A method for processing and early warning of monitoring data

Abstract

The application discloses a kind of processing and early warning method of monitoring data, it is related to offshore platform jacket monitoring technical field, comprising: obtaining jacket monitoring data, setting noise reduction method obtains analysis data;Adaptive selection method is constructed to carry out analysis, judge whether to replace noise reduction method to monitoring data is reduced, and constitute noise reduction dataset;According to the different noise reduction data, construct early warning method selection rule, select early warning method to obtain early warning result;According to noise reduction dataset and IDW interpolation algorithm, construct key data prediction model to obtain key data prediction result;According to early warning result and prediction result, determine jacket structure health condition;The application can select different noise reduction method for different data, adopt the most suitable method to carry out early warning, improve early warning speed and accuracy, based on interpolation algorithm according to the sea condition data that has occurred, predict the sea condition data that has not occurred, according to the early warning condition and key data condition obtained, assess the health condition of jacket.

Description

Technical Field

[0001] This invention relates to the field of offshore platform jacket monitoring technology, and in particular to a method for processing and early warning of monitoring data. Background Technology

[0002] Offshore platform jackets are exposed to the marine environment for extended periods, subjected to complex environmental loads and seawater corrosion. Due to external interference such as environmental and human factors, data noise is generated when sensors on offshore platform jackets collect data, meaning that some data may contain syntax errors, time discontinuities, data outside the instrument's range, or data outside the designated area.

[0003] In early warning of offshore platform jackets, traditional early warning methods mostly target a specific threshold. When the collected data exceeds the specified threshold range, an early warning is issued. The early warning method is singular and prone to false alarms. Moreover, traditional early warning methods are often based on real-time collected monitoring data and lack the ability to predict key data response values ​​(such as member stress) for jacket health management under sea conditions that have not occurred before. Although theoretical calculations and software simulations can predict key data, the modeling and solution process is complex and time-consuming, making it difficult to meet the requirements of rapid development of operational plans in actual production. Summary of the Invention

[0004] This invention provides a method for processing and issuing early warnings of monitoring data, in order to overcome the technical problems of inaccurate data and limited early warning methods in existing catheterization site health monitoring processes, which result in inaccurate early warnings and health predictions based on data for catheterization sites.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows:

[0006] A method for processing and issuing early warnings for monitoring data, comprising:

[0007] S1: Acquire catheter stent monitoring data, set the corresponding noise reduction method for the monitoring data, and acquire analysis data;

[0008] S2: Construct a noise reduction adaptive selection method, analyze the analysis data according to the noise reduction adaptive selection method, determine whether to change the noise reduction method corresponding to the monitoring data, and reduce the noise of the monitoring data according to the noise reduction method obtained after the determination, and form a noise reduction dataset together with the analysis data.

[0009] S3: Construct an early warning method based on the data characteristics of different noise reduction data in the noise reduction dataset, and select rules.

[0010] Then, based on the aforementioned warning rules, a warning method corresponding to the noise-reduced data is selected, a safety range and a warning value are set, and a warning result is obtained; the specific rules for constructing the warning method selection include:

[0011] S31. When monitoring data comes from the horizontal direction and it is necessary to combine the data values ​​of the horizontal direction for early warning, the ring boundary early warning method shall be selected.

[0012] S32. When the monitored data is a specific value of a certain data type and exceeds the normal value range, an early warning will be issued. The upper and lower limit early warning methods will be selected.

[0013] S33. When the monitoring data is a specific value of a certain data type at different locations in the vertical direction, and the difference between the specific values ​​at different locations exceeds the normal range, an early warning will be issued. The settlement difference early warning method is selected.

[0014] S4: Construct a key data prediction model based on the noise reduction dataset and IDW interpolation algorithm to obtain key data prediction results;

[0015] S5: Determine the health status of the duct stent structure based on the aforementioned early warning results and key data prediction results.

[0016] Furthermore, S2 constructs an adaptive noise reduction selection method, analyzes the analysis data according to the adaptive noise reduction selection method, determines whether to change the noise reduction method corresponding to the monitoring data, and performs noise reduction on the monitoring data according to the noise reduction method obtained after the determination. Together with the analysis data, they form a noise-reduced dataset, including:

[0017] S21. Set the quantity of analysis data and noise criteria, wherein the noise criteria include standard deviation criteria and noise quantity criteria:

[0018] The standard deviation criterion is set to n times the standard deviation. Data that falls outside the range of the mean plus or minus n times the standard deviation is considered noisy data.

[0019] Set a specific value for the noise quantity criterion. If the noise quantity in the analyzed data is lower than the noise quantity criterion, the nearest neighbor difference algorithm is used for data denoising; if the noise quantity in the analyzed data is higher than the noise quantity criterion, the bandpass filtering algorithm is used for data denoising.

