A method, system and device for detecting and evaluating well logging optical cables based on the Internet of Things

Abstract

The present invention discloses a method, system and device for detecting and evaluating well logging optical cables based on the Internet of Things, which relates to the field of artificial intelligence technology, including real-time data collection by deploying Internet of Things sensors, combining low-power wide area network technology to achieve efficient data transmission and preprocessing, using deep learning models to accurately evaluate the health status of optical cables, automatically identifying abnormal signals with the help of unsupervised learning technology, and finally intelligently recommending maintenance strategies based on abnormal signal detection results to achieve optimal allocation of maintenance resources. The invention has significant advantages in abnormal signal identification and intelligent maintenance strategy recommendation, can significantly improve the accuracy and efficiency of optical cable detection and evaluation, and reduce maintenance costs, and has important practical value and broad application prospects.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, system and device for detecting and evaluating well logging optical cables based on the Internet of Things. Background Art

[0002] In the oil and gas industries, logging optical cables, as an important infrastructure, play a key role in transmitting underground wellbore measurement data. Their health status directly affects the safety and efficiency of underground operations. In recent years, with the rapid development of Internet of Things technology, remote monitoring and automated operation and maintenance have become possible, bringing new opportunities for the detection and evaluation of logging optical cables.

[0003] However, although the Internet of Things and artificial intelligence technologies have shown great potential in the detection and evaluation of logging optical cables, existing technologies still have some limitations. Traditional detection methods often rely on manual inspections and regular maintenance, which are not only inefficient but also prone to miss potential failures in the early stages, resulting in high maintenance costs. In particular, in the identification of abnormal signals and the assessment of health status, existing technologies often rely on supervised learning models, which require a large amount of labeled data. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a well logging optical cable detection and evaluation method, system, device and storage medium based on the Internet of Things to solve the problems of real-time monitoring and intelligent evaluation of the health status of the well logging optical cable, and optimization of maintenance strategy formulation.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for detecting and evaluating a well logging optical cable based on the Internet of Things, which includes deploying an Internet of Things sensor to collect sensor data in real time;

[0008] Use low-power wide-area network technology to upload sensor data to the IoT platform and pre-process it;

[0009] Build a deep learning model to output the health status assessment results of the optical cable signal;

[0010] Using unsupervised learning technology, we can identify abnormal signals that are beyond the normal range based on the health status assessment results of the optical cable signal;

[0011] Based on the abnormal signal detection results, intelligent maintenance strategies are recommended to optimize maintenance resource allocation.

[0012] As a preferred solution of the IoT-based logging optical cable detection and evaluation method described in the present invention, the sensors include temperature sensors, pressure sensors, vibration sensors and distributed optical fiber sensors; the sensor data includes temperature, pressure, vibration and optical fiber status information.

[0013] As a preferred solution of the IoT-based logging optical cable detection and evaluation method of the present invention, the following steps are included: using low-power wide area network technology to upload sensor data to the IoT platform and pre-processing it:

[0014] The data collected by the sensor is encapsulated into data packets using a custom protocol. Each data packet contains the sensor ID, collection timestamp, data type, and value.

[0015] Use LoRaWAN specification to transmit data to IoT platform;

[0016] The IoT platform receives data packets from the sensor network through the LoRa gateway, converts them into IP packets and parses them;

[0017] The parsed data packets are cleaned, denoised, fused, compressed and standardized.

[0018] As a preferred solution of the IoT-based well logging optical cable detection and evaluation method of the present invention, building a deep learning model and outputting the health status evaluation result of the optical cable signal includes the following steps:

[0019] The processed data set is divided into training set, validation set and test set; the long short-term memory network is selected as the model architecture to identify abnormal patterns in optical cable signals; the mean square error is used as the loss function to train the training set in the model; the validation set is input into the loss function to evaluate the performance of the model; the final performance of the model is tested by the test set; the preprocessed real-time data is input into the trained model, and the health status evaluation result of the output signal is expressed as:

[0020]

[0021] Where A(x) represents the comprehensive evaluation index of the health status of the optical cable, n represents the total number of data points, represents the average value of sensor data, x i represents the normalized data point, G i represents the Gaussian smoothing value of the corresponding data point, ΔM i and Δm i They represent the changes of local maximum and minimum values ​​respectively.

