrated into operational status data, maintenance record data and risk trigger factor data to obtain a baseline data set and an extended data set. The running status data and maintenance record data of the baseline dataset are verified to obtain the status data verification results and maintenance data verification results; Based on the status data verification results, the risk and failure loss degree of the benchmark data set are judged to obtain the first risk status result set and the first loss degree result set; A comprehensive correlation strength assessment result is obtained by judging the correlation strength between the risk triggering factor data and the operational status data of the extended dataset. By analyzing the comprehensive correlation strength judgment results and the extended data set, we obtained the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set; By combining the results sets of the first risk status, the first loss degree, the second risk level, the second spread rate, the third risk level, and the third spread rate, an operational risk assessment of oil drilling equipment is conducted, and a risk assessment early warning command is output.

[0005] Preferably, the full lifecycle data and dynamic operational environment data are categorized and integrated into operational status data, maintenance record data, and risk trigger factor data to obtain a baseline data set and an extended data set. This process specifically includes the following steps: The full lifecycle data and dynamic operational environment data are divided into source subsets according to their data sources; The source subsets are classified into operational status data, maintenance record data, and risk trigger factor data to obtain a type identification result set. The following feature sets were extracted from the type identification result set: the running status subset, the maintenance record subset, and the risk triggering factor data feature set. The baseline dataset and the extended dataset are obtained by processing the runtime status subset, the maintenance record subset, and the risk trigger factor data feature set.

[0006] Preferably, the baseline data set and the extended data set are obtained by processing the runtime status subset, the maintenance record subset, and the risk trigger factor data feature set, specifically including the following steps: Based on the correlation characteristics of the operational status subset, maintenance record subset, and risk trigger factor data feature set, standardized operational status dataset, standardized maintenance record dataset, and standardized risk trigger factor dataset are obtained. A baseline dataset is obtained by integrating the standardized operating status dataset and the standardized maintenance record dataset through equipment operation and maintenance correlation. An expanded dataset is obtained by integrating the standardized risk trigger factor dataset and the standardized operational status dataset through risk factor correlation.

[0007] Preferably, the operational status data and maintenance record data of the baseline dataset are verified to obtain the status data verification results and maintenance data verification results, specifically including the following steps: The first state feature information is obtained by acquiring the collection cycle, data integrity rate, and abnormal data ratio of the standardized operating status dataset; The rationality of changes in key operating condition parameters in the standardized operating status dataset is verified to obtain second-state feature information; The first state feature information and the second state feature information are combined into a state data feature set; The integrity of the running status data is judged based on the status data feature set to obtain the status data verification result; The maintenance data feature set is obtained by verifying the maintenance items, maintenance cycles, and maintenance effect verification data in the standardized maintenance record dataset. The maintenance data verification result is obtained by judging the integrity of the maintenance record data based on the maintenance data feature set.

[0008] Preferably, the risk and failure loss severity are assessed based on the status data verification results to obtain a first risk status result set and a first loss severity result set, specifically including the following steps: A reliable set of data associations for detecting the numerical correlation between a baseline dataset and an extended dataset; Based on the data association reliability set and the status data verification results, the correspondence between the operating status data and equipment risks in the baseline data set and the extended data set is determined to obtain the risk correspondence judgment result set; The first valid data segment is obtained by effectively filtering the operation status data and maintenance record data according to the association rules of the data association reliability set; The risk corresponding to each data in the first valid data segment is judged based on the data association reliability set and the risk correspondence judgment result set to obtain the first risk status result set; Based on the first risk status result set, the status data feature set, and the maintenance data feature set, the degree of loss of equipment failure is judged to obtain the first loss degree result set.

[0009] Preferably, the comprehensive correlation strength judgment result is obtained by judging the correlation strength between the risk trigger factor data and the operational status data of the extended dataset, specifically including the following steps: The risk triggering feature information set is obtained by extracting the type, scope of influence and triggering threshold of each risk triggering factor in the standardized risk triggering factor dataset; The risk trigger level is obtained by judging the degree of danger of risk triggering factors based on the risk triggering feature information set; The extended data feature set is obtained by detecting the synchronicity of parameter changes and the efficiency of associated response in each associated dataset within the extended dataset. The correlation strength between risk trigger factor data and operational status data in the extended data set is judged based on the correlation response pattern of the extended data feature set. If the correlation strength is greater than or equal to the preset high-strength threshold, the first correlation strength judgment result is output. If the correlation strength is less than the preset high-strength threshold, then output the second correlation strength judgment result; The first association strength judgment result and the second association strength judgment result are combined to form the comprehensive association strength judgment result.

[0010] Preferably, the analysis of the comprehensive correlation strength judgment results and the extended data set yields the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set, specifically including the following steps: Based on the correlation response patterns in the extended data feature set, the risk trigger factor data and operational status data are correlated and segmented to obtain the second effective data segment; Based on the results of the first correlation strength judgment and the risk trigger level, the risk level corresponding to each data in the second effective data segment is evaluated to obtain the second risk level result set; The second spread rate result set is obtained by judging the spread rate of equipment hazards based on the second risk level result set and the risk triggering feature information set; Based on the results of the second correlation strength judgment, the risk level assessment and the speed of hazard spread are judged on the extended data set to obtain the third risk level result set and the third spread speed result set.

[0011] Preferably, based on the second correlation strength judgment result, the risk level assessment and the rate of hazard spread are judged on the extended data set to obtain the third risk level result set and the third spread rate result set, specifically including the following steps: Based on the second correlation strength judgment result and the correlation response efficiency in the extended data feature set, the delay time set of the impact of risk triggering factor data on the operation status data in the extended data set is statistically analyzed. Based on the set of impact delay durations, an information set of abnormal superposition effects of runtime status data in the extended data set is obtained; Based on the correlation response patterns in the information set of abnormal superposition effects and the feature set of extended data, the risk triggering factor data and the operational status data in the extended data set are correlated and extracted to obtain the third effective data segment. Based on the second correlation strength judgment result, the third effective data segment, the risk trigger level result, and the risk corresponding judgment result set, the risk level corresponding to each data in the third effective data segment is judged to obtain the third risk level result set; Based on the third risk level result set, the risk triggering feature information set, and the risk triggering level result, the spread rate of equipment hazards is judged to obtain the third spread rate result set.