[0020] S22. Set the analysis cycle, process the monitoring data in the next analysis cycle according to the changed noise reduction method, obtain new noise reduction data, and form a noise reduction dataset together with the analysis data.

[0021] Furthermore, the jacket monitoring data includes strain data, weight center of gravity data, acceleration data, displacement data, static horizontal data, wind speed data, wind direction data, reference electrode potential data, and sacrificial anode current data.

[0022] Furthermore, a ring boundary warning method is used for early warning of displacement data and weight center of gravity data, and early warning is also provided for reference electrode potential data, sacrificial anode current data, acceleration data, strain data, and wind speed data.

[0023] The upper and lower limit early warning methods are selected, and the settlement difference early warning method is selected for static horizontal data.

[0024] Furthermore, a key data prediction model is constructed based on the denoised dataset and the IDW interpolation algorithm to obtain key data prediction results, including:

[0025] S41. Determine the initial environmental parameters and key parameters:

[0026] Determine the initial environmental parameters, the types of which include, but are not limited to, wave height, wave period, wind speed, wind direction, ocean current speed, and ocean current direction, totaling m parameters;

[0027] The key parameters include, but are not limited to, stress values, strain values, weight center of gravity values, tilt angle values, displacement values, and dynamic response values ​​at various measuring points on the platform jacket;

[0028] S42. Establish an environmental parameter database and a key parameter database:

[0029] The environmental parameter database stores multiple data tables according to the sampling time, and each data table contains the numerical values ​​of all environmental parameters collected at the same sampling time.

[0030] The key parameter database stores multiple data tables according to the sampling time. Each data table is used to represent the correspondence between environmental parameters and key parameters at the same sampling time.

[0031] S43. Select a set of measured environmental parameter values ​​and choose the type of key parameter to be predicted;

[0032] S44. Determine the combination of environmental parameter values ​​Z. The specific steps include:

[0033] S441: Randomly select one of the measured environmental parameters as the first environmental parameter. Arrange the values ​​of the first environmental parameter in the environmental parameter database from smallest to largest to form a first sequence list. Determine the sorting number of the measured first environmental parameter value in the sequence list. Based on the sorting number, find the value corresponding to the position before and after it, and put the found value into an empty environmental parameter value combination.

[0034] S442: Based on the two values ​​of the first environmental parameter found in S441, search for data containing the two values ​​in the environmental parameter database, update the environmental parameter database, continue to randomly select the second environmental parameter from the measured environmental parameters and arrange the values ​​of the second environmental parameter from smallest to largest to form a second sequence list, determine the sorting number of the measured second environmental parameter value in the sequence list, and use the sorting number as a basis to find the value corresponding to the position before and after it, and put the found value into the combination of environmental parameter values;

[0035] S443: Repeat the above steps, using the found values ​​as a basis, to search the environmental parameter database after the last update for all data containing the values ​​found in the previous steps, update the environmental parameter database again, and sort the new environmental parameter values ​​to find the values ​​corresponding to the previous and next sequence numbers, until the values ​​of the last environmental parameter in the measured environmental parameters are arranged from smallest to largest, forming the m-th sequence list, and the measured values ​​are determined.

[0036] The m-th environmental parameter is sorted in the sequence list. Based on the sorting number, the corresponding values ​​at the positions before and after it are found. The found values ​​are put into the combination of environmental parameter values, and the database update is stopped.

[0037] S45. Based on the combination of environmental parameter values ​​and the type of key parameter to be predicted, find the value of the key parameter corresponding to each piece of environmental data in the key parameter database.

[0038] S46. Calculate the Euclidean distance between the measured environmental parameter values ​​and the environmental parameter values ​​in the combination with the environmental parameter values;

[0039] S47. Calculate the interpolation weights of the IDW interpolation algorithm, as shown in formula (1).

[0040] (1)

[0041] in, Indicates the interpolation weights. Represents Euclidean distance. The value is the average value adjusted based on the measured results, and is an adjustable parameter, as shown in formula (2).

[0042] (2)

[0043] in, This indicates the amount of data measured. This represents one set of data. This represents one set of P values;

[0044] S48. Calculate the key parameters to be predicted, as shown in formula (3).

[0045] (3)

[0046] in, This represents the key parameter to be predicted. This indicates the numerical values ​​of the key parameters corresponding to the combination of environmental parameter values.

[0047] Furthermore, the health status of the duct stent structure is determined based on the aforementioned early warning results and key data prediction results, including:

[0048] S51. Based on the warning results of the weight center of gravity, displacement, tilt angle and dynamic response sensors, determine whether there is an external force affecting the jacket, as well as the frequency and severity of the impact. Based on the assessment results of the severity of the impact, determine whether human intervention is required.

[0049] S52. Based on the stress and strain sensor monitoring results of the platform jacket structure members, determine whether the members are at risk of failure, and determine whether the platform jacket structure is at risk of health based on whether the members are at risk of failure.

