A control method and related equipment for a modular intelligent terminal for well inspection

Abstract

A control method and related equipment for a modular intelligent terminal used in well inspection, relating to the field of equipment calibration. Implementing this method, the control system acquires the performance and timing parameters of each gas detection module, establishes response characteristic curves, and calculates cumulative working time to determine the performance degradation index of each gas detection module, achieving comprehensive monitoring of the gas detection module status. The control system marks the gas detection module with the highest performance degradation index as the module to be compensated, and the other gas detection modules as cooperative modules. It selects at least two cooperative modules with the highest correlation coefficients as compensation benchmark modules to achieve data compensation for the performance degradation modules. When the data deviation rate between the theoretical detection data and the current detection data of the module to be compensated exceeds a preset deviation threshold, it is promptly determined that the module to be compensated needs to be replaced, effectively avoiding safety hazards caused by inaccurate detection and improving the detection reliability of the modular intelligent terminal.

Description

Technical Field

[0001] This application relates to the field of equipment calibration, and in particular to a control method and related equipment for a modular intelligent terminal for well inspection. Background Technology

[0002] With the continuous advancement of urban underground pipeline construction, a large number of manholes and tunnels have been built for the inspection and maintenance of underground pipelines. During the daily inspection of manholes and tunnels, it is necessary to comprehensively test parameters such as gas concentration, temperature, and humidity inside them. Traditional testing methods mainly rely on manual labor to carry multiple testing instruments to measure them one by one. This is not only inefficient but also carries the risk of missed or false detections, seriously affecting the safe operation of underground pipelines.

[0003] To address the aforementioned technical challenges, a novel integrated underground well inspection device has been developed. This device integrates multiple sensors into a single inspection unit, enabling the detection of multiple parameters with a single device. This significantly improves inspection efficiency and reduces the workload of inspection personnel.

[0004] However, integrating multiple sensors into a single detection unit makes it difficult to flexibly adjust the configuration of the detection modules according to different well environments and detection needs, resulting in poor equipment adaptability. When a detection module malfunctions or needs to be replaced, the entire equipment must be returned to the factory for repair, which not only increases maintenance costs but also affects the continuity of detection work. Summary of the Invention

[0005] This application provides a control method and related equipment for a modular intelligent terminal for well inspection, which improves the inspection reliability of the modular intelligent terminal.

[0006] In a first aspect, this application provides a control method for a modular intelligent terminal used for well inspection, applied to a control system. The method includes: acquiring performance parameters and timing parameters of each gas detection module of the intelligent terminal; establishing response characteristic curves corresponding to each gas detection module based on the performance parameters; calculating the cumulative working time corresponding to each gas detection module based on the timing parameters; performing deviation analysis between the response characteristic curves and the calibration reference curves to obtain characteristic deviation values; determining the performance decay index of each gas detection module based on the characteristic deviation values ​​and the cumulative working time; marking the gas detection module with the highest performance decay index as the module to be compensated, marking the other gas detection modules as cooperative modules, and calculating the correlation matrix between the module to be compensated and each cooperative module; selecting at least two cooperative modules with the highest correlation coefficients from the correlation matrix as compensation reference modules; acquiring the real-time detection data of the compensation reference modules; calculating the theoretical detection data of the module to be compensated based on a pre-established gas concentration correlation model; comparing and analyzing the theoretical detection data of the module to be compensated with the current detection data of the module to be compensated, and calculating the data deviation rate; and determining that the module to be compensated needs to be replaced when the data deviation rate exceeds a preset deviation threshold.

[0007] By adopting the above technical solution, the control system acquires the performance and timing parameters of each gas detection module, establishes response characteristic curves, and calculates the cumulative working time to determine the performance degradation index of each gas detection module, thus achieving comprehensive monitoring of the gas detection module status. The control system marks the gas detection module with the highest performance degradation index as the module to be compensated, and the other gas detection modules as collaborative modules. It selects at least two collaborative modules with the highest correlation coefficients as compensation benchmark modules to achieve data compensation for the performance degradation modules. When the data deviation rate between the theoretical detection data and the current detection data of the module to be compensated exceeds a preset deviation threshold, it promptly determines that the module to be compensated needs to be replaced, effectively avoiding safety hazards caused by inaccurate detection and improving the detection reliability of the modular intelligent terminal.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, deviation analysis is performed between the response characteristic curve and the calibration reference curve to obtain characteristic deviation values. Based on the characteristic deviation values ​​and the cumulative working time, the performance degradation index of each gas detection module is determined. Specifically, this includes: extracting the response values ​​of the response characteristic curve and the calibration reference curve at multiple feature points, calculating the difference between the response values ​​at corresponding feature points to obtain a difference sequence; performing wavelet transform on the difference sequence to extract high-frequency and low-frequency components, calculating the dynamic deviation coefficient based on the energy proportion of the high-frequency components, and calculating the static deviation coefficient based on the mean of the low-frequency components; weighting and summing the dynamic deviation coefficient and the static deviation coefficient according to preset weights to obtain the characteristic deviation value; determining the time degradation coefficient based on the cumulative working time and the preset working time-performance degradation mapping relationship; and multiplying the characteristic deviation value and the time degradation coefficient to obtain the performance degradation index.

[0009] By employing the above technical solution, the control system extracts the difference in response values ​​between the response characteristic curve and the calibration reference curve at multiple feature points, and uses wavelet transform to separate high-frequency and low-frequency components, calculating the dynamic deviation coefficient and static deviation coefficient respectively, thus achieving precise quantification of performance deviation. The control system weights the dynamic and static deviation coefficients and combines them with a time decay coefficient to obtain a comprehensive performance decay index, fully reflecting the actual performance status of the gas detection module. This multi-dimensional performance evaluation method not only considers static accuracy deviation but also focuses on dynamic response characteristics, making the performance decay assessment more scientific and accurate, and providing a reliable basis for subsequent compensation and maintenance.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, after performing deviation analysis on the response characteristic curve and the calibration reference curve to obtain characteristic deviation values, and determining the performance degradation index of each gas detection module based on the characteristic deviation values ​​and the cumulative working time, the method further includes: predicting the remaining service life of each gas detection module based on the performance degradation index; screening modules whose remaining service life is lower than a preset maintenance threshold, and determining the maintenance priority for the modules to be maintained based on the remaining service life; and generating a module maintenance plan including a suggested replacement time window according to the maintenance priority.