[0022] As a preferred solution of the well logging optical cable detection and evaluation method based on the Internet of Things described in the present invention, the following steps are included: using unsupervised learning technology, according to the health status evaluation results of the optical cable signal, identifying abnormal signals beyond the normal range:

[0023] Construct an autoencoder network consisting of an encoder and a decoder; use the health status assessment results of the optical cable signal under normal operating conditions as training data to train the autoencoder; after the model training is completed, input the preprocessed real-time data into the trained autoencoder model, and calculate the reconstruction error of the real-time data, which is expressed as:

[0024]

[0025] Among them, r i represents the reconstruction error of the i-th data point, d represents the dimension of the data point, x ij Represents the value of the original data point in the jth dimension, Represents the value of the model reconstructed data point in the jth dimension;

[0026] According to the reconstruction error distribution of historical normal data, an abnormal threshold of reconstruction error is set; for each real-time data point, if the reconstruction error is greater than the set abnormal threshold, the data point is determined to be an abnormal signal.

[0027] As a preferred solution of the IoT-based logging optical cable detection and evaluation method of the present invention, the severity of the abnormal signal is evaluated according to the identified abnormal signal, and the expression is:

[0028]

[0029] Among them, S(x) represents the severity evaluation index of abnormal signal, r i represents the reconstruction error of the ith data point, r avg represents the average value of the reconstruction error of all data points, σ r represents the standard deviation of the reconstruction error, A(x i ) represents the optical cable signal health status assessment result of the i-th data point, A avg represents the average value of the health status assessment results of all data points, σ A Represents the standard deviation of the health status assessment results.

[0030] According to the distribution of evaluation indicators of abnormal signals in historical data, a threshold of the severity of abnormal signals is set, which is compared with the calculated severity evaluation indicator of abnormal signals to distinguish the severity of abnormal signals.

[0031] As a preferred solution of the well logging optical cable detection and evaluation method based on the Internet of Things described in the present invention, wherein: based on the abnormal signal detection result, intelligently recommending maintenance strategies and optimizing maintenance resource allocation include the following steps:

[0032] When the severity assessment index of the abnormal signal is greater than the set threshold, the early warning mechanism is immediately activated; early warning information containing the timestamp, location, type, severity assessment result and preliminary fault type of the abnormal signal is generated; based on the type, location and severity of the abnormal signal, specific maintenance strategies are intelligently recommended; according to the distribution and severity of the abnormal signal, the allocation of maintenance resources is optimized.

[0033] In a second aspect, the present invention provides a well logging optical cable detection and evaluation system based on the Internet of Things, comprising:

[0034] Data acquisition module: deploy IoT sensors to collect sensor data in real time; data transmission and preprocessing module: use low-power wide area network technology to upload sensor data to the IoT platform and preprocess it; health status assessment module: build a deep learning model to output the health status assessment results of the optical cable signal; abnormal signal identification module: use unsupervised learning technology to identify abnormal signals that exceed the normal range based on the health status assessment results of the optical cable signal; intelligent decision recommendation and optimization module: based on the abnormal signal detection results, intelligently recommend maintenance strategies and optimize maintenance resource allocation.

[0035] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the Internet of Things-based logging optical cable detection and evaluation method as described in the first aspect of the present invention is implemented.

[0036] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the IoT-based logging optical cable detection and evaluation method as described in the first aspect of the present invention is implemented.

[0037] The beneficial effects of the present invention are: using IoT sensors to monitor key parameters such as temperature and pressure of logging optical cables in real time, and efficiently transmitting data to the platform for pre-processing through a low-power network to ensure that the information is complete and accurate. With the help of deep learning models, especially long short-term memory networks, the health status of optical cables can be accurately evaluated to achieve intelligent identification of abnormal signals. The application of unsupervised learning technology further enhances the anomaly detection capability through the automatic encoder network, accurately determines signal anomalies, and improves system reliability. For abnormal signals, an intelligent recommended maintenance strategy is invented to optimize resource allocation, immediately activate the early warning mechanism, generate detailed early warning information, ensure rapid response and precise maintenance, greatly improve the efficiency and economic benefits of optical cable maintenance, and improve the safety and stability of the logging optical cable system as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0039] Figure 1 This is a flow chart of the well logging optical cable detection and evaluation method based on the Internet of Things in Example 1.