[0050] S53. Based on the prediction results of key data, determine whether the key data of the platform jacket exceeds the specified value, and determine whether the platform jacket needs to be inspected and maintained based on the results of the key data.

[0051] Beneficial effects: This invention provides a method for processing and early warning of monitoring data. It can select different noise reduction methods for different data, resulting in more accurate noise-reduced data. It categorizes data from different types of sensors and uses the most suitable method for each category for early warning, which can improve the speed and accuracy of early warning. Based on the IDW interpolation algorithm, it predicts the sea state data that has not yet occurred based on the sea state data that has occurred. It can assess the health status of the jacket structure based on the acquired early warning situation and key data. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A flowchart of a monitoring data processing and early warning method provided by the present invention;

[0054] Figure 2 This is a schematic diagram of the ring boundary early warning method of the present invention;

[0055] Figure 3 This is a schematic diagram of the upper and lower limit early warning method of the present invention;

[0056] Figure 4 This is a schematic diagram of the settlement difference early warning method of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] This embodiment provides a method for processing and issuing early warnings for monitoring data, such as... Figure 1 As shown, it includes:

[0059] S1: Acquire catheter stent monitoring data, set the corresponding noise reduction method for the monitoring data, and acquire analysis data;

[0060] S2: Construct a noise reduction adaptive selection method, analyze the analysis data according to the noise reduction adaptive selection method, determine whether to change the noise reduction method corresponding to the monitoring data, and reduce the noise of the monitoring data according to the noise reduction method obtained after the determination, and form a noise reduction dataset together with the analysis data.

[0061] S3: Construct early warning method selection rules based on the data characteristics of different noise-reduced data in the noise-reduced dataset, select the early warning method corresponding to the noise-reduced data according to the early warning rules, set the safety range and warning value, and obtain the early warning result; the construction of early warning method selection rules specifically includes:

[0062] S31. When monitoring data comes from the horizontal direction and it is necessary to combine the data values ​​of the horizontal direction for early warning, the ring boundary early warning method shall be selected.

[0063] S32. When the monitored data is a specific value of a certain data type and exceeds the normal value range, an early warning will be issued. The upper and lower limit early warning methods will be selected.

[0064] S33. When the monitoring data is a specific value of a certain data type at different locations in the vertical direction, and the difference between the specific values ​​at different locations exceeds the normal range, an early warning will be issued. The settlement difference early warning method is selected.

[0065] S4: Construct a key data prediction model based on the noise reduction dataset and IDW interpolation algorithm to obtain key data prediction results;

[0066] S5: Determine the health status of the duct stent structure based on the aforementioned early warning results and key data prediction results.

[0067] Specifically, firstly, duct stent monitoring data is acquired, and a corresponding noise reduction method is set for the monitoring data. Analysis data is then acquired, and an initial noise reduction method is set for the monitoring data based on experience, providing analytical data for subsequent assessment of the suitability of the noise reduction method. Secondly, an adaptive noise reduction selection method is constructed. The analytical data is analyzed according to this method to determine whether to change the noise reduction method corresponding to the monitoring data. The noise reduction data is then denoised using the determined method, and together with the analytical data, forms a noise reduction dataset. The adaptive noise reduction selection method analyzes the initial analytical data to determine whether the selected noise reduction method meets the requirements. If it does, no change is made; otherwise, a more suitable noise reduction method is used, resulting in more accurate noise reduction data. Based on the data characteristics of different noise-reduced data in the noise-reduced dataset, a rule for selecting early warning methods is constructed. The corresponding early warning method is selected according to this rule, and a safety range and warning value are set to obtain early warning results. Selecting different early warning methods based on different data allows for more accurate early warnings based on different states, facilitating adjustments by management personnel for different issues. A key data prediction model is constructed based on the noise-reduced dataset and the IDW interpolation algorithm to obtain key data prediction results. This allows for the determination of whether the data of the duct support exceeds specified values, enabling early intervention to reduce losses. The health status of the duct support structure is determined based on the early warning results and key data prediction results. Combining these results provides a more accurate health prediction, allowing management personnel to view the health status of the duct support and obtain more precise health information.

[0068] In a specific embodiment, the process involves acquiring catheter stent monitoring data, setting a corresponding noise reduction method for the monitoring data, and obtaining the analysis data as follows:

[0069] S11. Acquire jacket monitoring data, including strain data, weight center of gravity data, acceleration data, displacement data, static horizontal data, wind speed data, wind direction data, reference electrode potential data, and sacrificial anode current data.

[0070] S12. Set the corresponding noise reduction method for the monitoring data:

[0071] Generation of strain data, weight center of gravity data, acceleration data, displacement data, and static horizontal data

[0072] The noise in the data is usually caused by irregular swaying of the platform due to sea wind, waves, and currents, as well as vibrations generated by platform operation and equipment operation. In addition, the data acquisition frequency is high (about 10 data points per second), and there will be significant low-frequency interference and high-frequency noise during the acquisition process. Therefore, a bandpass filtering algorithm is used to reduce data noise, remove low-frequency interference and high-frequency noise from the data, and retain the effective signal by setting a reasonable bandpass range.