[0012] Preferably, by combining the first risk status result set, the first loss degree result set, the second risk level result set, the second spread rate result set, the third risk level result set, and the third spread rate result set, an operational risk assessment of the oil drilling equipment is conducted, and a risk assessment early warning command is output. This specifically includes the following steps: The results set of the first risk status, the results set of the second risk level, and the results set of the third risk level are combined into a comprehensive risk level assessment set. The results sets of the first degree of loss, the second rate of spread, and the third rate of spread are combined into a comprehensive risk impact assessment set. Based on the comprehensive risk level assessment set and the comprehensive risk impact assessment set, the equipment operation risks corresponding to the source subset datasets are assessed to obtain the source risk assessment result set. The source risk assessment result set is then integrated to obtain the equipment risk assessment result. The difference between the risk assessment results of computing equipment and the preset standard safety risk results is the risk deviation value. When the risk deviation value is greater than or equal to the preset risk warning threshold, a risk assessment warning instruction will be output.

[0013] A big data processing-based risk assessment system for oil drilling equipment includes: Acquisition module: Acquires full lifecycle data of the target drilling equipment and dynamic data of the operating environment; Classification module: Classifies and integrates full lifecycle data and dynamic work environment data into operational status data, maintenance record data, and risk trigger factor data to obtain a baseline data set and an extended data set; Processing module: Performs verification processing on the running status data and maintenance record data of the baseline dataset to obtain the status data verification results and maintenance data verification results; First judgment module: Based on the status data verification results, the module judges the risk and failure loss level of the benchmark data set to obtain the first risk status result set and the first loss level result set. The second judgment module: judges the correlation strength between the risk trigger factor data and the operation status data of the extended data set to obtain a comprehensive correlation strength judgment result; Analysis module: Analyzes the comprehensive correlation strength judgment results and extended data sets to obtain the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set; Output module: Combining the first risk status result set, the first loss degree result set, the second risk level result set, the second spread rate result set, the third risk level result set, and the third spread rate result set, the module performs an operational risk assessment of the oil drilling equipment and outputs a risk assessment early warning command.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention unifies equipment lifecycle data and dynamic operating environment data into operational status, maintenance records, and risk triggering factors, constructing a baseline data set and an extended data set. This makes the data source for risk assessment more complete. A layered verification mechanism significantly improves data reliability and effectively reduces errors in risk judgment. A hierarchical, multi-dimensional risk assessment system is built, significantly improving the accuracy of risk assessment. Based on the baseline data set, the basic risks and failure loss levels of the equipment are determined. The extended data set is used to analyze the correlation strength between risk triggering factors and operational status data, assessing risk levels and the speed of hazard spread across different dimensions. For risk factors with high correlation, the impact of their rapid spread is assessed; for risk factors with medium to low correlation, their delayed effects and potential hazards after abnormal superposition are analyzed. This allows for precise characterization of different types of risks, enabling maintenance personnel to take differentiated measures for different risks. A triggering mechanism based on quantified comparison thresholds provides early warnings, offering clear action guidelines for on-site maintenance. Attached Figure Description

[0015] Figure 1 This invention provides a schematic diagram illustrating the steps of a big data processing-based risk assessment method for oil drilling equipment. Figure 2 This is a schematic diagram of a big data processing-based risk assessment system for oil drilling equipment, provided as an embodiment of the present invention. Detailed Implementation

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0018] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0019] Reference Figures 1-2 As shown.

[0020] The embodiments further illustrate the risk assessment method and system for oil drilling equipment using big data processing proposed in this invention.

[0021] A risk assessment method for oil drilling equipment using big data processing, comprising the following steps: Acquire full lifecycle data of the target drilling equipment and dynamic data of the operating environment; The full lifecycle data and dynamic operational environment data are classified and integrated into operational status data, maintenance record data and risk trigger factor data to obtain a baseline data set and an extended data set. The running status data and maintenance record data of the baseline dataset are verified to obtain the status data verification results and maintenance data verification results; Based on the status data verification results, the risk and failure loss degree of the benchmark data set are judged to obtain the first risk status result set and the first loss degree result set; A comprehensive correlation strength assessment result is obtained by judging the correlation strength between the risk triggering factor data and the operational status data of the extended dataset. By analyzing the comprehensive correlation strength judgment results and the extended data set, we obtained the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set; By combining the results sets of the first risk status, the first loss degree, the second risk level, the second spread rate, the third risk level, and the third spread rate, an operational risk assessment of oil drilling equipment is conducted, and a risk assessment early warning command is output.

[0022] The entire lifecycle data and dynamic operational environment data are categorized and integrated into operational status data, maintenance record data, and risk trigger factor data to obtain a baseline dataset and an extended dataset. This process includes the following steps: The full lifecycle data and dynamic operational environment data are divided into source subsets according to their data sources; The source subsets are classified into operational status data, maintenance record data, and risk trigger factor data to obtain a type identification result set. The following feature sets were extracted from the type identification result set: the running status subset, the maintenance record subset, and the risk triggering factor data feature set. The baseline dataset and the extended dataset are obtained by processing the runtime status subset, the maintenance record subset, and the risk trigger factor data feature set.

[0023] First, the full lifecycle data and dynamic data of the operating environment are divided into different source subsets according to their source. For example, parameter files and installation and commissioning records from when the equipment leaves the factory are classified as the equipment leaving the factory source subset; real-time drilling parameters from downhole sensors are classified as the operation monitoring source subset; maintenance records filled in by on-site maintenance personnel are classified as the maintenance source subset; downhole formation data from geological exploration departments are classified as the geological environment source subset; and temperature and humidity data from on-site weather stations are classified as the on-site environment source subset.

[0024] Specific data items within each source subset are identified and categorized into operational status data, maintenance record data, and risk trigger factor data. For example, in the operational monitoring source subset, the real-time rotational speed, torque, load, and oil temperature of the drilling rig are identified as operational status data; in the maintenance source subset, maintenance items, maintenance time, replaced parts, and descriptions of maintenance effects are identified as maintenance record data; and in the geological environment source subset, geological structure complexity, formation hardness, and drilling fluid density deviation are identified as risk trigger factor data.