[0040] Figure 2 This is a module diagram of the well logging optical cable detection and evaluation method based on the Internet of Things in Example 1. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a method for detecting and evaluating a well logging optical cable based on the Internet of Things, comprising the following steps:

[0045] S1, sensors include temperature sensors, pressure sensors, vibration sensors and distributed optical fiber sensors;

[0046] Sensor data includes temperature, pressure, vibration, and fiber status information.

[0047] Furthermore, the optimization algorithm is used to design the sensor network layout, and the expression of the objective function is:

[0048]

[0049] Where x represents the sensor layout vector, ΔTi represents the temperature of the i-th data point, ΔPi represents the pressure of the i-th data point, ΔVi represents the vibration change of the i-th data point, N represents the total number of data monitoring points, and L total Represents the total length of the sensor network, L max represents the maximum length of the well, β represents the weight coefficient of balanced monitoring accuracy, and γ represents the weight coefficient of network cost. The objective function maximizes the monitoring accuracy while minimizing the network cost.

[0050] It should be noted that by deploying IoT sensors to collect sensor data in real time, comprehensive monitoring of temperature, pressure, vibration and optical fiber status information in the logging environment is achieved, thereby ensuring timely response to the health of the optical cable and effectively improving the safety and reliability of the optical cable system.

[0051] S2, using low power wide area network technology, uploading sensor data to the IoT platform and preprocessing it includes the following steps:

[0052] The data collected by the sensor is encapsulated into data packets using a custom protocol. Each data packet contains the sensor ID, acquisition timestamp, data type (such as temperature, pressure, vibration) and value.

[0053] Use LoRaWAN specification to transmit data to IoT platform;

[0054] The IoT platform receives data packets from the sensor network through the LoRa gateway, converts them into IP data packets and performs parsing, including timestamp correction and data type identification;

[0055] The parsed data packets are processed by data cleaning (removing invalid or outliers), noise removal, data fusion (integration of multi-sensor data), data compression (reducing data volume) and standardization (unifying data format).

[0056] It should be noted that the use of low-power wide area network technology to upload data and perform preprocessing enables efficient transmission and processing of sensor data, reduces energy consumption and ensures data quality, thus laying a solid foundation for the accurate evaluation of subsequent deep learning models.

[0057] S3. Constructing a deep learning model to output the health status assessment results of the optical cable signal includes the following steps:

[0058] The processed data set is divided into 70% (training set), 15% (validation set), and 15% (test set).

[0059] Long Short-Term Memory (LSTM) network was selected as the model architecture to identify abnormal patterns in optical cable signals.

[0060] The mean square error (MSE) is used as the loss function to train the training set in the model.

[0061] The validation set is input into the loss function to evaluate the performance of the model.

[0062] The final performance of the model is tested using the test set.

[0063] The preprocessed real-time data is input into the trained model, and the health status evaluation result of the output signal is expressed as:

[0064]

[0065] Where A(x) represents the comprehensive evaluation index of the health status of the optical cable, n represents the total number of data points transmitted, represents the average value of sensor data, x i represents the normalized data point, G i represents the Gaussian smoothing value of the corresponding data point, ΔM i and Δm i They represent the changes in the local maximum and minimum values, respectively, reflecting the sudden change of the signal.

[0066] It should be noted that building a deep learning model and outputting the optical cable signal health status assessment results, using the long short-term memory network to identify abnormal patterns, not only improves the accuracy of anomaly detection, but also quantifies the health status of the optical cable through specific evaluation indicators, providing a scientific basis for maintenance decisions.

[0067] S4. Using unsupervised learning technology, based on the health status assessment results of the optical cable signal, identifying abnormal signals beyond the normal range includes the following steps:

[0068] Construct an autoencoder network consisting of an encoder and a decoder; use the health status assessment results of the optical cable signal under normal operating conditions as training data to train the autoencoder; after the model training is completed, input the preprocessed real-time data into the trained autoencoder model, and calculate the reconstruction error of the real-time data, which is expressed as:

[0069]

[0070] Among them, r i represents the reconstruction error of the i-th data point, d represents the dimension of the data point, x ij Represents the value of the original data point in the jth dimension, Represents the value of the model reconstructed data point in the jth dimension;

[0071] According to the reconstruction error distribution of historical normal data, an abnormal threshold of reconstruction error is set; for each real-time data point, if the reconstruction error is greater than the set abnormal threshold, the data point is determined to be an abnormal signal.

