Abnormal working condition identification method, device, medium, equipment and system in drilling process

Abstract

The invention relates to the field of oil drilling, in particular to a method, a device, a medium, equipment and a system for identifying abnormal working conditions in a drilling process. In order to solve the problem that an existing abnormal working condition recognition method is poor in recognition effect, the abnormal working condition recognition method in the well drilling process comprises the following steps that data in the well drilling process are collected and uploaded; the method comprises the following steps: preprocessing data in a drilling process to obtain processed data; analyzing and calculating the processed data, and extracting features of the processed data; clustering the features of the processed data, and obtaining cluster tags to which the features belong; calculating the distance between the characteristics of the processed data and the clustering label to which the data belong, and identifying abnormal points; and comparing the abnormal points with an existing fault library, and carrying out working condition abnormity identification and positioning. According to the method, data features are clustered, abnormal points in the data features are detected, the abnormal points are compared with a fault library, and the abnormal working conditions can be identified and positioned more efficiently.

Description

Technical Field

[0001] The present invention relates to the field of oil drilling, and in particular to a method, device, medium, equipment and system for identifying abnormal working conditions during drilling. Background Art

[0002] At present, the identification of abnormal working conditions during drilling is mostly based on experience, relying on the operating experience and perceptual judgment of drilling operators, and the judgment results often have problems such as subjective judgment and uncertainty. Therefore, it is necessary to seek a reliable and efficient identification method to improve the safety and efficiency of the drilling process.

[0003] Traditional machine learning and pattern recognition algorithms are mainly trained on fixed data sets. For new data, the performance of the algorithm is often generally unsatisfactory, and the algorithm parameters need to be constantly adjusted to optimize the algorithm performance.

[0004] Therefore, there is a need in the art to provide a method that can improve the effect of identifying abnormal operating conditions. Summary of the invention

[0005] The present invention aims to solve the above-mentioned prior art problem, that is, the existing abnormal operating condition identification method has poor identification effect.

[0006] In a first aspect, the present invention provides a method for identifying abnormal working conditions during drilling, comprising the following steps:

[0007] Collect and upload data during drilling;

[0008] Preprocessing the data in the drilling process to obtain processed data;

[0009] Analyzing and calculating the processed data to extract features of the processed data;

[0010] Clustering the features of the processed data and obtaining the cluster labels to which they belong;

[0011] Calculating the distance between the features of the processed data and the cluster labels to which they belong, and identifying abnormal points;

[0012] The abnormal point is compared with the existing fault library to identify and locate the abnormal working condition.

[0013] Preferably, the collecting and uploading of data during the drilling process includes:

[0014] Acquire at least one data in the drilling process through multiple sets of sensors installed on the drilling equipment;

[0015] Add timestamps to collected data;

[0016] sorting and matching the collected data according to the timestamps;

[0017] Upload the matched data in order.

[0018] Preferably, the preprocessing of the data in the drilling process includes:

[0019] The data in the drilling process are deduplicated, missing value processed, and outlier detected and processed.

[0020] Preferably, the missing value processing includes: using the previous data or the next data of the missing value to replace the missing value.

[0021] Preferably, the outlier detection and processing includes:

[0022] Calculate the average value of various data during the drilling process;

[0023] Calculate the difference between each data and the average value of the data;

[0024] Comparing the difference with a first set threshold, if the difference exceeds the first set threshold, determining that the data is an abnormal value, otherwise determining that the data is not an abnormal value;

[0025] Delete the outliers.

[0026] Preferably, analyzing and calculating the processed data to extract features of the processed data includes:

[0027] The waveform analysis method is used to analyze the amplitude of the real-time curve of the hook load and the frequency of the peaks and fluctuations in the real-time curve over a period of time;

[0028] Calculate the average, maximum, and minimum values ​​of the drill speed.

[0029] Preferably, clustering the features of the processed data and obtaining the cluster labels thereof includes:

[0030] Initialization: Select the number of clusters K, and randomly select K features of the processed data as initial cluster centers;

[0031] Assignment: for each feature of the processed data, calculate the distance between it and each cluster center, and assign the feature of the processed data to the cluster center with the closest distance;

[0032] Update: For each cluster, calculate the average value of the features of all the processed data in the cluster and use it as the new cluster center;

[0033] Repeat: Repeat the assignment and update steps until the cluster center no longer changes or a predetermined number of iterations is reached;

[0034] Result output: Output the obtained K cluster centers and the cluster labels of each feature of the processed data.

[0035] Preferably, calculating the distance between the feature of the processed data and the cluster label to which it belongs, and identifying the abnormal point, includes:

[0036] If the distance exceeds a second set threshold, the feature of the processed data is determined to be an abnormal point.