[0073] Since the wind direction and wind speed data are collected at a low frequency (about 1 data point per second) and are less affected by platform vibration, the nearest neighbor interpolation algorithm is used to remove data noise.

[0074] The noise in the reference electrode potential data and sacrificial anode data is caused by electromagnetic interference between sensors. This electromagnetic interference is irregular. In addition, since the values ​​of the reference electrode potential and the sacrificial anode current collected by the sensor change slowly during the lifespan of the platform guide frame, the nearest neighbor interpolation algorithm is used to remove the data noise.

[0075] Based on previous engineering experience, this solution sets an initial noise reduction method for the monitoring data, providing analytical data for subsequent evaluation of the suitability of the noise reduction method.

[0076] In a specific embodiment, a noise reduction adaptive selection method is constructed. The analysis data is analyzed according to this method to determine whether to change the noise reduction method corresponding to the monitoring data. The monitoring data is then denoised using the noise reduction method obtained after the determination. The scheme, which combines the noise reduction data with the analysis data to form a noise-reduced dataset, is as follows:

[0077] S21. Set the quantity of analysis data and noise criteria, wherein the noise criteria include standard deviation criteria and noise quantity criteria:

[0078] The standard deviation criterion is set to n times the standard deviation. Data that falls outside the range of the mean plus or minus n times the standard deviation is considered noisy data.

[0079] Set a specific value for the noise quantity criterion. If the noise quantity in the analyzed data is lower than the set noise quantity criterion, the nearest neighbor difference algorithm is used for data denoising; if the noise quantity in the analyzed data is higher than the set noise quantity criterion, the bandpass filtering algorithm is used for data denoising.

[0080] S22. Set the analysis cycle, process the monitoring data in the next analysis cycle according to the changed noise reduction method, obtain new noise reduction data, and combine it with the analysis data to form noise reduction data.

[0081] In this embodiment, the number of data points analyzed is set to 10,000, the standard deviation criterion is set to 3 (a multiple of the standard deviation), and the noise data criterion is set to 5. The standard deviation is calculated for each of the 10,000 different data points. Data falling outside the range of the mean ± 3 times the standard deviation is considered noise data. If the number of noise points is less than 5, nearest neighbor interpolation is used for data denoising; if the number of noise points is greater than 5, bandpass filtering is used. The analysis period is set to one day, with the data analyzed each day being evaluated.

[0082] Decide which noise reduction method to use for the data from the next day.

[0083] This solution constructs an adaptive noise reduction selection method. By analyzing the initial analysis data, it can determine whether the selected noise reduction method meets the requirements. If it does, no changes are made; if it does not, it is adjusted to a more suitable noise reduction method, which can make the obtained noise reduction data more accurate.

[0084] In a specific embodiment, the scheme for constructing early warning method selection rules based on the data characteristics of different noise-reduced data in the noise-reduced dataset, selecting the early warning method corresponding to the noise-reduced data according to the early warning rules, setting a safety range and a warning value, and obtaining the early warning result is as follows:

[0085] S31. When monitoring data comes from the horizontal direction and requires combining horizontal data values ​​for early warning, select the ring boundary early warning method:

[0086] In this embodiment, the early warning of displacement data uses the ring boundary early warning method. Under the action of sea wind, waves and currents, the platform is prone to displacement. When the displacement is large, it may pose a threat to the safety of the platform. The displacement sensor mainly measures the displacement of the platform jacket in the horizontal X and Y directions. The platform jacket may not necessarily be displaced in the X or Y direction alone. Therefore, it is necessary to combine the X and Y direction displacement to determine the early warning.

[0087] Because the horizontal cross-section of the jacket is usually a rectangle with varying lengths and widths, the warning thresholds for the jacket's horizontal offset in the X and Y directions are often different. Therefore, the warning threshold formed by the combination of X and Y offsets is generally elliptical. A schematic diagram of the warning method is shown below. Figure 2As shown, each sensor is configured with (X / Y) coordinate values ​​for this warning type, 8 values ​​per level, for a total of 24 values. These 8 values ​​are connected to form three nested rings, creating a warning map. After data collection, the warning level is determined based on the data's position on the map. The data with the largest offset among all sensor data is selected, and a consecutive count index (e.g., 10 times) is configured. A warning is issued when a data point appears consecutively in a Level 1, Level 2, or Level 3 warning level for 10 consecutive times. A Level 3 warning range includes Level 1 and Level 2 warnings, and a Level 2 warning range includes Level 1 warnings. For example, if 10 consecutive data points fall within the "Level 3-Level 3-Level 3-Level 3-Level 3-Level 2-Level 3-Level 3-Level 3" warning area, a Level 3 warning is issued.