[0072] Furthermore, the abnormal threshold of the reconstruction error is defined as T. If the reconstruction error is greater than T, the data point is determined to be an abnormal signal. If the reconstruction error is less than or equal to T, the data point is determined to be a normal signal.

[0073] It should be noted that the use of unsupervised learning techniques to identify abnormal signals, combined with an autoencoder network, can effectively learn and distinguish abnormal signals from normal operating modes, further improving the sensitivity and specificity of detection and ensuring early warning of potential faults.

[0074] According to the identified abnormal signal, the severity of the abnormal signal is evaluated, and the expression is:

[0075]

[0076] Among them, S(x) represents the severity evaluation index of abnormal signal, r i represents the reconstruction error of the i-th data point, r abg represents the average value of the reconstruction error of all data points, σ r represents the standard deviation of the reconstruction error, A(x i ) represents the optical cable signal health status assessment result of the i-th data point, A avg represents the average value of the health status assessment results of all data points, σ A Represents the standard deviation of the health status assessment results.

[0077] According to the distribution of evaluation indicators of abnormal signals in historical data, a threshold of the severity of abnormal signals is set, which is compared with the calculated severity evaluation indicator of abnormal signals to distinguish the severity of abnormal signals.

[0078] Furthermore, the threshold of the severity of the abnormal signal is set to A, and the severity of the abnormal signal is divided as follows:

[0079] When it is less than or equal to the 50th percentile, it indicates a slight abnormality;

[0080] When A is greater than the 50th percentile but less than or equal to the 95th percentile, it indicates moderate abnormality;

[0081] When A is greater than the 95th percentile, it indicates a serious abnormality.

[0082] S5. Based on the abnormal signal detection results, intelligently recommend maintenance strategies and optimize maintenance resource allocation, including the following steps:

[0083] When the severity assessment index of the abnormal signal is greater than the set threshold, the early warning mechanism is immediately activated; early warning information containing the timestamp, location, type, severity assessment result and preliminary fault type of the abnormal signal is generated; based on the type, location and severity of the abnormal signal, specific maintenance strategies are intelligently recommended, including inspection frequency, maintenance priority and spare parts demand forecast; according to the distribution and severity of the abnormal signal, the allocation of maintenance resources is optimized to ensure that abnormalities in key locations are given priority and maintenance efficiency is improved.

[0084] Furthermore, corresponding measures are taken according to the severity of the abnormal signal, as follows:

[0085] If it is a minor abnormality, record and monitor it, and increase the monitoring frequency, but no immediate action is required;

[0086] When it is a moderate anomaly, initiate a preliminary investigation to check the physical condition of the optical cable and the surrounding environment and assess whether maintenance or repair is needed;

[0087] When a serious abnormality occurs, respond immediately and conduct in-depth technical diagnosis, which may require emergency repair or replacement of damaged parts. At the same time, notify relevant departments to ensure that safety measures are in place.

[0088] It should be noted that by intelligently recommending maintenance strategies and optimizing maintenance resource allocation, dynamic maintenance planning based on abnormal signal detection results is achieved, which reduces unnecessary maintenance costs, improves maintenance efficiency, and ensures the continuous and stable operation of the optical cable system.

[0089] The present embodiment also provides a well logging optical cable detection and evaluation system based on the Internet of Things, including a data acquisition module: deploying Internet of Things sensors to collect sensor data in real time; a data transmission and preprocessing module: using low-power wide area network technology to upload sensor data to the Internet of Things platform and preprocess it; a health status evaluation module: building a deep learning model to output the health status evaluation results of the optical cable signal; an abnormal signal recognition module: using unsupervised learning technology to identify abnormal signals beyond the normal range based on the health status evaluation results of the optical cable signal; an intelligent decision recommendation and optimization module: based on the abnormal signal detection results, intelligently recommend maintenance strategies and optimize maintenance resource allocation.

[0090] This embodiment also provides a computer device, which is suitable for the case of the well logging optical cable detection and evaluation method based on the Internet of Things, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the well logging optical cable detection and evaluation method based on the Internet of Things proposed in the above embodiment.

