Fault diagnosis method and system for neutron detector array

Abstract

The invention relates to the technical field of geophysical logging, in particular to a fault diagnosis method and system for a neutron detector array. The method comprises the following steps: acquiring original counting rate sequences and well temperature curves of neutron logging near and far detectors, and performing non-zero clamping, alignment and statistical fluctuation smoothing. And based on the smoothed far detector data and well temperature, calculating the theoretical counting rate of the near detector by using the array response prediction model containing the temperature drift correction term. And calculating a prediction residual error of the smoothed near detector data and a theoretical value, calculating a stratigraphic gradient value of the smoothed far detector data, calculating a fault discrimination index by combining the prediction residual error, the stratigraphic gradient value, the near detector data and a weight coefficient, comparing the fault discrimination index with a threshold value, and if a continuity confirmation condition is satisfied, determining that the detector array has a fault. And determining the type according to the well temperature. According to the scheme of the invention, by introducing stratum gradient weighting, the stratum interface can be automatically identified, and the resolution mismatch false alarm is effectively inhibited while the sensitivity is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geophysical logging. More particularly, the present application relates to a fault diagnosis method and system for a neutron detector array. BACKGROUND

[0002] In the process of oil exploration and development, pulsed neutron logging technology is applied to the monitoring of residual oil saturation, lithology identification and element analysis in cased wells. Such an instrument is usually equipped with a neutron generator and multiple near detectors, far detectors, ultra-far detectors and the like distributed along the axial direction, forming a linear detector array. Since the logging instrument needs to work in an extremely harsh environment downhole, it faces multiple challenges such as high temperature and high pressure environment, high flux radiation damage and complexity of formation environment, which can easily lead to performance degradation or failure of the detector.

[0003] In order to solve the problem of performance degradation or failure of the detector, the existing fault diagnosis methods mainly rely on simple threshold discrimination method or multi-probe ratio method. Among them, the threshold discrimination method mainly monitors the instrument state by judging whether the count rate exceeds a certain fixed range. The multi-probe ratio method uses the ratio of near and far detectors for verification, trying to identify potential problems by analyzing the data relationship of detectors at different positions, thereby assisting the development of logging operations to some extent.

[0004] However, the above existing technology has obvious deficiencies in practical application. First, for the threshold discrimination method, when the instrument passes through a gas layer or a dense layer, the normal count rate changes dramatically, which can easily trigger false alarms. Second, for the multi-probe ratio method, due to the different source distances of near and far detectors, their detection depths and longitudinal resolutions differ significantly. When the instrument passes through a formation interface, i.e. a lithology mutation, the near detector responds first and changes quickly, while the far detector responds later and changes slowly, resulting in a serious mismatch of data at the interface. This mismatch makes it impossible for the existing technology to effectively distinguish between data fluctuations caused by formation changes and data anomalies caused by instrument failure, thereby easily producing a large number of false fault alarms at the formation interface, seriously affecting the efficiency of logging operations and the accuracy of data interpretation. SUMMARY

[0005] The present application aims to provide a fault diagnosis method and system for a neutron detector array to solve the technical problems of false alarms at the formation interface and the inability to accurately distinguish between temperature drift and real faults in the prior art. To this end, the present application provides solutions in the following two aspects.

[0006] In a first aspect, the present application provides a fault diagnosis method of a neutron detector array, comprising: acquiring a near-probe original count rate sequence, a far-probe original count rate sequence and a downhole temperature curve uploaded on a neutron logging instrument, performing non-zero clamping processing, depth alignment correction and statistical fluctuation smoothing processing on the near-probe original count rate sequence and the far-probe original count rate sequence to obtain smoothed near-probe data and far-probe data; based on the smoothed far-probe data and the downhole temperature curve, using an array response prediction model containing a temperature drift correction term, calculating a theoretical prediction count rate of the near-probe at a current depth point; calculating a prediction residual between the smoothed near-probe data and the theoretical prediction count rate, and calculating a formation gradient value of the smoothed far-probe data, based on the prediction residual, the smoothed near-probe data, the formation gradient value and a gradient suppression weight coefficient, calculating a fault discrimination index; comparing the fault discrimination index with a preset fault alarm threshold value, if the fault discrimination index is greater than or equal to the fault alarm threshold value and a preset continuity confirmation condition is met, it is determined that the neutron detector array has a fault, and a fault type is determined according to the downhole temperature curve.