[0088] S32. When the monitored data is a specific value of a certain data type and exceeds the normal value range, an early warning will be issued. The upper and lower limit early warning methods are selected as follows:

[0089] In this embodiment, an upper and lower limit warning method is selected for the warning of reference electrode potential data, sacrificial anode current data, acceleration data, and strain data:

[0090] The data collected by the reference electrode is the potential value at the measuring point. When the potential value at the measuring point is not within the normal range (for example, the range of Ag / Agcl reference electrode is -800mV to -1100mV), it indicates that the cathodic protection status of the jacket platform is poor.

[0091] The data collected by the accelerometer is the acceleration at the measuring point. When the acceleration at the measuring point exceeds the normal range, it indicates that external factors (construction, earthquake, impact of unknown organisms, etc. on the jacket platform) may pose a safety hazard to the jacket, and corresponding measures should be taken in a timely manner.

[0092] The strain sensor collects data as strain values ​​at the measuring points. When the strain value at a measuring point exceeds the normal range, it indicates a safety hazard in the jacket platform structure. Upper and lower limit warning methods are as follows: Figure 3 As shown, after collecting data, the corresponding warning level is determined based on the position of the data in the graph. The data with the largest offset among all sensor data is selected, and a consecutive count index (such as 10 times) is configured. If the data point appears in the first, second, or third warning level for 10 consecutive times, a warning message is issued.

[0093] S33. When the monitoring data consists of specific values ​​of a certain data type at different locations in the vertical direction, and the difference between the different directions exceeds the normal range, an early warning will be issued. The settlement difference early warning method is selected as follows:

[0094] In this embodiment, a settlement difference early warning method is selected for static level data. The static level is typically installed at the four corners of the jacket platform, and the collected data is the vertical movement distance of the measuring points. When the vertical distance difference between the measuring points is large, the jacket platform is at risk of tilting. The settlement difference early warning method is as follows: Figure 4 As shown in the figure, assuming that the static level of data point 1 is significantly lower than that of data point 3, the jacket platform is at risk of tilting in the direction of data point 1. After collecting the data, the corresponding warning level is determined based on the position of the data in the figure, and a consecutive number index (such as 10 times) is configured. If the data point appears in the first, second or third warning level for 10 consecutive times, a warning message is issued.

[0095] By selecting different early warning methods based on different data, more accurate early warnings can be provided according to different states, making it easier for managers to make adjustments for different problems.

[0096] In a specific embodiment, the scheme for constructing a key data prediction model based on the denoised dataset and the IDW interpolation algorithm to obtain the key data prediction results is as follows:

[0097] S41. Determine the initial environmental parameters and key parameters:

[0098] Determine the initial environmental parameters, the types of which include, but are not limited to, wave height, wave period, wind speed, wind direction, ocean current speed, and ocean current direction, totaling m parameters;

[0099] The key parameters include, but are not limited to, stress values, strain values, weight center of gravity values, tilt angle values, displacement values, and dynamic response values ​​at various measuring points on the platform jacket;

[0100] S42. Establish a database of environmental parameters and key parameters:

[0101] The environmental parameter database stores multiple data tables according to the sampling time, and each data table is identical.

[0102] The numerical values ​​of all environmental parameters collected at a given time.

[0103] The key parameter database stores multiple data tables according to the sampling time. Each data table is used to represent the correspondence between environmental parameters and key parameters at the same sampling time.

[0104] S44. Determine the combination of environmental parameter values ​​Z. The specific steps include:

[0105] S441: Randomly select one of the measured environmental parameters as the first environmental parameter. Arrange the values ​​of the first environmental parameter in the environmental parameter database from smallest to largest to form a first sequence list. Determine the sorting number of the measured first environmental parameter value in the sequence list. Based on the sorting number, find the value corresponding to the position before and after it, and put the found value into an empty environmental parameter value combination.

[0106] S442: Based on the two values ​​of the first environmental parameter found in S441, search for data containing the two values ​​in the environmental parameter database, update the environmental parameter database, continue to randomly select the second environmental parameter from the measured environmental parameters and arrange the values ​​of the second environmental parameter from smallest to largest to form a second sequence list, determine the sorting number of the measured second environmental parameter value in the sequence list, and use the sorting number as a basis to find the value corresponding to the position before and after it, and put the found value into the combination of environmental parameter values;

[0107] S443: Repeat the above steps based on the found values, search for all data containing the values ​​found in the previous steps in the environmental parameter database after the last update, update the environmental parameter database again, and sort the values ​​of the new environmental parameters to find the values ​​corresponding to the previous and next sequence positions, until the values ​​of the last environmental parameter in the measured environmental parameters are arranged from smallest to largest to form the m-th sequence list, determine the sorting number of the measured m-th environmental parameter value in the sequence list, use the sorting number as a basis to find the values ​​corresponding to the previous and next sequence positions, put the found values ​​into the environmental parameter value combination, and stop updating the database;

[0108] In this embodiment, m=3, that is, there are 3 environmental parameters, namely A, B and C. A set of measured environmental parameter values ​​is selected, namely (A0, B0, C0).