[0025] The system extracts three subsets of data from the type identification results: operational status, maintenance records, and risk triggering factors. These subsets are then processed to generate the final baseline and extended datasets. The processing involves standardizing the three subsets, such as unifying operational status data from different acquisition cycles to a 10-second sampling frequency, converting maintenance record data of different formats into a unified table structure, and normalizing risk triggering factor data of different dimensions. The standardized operational status subset is then integrated with the maintenance record subset through equipment operation and maintenance correlation analysis. For example, drilling rig torque data within a specific time period is matched with maintenance records from the same period to establish a correspondence between equipment operational status and operational behavior, thus obtaining the baseline dataset. The standardized risk triggering factor dataset is then integrated with the operational status subset through risk factor correlation analysis. For example, geological structural complexity data is aligned with corresponding drilling rig torque fluctuation data over time to establish a correlation between external risk factors and equipment operational status, thus obtaining the extended dataset.

[0026] The baseline dataset and the extended dataset are obtained by processing the runtime status subset, the maintenance record subset, and the risk trigger factor data feature set. This process includes the following steps: Based on the correlation characteristics of the operational status subset, maintenance record subset, and risk trigger factor data feature set, standardized operational status dataset, standardized maintenance record dataset, and standardized risk trigger factor dataset are obtained. A baseline dataset is obtained by integrating the standardized operating status dataset and the standardized maintenance record dataset through equipment operation and maintenance correlation. An expanded dataset is obtained by integrating the standardized risk trigger factor dataset and the standardized operational status dataset through risk factor correlation.

[0027] Standardization is performed based on the correlation characteristics of the feature sets of the operational status subset, maintenance record subset, and risk trigger factor data. The inherent correlation rules of each of the three types of data are identified, such as the linkage between drilling rig torque and rotational speed in the operational status data; the correspondence between maintenance cycles and failure frequencies of different components in the maintenance record data; and the influence of geological structural complexity and drilling fluid density in the risk trigger factor data. These data are then standardized by unifying the format, dimensions, and time granularity.

[0028] A baseline dataset is generated by integrating and correlating equipment operation and maintenance data. A correspondence is established between equipment operating status and maintenance actions. For example, the drilling rig oil temperature and pressure parameters for a specific time period in the standardized operating status dataset are matched with the hydraulic system maintenance records for the same period in the standardized maintenance record dataset. If the drilling rig's oil temperature is found to be consistently high within a week, it will be correlated with the hydraulic oil replacement records for that time period, thereby determining the impact of maintenance actions on the operating status. The resulting baseline dataset comprehensively presents the entire data correlation from equipment operation to maintenance.

[0029] An expanded dataset is generated by integrating and correlating risk triggers. This involves establishing a correlation between external risk triggers and equipment operating status. For example, the geological structural complexity data in the standardized risk trigger dataset is aligned with the drilling rig torque data in the standardized operating status dataset along the time dimension. The resulting expanded dataset will then demonstrate the dynamic correlation between risk triggers and equipment operating status.

[0030] The operational status data and maintenance record data of the baseline dataset are verified to obtain the status data verification results and maintenance data verification results. This process includes the following steps: The first state feature information is obtained by acquiring the collection cycle, data integrity rate, and abnormal data ratio of the standardized operating status dataset; The rationality of changes in key operating condition parameters in the standardized operating status dataset is verified to obtain second-state feature information; The first state feature information and the second state feature information are combined into a state data feature set; The integrity of the running status data is judged based on the status data feature set to obtain the status data verification result; The maintenance data feature set is obtained by verifying the maintenance items, maintenance cycles, and maintenance effect verification data in the standardized maintenance record dataset. The maintenance data verification result is obtained by judging the integrity of the maintenance record data based on the maintenance data feature set.

[0031] To extract first-state feature information from a standardized operational status dataset, the data collection period is first determined, for example, setting the collection interval for drilling rig operating parameters to 10 seconds. Data integrity rate = actual number of valid data entries ÷ theoretically required number of data entries × 100%. For example, if 360 data entries should theoretically be collected in one hour of continuous operation, and 356 valid data entries are actually collected, then the data integrity rate is 356 ÷ 360 × 100% ≈ 98.9%. Abnormal data percentage = number of abnormal data entries ÷ total number of collected data entries × 100%. If 8 abnormal data entries occur during this period, the abnormal data percentage is 8 ÷ 360 × 100% ≈ 2.2%. These indicators together constitute the first-state feature information, reflecting the stability and effectiveness of data collection.

[0032] The rationality of changes in key operating parameters in the standardized operating status dataset is verified to obtain second-state feature information. Key operating parameters include drilling rig torque, speed, load, and oil temperature. The changes in these parameters are judged based on the physical laws of equipment operation to determine whether they conform to normal logic. When the drilling rig speed steadily increases from 100 rpm to 130 rpm, the torque should normally increase accordingly. If the torque decreases significantly at this time, the parameter change is deemed unreasonable. This type of verification identifies abnormal fluctuations in the data, further validating the effectiveness of the operating status data.

[0033] The first and second state feature information are combined to form a state data feature set. The integrity of the operating state data is judged based on the state data feature set, and the final state data verification result is obtained. When the data integrity rate is higher than 95%, the proportion of abnormal data is lower than 2%, and the changes in key operating parameters meet the reasonableness standards, the operating state data is judged to be complete and valid; if any indicator does not meet the requirements, the data is marked as defective.

[0034] In the maintenance record data verification stage, each maintenance item, maintenance cycle, and maintenance effect verification data in the standardized maintenance record dataset is verified item by item to form a maintenance data feature set. Maintenance item verification checks whether it covers key components of the drilling rig, such as drilling tools, hydraulic systems, and power units, ensuring no core maintenance content is omitted. Maintenance cycle verification compares the actual maintenance time with the cycle specified in the equipment manual. The maintenance cycle deviation rate is calculated as |Actual Maintenance Interval - Specified Maintenance Interval| ÷ Specified Maintenance Interval × 100%. For example, if the specified replacement cycle for hydraulic oil is 3 months, and the actual replacement interval is 3.5 months, then the maintenance cycle deviation rate is |3.5 - 3| ÷ 3 × 100% ≈ 16.7%. When the deviation rate exceeds a preset threshold, the cycle is considered abnormal. Maintenance effect verification data verification checks for post-maintenance performance test records, such as verification data for oil temperature and pressure parameters after hydraulic oil replacement, ensuring the effectiveness and traceability of maintenance actions. Based on the maintenance data feature set, the completeness of the maintenance record data is judged, thus obtaining the maintenance data verification result. For example, if the maintenance project coverage is complete, the maintenance cycle deviation rate is less than 20%, and the maintenance effect verification data is complete, then the maintenance record data is determined to be complete and valid.