[0007] The present application has the beneficial effects that: through the above technical solution, the far-probe data with relatively stable working state is combined with the well temperature data to establish an array response prediction model containing temperature drift correction, the theoretical value of the near-probe under normal state is calculated, and a fault discrimination index is calculated, the index is weighted by introducing the formation gradient value, can automatically identify the gradient change caused by the formation interface, so as to ensure the fault detection sensitivity while effectively suppressing the resolution mismatch false alarm caused by the formation interface.

[0008] Preferably, the non-zero clamping processing, depth alignment correction and statistical fluctuation smoothing processing on the near-probe original count rate sequence and the far-probe original count rate sequence comprise: detecting the original count rate, if the count rate is zero or negative, forcibly setting it to a preset positive integer; taking the far-probe as a reference, according to the physical source distance difference between the near-probe and the far-probe, performing depth translation on the near-probe original count rate sequence to make them correspond to the same measurement depth; using a sliding average filter to denoise the aligned data.

[0009] The present application has the beneficial effects that: through the non-zero clamping processing, the zero division or negative square root error in subsequent mathematical operation is avoided, through the depth alignment, the depth lag caused by different source distances is eliminated, through the smoothing processing, the interference of nuclear signal statistical fluctuation on fault judgment is reduced, and a high-quality data basis is provided for subsequent model calculation.

[0010] Preferably, the array response prediction model satisfies the expression: ; in the formula, for depth Theoretical predicted count rate at the near detector; for depth Smoothed far detector data at depth 、 、 For Formation response coupling coefficient; for reference temperature; for temperature drift suppression constant; for depth Downhole temperature at depth

[0011] The beneficial effects of the present application are: by constructing a prediction model containing formation response and temperature drift characteristics, the dynamic correlation of data between detectors is realized, which can decouple the influence of environmental temperature and formation change on count rate from the physical mechanism, and provides a precise dynamic benchmark for fault judgment.

[0012] Preferably, the formation gradient value satisfies the expression: ; In the formula, for depth Formation gradient value at depth and are the smoothed far detector data at the current depth point and the last depth point respectively, is the sampling depth interval.

[0013] The beneficial effects of the present application are: by calculating the formation gradient value, the degree of data change of the current depth point relative to the last depth point can be quantified, and the existence of the formation interface can be accurately represented, which provides a key parameter for introducing a gradient suppression factor in the subsequent fault discrimination index.

[0014] Preferably, the fault discrimination index satisfies the expression: ; In the formula, for depth Fault discrimination index at depth for depth Smoothed near detector data at depth Theoretical predicted count rate; Prediction residual; Poisson noise normalization term; Gradient suppression weight coefficient; 1.0 is an anti-odd anomaly number; for depth Formation gradient value at depth

[0015] The beneficial effects of the present application are: by introducing the gradient term ， At the stratigraphic interface, the gradient value increases, which in turn increases the denominator, thereby reducing the discrimination exponent and avoiding false high residual alarms caused by resolution mismatch. In homogeneous strata, the gradient term approaches zero, and the algorithm degenerates into a highly sensitive residual detection, ensuring the ability to capture minor faults. At the same time, the introduction of a constant term ensures the mathematical robustness of the algorithm under extreme data.

[0016] Preferably, the gradient suppression weight coefficient ranges from 2.0 to 5.0.