[0109] Based on three environmental parameters A, B, and C, the values ​​of environmental parameter A are first arranged in ascending order in the database to form a sequence list. The sorting number of the measured environmental parameter value A0 in the sequence list is determined, and the values ​​corresponding to its preceding and following positions, i.e. (A1, A2), are found and placed into the combination of environmental parameter values.

[0110] Based on the determined environmental parameter values ​​A1 and A2, the database is updated. The updated database contains only the values ​​of environmental parameter A1 and A2. Then, the values ​​of environmental parameter B are sorted from smallest to largest to form a sequence list of environmental parameter B. The measured environmental parameter value B0 is then determined to be in the sequence list.

[0111] Find the sorting sequence number, find the corresponding values ​​at the positions before and after it, i.e. (B1, B2), and put them into the combination of environment parameter values;

[0112] Based on the determined environmental parameter values ​​B1 and B2, the database of the determined environmental parameter values ​​A1 and A2 is updated. After the update, the values ​​of environmental parameter A are only A1 and A2, and the values ​​of environmental parameter B are only B1 and B2. Based on this, the values ​​of C are sorted from smallest to largest to form a sequence list of environmental parameter C. The sorting number of the measured environmental parameter value C0 in the sequence list is determined, and the values ​​corresponding to its preceding and following positions, i.e. (C1, C2), are found and put into the combination of environmental parameter values.

[0113] Environmental parameter value combination Z, Z=2 m In this embodiment, Z=8;

[0114] If m=3, and the environmental parameters within the combination of environmental parameter values ​​are (A1,A2), (B1,B2), and (C1,C2), and different types of environmental parameters are randomly combined, then the combination of environmental parameter values ​​within the combination of environmental parameter values ​​is:

[0115] Z1-(A1, B1, C1), Z2-(A2, B1, C1), Z3-(A1, B2, C1), Z4-(A2, B2, C1), Z5-(A1, B1, C2), Z6-(A2, B1, C2), Z7-(A1, B2, C2), Z8-(A2, B2, C2), total 2 3 =8;

[0116] S45. Based on the combination of environmental parameter values ​​and the type of key parameter to be predicted, find the value of the key parameter corresponding to each piece of environmental data in the key parameter database.

[0117] That is, the key parameter value T0 corresponding to the environment (A0, B0, C0). Assuming that the key parameter to be predicted is stress, then T is σ, that is, the key parameter to be predicted is stress σ0.

[0118] In this embodiment, the environmental parameter value combinations formed based on (A0, B0, C0) are (A1, B1, C1), (A2, B1, C1), (A1, B2, C1), (A2, B2, C1), (A1, B1, C2), (A2, B1, C2), (A1, B2, C2), (A2, B2, C2). Then, the key parameter values ​​T corresponding to these environmental parameter value combinations are extracted from the database.

[0119] Z1-(A1, B1, C1)-T1, Z2-(A2, B1, C1)-T2, Z3-(A1, B2, C1)-T3, Z4-(A2, B2, C1)-T4, Z5-(A1, B1, C2)-T5, Z6-(A2, B1, C2)-T6, Z7-(A1, B2, C2)-T7, Z8-(A2, B2, C2)-T8;

[0120] S46. Calculate the Euclidean distance between the measured environmental parameter values ​​and the environmental parameter values ​​in the combination with the environmental parameter values;

[0121] Taking the calculation of the Euclidean distance between (A0, B0, C0) and (A1, B1, C1) as an example, as shown in formula (4),

[0122] (4)

[0123] Calculate sequentially to obtain all Euclidean distances d1, d2...d8;

[0124] S47. Calculate the interpolation weights of the IDW interpolation algorithm as shown in (5).

[0125] (5)

[0126] in, Indicates the interpolation weights. Represents Euclidean distance. The P-value is the average value adjusted based on the measured results. It is an adjustable parameter. The P-value is periodically corrected based on the measured results. Take n sets of measured data and adjust the P-value to make the measured data and the predicted data similar, so that the error is within 1%, as shown in formula (6).

[0127] (6)

[0128] in, This indicates the amount of data measured. This represents one set of data. This represents one set of P values;

[0129] S48. Calculate the key parameters to be predicted, as shown in formula (7).

[0130] (7)

[0131] in, This represents the key parameter to be predicted. In this embodiment, m=3, therefore there are 8 combinations of environmental parameter values ​​that are closest to the new environmental parameter value, resulting in 8 weight values ​​w1, w2...w8. .