[0035] Based on the status data verification results, the risk and failure loss level of the baseline dataset are judged to obtain the first risk status result set and the first loss level result set. The specific steps include: A reliable set of data associations for detecting the numerical correlation between a baseline dataset and an extended dataset; Based on the data association reliability set and the status data verification results, the correspondence between the operating status data and equipment risks in the baseline data set and the extended data set is determined to obtain the risk correspondence judgment result set; The first valid data segment is obtained by effectively filtering the operation status data and maintenance record data according to the association rules of the data association reliability set; The risk corresponding to each data in the first valid data segment is judged based on the data association reliability set and the risk correspondence judgment result set to obtain the first risk status result set; Based on the first risk status result set, the status data feature set, and the maintenance data feature set, the degree of loss of equipment failure is judged to obtain the first loss degree result set.

[0036] The numerical correlation between the baseline and extended datasets is examined to generate a data correlation reliability set. To verify whether the inherent logic between the two types of data is consistent, for example, the Pearson correlation coefficient between drilling torque data in the baseline dataset and geological structural complexity data in the extended dataset is calculated. If the calculated correlation coefficient is 0.92, it indicates that the two are highly positively correlated, and this correlation is marked as high reliability. The correlation strength of all data pairs together constitutes the data correlation reliability set.

[0037] By combining the data association reliability set and the status data verification results, the correspondence between operating status data and equipment risks is determined to obtain a risk correspondence judgment result set. When the status data verification results show that the drilling rig torque data is complete and valid, and the data association reliability set shows that the torque is highly correlated with the complexity of the geological structure, a correspondence is established between the continuously increasing torque and the risk of drill string stuck. If the maintenance record data shows that no flaw detection maintenance has been performed on the drill string recently, the credibility of this risk correspondence is further strengthened, and finally a risk correspondence judgment result set containing various risk triggering logics is formed.

[0038] Based on the association rules of the data association reliability set, operational status data and maintenance record data are effectively filtered to obtain the first valid data segment. The association rules set filtering thresholds, such as retaining only data groups with an association strength higher than 0.8 and time periods with a maintenance record data integrity rate higher than 95%. Taking a drilling platform as an example, the data for the time period with a correlation strength of 0.92 between torque and geological structure complexity is filtered out, while retaining complete drill string maintenance records within that time period, thus obtaining the first valid data segment.

[0039] Based on the data association reliability set and the risk correspondence judgment result set, the risk corresponding to each data point in the first valid data segment is judged, thereby generating the first risk status result set. For example, if the standardized value of the drilling rig torque is detected to rise from 0.4 to 0.8 in the first valid data segment, combined with the torque increase corresponding to stuck drill risk rule in the risk correspondence judgment result set, the stuck drill risk level for this period is determined to be medium. If the maintenance record for this period shows that the drill string flaw detection cycle has exceeded the specified time, the risk level is upgraded to high, ultimately forming the first risk status result set containing the risk types and levels for each period.

[0040] By combining the first risk status result set, the status data feature set, and the maintenance data feature set, the degree of loss due to equipment failure is assessed, thus obtaining the first loss degree result set. The assessment of the loss degree comprehensively considers the duration of the failure impact, maintenance costs, and production interruption losses. Loss degree = (maintenance duration × output value per unit time) + component replacement cost + maintenance labor cost.

[0041] For example, when the risk of drill string getting stuck is determined to be high, combining the duration of abnormal torque in the status data feature set and the drill string maintenance history in the maintenance data feature set, the maintenance time is found to be 8 hours, the output value per unit time is 5,000 yuan, the component replacement cost is 20,000 yuan, and the maintenance labor cost is 10,000 yuan. Therefore, the loss level = 8 × 5,000 + 20,000 + 10,000 = 70,000 yuan. This type of quantification generates a first loss level result set containing the corresponding loss values ​​for each risk.

[0042] The comprehensive correlation strength assessment result is obtained by judging the correlation strength between the risk triggering factor data and the operational status data of the extended dataset, specifically including the following steps: The risk triggering feature information set is obtained by extracting the type, scope of influence and triggering threshold of each risk triggering factor in the standardized risk triggering factor dataset; The risk trigger level is obtained by judging the degree of danger of risk triggering factors based on the risk triggering feature information set; The extended data feature set is obtained by detecting the synchronicity of parameter changes and the efficiency of associated response in each associated dataset within the extended dataset. The correlation strength between risk trigger factor data and operational status data in the extended data set is judged based on the correlation response pattern of the extended data feature set. If the correlation strength is greater than or equal to the preset high-strength threshold, the first correlation strength judgment result is output. If the correlation strength is less than the preset high-strength threshold, then output the second correlation strength judgment result; The first association strength judgment result and the second association strength judgment result are combined to form the comprehensive association strength judgment result.

[0043] The system extracts the type, scope of influence, and trigger threshold of each risk trigger factor from a standardized risk trigger factor dataset, thus forming a risk trigger feature information set. For example, geological structural complexity is a geological risk trigger factor, primarily affecting the drilling system, with a trigger threshold set to enter a high-risk state when the complexity level is ≥8; environmental temperature and humidity fluctuations are an environmental risk trigger factor, affecting the hydraulic system, with a trigger threshold set to enter a medium-risk state when the temperature fluctuation range is ≥10℃. This extracted feature information is then systematically organized into a structured risk trigger feature information set.

[0044] The risk level of each risk triggering factor is determined based on the risk triggering feature information set, resulting in a risk triggering level. The determination of risk level considers both the factor's influence range and triggering threshold. For example, a geological structure complexity of level 9 is considered a high risk level, while an environmental temperature and humidity fluctuation of 8°C is considered a low risk level. All risk triggering factors are assigned a specific risk level.