[0011] By adopting the above technical solution, the control system predicts the remaining service life of each gas detection module based on the performance degradation index, selects the modules requiring maintenance, determines the maintenance priority based on the remaining service life, and generates a module maintenance plan that includes suggested replacement time windows, thus achieving predictive management of gas detection module maintenance. This prediction-based maintenance scheme can plan the replacement time of gas detection modules in advance, avoid detection interruptions caused by sudden failures, and optimize the allocation efficiency of maintenance resources by rationally arranging the maintenance sequence. It realizes a shift from passive maintenance to proactive preventative maintenance, improving the reliability and maintainability of the control system.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the correlation matrix between the module to be compensated and each cooperating module specifically includes: when the remaining service life of all gas detection modules is greater than a preset maintenance threshold, obtaining the time-aligned historical data sequences of the module to be compensated and each cooperating module; calculating the Pearson correlation coefficient between the historical data sequence of the module to be compensated and the historical data sequences of each cooperating module to construct an initial correlation matrix; based on the initial correlation matrix and combined with the remaining service life of each cooperating module, calculating the cooperating weight coefficient; and weighting the initial correlation matrix according to the cooperating weight coefficient to obtain an optimized correlation matrix.

[0013] By adopting the above technical solution, the control system acquires the time-aligned historical data sequences of the module to be compensated and each coordinating module, calculates the Pearson correlation coefficient to construct an initial correlation matrix, and calculates the coordinating weight coefficients based on the remaining service life of each coordinating module to optimize the initial correlation matrix, thus achieving a scientific selection of the compensation benchmark module. This mechanism, based on a dual consideration of historical data correlation and the lifespan of the gas detection module, avoids selecting a gas detection module whose lifespan is about to expire as the compensation benchmark, improving the reliability and continuity of data compensation.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, real-time detection data of the compensation benchmark module is acquired, and theoretical detection data of the module to be compensated is calculated based on a pre-established gas concentration correlation model. Specifically, this includes: when the remaining service life of all gas detection modules is greater than a preset maintenance threshold, acquiring historical detection data of the compensation benchmark module and historical detection data of the module to be compensated under historical operating conditions; training and constructing a gas concentration correlation model with the detection data of the compensation benchmark module as input and the detection data of the module to be compensated as output based on the historical detection data of the compensation benchmark module and the historical detection data of the module to be compensated; inputting the real-time detection data of the compensation benchmark module into the gas concentration correlation model, and outputting the theoretical detection data of the module to be compensated.

[0015] By adopting the above technical solution, when the remaining service life of all gas detection modules exceeds the preset maintenance threshold, the control system trains a gas concentration correlation model based on historical operating data, achieving accurate prediction of the theoretical detection data of the module to be compensated. The control system inputs the real-time detection data of the compensation benchmark module into the trained gas concentration correlation model to obtain the theoretical detection data of the module to be compensated that matches the actual operating conditions. This compensation method based on historical data modeling fully utilizes the inherent correlation between gas concentrations between modules, avoids errors that may arise from simple linear compensation, and improves compensation accuracy.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, after comparing and analyzing the theoretical detection data of the module to be compensated with the current detection data of the module to be compensated and calculating the data deviation rate, the method further includes: when the data deviation rate does not exceed a preset deviation threshold, constructing a real-time error mapping dataset between the theoretical detection data and the current detection data; and training a compensation calibration model based on the real-time error mapping dataset to perform dynamic compensation calibration on the subsequent detection data of the module to be compensated, wherein the compensation calibration model fits the nonlinear deviation relationship between the current detection data and the theoretical detection data.

[0017] By adopting the above technical solution, when the data deviation rate does not exceed the preset deviation threshold, the control system constructs a real-time error mapping dataset and trains a compensation calibration model, realizing dynamic compensation calibration of subsequent detection data of the module to be compensated. Compared with the traditional linear compensation method, it can more accurately reflect the complex deviation characteristics in the actual detection process.

[0018] In some embodiments of the first aspect, after marking the gas detection module with the highest performance degradation index as the module to be compensated and marking the other gas detection modules as collaborative modules, the method further includes: iteratively selecting at least one verification module and the remaining reference modules from the collaborative modules; training and constructing a temporary verification model for predicting the detection data of the verification modules based on the historical data of the reference modules and the historical data of the verification modules; inputting the real-time detection data of the reference modules into the temporary verification model to obtain the verification prediction data of the verification modules; calculating the verification deviation between the verification prediction data and the current detection data of the verification modules; when the statistical value of the verification deviation exceeds a preset consistency threshold, determining that the overall data credibility of the collaborative modules has decreased, suspending the execution of the compensation process based on the Pearson correlation coefficient, and triggering a diagnostic alarm.

[0019] By adopting the above technical solution, the control system iteratively selects verification and reference modules, establishes a temporary verification model for cross-validation, and achieves dynamic monitoring of the overall reliability of the collaborative modules. When the verification deviation exceeds the preset consistency threshold, the compensation process is promptly paused and an alarm is triggered to avoid using unreliable collaborative data for compensation. This multi-stage cross-validation mechanism can promptly detect abnormal performance of the collaborative module group, prevent the expansion and accumulation of compensation errors, and ensure the reliability of compensation.