[0091] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0092] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing the detection and evaluation of well logging optical cables based on the Internet of Things proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0093] In summary, the present invention uses IoT sensors to monitor key parameters such as temperature and pressure of logging optical cables in real time, and efficiently transmits data to the platform for pre-processing through a low-power network to ensure that the information is complete and accurate. With the help of deep learning models, especially long short-term memory networks, the health status of optical cables can be accurately evaluated, and intelligent identification of abnormal signals can be achieved. The application of unsupervised learning technology further enhances the anomaly detection capability through the automatic encoder network, accurately determines signal anomalies, and improves system reliability. For abnormal signals, an intelligent maintenance strategy is invented to optimize resource allocation, immediately start the early warning mechanism, generate detailed early warning information, ensure rapid response and precise maintenance, greatly improve the efficiency and economic benefits of optical cable maintenance, and improve the safety and stability of the logging optical cable system as a whole.

[0094] Example 2

[0095] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of the well logging optical cable detection and evaluation method based on the Internet of Things is provided.

[0096] In order to verify the innovation and advantages of the intelligent logging optical cable monitoring and maintenance system, a comprehensive experiment was designed to quantify the effectiveness of different monitoring schemes on optical cable health status assessment and abnormal signal detection. The experiment selected two deep wells located in a complex geological environment as research objects, with depths of 3,000 meters and 4,000 meters respectively, each equipped with a monitoring network consisting of temperature sensors, pressure sensors, vibration sensors and distributed optical fiber sensors. At the same time, low-power wide area network technology was used for data transmission, while deep learning models and unsupervised learning techniques were used to evaluate the health status of optical cables and identify abnormal signals.

[0097] During the experiment, the sensor network ran continuously for 30 days and collected a large amount of temperature, pressure, vibration and fiber status information, as shown in Table 1:

[0098] Table 1 Experimental record table

[0099]

[0100] By analyzing the tabular data, the intelligent logging optical cable monitoring and maintenance system is significantly superior to the traditional monitoring scheme in many indicators. The reduction in temperature change (ΔT), pressure change (ΔP) and vibration change (ΔV) indicates that the intelligent scheme can capture the change of the optical cable state more finely, thereby improving the monitoring accuracy (J). In Well 1 and Well 2, the monitoring accuracy of the intelligent scheme reached 0.9 and 0.85 respectively, which is significantly higher than the 0.7 and 0.65 of the traditional scheme, reflecting its advantage in monitoring accuracy.

[0101] The anomaly detection rate is a key indicator to measure the system's ability to identify abnormal signals. The intelligent solution achieved a detection rate of 90% and 88% in Well 1 and Well 2, respectively, while the traditional solution was only 65% ​​and 60%, indicating that the intelligent solution can more effectively identify abnormal signals beyond the normal range.

[0102] In terms of maintenance response time, the intelligent solution showed a faster response speed, with an average response time of 3.5 hours, while the traditional solution averaged 13 hours. This shows that the intelligent solution can activate the early warning mechanism in a timely manner, optimize the allocation of maintenance resources, and ensure that abnormalities in key locations are handled with priority, thereby significantly improving maintenance efficiency.

[0103] In summary, the intelligent logging optical cable monitoring and maintenance system has demonstrated superior performance in monitoring accuracy, anomaly detection rate and maintenance response time, reflecting its significant advantages in innovation and practicality, and providing a more intelligent, efficient and reliable solution for optical cable maintenance.