[0045] The extended data feature set is obtained by detecting the synchronicity of parameter changes and the correlation response efficiency of each associated dataset in the extended data set. Parameter change synchronicity measures the time difference between changes in risk triggering factors and operational status data. For example, if the drilling rig torque increases within a 30-second interval after a 1-level increase in geological structural complexity, it indicates high synchronicity. Correlation response efficiency measures the sensitivity of operational status data to risk triggering factors. Correlation response efficiency = (Amplitude of change in operational status parameters ÷ Amplitude of change in risk triggering factors) × 100%. If the geological structural complexity increases from level 6 to level 8 (a 2-level change), and the corresponding drilling rig torque increases from 0.4 to 0.8 (a 0.4 change), then the correlation response efficiency is 0.4 ÷ 2 × 100% = 20%. These indicators together constitute the extended data feature set, reflecting the dynamic correlation between risk triggering factors and operational status data.

[0046] The correlation strength between risk trigger factor data and operational status data in the extended data set is determined based on the correlation response patterns of the extended data feature set. The correlation strength is calculated using the Pearson correlation coefficient formula. If the correlation coefficient between geological structural complexity and drilling rig torque is 0.95, and the correlation coefficient between environmental temperature and humidity fluctuations and drilling rig oil temperature is 0.75, this result is compared with a preset high-intensity threshold (e.g., 0.9). When the correlation strength is greater than or equal to the preset high-intensity threshold, the first correlation strength judgment result is output. For example, if the correlation strength between geological structural complexity and drilling rig torque is 0.95, it is judged as a high-intensity correlation. When the correlation strength is less than the preset high-intensity threshold, the second correlation strength judgment result is output. For example, if the correlation strength between environmental temperature and humidity fluctuations and drilling rig oil temperature is 0.75, it is judged as a medium-low intensity correlation.

[0047] The analysis of the comprehensive correlation strength assessment results and the extended data set yields the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set, specifically including the following steps: Based on the correlation response patterns in the extended data feature set, the risk trigger factor data and operational status data are correlated and segmented to obtain the second effective data segment; Based on the results of the first correlation strength judgment and the risk trigger level, the risk level corresponding to each data in the second effective data segment is evaluated to obtain the second risk level result set; The second spread rate result set is obtained by judging the spread rate of equipment hazards based on the second risk level result set and the risk triggering feature information set; Based on the results of the second correlation strength judgment, the risk level assessment and the speed of hazard spread are judged on the extended data set to obtain the third risk level result set and the third spread speed result set.

[0048] Based on the correlation response patterns of the extended data feature set, correlation segments are extracted from the risk triggering factor data and operational status data to obtain a second effective data segment. Time periods where there is a clear correlation between the risk triggering factors and operational status data are selected. For example, when a significant increase in geological structural complexity is identified, and drilling rig torque fluctuates synchronously, the two types of complete data within that time period are extracted to form the second effective data segment.

[0049] Based on the results of the first correlation strength assessment and the risk trigger level assessment, the risk level corresponding to each data point in the second valid data segment is evaluated, resulting in a second risk level result set. Taking the correlation between geological structure complexity and drilling rig torque as an example, if the first correlation strength assessment result is a high-strength correlation, and the risk trigger level result shows that the geological structure complexity is at a high-risk level, combined with the torque increase in the second valid data segment, the risk level of drill string stuck during this period is assessed as extremely high. If the correlation between ambient temperature and humidity fluctuations and drilling rig oil temperature is of medium to low strength, and the risk trigger level is at a low-risk level, then the risk level of hydraulic system leakage is assessed as medium. These assessment results are integrated into the second risk level result set, clarifying the risk level under high-strength correlation.

[0050] The propagation speed of equipment hazards is determined based on the second risk level result set and the risk triggering feature information set, resulting in a second propagation speed result set. Propagation speed = number of components covered by the risk impact range ÷ time it takes for operating status parameters to reach the abnormal threshold. For example, when the drill string stuck risk level is extremely high, combined with the risk triggering feature information set, it can be seen that its impact range covers three components: the drill string and the power unit. Furthermore, the drilling rig torque rises from the normal threshold to the abnormal threshold in only 15 minutes, resulting in a propagation speed of 3 ÷ 15 = 0.2 components per minute. This indicates that the hazard will rapidly spread to multiple components. This type of quantification generates a second propagation speed result set containing the propagation speed corresponding to each risk.

[0051] Based on the results of the second correlation strength assessment, the extended dataset is evaluated for risk level and hazard propagation speed, resulting in a third risk level result set and a third propagation speed result set. For risk factors with medium to low correlation strength, their impact delay and anomaly superposition effects are assessed. For example, environmental temperature and humidity fluctuations and drilling rig oil temperature have a medium to low correlation. The statistically significant delay in oil temperature anomalies after temperature and humidity fluctuations is 60 minutes, and this anomaly is superimposed on the existing wear of the hydraulic system. Ultimately, the aging risk level of the hydraulic system during this period is assessed as medium, and the hazard propagation speed is 0.05 components per minute. These results are integrated into the third risk level result set and the third propagation speed result set.

[0052] Based on the second correlation strength judgment result, the risk level assessment and the rate of hazard spread are judged on the extended data set to obtain the third risk level result set and the third spread rate result set, which specifically includes the following steps: Based on the second correlation strength judgment result and the correlation response efficiency in the extended data feature set, the delay time set of the impact of risk triggering factor data on the operation status data in the extended data set is statistically analyzed. Based on the set of impact delay durations, an information set of abnormal superposition effects of runtime status data in the extended data set is obtained; Based on the correlation response patterns in the information set of abnormal superposition effects and the feature set of extended data, the risk triggering factor data and the operational status data in the extended data set are correlated and extracted to obtain the third effective data segment. Based on the second correlation strength judgment result, the third effective data segment, the risk trigger level result, and the risk corresponding judgment result set, the risk level corresponding to each data in the third effective data segment is judged to obtain the third risk level result set; Based on the third risk level result set, the risk triggering feature information set, and the risk triggering level result, the spread rate of equipment hazards is judged to obtain the third spread rate result set.