[0020] In a second aspect, embodiments of this application provide a control system comprising: one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, the computer program code including computer instructions, wherein the one or more processors invoke the computer instructions to cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a control system, cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a control system, cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the control system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0025] 1. By adopting the above technical solution, the control system acquires the performance and timing parameters of each gas detection module, establishes response characteristic curves, and calculates the cumulative working time to determine the performance degradation index of each gas detection module, thus achieving comprehensive monitoring of the gas detection module status. The control system marks the gas detection module with the highest performance degradation index as the module to be compensated, and marks the other gas detection modules as cooperative modules. It selects at least two cooperative modules with the highest correlation coefficients as compensation benchmark modules to achieve data compensation for the performance degradation modules. When the data deviation rate between the theoretical detection data and the current detection data of the module to be compensated exceeds a preset deviation threshold, it is promptly determined that the module to be compensated needs to be replaced, effectively avoiding safety hazards caused by inaccurate detection and improving the detection reliability of the modular intelligent terminal.

[0026] 2. By adopting the above technical solution, the control system acquires the time-aligned historical data sequences of the module to be compensated and each coordinating module, calculates the Pearson correlation coefficient to construct an initial correlation matrix, and calculates the coordinating weight coefficients based on the remaining service life of each coordinating module to optimize the initial correlation matrix, thus achieving a scientific selection of the compensation benchmark module. This mechanism, based on a dual consideration of historical data correlation and the lifespan of the gas detection module, avoids selecting a gas detection module whose lifespan is about to expire as the compensation benchmark, improving the reliability and continuity of data compensation.

[0027] 3. By adopting the above technical solution, the control system iteratively selects verification and reference modules, establishes a temporary verification model for cross-validation, and achieves dynamic monitoring of the overall reliability of the collaborative modules. When the verification deviation exceeds the preset consistency threshold, the compensation process is promptly suspended and an alarm is triggered to avoid using unreliable collaborative data for compensation. This multi-stage cross-validation mechanism can promptly detect abnormal performance of the collaborative module group, prevent the expansion and accumulation of compensation errors, and ensure the reliability of compensation. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating a control method for a modular intelligent terminal used for well inspection in an embodiment of this application.

[0029] Figure 2 This is another flowchart illustrating the control method of the modular intelligent terminal for well inspection in this application embodiment;

[0030] Figure 3 This is a schematic diagram of the physical device structure of a control system in an embodiment of this application. Detailed Implementation

[0031] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0032] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0033] The modular smart terminal in this application embodiment is described below. The modular smart terminal consists of a core device and peripheral interface devices, as detailed below:

[0034] Core equipment: 1 modular smart terminal (integrating core functional modules);

[0035] External docking equipment: 1 laser rangefinder, 1 voltage detector, 1 video acquisition device, 1 live cable identification device (Radio 8000), 1 water level sensor;

[0036] Location Relationship: The laser rangefinder, temperature and humidity acquisition module, gas detection module, coordinate positioning module, compass module, interface expansion module, Bluetooth module, NFC module, and large screen display module are integrated into the smart terminal; the voltage detector and water level sensor are connected to the smart terminal through the physical interfaces reserved in the smart terminal (such as Type-C, dedicated detection interface); the video acquisition device is associated with the smart terminal through the data interface; the Radio8000 is directly connected to the smart terminal or mobile phone via Bluetooth; the smart terminal and mobile phone establish communication via Bluetooth / 4G.

[0037] Technical implementation schemes for each function:

[0038] (1) Measurement of physical parameters (length, width, elevation)

[0039] Implementation method: The smart terminal integrates a laser rangefinder. The staff aligns the laser rangefinder with the measurement point on the inner wall of the manhole / channel. The laser rangefinder emits a laser and receives the reflected signal, calculates the size data, and automatically transmits it to the terminal storage module.

[0040] (2) Measurement of environmental parameters (temperature, humidity, water level, gas)

[0041] Temperature and humidity: The smart terminal integrates a temperature and humidity sensor to collect ambient temperature and humidity data in real time and automatically upload it to the terminal storage module;

[0042] Water level: The water level sensor is connected through the physical interface reserved in the smart terminal. After the water level sensor probe contacts the water surface, it converts the water level electrical signal into a digital signal and transmits it to the terminal storage module.

[0043] Gas: The intelligent terminal integrates a gas detection module (including gas sensors for carbon monoxide, methane, oxygen, hydrogen sulfide, hydrogen, and nitrogen oxides). After the gas detection module draws in the gas in the well, the gas sensors convert the gas concentration signal into digital data and transmit it to the terminal storage module.

[0044] (3) Electrical parameters and cable identification (cable voltage, identity of live cables)

[0045] Cable voltage: The voltage detector is connected through the physical interface reserved in the smart terminal. After the voltage detector probe contacts the cable, it converts the voltage signal into digital data and transmits it to the terminal storage module.

[0046] Cable identification: When the Radio8000 is connected to a mobile phone via Bluetooth, the collected cable identification data (number, live status) is transmitted to the mobile phone via Bluetooth.

[0047] (4) Coordinate and orientation measurement

[0048] Coordinates: The smart terminal integrates a GPS / BeiDou coordinate positioning module to receive satellite signals in real time, calculate the location coordinates of the well / channel, and automatically store them in the terminal storage module;

[0049] Orientation: The smart terminal integrates a compass module, which determines the direction through geomagnetic induction, and the data is displayed on a large screen and stored synchronously.

[0050] (5) Video recording and data transmission

[0051] Video recording: The video capture device captures on-site images and generates large-capacity video data;

[0052] Data transmission:

[0053] ① Small data (size, temperature and humidity, gas concentration, voltage, coordinates, orientation): After the terminal processing module integrates the data, it is transmitted to the mobile phone via Bluetooth;

[0054] ② Video Big Data: The video capture device transmits data directly to the mobile phone via the 4G network, avoiding the pressure on terminal storage;

[0055] ③Radio 8000 data: Transmitted directly to mobile phone via Bluetooth.

[0056] (6) Data processing and display

[0057] The terminal storage module stores the raw data of all connected devices, and the terminal processing module performs data format standardization and outlier detection (such as gas concentration exceeding the standard warning).

[0058] The smart terminal is equipped with a large-screen display module, which displays various measurement data in real time, making it convenient for staff to view on-site.