[0017] Preferably, satisfying the preset continuity confirmation condition includes: determining whether the fault discrimination index is within the continuous range. All depth points are greater than or equal to the fault alarm threshold; if so, a fault alarm is confirmed to be triggered; wherein, This refers to the number of sampling points included at a depth distance of at least 0.5 meters.

[0018] Preferably, determining the fault type based on the downhole temperature curve includes: when a fault is determined to exist, if the current downhole temperature exceeds a preset high temperature threshold, marking the fault type as a high temperature thermal decay warning; when a fault is determined to exist, if the current downhole temperature does not exceed the preset high temperature threshold, marking the fault type as a detector response inconsistency fault.

[0019] Preferably, the curve formed by the theoretically predicted count rate and the curve formed by the smoothed near-detector data are displayed on the same screen; the fault discrimination index is plotted as an independent quality control channel for output.

[0020] In the second aspect, the fault diagnosis system for the neutron detector array includes: processor; The memory stores computer instructions for fault diagnosis of the neutron detector array, which, when executed by the processor, cause the system to perform the aforementioned fault diagnosis method for the neutron detector array.

[0021] The beneficial effects of this invention are as follows: 1. Significantly reduced the false alarm rate at the formation interface; by innovatively adding a gradient suppression term to the denominator of the discrimination formula, the false residuals caused by the inconsistency between near and far detector resolutions at abrupt changes in formation are automatically offset by mathematical logic, thus solving the problem of "false alarms at the interface" that has plagued the industry.

[0022] 2. Dynamic decoupling is achieved in high-temperature deep well environments; the solution integrates a temperature drift correction model based on physical laws, enabling the algorithm to automatically distinguish between the physical temperature drift of the detector and actual circuit faults, which is particularly suitable for operational support in high-temperature environments. Attached Figure Description

[0023] Figure 1 A flow chart of steps of the fault diagnosis method of the neutron detector array in the embodiment is schematically shown; Figure 2 A curve graph of array detector depth alignment data is schematically shown; Figure 3 A comparison graph of the prior art and the fault discrimination effect of the present application is schematically shown; Figure 4 A graph of dynamic reference prediction and measured deviation analysis is schematically shown. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application.

[0025] As Figure 1 shown, the fault diagnosis method of the neutron detector array in the embodiment includes the following steps: Step S1, obtaining a near-probe original count rate sequence, a far-probe original count rate sequence and a downhole temperature curve uploaded by a neutron logging instrument, performing non-zero clamping processing, depth alignment correction and statistical fluctuation smoothing processing on the near-probe original count rate sequence and the far-probe original count rate sequence to obtain smoothed near-probe data and far-probe data.

[0026] In an optional embodiment, the non-zero clamping processing, depth alignment correction and statistical fluctuation smoothing processing on the near-probe original count rate sequence and the far-probe original count rate sequence include: detecting the original count rate, and forcibly setting the original count rate to a preset positive integer if the original count rate is zero or negative; performing depth translation on the near-probe original count rate sequence according to the physical source distance difference between the near-probe and the far-probe based on the far-probe as a reference, so that the near-probe and the far-probe correspond to the same measurement depth; and performing denoising processing on the aligned data by using a sliding average filter.

[0027] Specifically, first, a near-probe total count rate sequence, a far-probe total count rate sequence and a downhole instrument internal temperature curve are extracted from the telemetry sub of the surface system.

[0028] Then, data validity pre-checking is performed to execute non-zero clamping processing. Specifically, if the collected count rate is 0 or negative, it is set to a minimum positive integer 1CPS to ensure the legality of subsequent mathematical operations.

[0029] Subsequently, depth alignment correction is performed. Due to the physical spacing between the near detector and the far detector, the near detector and the far detector measure different depths at the same time. Specifically, the near detector data is depth-translated based on the far detector, and the aligned near detector data is: ； wherein, is the aligned near detector data; is the total count rate of the near detector obtained; represents the current logging depth point; is the physical source spacing difference between the near detector and the far detector.