[0053] Based on the results of the second correlation strength assessment and the correlation response efficiency in the extended data feature set, a set of impact delay durations of risk triggering factors on operational status data is statistically analyzed. Correlation response efficiency reflects the sensitivity of operational status data to risk triggering factors, while impact delay duration refers to the time interval between changes in the risk triggering factor and the occurrence of anomalies in the operational status data. For example, if the risk triggering factor of ambient temperature and humidity fluctuations experiences an 8°C fluctuation, and the drilling rig oil temperature only shows a significant anomaly after 60 minutes, then 60 minutes is the impact delay duration corresponding to this risk factor. This type of statistical analysis is performed on all risk factors with medium to low correlation strength to form an impact delay duration set.

[0054] An information set of abnormal superposition effects on operational status data in the extended dataset is obtained based on the impact delay duration set. An abnormal superposition effect refers to the superposition of the delayed effects of multiple risk triggering factors within the same time period, leading to more severe anomalies in equipment operation. For example, the delayed impact of ambient temperature and humidity fluctuations combined with the abnormal superposition of pre-existing wear in the hydraulic system causes the oil temperature to rise abnormally from 10℃ to 15℃. By combining the impact delay duration set and historical operational data, the time period, abnormal amplitude, and involved components of this type of superposition effect are identified, thus forming an information set of abnormal superposition effects.

[0055] Based on the correlation response patterns in the information set of abnormal superposition effects and the extended data feature set, risk triggering factor data and operational status data are correlated and extracted to obtain a third effective data segment. Focusing on the time period where abnormal superposition effects exist, for example, temperature and humidity data within 60 minutes after an environmental temperature and humidity fluctuation occurs are completely extracted along with oil temperature data from the same period to form the third effective data segment.

[0056] Based on the results of the second correlation strength assessment, the third valid data segment, the risk trigger level results, and the risk correspondence assessment result set, the risk level corresponding to each data point in the third valid data segment is assessed to obtain the third risk level result set. For example, combining the second correlation strength assessment result of medium to low intensity, the risk trigger level result of low danger, and the rule in the risk correspondence assessment result set that abnormal oil temperature corresponds to the aging risk of the hydraulic system, the magnitude of the abnormal oil temperature in the third valid data segment is assessed. When the cumulative effect causes the abnormal oil temperature to reach 15°C, the aging risk level of the hydraulic system during that period is assessed as medium. These assessment results are integrated into the third risk level result set, clarifying the risk level of the cumulative effect under medium to low intensity correlation.

[0057] Based on the third risk level result set, the risk triggering characteristic information set, and the risk triggering level results, the spread rate of equipment hazards is judged, resulting in a third spread rate result set. Spread rate = number of components covered by the risk's impact range ÷ time taken for the cumulative anomalies to reach the severe threshold. For example, the impact range of the hydraulic system aging risk covers two components: the hydraulic pump and the oil pipe. The cumulative effect causes the oil temperature to reach the severe threshold in 120 minutes, resulting in a spread rate of 2 ÷ 120 ≈ 0.017 components per minute. This indicates that the spread rate of this type of hazard is relatively slow, but continuous monitoring is still necessary. This quantitative calculation generates a third spread rate result set containing the corresponding spread rates for each risk, providing a time-dimensional reference for handling low- to medium-intensity associated risks.

[0058] Combining the results sets of the first risk status, the first loss extent, the second risk level, the second spread rate, the third risk level, and the third spread rate, an operational risk assessment of the oil drilling equipment is conducted, and a risk assessment early warning instruction is output. This process includes the following steps: The results set of the first risk status, the results set of the second risk level, and the results set of the third risk level are combined into a comprehensive risk level assessment set. The results sets of the first degree of loss, the second rate of spread, and the third rate of spread are combined into a comprehensive risk impact assessment set. Based on the comprehensive risk level assessment set and the comprehensive risk impact assessment set, the equipment operation risks corresponding to the source subset datasets are assessed to obtain the source risk assessment result set. The source risk assessment result set is then integrated to obtain the equipment risk assessment result. The difference between the risk assessment results of computing equipment and the preset standard safety risk results is the risk deviation value. When the risk deviation value is greater than or equal to the preset risk warning threshold, a risk assessment warning instruction will be output.

[0059] First, the results sets for the first risk status, second risk level, and third risk level are combined into a comprehensive risk level assessment set. Risk level data from different dimensions are unified and integrated. For example, the first risk status result set includes the basic risk level of drill string stuck, the second risk level result set includes the high-intensity associated risk level caused by geological structural complexity, and the third risk level result set includes the medium-to-low intensity superimposed risk level caused by environmental temperature and humidity fluctuations. These risk levels from different sources are then summarized to form a comprehensive risk level assessment set covering all potential risks to the equipment.

[0060] The results sets for the first level of loss, the second level of spread rate, and the third level of spread rate are combined into a comprehensive risk impact assessment set. The first level of loss result set contains the quantified economic losses corresponding to various risks; the second level of spread rate result set contains the hazard diffusion rate of highly correlated risks; and the third level of spread rate result set contains the hazard diffusion rate of medium- and low-intensity superimposed risks. These data are integrated into a comprehensive risk impact assessment set, fully presenting the scale of loss and the rate of spread after a risk occurs.

[0061] Based on the comprehensive risk level assessment set and the comprehensive risk impact assessment set, the operational risks of equipment corresponding to each source subset are assessed, resulting in a source risk assessment result set. This result set is then integrated to obtain the equipment risk assessment result. For example, for risk data from different sources such as the operation monitoring subset, maintenance subset, and geological environment subset, their corresponding risk levels and impact degrees are assessed separately, and then a weighted integration method is used to obtain the overall risk assessment value of the equipment. Equipment risk assessment result = ∑ i=1 n (Source Risk Level i) ×Source Risk Impact Weight (i), where the source risk impact weight is set according to the importance of the source data to equipment safety. For example, the weight of the geological environment subset is set to 0.4, the weight of the operation monitoring subset is set to 0.3, the weight of the maintenance subset is set to 0.2, and the weight of the field environment subset is set to 0.1. In this way, a quantitative value reflecting the overall risk level of the equipment is obtained.