[0059] (7) Additional functions (NFC, interface expansion)

[0060] NFC Function: Smart terminals integrate an NFC module, which can read device tags and personnel identification information through near-field communication to assist in data association;

[0061] Interface expansion: The smart terminal has reserved multiple general interfaces (such as Type-C and RS485) to be compatible with other testing equipment and improve expandability.

[0062] The following describes the process of the method provided in this implementation. Please refer to [link / reference]. Figure 1 This is a flowchart illustrating a control method for a modular intelligent terminal used for well inspection in an embodiment of this application.

[0063] S101. Obtain the performance parameters and timing parameters of each gas detection module of the smart terminal, establish the response characteristic curves corresponding to each gas detection module according to the performance parameters, and calculate the cumulative working time corresponding to each gas detection module according to the timing parameters.

[0064] Among them, the gas detection module refers to the functional module in the smart terminal used to detect the concentration of a specific gas; the performance parameters refer to various index data reflecting the detection performance of the gas detection module, including but not limited to sensitivity, range, resolution, response time, etc.; the timing parameters refer to the time-related data that records the working status of the gas detection module, including power-on time, power-off time, working duration, etc.; the response characteristic curve represents the output response change curve of the gas detection module under different concentrations of gas stimulation; and the cumulative working time represents the total actual working time of the gas detection module from when it was put into use to the current moment.

[0065] Specifically, the control system collects performance parameters of each gas detection module in real time through the system interface, including raw data such as the electrical signal strength and response delay output by the gas detection modules. Simultaneously, the control system reads the operating time records of each gas detection module to obtain timing parameters such as power-on / off timestamps. Then, the control system processes and extracts features from the collected performance parameters, using interpolation and fitting algorithms to establish a response characteristic curve for each gas detection module. This response characteristic curve reflects the dynamic response characteristics of the gas detection module under different gas concentrations. Based on the timing parameters, the control system calculates the cumulative operating time of each gas detection module.

[0066] S102. Perform deviation analysis between the response characteristic curve and the calibration reference curve to obtain the characteristic deviation value. Based on the characteristic deviation value and the cumulative working time, determine the performance degradation index of each gas detection module.

[0067] Among them, the calibration reference curve represents the standard response curve established by the gas detection module during factory calibration; the characteristic deviation value represents the degree of deviation of the response characteristic curve from the calibration reference curve; and the performance degradation index represents the quantitative indicator of the performance degradation of the gas detection module, taking into account both performance deviation and usage time.

[0068] Specifically, the control system retrieves the calibration reference curves for each gas detection module from the database. Then, it uses numerical calculation methods to extract feature points and compare the response characteristic curves with the calibration reference curves, calculating the feature deviation value reflecting the difference between the two curves. Next, based on a preset working time-performance decay mapping relationship, the control system converts the cumulative working time into a time decay coefficient. Finally, the control system weights the feature deviation value and the time decay coefficient to obtain a performance decay index that comprehensively reflects the performance status of the gas detection modules.

[0069] Optionally, under normal circumstances, deviation analysis is performed between the response characteristic curve and the calibration reference curve to obtain characteristic deviation values. Based on the characteristic deviation values ​​and the cumulative working time, the performance degradation index of each gas detection module can be determined in the following ways, which are not limited here: Extract the response values ​​of the response characteristic curve and the calibration reference curve at multiple characteristic points, calculate the difference between the response values ​​at the corresponding characteristic points, and obtain a difference sequence; perform wavelet transform on the difference sequence to extract high-frequency and low-frequency components, calculate the dynamic deviation coefficient based on the energy proportion of the high-frequency components, and calculate the static deviation coefficient based on the mean of the low-frequency components; perform a weighted sum of the dynamic deviation coefficient and the static deviation coefficient according to preset weights to obtain the characteristic deviation value; determine the time decay coefficient based on the cumulative working time and the preset working time-performance degradation mapping relationship; and multiply the characteristic deviation value and the time decay coefficient to obtain the performance degradation index.

[0070] S103. Mark the gas detection module with the highest performance degradation index as the module to be compensated, mark the other gas detection modules as cooperative modules, and calculate the correlation matrix between the module to be compensated and each cooperative module.

[0071] Among them, the module to be compensated represents the gas detection module with the most severe performance degradation that needs data compensation; the cooperating module represents other gas detection modules with better performance that can be used to assist the module to be compensated in data correction; the correlation matrix represents a two-dimensional array representing the degree of correlation between the detection data of the module to be compensated and each cooperating module.

[0072] Specifically, firstly, the control system ranks and compares the performance degradation indices of all gas detection modules, marking the module with the highest performance degradation index as the module to be compensated, and the remaining gas detection modules as cooperative modules. Then, the control system acquires historical detection data from the module to be compensated and each cooperative module, performing time-series alignment preprocessing. Next, the control system uses the Pearson correlation coefficient calculation method to calculate the correlation coefficient between the detection data of the module to be compensated and each cooperative module, ultimately constructing a complete correlation matrix to provide a basis for subsequently selecting the optimal compensation benchmark module.

[0073] Optionally, in general, the correlation matrix between the module to be compensated and each cooperating module can be calculated in the following way, without limitation: When the remaining service life of all gas detection modules is greater than the preset maintenance threshold, obtain the time-aligned historical data sequences of the module to be compensated and each cooperating module; calculate the Pearson correlation coefficient between the historical data sequence of the module to be compensated and the historical data sequences of each cooperating module to construct an initial correlation matrix; based on the initial correlation matrix and combined with the remaining service life of each cooperating module, calculate the cooperating weight coefficient; adjust the initial correlation matrix according to the cooperating weight coefficient to obtain the optimized correlation matrix.