[0030] As shown in Figure 2 , the original count rates of the far detector and the near detector after depth alignment are shown. As can be seen from Figure 2 , in the interval of 3035 meters to 3045 meters, the near detector data appears to be abnormally concave, which represents the simulated “detector sensitivity drift” soft fault. Finally, statistical fluctuation smoothing is performed, and a 5-point moving average filter is used to denoise the aligned data to obtain the smoothed near detector data Figure 2 and the far detector data .

[0031] In this way, through non-zero clamping, depth alignment and smoothing, the singular points, depth lag and statistical noise in the data are eliminated, ensuring the quality and spatiotemporal consistency of the input data, and providing a reliable basis for subsequent correlation analysis.

[0032] Step S2, based on the far detector data and the downhole temperature curve, the theoretical predicted count rate of the near detector at the current depth point is calculated by using the array response prediction model containing the temperature drift correction term.

[0033] In an optional embodiment, the count rate value that the near detector should have “theoretically” under normal working state is calculated by using the far detector with relatively stable working state and combining with the well temperature data. And a dynamic reference prediction model is constructed based on physical laws, and the array response prediction model satisfies the expression: ; wherein, is the theoretical predicted count rate of the near detector at depth ; is the smoothed far detector data at depth ; , , ​The formation response coupling coefficient is obtained by nonlinear least squares regression fitting of a known standard logging curve. For reference temperature, e.g., room temperature 25℃; This is the temperature drift suppression constant, obtained through high-temperature laboratory tests. For depth The downhole temperature at that location.

[0034] For example, the calculated depth under certain temperature and geological conditions. The theoretical predicted count rate of the proximity detector is 2696.4 CPS, indicating that under these temperature and formation conditions, if the proximity detector is functioning correctly, its count rate should be 2696.4 CPS. If the measured value deviates significantly from this value, a malfunction may exist.

[0035] Thus, by constructing a predictive model that incorporates formation response and temperature drift characteristics, dynamic correlation of data between detectors is achieved. This decouples the influence of ambient temperature and formation changes on the count rate from a physical mechanism perspective, providing an accurate dynamic benchmark for fault diagnosis.

[0036] Step S3: Calculate the prediction residual between the near detector data and the theoretical predicted count rate, and calculate the formation gradient value of the far detector data. Based on the prediction residual, the near detector data, the formation gradient value, and the gradient suppression weight coefficient, calculate the fault discrimination index.

[0037] Specifically, the first step is to calculate the formation gradient value, which is used to characterize the homogeneity of the current formation. The formation gradient value satisfies the formula: ; In the formula, For depth The stratigraphic gradient value at that location, and These are smoothed remote sensor data from the current depth point and the previous depth point, respectively. The sampling depth interval is denoted as 0.1 meters.

[0038] Then, a fault discrimination index is constructed, satisfying the formula: ; In the formula, It is a dimensionless fault discrimination index; For depth Smoothed near-detector data, To predict the count rate theoretically; To predict residuals; This is the normalized term for Poisson noise; The gradient suppression weight coefficient is typically set between 2.0 and 5.0; 1.0 is the outlier prevention coefficient, used to prevent the calculation results from diverging when the denominator is close to zero, thus ensuring numerical stability. For depth The stratigraphic gradient value at that location.

[0039] When the strata are uniform, the changes in the remote detector are very small, and the corresponding fault discrimination index value is very small, far below the alarm threshold, it is judged as normal.

[0040] When the instrument passes through the formation interface, the different source distances cause the near detector to respond quickly and the far detector to respond slowly, resulting in a high residual between the near and far detectors. At this time, the data of the far detector will also change drastically. Although the residual between the near and far detectors is large, the existence of the gradient term results in a low discrimination index, which will not trigger an alarm, thus avoiding false alarms.