[0037] In a second aspect, the present invention provides a device for identifying abnormal working conditions during drilling, comprising:

[0038] A data acquisition unit, which is used to collect and upload data during the drilling process;

[0039] A data preprocessing unit, which is used to preprocess the data in the drilling process and obtain processed data;

[0040] A data analysis and calculation unit, which is used to analyze and calculate the processed data and extract features of the processed data;

[0041] A clustering unit, which is used to cluster the features of the processed data and obtain the cluster label to which it belongs;

[0042] An outlier identification unit, which is used to calculate the distance between the feature of the processed data and the cluster label to which it belongs, and identify the outlier;

[0043] The abnormal operating condition identification and positioning unit is used to compare the abnormal point with the existing fault library to identify and locate the abnormal operating condition.

[0044] In a third aspect, the present invention provides a storage medium storing a computer program, wherein the computer program, when executed, implements the method described in the first aspect.

[0045] In a fourth aspect, the present invention provides an electronic device, comprising: a memory and a processor communicatively connected to the memory, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0046] In a fifth aspect, the present invention provides a system for identifying abnormal operating conditions during drilling, characterized in that it includes the electronic device as described in the fourth aspect.

[0047] Through the above technical solution, the present invention has the following beneficial effects:

[0048] By extracting data features and clustering them, we can detect anomalies in the data features, compare the anomalies with the fault library, and then identify and locate abnormal conditions. When faced with new data, there is no need to adjust the algorithm parameters, and abnormal conditions can be identified and located more efficiently.

[0049] By collecting multiple data during the drilling process, we can detect whether abnormal conditions occur during the drilling process in multiple dimensions, and can more comprehensively identify and locate abnormal conditions during the drilling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the main steps of the working condition identification method during drilling;

[0051] Figure 2 It is a schematic diagram of the main steps of collecting and uploading data during the drilling process;

[0052] Figure 3 It is a schematic diagram of the main steps of outlier detection and processing;

[0053] Figure 4 It is a schematic diagram of the main steps of clustering the features of the processed data and obtaining the cluster labels to which they belong. DETAILED DESCRIPTION

[0054] The present disclosure is further described below in conjunction with the embodiments shown in the accompanying drawings.

[0055] Reference Figure 1 In a first aspect, this embodiment provides a method for identifying abnormal working conditions during drilling, the method comprising the following steps:

[0056] S1. Collect and upload data during drilling.

[0057] S2. Preprocess the data during the drilling process to obtain processed data; the preprocessing includes: removing duplicate data in the data; for missing values, using the previous data or the next data of the missing value to replace the missing value; and detecting and processing outliers on the collected data.

[0058] S3. Analyze and calculate the processed data to extract the features of the processed data.

[0059] The waveform analysis method is used to analyze the amplitude of the real-time curve of the hook load and the frequency of the peaks and fluctuations in the real-time curve over a period of time;

[0060] Calculate the average, maximum, and minimum values ​​of the drill speed.

[0061] S4. Cluster the features of the processed data and obtain the cluster label to which it belongs.

[0062] S5. Calculate the distance between the feature of the processed data and the cluster label to which it belongs, and identify the outlier. If the distance exceeds the second set threshold, the feature of the processed data is determined to be an outlier.

[0063] S6. Compare the abnormal point with the existing fault library to identify and locate the abnormal working condition.

[0064] Reference Figure 2 In a preferred embodiment, collecting and uploading data during drilling includes the following steps:

[0065] S101. Acquire at least one data of the drilling process through multiple sets of sensors installed on the drilling equipment;

[0066] S102. Add a timestamp to at least one piece of data;

[0067] S103. Sort and match the collected data according to timestamps;

[0068] S104. Upload the matched data in order.

[0069] By installing multiple sets of sensors on the drilling equipment, various data during the drilling process are obtained. Sensors include but are not limited to: high-precision downhole displacement sensors and microwave wireless temperature sensors. Since the time of each sensor is not synchronized when uploading data, it is necessary to add a timestamp to each data. After all the data is uploaded, the data is sorted according to the timestamp and the data is matched. Finally, the matched data is uploaded in order. This solves the problem of time asynchrony between the sensors.

[0070] Reference Figure 3 In a preferred embodiment, outlier detection and processing includes the following steps:

[0071] S201. Calculate the average value of various data during the drilling process;

[0072] S202. Calculate the difference between each data item and the average value of the data item;

[0073] S203. Compare the difference with the first set threshold value. If the difference exceeds the first set threshold value, the data is determined to be an abnormal value. Otherwise, the data is determined not to be an abnormal value.

[0074] S204. Delete outliers.

[0075] When the difference between a data and the average value of all data exceeds the first set threshold, it means that the data is obviously beyond the normal value range and the data is an abnormal value. Abnormal values ​​will cause deviations in the identification and positioning of abnormal conditions, so the output of abnormal values ​​can reduce the possibility of deviations in the identification and positioning of abnormal conditions.