[0074] The following is a specific example to illustrate this process. Suppose there are 5 gas detection modules (numbered AE), and their performance degradation index and remaining service life data are as follows:

[0075] Module A: Performance degradation index = 0.82, remaining service life = 180 days;

[0076] Module B: Performance degradation index = 0.45, remaining service life = 360 days;

[0077] Module C: Performance degradation index = 0.38, remaining service life = 420 days;

[0078] Module D: Performance degradation index = 0.51, remaining service life = 300 days;

[0079] Module E: Performance degradation index = 0.29, remaining service life = 480 days;

[0080] Step 1: Marking Modules: Module A has the highest performance degradation index (0.82), so it is marked as the module to be compensated; Modules B, C, D, and E are marked as collaborative modules;

[0081] Step 2: Obtain historical data and align the time series:

[0082] Assume the detection data (unit: ppm) for the most recent 5 time points are as follows:

[0083]

[0084] Table 1 Historical Data Sequence List

[0085] Step 3: Calculate the Pearson correlation coefficient to obtain the initial correlation matrix:

[0086] Correlation coefficients between module A to be compensated and each collaborative module:

[0087] AB: 0.95;

[0088] AC: 0.92;

[0089] AD: 0.98;

[0090] AE: 0.93;

[0091] Step 4: Calculate the collaborative weighting coefficient based on the remaining useful life:

[0092] Module B: 360 / 480 = 0.75;

[0093] Module C: 420 / 480 = 0.88;

[0094] Module D: 300 / 480 = 0.63;

[0095] Module E: 480 / 480 = 1.00;

[0096] Step 5: Obtain the final weighted correlation matrix.

[0097] AB: 0.95 × 0.75 = 0.71;

[0098] AC: 0.92 × 0.88 = 0.81;

[0099] AD: 0.98 × 0.63 = 0.62;

[0100] AE: 0.93 × 1.00 = 0.93;

[0101] The final results show that:

[0102] Although module E did not have the highest original correlation with A (0.93 < 0.98), it had the highest weighted correlation (0.93) due to its longest remaining lifetime.

[0103] Although module D has the highest original correlation with A (0.98), its weighted correlation is the lowest (0.62) due to its short remaining lifetime.

[0104] S104. Select at least two collaborative modules with the highest correlation coefficient from the correlation matrix as compensation benchmark modules, obtain the real-time detection data of the compensation benchmark modules, and calculate the theoretical detection data of the module to be compensated based on the pre-established gas concentration correlation model.

[0105] Among them, the compensation benchmark module represents the collaborative module with the strongest correlation to the detection data of the module to be compensated and with good performance; the correlation coefficient represents a statistical indicator used to measure the consistency of the data change trends of the two gas detection modules; the real-time detection data represents the gas concentration data collected by the compensation benchmark module at the current moment; the gas concentration correlation model represents a mathematical model describing the correspondence between the gas concentrations of the compensation benchmark module and the module to be compensated; and the theoretical detection data represents the detection data that the module to be compensated should have, calculated according to the gas concentration correlation model.

[0106] Specifically, the control system selects at least two coordinating modules with the highest correlation coefficients to the module to be compensated from the correlation matrix and sets them as compensation benchmark modules. Then, the control system collects real-time detection data from these compensation benchmark modules through the system interface. Next, the control system calls a pre-trained gas concentration correlation model using machine learning methods, which establishes a mapping relationship between the detection data of the compensation benchmark modules and the detection data of the module to be compensated. Finally, the control system inputs the real-time detection data of the compensation benchmark modules into the gas concentration correlation model to calculate the theoretical detection data of the module to be compensated under the current operating conditions.

[0107] Optionally, under normal circumstances, obtaining real-time detection data from the compensation benchmark module and calculating theoretical detection data for the module to be compensated based on a pre-established gas concentration correlation model can be achieved in the following ways, without limitation: When the remaining service life of all gas detection modules is greater than the preset maintenance threshold, obtain historical detection data of the compensation benchmark module and the module to be compensated under historical operating conditions; based on the historical detection data of the compensation benchmark module and the module to be compensated, train and construct a gas concentration correlation model with the detection data of the compensation benchmark module as input and the detection data of the module to be compensated as output; input the real-time detection data of the compensation benchmark module into the gas concentration correlation model and output the theoretical detection data of the module to be compensated.

[0108] The following is a specific example to illustrate this process, continuing the example scenario from step S103, to obtain the weighted correlation matrix result:

[0109] AB: 0.71;

[0110] AC: 0.81;

[0111] AD: 0.62;

[0112] AE: 0.93;

[0113] Step 1: Select the compensation benchmark modules: Select the two modules with the highest correlation coefficients as the compensation benchmark modules: Module E (correlation coefficient 0.93) and Module C (correlation coefficient 0.81).

[0114] Step 2: Obtain historical test data of the compensation benchmark module and the module to be compensated under historical operating conditions:

[0115] Suppose we obtain historical data (unit: ppm) for the past 10 time points:

[0116]

[0117] Table 2 Historical Training Data

[0118] Step 3: Train a gas concentration correlation model based on historical detection data of the compensation benchmark module and historical detection data of the module to be compensated: Use machine learning methods (such as multiple linear regression) to build a model. Assume that the established model is A=α×E+β×C+γ. The parameters obtained through training are: α=0.8, β=0.4, γ=3.2, that is, the theoretical value of the module to be compensated A = 0.8×the value of the compensation benchmark module E + 0.4×the value of the compensation benchmark module C + 3.2;

[0119] Step 4: Calculate the theoretical detection data of the module to be compensated based on the real-time detection data of the compensation benchmark module: Assume that the real-time detection data obtained at the current moment is: compensation benchmark module E: 48ppm, compensation benchmark module C: 47ppm;

[0120] Step 5: Calculate the theoretical test data of the module to be compensated: Theoretical test data = 0.8×48 + 0.4×47 + 3.2 = 60.4ppm.

[0121] S105. Compare and analyze the theoretical test data of the module to be compensated with the current test data of the module to be compensated, and calculate the data deviation rate.

[0122] Among them, the current detection data represents the actual detection data output by the module to be compensated; the comparative analysis represents the degree of difference between the two sets of data through numerical calculation methods; and the data deviation rate represents the percentage of relative error between the current detection data of the module to be compensated and the theoretical detection data.