[0132] This solution can determine whether the data of the duct stent exceeds the specified values, and intervene in the condition of the duct stent in advance to reduce losses.

[0133] In a specific embodiment, the scheme for determining the health status of the duct stent structure based on the early warning results and key data prediction results is as follows:

[0134] S51. Combining the warning results from weight center of gravity, displacement, tilt angle, and dynamic response sensors, determine whether external forces are affecting the jacket, as well as the frequency and severity of such impacts. Based on the assessment of the severity of the impact, determine whether human intervention is necessary.

[0135] When an alert is triggered, the corresponding alert data is located, and the collected data and business data for the preceding and following time periods are examined based on the time of the alert data to determine if the abnormal data occurred when the sensor data at the source was collected. If the collected data already shows a significant deviation, workers are dispatched to further investigate the actual sensors. If no abnormalities are found, it is determined that a genuine abnormality alert has occurred, and manual assessment is conducted based on the severity level to determine if further action is needed.

[0136] Actions such as replacing rods, replacing parts, or removing the jacket structure may be necessary.

[0137] S52. Based on the stress and strain sensor monitoring results of the platform jacket, determine whether there is a risk of failure in the members, and determine whether there is a health risk in the platform jacket based on whether the members fail:

[0138] If multiple components show signs of failure, the overall platform jacket is deemed to have a health risk and requires adjustment; it may be necessary to replace components, replace some parts, or remove the jacket.

[0139] S53. Based on the key data prediction results, determine whether the key data of the platform jacket structure exceeds the specified values, and determine whether the platform jacket structure needs inspection and maintenance based on the key data results:

[0140] If the value exceeds the specified value, it is determined that the overall health condition of the platform jacket is poor, and the jacket needs to be inspected and maintained in a timely manner. It is necessary to determine whether to replace the jacket rods, replace some parts, or remove the entire jacket.

[0141] In summary, when stress-strain, weight center of gravity, displacement, tilt angle, and dynamic response sensors continuously issue Level 1 warnings, it indicates that the jacket structure has potential accident risks, but has not yet developed to a serious level; when Level 2 warnings are continuously issued, it indicates that the jacket structure may have localized, relatively large accident risks, which should be paid attention to; when Level 3 warnings are continuously issued, it indicates that the jacket structure may have major safety accidents, systemic safety risks, or have extremely significant negative impacts on economic production, and personnel intervention should be carried out immediately to take timely countermeasures.

[0142] By combining early warning results with key data predictions, more accurate health predictions can be obtained, making it easier for managers to check the health status of catheter stents and obtain more precise health information.

[0143] 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing and issuing early warning for monitoring data, characterized in that, include: S1: Acquire jacket monitoring data, set corresponding noise reduction methods for the monitoring data, and acquire analysis data; the jacket monitoring data includes strain data, weight center of gravity data, acceleration data, displacement data, static horizontal data, wind speed data, wind direction data, reference electrode potential data, and sacrificial anode current data; S2: Construct a noise reduction adaptive selection method, analyze the analysis data according to the noise reduction adaptive selection method, determine whether to change the noise reduction method corresponding to the monitoring data, and reduce the noise of the monitoring data according to the noise reduction method obtained after the determination, and form a noise reduction dataset together with the analysis data. S3: Construct early warning method selection rules based on the data characteristics of different noise reduction data in the noise reduction dataset, select the early warning method corresponding to the noise reduction data according to the early warning method selection rules, set the safety range and warning value, and obtain the early warning result; The specific rules for selecting early warning methods include: S31. When monitoring data comes from the horizontal direction and needs to be combined with horizontal data values ​​for early warning, the ring boundary early warning method should be selected; the ring boundary early warning method should be used for early warning of displacement data and weight center of gravity data. S32. When the monitored data is a specific value of a certain data type and exceeds the normal value range, an early warning will be issued, and the upper and lower limit early warning method will be selected; for the early warning of reference electrode potential data, sacrificial anode current data, acceleration data, strain data and wind speed data, the upper and lower limit early warning method will be selected. S33. When the monitoring data is a specific value of a certain data type at different locations in the vertical direction, and the difference between the specific values ​​at different locations exceeds the normal range, an early warning will be issued, and the settlement difference early warning method will be selected; the settlement difference early warning method will be selected for static horizontal data. S4: Construct a key data prediction model based on the aforementioned denoised dataset and IDW interpolation algorithm to obtain key data prediction results, including: Determine the key parameters, which include, but are not limited to, stress values, strain values, weight center of gravity values, tilt angle values, displacement values, and dynamic response values ​​at each measuring point of the platform jacket; S5: Determine the health status of the duct stent structure based on the aforementioned early warning results and key data prediction results.