[0076] Reference Figure 4 In a preferred embodiment, the features of the processed data are clustered and the cluster labels to which they belong are obtained, including:

[0077] S401. Initialization: Select the number of clusters K, and randomly select K processed data features as initial cluster centers.

[0078] S402. Allocation: For each feature of the processed data, calculate the distance between it and each cluster center, and allocate the feature of the processed data to the cluster center with the closest distance.

[0079] S403. Update: For each cluster, calculate the average value of the features of all processed data in the cluster and use it as the new cluster center.

[0080] S404. Repeat: Repeat steps S502 and S503 until the cluster center no longer changes or a predetermined number of iterations is reached.

[0081] S505. Result output: output the obtained K cluster centers and the cluster labels of each feature of the processed data.

[0082] In a preferred embodiment, the present invention provides a method for identifying abnormal working conditions during drilling, the method comprising the following steps:

[0083] S1. Collect and upload data during drilling.

[0084] Step S1 specifically includes:

[0085] S101. Acquire at least one data of the drilling process through multiple sets of sensors installed on the drilling equipment;

[0086] S102. Add a timestamp to the collected data;

[0087] S103. Sort and match the collected data according to timestamps;

[0088] S104. Upload the matched data in order.

[0089] S2. Preprocess the data during the drilling process to obtain processed data; the preprocessing includes: removing duplicate data in the data; for missing values, using the previous data or the next data of the missing value to replace the missing value; and detecting and processing outliers on the collected data.

[0090] The outlier detection and processing of the collected data in step S2 specifically includes:

[0091] S201. Calculate the average value of various data during the drilling process;

[0092] S202. Calculate the difference between each data item and the average value of the data item;

[0093] S203. Compare the difference with the first set threshold value. If the difference exceeds the first set threshold value, the data is determined to be an abnormal value. Otherwise, the data is determined not to be an abnormal value.

[0094] S204. Delete outliers.

[0095] S3. Analyze and calculate the processed data to extract the features of the processed data.

[0096] The waveform analysis method is used to analyze the amplitude of the real-time curve of the hook load and the frequency of the peaks and fluctuations in the real-time curve over a period of time;

[0097] Calculate the average, maximum, and minimum values ​​of the drill speed.

[0098] S4. Cluster the features of the processed data and obtain the cluster label to which it belongs.

[0099] In step S4, a K-means clustering algorithm is used, which specifically includes:

[0100] S401. Initialization: Select the number of clusters K, and randomly select K processed data features as initial cluster centers.

[0101] S402. Allocation: For each feature of the processed data, calculate the distance between it and each cluster center, and allocate the feature of the processed data to the cluster center with the closest distance.

[0102] S403. Update: For each cluster, calculate the average value of the features of all processed data in the cluster and use it as the new cluster center.

[0103] S404. Repeat: Repeat steps S502 and S503 until the cluster center no longer changes or a predetermined number of iterations is reached.

[0104] S5. Calculate the distance between the feature of the processed data and the cluster label to which it belongs, and identify the outlier. If the distance exceeds the second set threshold, the feature of the processed data is determined to be an outlier.

[0105] S6. Compare the abnormal point with the existing fault library to identify and locate the abnormal working condition.

[0106] Multiple sensors are installed on the drilling equipment to collect various data during the drilling process, so as to ensure that abnormal conditions during the drilling process can be fully identified. By adding timestamps to the data, the problem of time asynchrony between sensors is solved, which is conducive to improving the efficiency of identifying abnormal conditions.

[0107] The collected data is preprocessed to remove duplicate data and outliers, and the missing value is replaced with the previous or next data of the missing value, so as to standardize and normalize the data, which is conducive to improving the accuracy of identifying abnormal working conditions.

[0108] The features of the processed data are clustered, and the abnormal points are identified by calculating the distance between the features of the processed data and their cluster labels. The abnormal points are compared with the existing fault library to identify and locate the abnormal conditions. The abnormal conditions in the drilling process can be identified quickly and accurately. During the identification process, there is no need to adjust the parameters of the algorithm, which can improve the identification efficiency.

[0109] In a second aspect, this embodiment provides a device for identifying abnormal working conditions during drilling, comprising:

[0110] A data acquisition unit, which is used to collect and upload data during the drilling process;

[0111] A data preprocessing unit, which is used to preprocess the data during the drilling process and obtain the processed data;

[0112] A data analysis and calculation unit, which is used to analyze and calculate the processed data and extract the features of the processed data;

[0113] A clustering unit, which is used to cluster the features of the processed data and obtain the cluster label to which it belongs;

[0114] An outlier identification unit, which is used to calculate the distance between the features of the processed data and the cluster labels to which it belongs, and identify outliers;

[0115] The abnormal operating condition identification and positioning unit is used to compare the abnormal point with the existing fault library to identify and locate the abnormal operating condition.