[0123] Specifically, firstly, the control system collects the current detection data of the module to be compensated through the system interface. Then, the control system compares the collected current detection data with the calculated theoretical detection data, calculating the absolute difference between the two sets of data at each sampling point. Next, based on a preset deviation rate calculation formula and using the theoretical detection data as a benchmark, the control system calculates the relative percentage deviation of the current detection data, obtaining a data deviation rate index reflecting the detection accuracy of the module to be compensated.

[0124] The following is a specific example to illustrate this process. Continuing from the example scenario in step S104, the theoretical detection data of the module to be compensated, A, is 60.4 ppm. Assuming that the current detection data of the module to be compensated, A, is 52.5 ppm, calculate the data deviation rate:

[0125] Data deviation rate = (|theoretical test data - current test data| ÷ theoretical test data) × 100% = (7.9 ÷ 60.4) × 100% = 13.08%;

[0126] To illustrate this process more comprehensively, let's look at a comparison of data over consecutive time periods:

[0127]

[0128] Table 3 Data Deviation Rate Table

[0129] Analysis results explanation:

[0130] 1. The current detection data of the module to be compensated, A, is consistently lower than the theoretical detection data;

[0131] 2. The data deviation rate is stable at around 13%, indicating that the performance degradation is relatively serious;

[0132] 3. The deviation trend is relatively stable, indicating that the attenuation is relatively stable.

[0133] S106. When the data deviation rate exceeds the preset deviation threshold, it is determined that the module to be compensated needs to be replaced.

[0134] The preset deviation threshold represents the upper limit of the maximum allowable data deviation rate.

[0135] Specifically, the control system compares the calculated data deviation rate with the preset deviation threshold. When the data deviation rate exceeds the preset deviation threshold, it indicates that the performance of the module to be compensated has been severely degraded and the reliability of the detection results is low. The control system will trigger a replacement alarm signal to prompt the maintenance personnel to replace the module to be compensated in a timely manner.

[0136] By adopting the above technical solution, the control system acquires the performance and timing parameters of each gas detection module, establishes response characteristic curves, and calculates the cumulative working time to determine the performance degradation index of each gas detection module, thus achieving comprehensive monitoring of the gas detection module status. The control system marks the gas detection module with the highest performance degradation index as the module to be compensated, and the other gas detection modules as collaborative modules. It selects at least two collaborative modules with the highest correlation coefficients as compensation benchmark modules to achieve data compensation for the performance degradation modules. When the data deviation rate between the theoretical detection data and the current detection data of the module to be compensated exceeds a preset deviation threshold, it promptly determines that the module to be compensated needs to be replaced, effectively avoiding safety hazards caused by inaccurate detection and improving the detection reliability of the modular intelligent terminal.

[0137] The following provides a more detailed description of the process of the method provided in this implementation. Please refer to [link / reference]. Figure 2 This is another flowchart illustrating the control method of the modular intelligent terminal for well inspection in this application.

[0138] S201. Obtain the performance parameters and timing parameters of each gas detection module in the smart terminal, establish the response characteristic curves corresponding to each gas detection module based on the performance parameters, and calculate the cumulative working time corresponding to each gas detection module based on the timing parameters.

[0139] For details, please refer to step S101, which will not be repeated here.

[0140] S202. Perform deviation analysis between the response characteristic curve and the calibration reference curve to obtain the characteristic deviation value. Based on the characteristic deviation value and the cumulative working time, determine the performance degradation index of each gas detection module.

[0141] For details, please refer to step S102, which will not be repeated here.

[0142] S203. Based on the performance degradation index, predict the remaining service life of each gas detection module.

[0143] Among them, remaining service life represents the remaining time from the current moment until the gas detection module's performance no longer meets the usage requirements; prediction represents an estimate of future trends based on historical data and the current state.

[0144] Specifically, the control system loads a pre-trained lifespan prediction model, which is trained using a large amount of historical data and reflects the mapping relationship between the performance degradation index and the remaining service life. Then, the control system inputs the current performance degradation index of each gas detection module into the lifespan prediction model to obtain the expected remaining service life of each gas detection module. During the prediction process, the control system also considers influencing factors such as ambient temperature and usage frequency to correct the prediction results and improve accuracy.

[0145] S204. Filter modules whose remaining service life is lower than the preset maintenance threshold, and determine the maintenance priority for the modules to be maintained based on their remaining service life.

[0146] Among them, the preset maintenance threshold represents the lower limit of the remaining service life that triggers the maintenance warning; the module to be maintained represents the gas detection module whose remaining service life has fallen below the preset maintenance threshold and needs maintenance; and the maintenance priority represents the order of urgency of maintenance for different modules to be maintained.

[0147] Specifically, the control system compares the remaining service life of each gas detection module with a preset maintenance threshold, selecting those with remaining service life below the threshold as modules to be maintained. Then, based on a priority calculation model, the control system comprehensively considers multiple factors such as remaining service life, module importance, and the hazard level of the detected gas to calculate a maintenance priority score for each module. Finally, the control system sorts the modules according to their priority scores to determine the final maintenance priority sequence.

[0148] S205. Generate a module maintenance plan that includes suggested replacement time windows based on maintenance priorities.

[0149] Among them, the recommended replacement time window indicates the optimal time range for module replacement; the module maintenance plan indicates the system maintenance schedule that includes information such as maintenance objects, maintenance time, and maintenance content.

[0150] Specifically, the control system determines the maintenance sequence of each module based on the maintenance priority sequence, and sets an appropriate recommended replacement time window for each module (it needs to consider the remaining service life of the gas detection module to avoid replacing it before it fails, and at the same time, it needs to reserve enough operation time to ensure that the maintenance work can be completed smoothly).

[0151] S206. Mark the gas detection module with the highest performance degradation index as the module to be compensated, and mark the other gas detection modules as cooperative modules.

[0152] For details, please refer to step S103, which will not be repeated here.

[0153] S207. From the collaborative modules, iteratively select at least one verification module and the remaining reference modules.