[0041] When a soft fault occurs in a homogeneous layer, the corresponding fault discrimination index value is very large, far exceeding the threshold, and the system will accurately issue an alarm.

[0042] Thus, by introducing a gradient suppression factor and anomaly prevention, the index maintains high sensitivity in homogeneous formations while automatically reducing sensitivity at formation interfaces. This cleverly solves the problem of false alarms at formation interfaces using mathematical logic, while ensuring the robustness of the algorithm.

[0043] Step S4: Compare the fault discrimination index with the preset fault alarm threshold. If the fault discrimination index is greater than or equal to the fault alarm threshold and the preset continuity confirmation condition is met, then it is determined that there is a fault in the neutron detector array, and the fault type is determined according to the downhole temperature curve.

[0044] For example, the fault alarm threshold is set to 6.0. If the fault discrimination index is less than the fault alarm threshold, it is determined to be normal; if the fault discrimination index is greater than or equal to the fault alarm threshold, the determination logic is entered.

[0045] In an optional embodiment, satisfying the preset continuity confirmation condition includes: Determine whether the fault discrimination index is in a continuous state. The fault alarm threshold is greater than or equal to the fault alarm threshold at each depth point; If so, then confirm that a fault alarm has been triggered; among which, This refers to the number of sampling points included at a depth distance of at least 0.5 meters.

[0046] This prevents single-point spike interference caused by cosmic rays or sudden electronic noise.

[0047] like Figure 3As shown, in the prior art, a spike false alarm occurs at the formation interface at 3015 meters, while the curve of the present invention remains stable at this point. Obviously, the present invention effectively eliminates interface false alarms by introducing a gradient suppression factor. In the real fault zone of 3035-3045 meters, the curve of the present invention accurately breaks through the alarm threshold, achieving precise capture of real faults.

[0048] In this way, by threshold determination, continuity confirmation and multi-parameter joint analysis, the final qualitative and classification of instrument faults can be achieved, effectively eliminating random noise interference and providing operators with intuitive fault type indications and visual basis.

[0049] In addition, such as Figure 4 As shown, Figure 4 The diagram illustrates the comparison between the measured values ​​of the near-detector and the "dynamic benchmark prediction values" calculated by the algorithm of this invention. In the normal well section of 3000-3035 meters, the predicted values ​​and measured values ​​highly overlap, indicating that the model accurately learned the formation characteristics. In the fault zone of 3035-3045 meters, the measured values ​​are significantly lower than the predicted values, forming a clear red-filled area between them, intuitively revealing the existence and magnitude of the fault.

[0050] In an optional embodiment, determining the fault type based on the downhole temperature profile includes: When a fault is detected, if the current downhole temperature exceeds the preset high temperature threshold, the fault type is marked as a high temperature thermal decay warning. When a fault is detected, if the current downhole temperature does not exceed the preset high temperature threshold, the fault type is marked as a detector response inconsistency fault.

[0051] In an optional embodiment, the curve formed by the theoretically predicted count rate and the curve formed by the smoothed near-detector data are displayed on the same screen; the fault discrimination index is plotted as an independent quality control channel for output.

[0052] The present invention also provides a fault diagnosis system for a neutron detector array. The system includes a processor and a memory, the memory storing computer program instructions. When the processor executes the computer program instructions, it implements the fault diagnosis method for a neutron detector array according to the present invention.

[0053] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and therefore will not be described in detail here.

[0054] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented by computer-readable / executable instructions stored or otherwise maintained on such a computer-readable medium.

[0055] In the description of this specification, "multiple" means at least two, such as two, three or more, etc., unless otherwise expressly and specifically defined.

[0056] While various embodiments of the invention have been shown and described in this specification, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention.