2. The method for processing and issuing early warning for monitoring data according to claim 1, characterized in that, S2 constructs an adaptive noise reduction selection method, analyzes the analysis data according to the adaptive noise reduction selection method, determines whether to change the noise reduction method corresponding to the monitoring data, and performs noise reduction on the monitoring data according to the noise reduction method obtained after the determination. Together with the analysis data, they form a noise-reduced dataset, including: S21. Set the quantity of analysis data and noise criteria, wherein the noise criteria include standard deviation criteria and noise quantity criteria: The standard deviation criterion is set to n times the standard deviation. Data that falls outside the range of the mean plus or minus n times the standard deviation is considered noisy data. Set a specific value for the noise quantity criterion. If the noise quantity in the analyzed data is lower than the noise quantity criterion, the nearest neighbor difference algorithm is used for data denoising; if the noise quantity in the analyzed data is higher than the noise quantity criterion, the bandpass filtering algorithm is used for data denoising. S22. Set the analysis cycle, process the monitoring data in the next analysis cycle according to the changed noise reduction method, obtain new noise reduction data, and form a noise reduction dataset together with the analysis data.

3. The method for processing and issuing early warning for monitoring data according to claim 1, characterized in that, Based on the denoised dataset and IDW interpolation algorithm, a key data prediction model is constructed to obtain the key data prediction results, which also includes: S41. Determine the initial environment parameters: Determine m initial environmental parameters, the types of which include, but are not limited to, wave height, wave period, wind speed, wind direction, ocean current speed, and ocean current direction; S42. Establish an environmental parameter database and a key parameter database: The environmental parameter database stores multiple data tables according to the sampling time, and each data table contains the numerical values ​​of all environmental parameters collected at the same sampling time. The key parameter database stores multiple data tables according to the sampling time. Each data table is used to represent the correspondence between environmental parameters and key parameters at the same sampling time. S43. Select a set of measured environmental parameter values ​​and choose the type of key parameter to be predicted; S44. Determine the combination of environmental parameter values ​​Z. The specific steps include: S441: Randomly select one of the measured environmental parameters as the first environmental parameter. Arrange the values ​​of the first environmental parameter in the environmental parameter database from smallest to largest to form a first sequence list. Determine the sorting number of the measured first environmental parameter value in the sequence list. Based on the sorting number, find the value corresponding to the position before and after it, and put the found value into an empty environmental parameter value combination. S442: Based on the two values ​​of the first environmental parameter found in S441, search for data containing the two values ​​in the environmental parameter database, update the environmental parameter database, continue to randomly select the second environmental parameter from the measured environmental parameters and arrange the values ​​of the second environmental parameter from smallest to largest to form a second sequence list, determine the sorting number of the measured second environmental parameter value in the sequence list, and use the sorting number as a basis to find the value corresponding to the position before and after it, and put the found value into the combination of environmental parameter values; S443: Repeat the above steps based on the found values, search for all data containing the values ​​found in the previous steps in the environmental parameter database after the last update, update the environmental parameter database again, and sort the values ​​of the new environmental parameters to find the values ​​corresponding to the previous and next sequence positions, until the values ​​of the last environmental parameter in the measured environmental parameters are arranged from smallest to largest to form the m-th sequence list, determine the sorting number of the measured m-th environmental parameter value in the sequence list, use the sorting number as a basis to find the values ​​corresponding to the previous and next sequence positions, put the found values ​​into the environmental parameter value combination, and stop updating the database; S45. Based on the combination of environmental parameter values ​​and the type of key parameter to be predicted, find the value of the key parameter corresponding to each piece of environmental data in the key parameter database. S46. Calculate the Euclidean distance between the measured environmental parameter values ​​and the environmental parameter values ​​in the combination with the environmental parameter values; S47. Calculate the interpolation weights of the IDW interpolation algorithm, as shown in formula (1). （1） in, Indicates the interpolation weights. Represents Euclidean distance. The value is the average value adjusted based on the measured results, and is an adjustable parameter, as shown in formula (2). （2） in, This indicates the amount of data measured. This represents one set of data. This represents one set of P values; S48. Calculate the key parameters to be predicted, as shown in formula (3). （3） in, This represents the key parameter to be predicted. This indicates the numerical values ​​of the key parameters corresponding to the combination of environmental parameter values.

4. The method for processing and issuing early warning for monitoring data according to claim 1, characterized in that, The health status of the duct stent structure is determined based on the aforementioned early warning results and key data prediction results, including: S51. Based on the warning results of the weight center of gravity, displacement, tilt angle and dynamic response sensors, determine whether there is an external force affecting the jacket, as well as the frequency and severity of the impact. Based on the assessment results of the severity of the impact, determine whether human intervention is required. S52. Based on the stress and strain sensor monitoring results of the platform jacket structure members, determine whether the members are at risk of failure, and determine whether the platform jacket structure is at risk of health based on whether the members are at risk of failure. S53. Based on the prediction results of key data, determine whether the key data of the platform jacket exceeds the specified value, and determine whether the platform jacket needs to be inspected and maintained based on the results of the key data.

Images