[0154] Among them, the verification module represents the test module used to verify the reliability of the collaborative module's group data; the reference module represents the benchmark module used to predict the verification module's data; and the iterative selection means cyclically changing different modules as verification modules according to preset rules.

[0155] Specifically, the control system selects a collaborative module with good performance and high data stability from all collaborative modules as the initial verification module, based on the module selection strategy (the specific rules and methods for selecting verification and reference modules). The remaining collaborative modules are marked as the initial reference modules. The control system periodically replaces different collaborative modules as verification modules according to a preset iteration cycle to achieve rotating verification of all collaborative modules. During the selection process, the control system considers factors such as the module's performance status and historical reliability to ensure that the selected verification module is sufficiently representative.

[0156] S208. Based on the historical data of the reference module and the historical data of the verification module, train and construct a temporary verification model for predicting the detection data of the verification module.

[0157] Among them, historical data represents the sequence of detection data collected by the module over a period of time in the past; the temporary verification model represents the mathematical model used to establish the mapping relationship between the reference module data and the verification module data.

[0158] Specifically, first, the control system extracts historical data from the database for the reference module and the verification module, and performs preprocessing operations such as time alignment and outlier filtering. Then, the control system uses machine learning algorithms (such as neural networks and support vector machines) to train a temporary verification model, using the historical data from the reference module as input and the historical data from the verification module as output. During training, the control system uses methods such as cross-validation to evaluate the model's performance, ensuring that the model has good predictive capabilities.

[0159] S209. Input the real-time detection data of the reference module into the temporary verification model to obtain the verification prediction data of the verification module.

[0160] Among them, real-time detection data represents the detection data collected by the reference module at the current moment; verification prediction data represents the theoretical data of the verification module predicted by the temporary verification model.

[0161] Specifically, firstly, the control system collects real-time detection data from each reference module and performs necessary standardization preprocessing. Then, the control system inputs the processed real-time detection data from the reference modules into a trained temporary verification model. Finally, the control system runs the model to calculate and obtain the predicted results for the verification module's detection data, i.e., the verification prediction data. During the prediction process, the control system performs real-time data quality monitoring to ensure the validity of the input data.

[0162] S210. Calculate the verification deviation between the verification prediction data and the current detection data of the verification module.

[0163] Here, the current detection data represents the real-time detection value actually output by the verification module; the verification deviation represents the degree of difference between the predicted data and the actual data.

[0164] Specifically, first, the control system collects the current detection data from the verification module and aligns it with the verification prediction data in time. Then, the control system uses a preset deviation calculation method to calculate the difference between the two sets of data at various time points. Finally, the control system performs statistical analysis on these differences to obtain the verification deviation, which reflects the overall degree of deviation. During the calculation process, the control system considers the dynamic characteristics of the data and uses multiple statistical indicators to comprehensively evaluate the degree of deviation.

[0165] S211. When the statistical value of the verification deviation exceeds the preset consistency threshold, it is determined that the overall data credibility of the collaborative module has decreased, the execution of the compensation process based on the Pearson correlation coefficient is suspended, and a diagnostic alarm is triggered.

[0166] Among them, the preset consistency threshold represents the maximum allowable verification deviation; data credibility represents the reliability of the collaborative module's group data; diagnostic alarm represents the issuance of abnormal status prompts; and compensation process represents the data compensation calculation process based on the Pearson correlation coefficient.

[0167] Specifically, the control system compares the calculated verification deviation with a preset consistency threshold. When the verification deviation exceeds the preset consistency threshold, it indicates that the detection data of the collaborative module cannot be used to predict the detection data of the module to be compensated, and the control system immediately suspends the ongoing data compensation process. At the same time, the control system generates a diagnostic alarm containing information such as the abnormal time, the module involved, and the degree of deviation, and notifies relevant personnel through the system interface, SMS, and other means.

[0168] S212. Calculate the correlation matrix between the module to be compensated and each collaborative module.

[0169] For details, please refer to step S103, which will not be repeated here.

[0170] S213. Select at least two collaborative modules with the highest correlation coefficient from the correlation matrix as compensation benchmark modules, obtain the real-time detection data of the compensation benchmark modules, and calculate the theoretical detection data of the module to be compensated based on the pre-established gas concentration correlation model.

[0171] For details, please refer to step S104, which will not be repeated here.

[0172] S214. Compare and analyze the theoretical test data of the module to be compensated with the current test data of the module to be compensated, and calculate the data deviation rate.

[0173] For details, please refer to step S105, which will not be repeated here.

[0174] S215. When the data deviation rate does not exceed the preset deviation threshold, construct a real-time error mapping dataset between the theoretical detection data and the current detection data; based on the real-time error mapping dataset, train a compensation calibration model to perform dynamic compensation calibration on the subsequent detection data of the module to be compensated, and fit the nonlinear deviation relationship between the current detection data and the theoretical detection data.

[0175] Among them, the real-time error mapping dataset represents a sample set that records the correspondence between theoretical detection data and current detection data; the compensation calibration model represents a mathematical model used to correct the detection data of the module to be compensated; the dynamic compensation calibration represents a compensation correction process that is adaptively adjusted according to the characteristics of real-time data; and the nonlinear deviation relationship represents a complex correspondence between theoretical values ​​and measured values ​​that is not a simple proportion.

[0176] Specifically, the control system pairs recent theoretical detection data with current detection data to construct a real-time error mapping dataset containing input-output correspondences. The time window length of this real-time error mapping dataset is dynamically adjusted based on gas detection characteristics and system operating status, typically remaining between 30 minutes and 2 hours. Then, the control system uses deep learning algorithms (such as LSTM networks or gated recurrent units) to train a compensation calibration model, which captures temporal characteristics and nonlinear deviation patterns in the detection data. During training, the control system employs an online learning strategy, continuously updating model parameters to adapt to dynamic changes in the detection environment. After model training is complete, the control system inputs subsequent detection data from the module to be compensated into the compensation calibration model for real-time calibration, outputting deviation-corrected detection results.