Claims

1. A method of fault diagnosis of a neutron detector array, characterized in that, The method comprises the following steps: obtaining a near-probe raw count rate sequence, a far-probe raw count rate sequence and a downhole temperature curve uploaded by a neutron logging instrument, performing non-zero clamping processing, depth alignment correction and statistical fluctuation smoothing processing on the near-probe raw count rate sequence and the far-probe raw count rate sequence to obtain smoothed near-probe data and far-probe data; based on the smoothed far-probe data and the downhole temperature curve, using an array response prediction model containing a temperature drift correction term to calculate a theoretical prediction count rate of the near-probe at a current depth point; calculating a prediction residual between the smoothed near-probe data and the theoretical prediction count rate, and calculating a formation gradient value of the smoothed far-probe data, based on the prediction residual, the smoothed near-probe data, the formation gradient value and a gradient suppression weight coefficient, calculating a fault discrimination index; comparing the fault discrimination index with a preset fault alarm threshold, if the fault discrimination index is greater than or equal to the fault alarm threshold and a preset continuity confirmation condition is met, it is determined that the neutron probe array has a fault, and the fault type is determined according to the downhole temperature curve.

2. The method of claim 1, wherein, The non-zero clamping processing, depth alignment correction and statistical fluctuation smoothing processing on the near-probe raw count rate sequence and the far-probe raw count rate sequence comprise: detecting the original count rate, if the original count rate is zero or negative, setting it to a preset positive integer; taking the far-probe as a reference, performing depth translation on the near-probe raw count rate sequence according to the physical source distance difference between the near-probe and the far-probe, so that they correspond to the same measurement depth; using a sliding average filter to denoise the aligned data.

3. The method of claim 1, wherein, The array response prediction model satisfies the expression: ； where is the theoretical predicted count rate at depth is the theoretical predicted count rate at depth is the theoretical predicted count rate at depth is the smoothed far detector data at depth , , is the formation response coupling coefficient is the reference temperature is the temperature drift suppression constant is the theoretical predicted count rate at depth is the downhole temperature at depth 4. The method of claim 1, wherein, The formation gradient value satisfies the expression: ； wherein is the depth is the formation gradient value at the current depth point, and are the smoothed far detector data at the current depth point and the previous depth point, respectively, is the sampling depth interval.

5. The method of claim 1, wherein, The fault discrimination index satisfies the expression: ； wherein is the depth of the fault discrimination index; is the depth of the smoothed near detector data, is the theoretical predicted count rate; is the predicted residual; is the Poisson noise normalization term; is the gradient suppression weight coefficient; 1.0 is the anti- anomaly number; is the depth of the formation gradient value.

6. The method of claim 5, wherein, The value range of the gradient suppression weight coefficient is 2.0 to 5.

0.

7. The method of claim 1, wherein, The preset continuity confirmation condition comprises: determining whether the fault determination index is greater than or equal to the fault alarm threshold at each of the plurality of depth points; and determining whether the fault determination index is greater than or equal to the fault alarm threshold at each of the plurality of depth points; and If yes, it is confirmed that a fault alarm is triggered; wherein, The sampling points contained in the corresponding depth distance of at least 0.5 meters.

8. The method of claim 1, wherein, The fault type determined according to the downhole temperature curve comprises: when it is determined that there is a fault, if the current downhole temperature exceeds a preset high temperature threshold, the fault type is marked as a high temperature thermal decay warning; when it is determined that there is a fault, if the current downhole temperature does not exceed a preset high temperature threshold, the fault type is marked as a probe response inconsistency fault.

9. The method of claim 1, wherein, The curve formed by the theoretical prediction count rate is displayed on the same screen with the curve formed by the smoothed near-probe data; the fault discrimination index is plotted into an independent quality control channel for output.

10. A fault diagnosis system of a neutron detector array, characterized by, The system comprises: a processor; a memory storing computer instructions for fault diagnosis of a neutron probe array, when the computer instructions are run by the processor, the system performs the fault diagnosis method of the neutron probe array according to any one of claims 1-9.

Images