[0062] The risk deviation value is calculated by comparing the equipment risk assessment result with the preset standard safety risk result. The preset standard safety risk result is a benchmark risk value set according to equipment design specifications and industry safety standards, for example, set at 50 points. If the equipment risk assessment result is 75 points, then the risk deviation value is 75 - 50 = 25 points. The risk deviation value directly reflects the gap between the current equipment risk and the safety benchmark.

[0063] When the risk deviation value is greater than or equal to the preset risk warning threshold, a risk assessment warning instruction is output. For example, if the preset risk warning threshold is 20 points, and the calculated risk deviation value is 25 points, meeting the condition of being greater than or equal to the threshold, a warning is immediately triggered, pushing warning information containing the risk level, scope of impact, and spread speed to on-site operation and maintenance personnel, reminding relevant personnel to take timely measures to avoid equipment failure or safety accidents.

[0064] A big data processing-based risk assessment system for oil drilling equipment includes: Acquisition module: Acquires full lifecycle data of the target drilling equipment and dynamic data of the operating environment; Classification module: Classifies and integrates full lifecycle data and dynamic work environment data into operational status data, maintenance record data, and risk trigger factor data to obtain a baseline data set and an extended data set; Processing module: Performs verification processing on the running status data and maintenance record data of the baseline dataset to obtain the status data verification results and maintenance data verification results; First judgment module: Based on the status data verification results, the module judges the risk and failure loss level of the benchmark data set to obtain the first risk status result set and the first loss level result set. The second judgment module: judges the correlation strength between the risk trigger factor data and the operation status data of the extended data set to obtain a comprehensive correlation strength judgment result; Analysis module: Analyzes the comprehensive correlation strength judgment results and extended data sets to obtain the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set; Output module: Combining the first risk status result set, the first loss degree result set, the second risk level result set, the second spread rate result set, the third risk level result set, and the third spread rate result set, the module performs an operational risk assessment of the oil drilling equipment and outputs a risk assessment early warning command.

[0065] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0066] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A risk assessment method for oil drilling equipment using big data processing, characterized in that, The method includes the following steps: Acquire full lifecycle data of the target drilling equipment and dynamic data of the operating environment; The full lifecycle data and dynamic operational environment data are classified and integrated into operational status data, maintenance record data and risk trigger factor data to obtain a baseline data set and an extended data set. The running status data and maintenance record data of the baseline dataset are verified to obtain the status data verification results and maintenance data verification results; Based on the status data verification results, the risk and failure loss degree of the benchmark data set are judged to obtain the first risk status result set and the first loss degree result set; The comprehensive correlation strength assessment result is obtained by judging the correlation strength between the risk triggering factor data and the operational status data of the extended dataset, specifically including the following steps: The risk triggering feature information set is obtained by extracting the type, scope of influence and triggering threshold of each risk triggering factor in the standardized risk triggering factor dataset; The risk trigger level is obtained by judging the degree of danger of risk triggering factors based on the risk triggering feature information set; The extended data feature set is obtained by detecting the synchronicity of parameter changes and the efficiency of associated response in each associated dataset within the extended dataset. The correlation strength between risk trigger factor data and operational status data in the extended data set is judged based on the correlation response pattern of the extended data feature set. The correlation strength is calculated using the Pearson correlation coefficient formula. If the correlation strength is greater than or equal to the preset high-strength threshold, the first correlation strength judgment result is output. If the correlation strength is less than the preset high-strength threshold, then output the second correlation strength judgment result; The first association strength judgment result and the second association strength judgment result are combined to form the comprehensive association strength judgment result; The analysis of the comprehensive correlation strength assessment results and the extended data set yields the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set, specifically including the following steps: Based on the correlation response patterns in the extended data feature set, the risk trigger factor data and operational status data are correlated and segmented to obtain the second effective data segment; Based on the results of the first correlation strength judgment and the risk trigger level, the risk level corresponding to each data in the second effective data segment is evaluated to obtain the second risk level result set; The second spread rate result set is obtained by judging the spread rate of equipment hazards based on the second risk level result set and the risk triggering feature information set; Based on the second correlation strength judgment result, the risk level assessment and the speed of hazard spread are judged on the extended data set to obtain the third risk level result set and the third spread speed result set; By combining the results sets of the first risk status, the first loss degree, the second risk level, the second spread rate, the third risk level, and the third spread rate, an operational risk assessment of oil drilling equipment is conducted, and a risk assessment early warning command is output.

2. The method for risk assessment of oil drilling equipment using big data processing according to claim 1, characterized in that, The entire lifecycle data and dynamic operational environment data are categorized and integrated into operational status data, maintenance record data, and risk trigger factor data to obtain a baseline dataset and an extended dataset. This process includes the following steps: The full lifecycle data and dynamic operational environment data are divided into source subsets according to their data sources; The source subsets are classified into operational status data, maintenance record data, and risk trigger factor data to obtain a type identification result set. The following feature sets were extracted from the type identification result set: the running status subset, the maintenance record subset, and the risk triggering factor data feature set. The baseline dataset and the extended dataset are obtained by processing the runtime status subset, the maintenance record subset, and the risk trigger factor data feature set.

3. The method for risk assessment of oil drilling equipment using big data processing according to claim 2, characterized in that, The baseline dataset and the extended dataset are obtained by processing the runtime status subset, the maintenance record subset, and the risk trigger factor data feature set. This process includes the following steps: Based on the correlation characteristics of the operational status subset, maintenance record subset, and risk trigger factor data feature set, standardized operational status dataset, standardized maintenance record dataset, and standardized risk trigger factor dataset are obtained. A baseline dataset is obtained by integrating the standardized operating status dataset and the standardized maintenance record dataset through equipment operation and maintenance correlation. An expanded dataset is obtained by integrating the standardized risk trigger factor dataset and the standardized operational status dataset through risk factor correlation.