[0177] S216. When the data deviation rate exceeds the preset deviation threshold, it is determined that the module to be compensated needs to be replaced.

[0178] For details, please refer to step S106, which will not be repeated here.

[0179] The control system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3 This is a schematic diagram of the physical device structure of the control system in an embodiment of this application.

[0180] It should be noted that, Figure 3 The structure of the control system shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0181] like Figure 3 As shown, the control system includes a CPU 301, which can perform various appropriate actions and processes based on a program stored in the read-only memory ROM 302 or a program loaded from the storage section 308 into the random access memory RAM 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0182] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0183] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by CPU 301, it performs the various functions defined in the present invention.

[0184] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0186] Specifically, the control system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the control method of the modular intelligent terminal for well inspection provided in the above embodiment.

[0187] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the control system described in the above embodiments; or it may exist independently and not assembled into the control system. The storage medium carries one or more computer programs that, when executed by a processor of the control system, cause the control system to implement the control method for the modular intelligent terminal for well inspection provided in the above embodiments.

[0188] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application 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. Such 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 this application.

[0189] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0190] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A control method of a modular intelligent terminal for a manhole inspection, characterized by, The method is applied to a control system and comprises the following steps: acquiring performance parameters and timing parameters of each gas detection module of an intelligent terminal, establishing a response characteristic curve corresponding to each gas detection module according to the performance parameters, and calculating a cumulative working time length corresponding to each gas detection module according to the timing parameters; performing deviation analysis on the response characteristic curve and a calibration reference curve to obtain a characteristic deviation value, determining a performance attenuation index of each gas detection module based on the characteristic deviation value and the cumulative working time length; marking a gas detection module with the highest performance attenuation index as a compensation module to be compensated, marking other gas detection modules as collaborative modules, and calculating a correlation matrix between the compensation module to be compensated and each collaborative module; selecting at least two collaborative modules with the highest correlation coefficients from the correlation matrix as compensation reference modules, acquiring real-time detection data of the compensation reference modules, and calculating theoretical detection data of the compensation module to be compensated according to a pre-established gas concentration correlation model; performing comparative analysis on the theoretical detection data of the compensation module to be compensated and current detection data of the compensation module to be compensated, and calculating a data deviation rate; and determining that the compensation module to be compensated needs to be replaced when the data deviation rate exceeds a preset deviation threshold. The deviation analysis on the response characteristic curve and the calibration reference curve to obtain the characteristic deviation value and the determination of the performance attenuation index of each gas detection module based on the characteristic deviation value and the cumulative working time length specifically include the following steps: extracting response values of the response characteristic curve and the calibration reference curve at a plurality of feature points, calculating differences between the response values of the corresponding feature points to obtain a difference sequence; performing wavelet transform on the difference sequence, extracting high-frequency components and low-frequency components, calculating a dynamic deviation coefficient according to an energy proportion of the high-frequency components, and calculating a static deviation coefficient according to a mean value of the low-frequency components; performing weighted summation on the dynamic deviation coefficient and the static deviation coefficient according to a preset weight to obtain the characteristic deviation value; determining a time attenuation coefficient based on the cumulative working time length and a preset working time length-performance attenuation mapping relationship; and performing product operation on the characteristic deviation value and the time attenuation coefficient to obtain the performance attenuation index. After the step of performing deviation analysis on the response characteristic curve and the calibration reference curve to obtain the characteristic deviation value and determining the performance attenuation index of each gas detection module based on the characteristic deviation value and the cumulative working time length, the method further comprises the following steps: predicting a remaining service life corresponding to each gas detection module based on the performance attenuation index; screening a module to be maintained with a remaining service life lower than a preset maintenance threshold, and determining a maintenance priority of the module to be maintained in combination with the remaining service life; and generating a module maintenance plan including a recommended replacement time window according to the maintenance priority. The method also comprises the following steps: when the data deviation rate does not exceed the preset deviation threshold, constructing real-time error mapping data set of the theoretical detection data and the current detection data; and training a compensation calibration model based on the real-time error mapping data set, so as to dynamically compensate and calibrate subsequent detection data of the to-be-compensated module, wherein the compensation calibration model fits a nonlinear deviation relationship between the current detection data and the theoretical detection data. The method also comprises the following steps: when the data deviation rate does not exceed the preset deviation threshold, constructing real-time error mapping data set of the theoretical detection data and the current detection data; and training a compensation calibration model based on the real-time error mapping data set, so as to dynamically compensate and calibrate subsequent detection data of the to-be-compensated module, wherein the compensation calibration model fits a nonlinear deviation relationship between the current detection data and the theoretical detection data.

2. The method of claim 1, wherein, The method also comprises the following steps: when the data deviation rate does not exceed the preset deviation threshold, constructing real-time error mapping data set of the theoretical detection data and the current detection data; and training a compensation calibration model based on the real-time error mapping data set, so as to dynamically compensate and calibrate subsequent detection data of the to-be-compensated module, wherein the compensation calibration model fits a nonlinear deviation relationship between the current detection data and the theoretical detection data.

3. The method of claim 1, wherein, The method also comprises the following steps: when the data deviation rate does not exceed the preset deviation threshold, constructing real-time error mapping data set of the theoretical detection data and the current detection data; and training a compensation calibration model based on the real-time error mapping data set, so as to dynamically compensate and calibrate subsequent detection data of the to-be-compensated module, wherein the compensation calibration model fits a nonlinear deviation relationship between the current detection data and the theoretical detection data.

4. A control system characterized by, The control system comprises one or more processors and a memory; the memory is coupled with the one or more processors, the memory is configured to store computer program codes, the computer program codes comprise computer instructions, the one or more processors invoke the computer instructions to enable the control system to perform the method according to any one of claims 1 to 3.

5. A computer-readable storage medium comprising instructions, characterized in that, The instructions, when running on the control system, enable the control system to perform the method according to any one of claims 1 to 3.

6. A computer program product, characterised in that, The computer program product, when running on the control system, enables the control system to perform the method according to any one of claims 1 to 3.

Images