[0104] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting and evaluating well logging optical cables based on the Internet of Things, characterized in that: include, Deploy IoT sensors to collect sensor data in real time; Use low-power wide-area network technology to upload sensor data to the IoT platform and pre-process it; A deep learning model is constructed, and the processed data set is divided into training set, validation set and test set. The long short-term memory network is selected as the model architecture to identify abnormal patterns in optical cable signals. The mean square error is used as the loss function to train the training set in the model. The validation set is input into the loss function to evaluate the performance of the model. The final performance of the model is tested by the test set. The preprocessed real-time data is input into the trained model, and the health status evaluation result of the output signal is expressed as: Where A(x) represents the comprehensive evaluation index of the health status of the optical cable, n represents the total number of data points, represents the average value of sensor data, x i represents the normalized data point, G i represents the Gaussian smoothing value of the corresponding data point, ΔM i and Δm i Respectively represent the changes of local maximum and minimum values; Using unsupervised learning technology, an autoencoder network consisting of an encoder and a decoder is constructed. The health status assessment results of the optical cable signal under normal operating conditions are used as training data to train the autoencoder. After the model training is completed, the preprocessed real-time data is input into the trained autoencoder model to calculate the reconstruction error of the real-time data. The expression is: Among them, r i represents the reconstruction error of the i-th data point, d represents the dimension of the data point, x ij Represents the value of the original data point in the jth dimension, Represents the value of the model reconstructed data point in the jth dimension; According to the reconstruction error distribution of historical normal data, an abnormal threshold of reconstruction error is set. For each real-time data point, if the reconstruction error is greater than the set abnormal threshold, the data point is determined to be an abnormal signal; Based on the abnormal signal detection results, intelligent maintenance strategies are recommended to optimize maintenance resource allocation.

2. The method for detecting and evaluating well logging optical cables based on the Internet of Things according to claim 1, characterized in that: The sensors include temperature sensors, pressure sensors, vibration sensors and distributed optical fiber sensors; The sensor data includes temperature, pressure, vibration and fiber status information.

3. The method for detecting and evaluating well logging optical cables based on the Internet of Things according to claim 1, characterized in that: Using low-power wide area network technology, uploading sensor data to the IoT platform and preprocessing it includes the following steps: The data collected by the sensor is encapsulated into data packets using a custom protocol. Each data packet contains the sensor ID, collection timestamp, data type, and value. Use LoRaWAN specification to transmit data to IoT platform; The IoT platform receives data packets from the sensor network through the LoRa gateway, converts them into IP packets and parses them; The parsed data packets are cleaned, denoised, fused, compressed and standardized.

4. The method for detecting and evaluating well logging optical cables based on the Internet of Things according to claim 3, characterized in that: According to the identified abnormal signal, the severity of the abnormal signal is evaluated, and the expression is: Among them, S(x) represents the severity evaluation index of abnormal signal, r i represents the reconstruction error of the i-th data point, r avg represents the average value of the reconstruction error of all data points, σ r represents the standard deviation of the reconstruction error, A(x i ) represents the optical cable signal health status assessment result of the i-th data point, A avg represents the average value of the health status assessment results of all data points, σ A It represents the standard deviation of the health status assessment results; According to the distribution of evaluation indicators of abnormal signals in historical data, a threshold of the severity of abnormal signals is set, which is compared with the calculated severity evaluation indicator of abnormal signals to distinguish the severity of abnormal signals.

5. The method for detecting and evaluating well logging optical cables based on the Internet of Things according to claim 4, characterized in that: Based on the abnormal signal detection results, intelligently recommend maintenance strategies and optimize maintenance resource allocation, including the following steps: When the severity evaluation index of the abnormal signal is greater than the set threshold, the early warning mechanism is immediately activated; Generate early warning information including timestamp, location, type, severity assessment result and preliminary fault type of abnormal signal; Intelligently recommend specific maintenance strategies based on the type, location and severity of abnormal signals; Optimize the allocation of maintenance resources based on the distribution and severity of abnormal signals.

6. A well logging optical cable detection and evaluation system based on the Internet of Things, based on the well logging optical cable detection and evaluation method based on the Internet of Things according to any one of claims 1 to 5, characterized in that: include, Data collection module: deploy IoT sensors and collect sensor data in real time; Data transmission and preprocessing module: uses low-power wide area network technology to upload sensor data to the IoT platform and preprocess it; Health status assessment module: builds a deep learning model and outputs the health status assessment results of the optical cable signal; Abnormal signal identification module: using unsupervised learning technology to identify abnormal signals beyond the normal range based on the health status assessment results of the optical cable signal; Intelligent decision-making recommendation and optimization module: Based on the abnormal signal detection results, intelligently recommend maintenance strategies and optimize maintenance resource allocation.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the well logging optical cable detection and evaluation method based on the Internet of Things according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the well logging optical cable detection and evaluation method based on the Internet of Things according to any one of claims 1 to 5 are implemented.

Images