4. The method for risk assessment of oil drilling equipment using big data processing according to claim 3, characterized in that, The operational status data and maintenance record data of the baseline dataset are verified to obtain the status data verification results and maintenance data verification results. This process includes the following steps: The first state feature information is obtained by acquiring the collection cycle, data integrity rate, and abnormal data ratio of the standardized operating status dataset; The rationality of changes in key operating condition parameters in the standardized operating status dataset is verified to obtain second-state feature information; The first state feature information and the second state feature information are combined into a state data feature set; The integrity of the running status data is judged based on the status data feature set to obtain the status data verification result; The maintenance data feature set is obtained by verifying the maintenance items, maintenance cycles, and maintenance effect verification data in the standardized maintenance record dataset. The maintenance data verification result is obtained by judging the integrity of the maintenance record data based on the maintenance data feature set.

5. The method for risk assessment of oil drilling equipment using big data processing according to claim 4, characterized in that, Based on the status data verification results, the risk and failure loss level of the baseline dataset are judged to obtain the first risk status result set and the first loss level result set. The specific steps include: A reliable set of data associations for detecting the numerical correlation between a baseline dataset and an extended dataset; Based on the data association reliability set and the status data verification results, the correspondence between the operating status data and equipment risks in the baseline data set and the extended data set is determined to obtain the risk correspondence judgment result set; The first valid data segment is obtained by effectively filtering the operation status data and maintenance record data according to the association rules of the data association reliability set; The risk corresponding to each data in the first valid data segment is judged based on the data association reliability set and the risk correspondence judgment result set to obtain the first risk status result set; Based on the first risk status result set, the status data feature set, and the maintenance data feature set, the degree of loss of equipment failure is judged to obtain the first loss degree result set.

6. The method for risk assessment of oil drilling equipment using big data processing according to claim 5, characterized in that, Based on the second correlation strength judgment result, the risk level assessment and the rate of hazard spread are judged on the extended data set to obtain the third risk level result set and the third spread rate result set, which specifically includes the following steps: Based on the second correlation strength judgment result and the correlation response efficiency in the extended data feature set, the delay time set of the impact of risk triggering factor data on the operation status data in the extended data set is statistically analyzed. Based on the set of impact delay durations, an information set of abnormal superposition effects of runtime status data in the extended data set is obtained; Based on the correlation response patterns in the information set of abnormal superposition effects and the feature set of extended data, the risk triggering factor data and the operational status data in the extended data set are correlated and extracted to obtain the third effective data segment. Based on the second correlation strength judgment result, the third effective data segment, the risk trigger level result, and the risk corresponding judgment result set, the risk level corresponding to each data in the third effective data segment is judged to obtain the third risk level result set; Based on the third risk level result set, the risk triggering feature information set, and the risk triggering level result, the spread rate of equipment hazards is judged to obtain the third spread rate result set.

7. The method for risk assessment of oil drilling equipment using big data processing according to claim 6, characterized in that, Combining the results sets of the first risk status, the first loss extent, the second risk level, the second spread rate, the third risk level, and the third spread rate, an operational risk assessment of the oil drilling equipment is conducted, and a risk assessment early warning instruction is output. This process includes the following steps: The results set of the first risk status, the results set of the second risk level, and the results set of the third risk level are combined into a comprehensive risk level assessment set. The results sets of the first degree of loss, the second rate of spread, and the third rate of spread are combined into a comprehensive risk impact assessment set. Based on the comprehensive risk level assessment set and the comprehensive risk impact assessment set, the equipment operation risks corresponding to the source subset datasets are assessed to obtain the source risk assessment result set. The source risk assessment result set is then integrated to obtain the equipment risk assessment result. The difference between the risk assessment results of computing equipment and the preset standard safety risk results is the risk deviation value. When the risk deviation value is greater than or equal to the preset risk warning threshold, a risk assessment warning instruction will be output.

8. A big data processing-based risk assessment system for oil drilling equipment, applied to the big data processing-based risk assessment method for oil drilling equipment as described in any one of claims 1 to 7, characterized in that, include: Acquisition module: Acquires full lifecycle data of the target drilling equipment and dynamic data of the operating environment; Classification module: Classifies and integrates full lifecycle data and dynamic work environment data into operational status data, maintenance record data, and risk trigger factor data to obtain a baseline data set and an extended data set; Processing module: Performs verification processing on the running status data and maintenance record data of the baseline dataset to obtain the status data verification results and maintenance data verification results; First judgment module: Based on the status data verification results, the module judges the risk and failure loss level of the benchmark data set to obtain the first risk status result set and the first loss level result set. The second judgment module: This module assesses the correlation strength between the risk triggering factor data and the operational status data in the extended dataset to obtain a comprehensive correlation strength judgment result. Specifically, it includes the following steps: The risk triggering feature information set is obtained by extracting the type, scope of influence and triggering threshold of each risk triggering factor in the standardized risk triggering factor dataset; The risk trigger level is obtained by judging the degree of danger of risk triggering factors based on the risk triggering feature information set; The extended data feature set is obtained by detecting the synchronicity of parameter changes and the efficiency of associated response in each associated dataset within the extended dataset. The correlation strength between risk trigger factor data and operational status data in the extended data set is judged based on the correlation response pattern of the extended data feature set. The correlation strength is calculated using the Pearson correlation coefficient formula. If the correlation strength is greater than or equal to the preset high-strength threshold, the first correlation strength judgment result is output. If the correlation strength is less than the preset high-strength threshold, then output the second correlation strength judgment result; The first association strength judgment result and the second association strength judgment result are combined to form the comprehensive association strength judgment result; Analysis module: Analyzes the comprehensive correlation strength judgment results and extended data sets to obtain the second risk level result set, the third risk level result set, the second spread rate result set, and the third spread rate result set. Specifically, it includes the following steps: Based on the correlation response patterns in the extended data feature set, the risk trigger factor data and operational status data are correlated and segmented to obtain the second effective data segment; Based on the results of the first correlation strength judgment and the risk trigger level, the risk level corresponding to each data in the second effective data segment is evaluated to obtain the second risk level result set; The second spread rate result set is obtained by judging the spread rate of equipment hazards based on the second risk level result set and the risk triggering feature information set; Based on the second correlation strength judgment result, the risk level assessment and the speed of hazard spread are judged on the extended data set to obtain the third risk level result set and the third spread speed result set; Output module: Combining the first risk status result set, the first loss degree result set, the second risk level result set, the second spread rate result set, the third risk level result set, and the third spread rate result set, the module performs an operational risk assessment of the oil drilling equipment and outputs a risk assessment early warning command.

Images