[0116] In a third aspect, this embodiment provides a storage medium, in which a computer program is stored, and when the computer program is executed, the method of the first aspect is implemented.

[0117] In a fourth aspect, this embodiment provides an electronic device, comprising: a memory and a processor communicatively connected to the memory, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method of the first aspect is implemented.

[0118] In a fifth aspect, this embodiment provides a system for identifying abnormal operating conditions during drilling, characterized in that it includes an electronic device as in the fourth aspect.

[0119] The various embodiments in the present disclosure are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0120] The protection scope of the present disclosure is not limited to the above-mentioned embodiments. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and modifications fall within the scope of the claims of the present disclosure and their equivalents, the intention of the present disclosure also includes these changes and modifications.

Claims

1. A method for identifying abnormal working conditions during drilling, characterized in that: The following steps are involved: Collect and upload data during drilling; Preprocessing the data in the drilling process to obtain processed data; Analyzing and calculating the processed data to extract features of the processed data; Clustering the features of the processed data and obtaining the cluster labels to which they belong; Calculating the distance between the features of the processed data and the cluster labels to which they belong, and identifying abnormal points; The abnormal point is compared with the existing fault library to identify and locate the abnormal working condition.

2. The method for identifying abnormal conditions during drilling according to claim 1, characterized in that: The data collected and uploaded during the drilling process include: Acquire at least one data in the drilling process through multiple sets of sensors installed on the drilling equipment; Add timestamps to collected data; sorting and matching the collected data according to the timestamps; Upload the matched data in order.

3. The method for identifying abnormal conditions during drilling according to claim 1, characterized in that: The preprocessing of the data in the drilling process includes: The data in the drilling process are deduplicated, missing value processed, and outlier detected and processed.

4. The method for identifying abnormal conditions during drilling according to claim 3, characterized in that: The missing value processing includes: using the previous data or the next data of the missing value to replace the missing value.

5. The method for identifying abnormal conditions during drilling according to claim 3, characterized in that: The outlier detection and processing includes: Calculate the average value of various data during the drilling process; Calculate the difference between each data and the average value of the data; Comparing the difference with a first set threshold, if the difference exceeds the first set threshold, determining that the data is an abnormal value, otherwise determining that the data is not an abnormal value; Delete the outliers.

6. The method for identifying abnormal conditions during drilling according to claim 1, characterized in that: The analyzing and calculating the processed data to extract features of the processed data includes: The waveform analysis method is used to analyze the amplitude of the real-time curve of the hook load and the frequency of the peaks and fluctuations in the real-time curve over a period of time; Calculate the average, maximum, and minimum values ​​of the drill speed.

7. The method for identifying abnormal conditions during drilling according to claim 1, characterized in that: The clustering of the features of the processed data and obtaining the cluster labels thereof includes: Initialization: Select the number of clusters K, and randomly select K features of the processed data as initial cluster centers; Assignment: for each feature of the processed data, calculate the distance between it and each cluster center, and assign the feature of the processed data to the cluster center with the closest distance; Update: For each cluster, calculate the average value of the features of all the processed data in the cluster and use it as the new cluster center; Repeat: Repeat the assignment and update steps until the cluster center no longer changes or a predetermined number of iterations is reached; Result output: Output the obtained K cluster centers and the cluster labels of each feature of the processed data.

8. The method for identifying abnormal conditions during drilling according to claim 1, characterized in that: The calculating the distance between the feature of the processed data and the cluster label to which it belongs, and identifying the abnormal point, comprises: If the distance exceeds a second set threshold, the feature of the processed data is determined to be an abnormal point.

9. A device for identifying abnormal working conditions during drilling, characterized in that: include: A data acquisition unit, which is used to collect and upload data during the drilling process; A data preprocessing unit, which is used to preprocess the data in the drilling process and obtain processed data; A data analysis and calculation unit, which is used to analyze and calculate the processed data and extract features of the processed data; A clustering unit, which is used to cluster the features of the processed data and obtain the cluster label to which it belongs; An outlier identification unit, which is used to calculate the distance between the feature of the processed data and the cluster label to which it belongs, and identify the outlier; The abnormal operating condition identification and positioning unit is used to compare the abnormal point with the existing fault library to identify and locate the abnormal operating condition.

10. A storage medium, characterized in that: The storage medium stores a computer program, which implements the method according to any one of claims 1 to 8 when executed.

11. An electronic device, characterized in that: include: A memory and a processor communicatively connected to the memory, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

12. A system for identifying abnormal conditions during drilling, characterized in that: Comprising the electronic device as claimed in claim 11.

Images