CN-122020366-A - Early warning method, device, equipment, medium and product for well drilling overflow

Abstract

The embodiment of the application provides a method, a device, equipment, a medium and a product for early warning of well drilling overflow, which are applied to the technical field of petroleum engineering. The method comprises the steps of generating second logging data in a second period based on first logging data in a first period, obtaining risk identification results of each moment in the first period and the second period according to the first logging data and the second logging data, constructing evidence according to the moment based on the risk identification results of each moment, obtaining evidence of different time steps, carrying out evidence fusion based on a plurality of pieces of evidence and a preset fusion rule, obtaining a lowest probability value and a highest probability value of overflow in the second period, and sending early warning information when at least one of the lowest probability value and the highest probability value is larger than a preset threshold value, wherein the early warning information represents overflow phenomenon in the second period in the future. The technical effect of improving the overflow early warning reliability of the drilling well is achieved.

Inventors

• WU SHENGNAN
• ZHANG LAIBIN
• HU BINGYAN
• HU YIMING

Assignees

• 中国石油大学(北京)

Dates

Publication Date

20260512

Application Date

20260113

Claims (10)

1. 1. A method for pre-warning of well overflow, comprising: generating second logging data in a second period based on the first logging data in the first period, wherein the first logging data refers to geological layer data and drilling equipment data when drilling is performed in the first period; obtaining risk identification results of each moment in the first period and the second period according to the first logging data and the second logging data, wherein the risk identification results of each moment represent overflow risks at each moment; based on risk identification results of all moments, carrying out evidence construction according to the moments to obtain evidences corresponding to different time steps, wherein the evidence with more time steps comprises evidence with less time steps, one time step corresponds to one moment, and each evidence comprises risk identification results corresponding to a plurality of time steps; And carrying out evidence fusion based on a plurality of evidences and a preset fusion rule to obtain a lowest probability value and a highest probability value of overflow in the second time period, and sending out early warning information when at least one of the lowest probability value and the highest probability value is larger than a preset threshold value, wherein the early warning information represents overflow phenomenon in the future second time period.
2. 2. The method of claim 1, wherein deriving risk identification results for each time instant during the first and second time periods from the first and second logging data comprises: determining sub-data corresponding to each time in the first period and the second period based on the first logging data and the second logging data; Performing risk identification on the sub-data corresponding to each moment to obtain a risk identification result corresponding to the sub-data of each moment; the sub-data represent geological layer data and drilling equipment data when the drilling process is carried out at the corresponding moment, and the risk identification result refers to a predicted risk type corresponding to the sub-data at each moment.
3. 3. The method of claim 1, wherein the performing evidence fusion based on the plurality of pieces of evidence and the preset fusion rule to obtain a lowest probability value and a highest probability value of the overflow occurring in the second period of time comprises: Determining an original risk type corresponding to the sub-data at each moment based on the first logging data and the second logging data; calculating the distribution probability of each original risk type in each risk identification result based on the risk identification result corresponding to the sub-data at each moment and the original risk type corresponding to the sub-data, wherein the distribution probability represents the reliability degree of the risk identification result under different original risk types in the first period and the second period; Determining the distribution probability of each overflow state in each risk identification result based on the mapping relation between the original risk type and the overflow state, and obtaining a distribution matrix composed of a plurality of distribution probabilities, wherein the distribution probabilities represent the reliability degree of the risk identification result in different overflow states in the first period and the second period; and calculating the lowest probability value and the highest probability value of overflow in the second period based on the distribution matrix corresponding to the overflow state.
4. 4. The method of claim 3, wherein the calculating, based on the distribution matrix corresponding to the overflow state, a lowest probability value and a highest probability value of overflow occurring in the second period of time includes: calculating the number of sub-data corresponding to different risk identification results in the evidence aiming at each evidence, wherein each evidence corresponds to a time period divided from the first time period and the second time period, and each evidence comprises the risk identification results corresponding to a plurality of sub-data; Generating a risk ratio vector corresponding to the evidence based on the number of sub-data corresponding to different risk recognition results in each evidence, and correcting the distribution matrix based on the risk ratio vector to obtain a distribution probability vector corresponding to each evidence, wherein the distribution probability in the distribution probability vector represents the reliability degree of the risk recognition results in different overflow states in a time period corresponding to the evidence; synthesizing and calculating based on the distribution probability vectors corresponding to the evidences to obtain fusion probabilities corresponding to different overflow states, wherein the fusion probabilities represent the probability of the different overflow states in the future second period; and calculating the lowest probability value and the highest probability value of overflow in the second period based on the fusion probabilities corresponding to the different overflow states.
5. 5. The method of claim 4, wherein the synthesizing based on the distribution probability vectors corresponding to each evidence to obtain the fusion probabilities corresponding to different overflow states comprises: Determining the distribution probability of each evidence aiming at the same overflow state based on the distribution probability vector corresponding to each evidence; And calculating fusion probabilities corresponding to different overflow states based on the product of the distribution probabilities corresponding to the same overflow state under each evidence.
6. 6. The method of claim 4, wherein calculating a lowest probability value and a highest probability value for flooding occurring during the second period based on the fusion probabilities corresponding to the different flooding states comprises: Based on the fusion probabilities corresponding to the different overflow states, performing reliability calculation and likelihood calculation to obtain a lowest probability value and a highest probability value of overflow in the second period; Wherein the confidence calculation and likelihood calculation are used to convert the fusion probability into a probability value usable for decision, the confidence calculation is used to calculate a lowest probability value for flooding occurring within a second time period in the future, and the likelihood calculation is used to calculate a highest probability value for flooding occurring within the second time period in the future.
7. 7. An overflow drilling warning device, comprising: The system comprises a first processing module, a second processing module and a third processing module, wherein the first processing module is used for generating second logging data in a second period based on first logging data in the first period, the first logging data refer to geological layer data and drilling equipment data when drilling is carried out in the first period, and the second logging data refer to geological layer data and drilling equipment data when drilling is carried out in the second period in the future; The second processing module is used for obtaining risk identification results of each moment in the first time period and the second time period according to the first logging data and the second logging data, wherein the risk identification results of each moment represent overflow risks at each moment; the third processing module is used for constructing evidences according to time based on risk identification results at each time to obtain evidences corresponding to different time steps, wherein the evidence with more time steps comprises evidence with less time steps, one time step corresponds to one time, and each evidence comprises risk identification results corresponding to a plurality of time steps; The fourth processing module is used for carrying out evidence fusion based on a plurality of evidences and a preset fusion rule to obtain a lowest probability value and a highest probability value of overflow in the second time period, and sending out early warning information when at least one of the lowest probability value and the highest probability value is larger than a preset threshold value, wherein the early warning information represents overflow phenomenon in the future second time period.
8. 8. An electronic device is characterized by comprising a memory and a processor; The memory stores computer-executable instructions; The processor executing computer-executable instructions stored in the memory, causing the processor to perform the method of any one of claims 1-6.
9. 9. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-6.
10. 10. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-6.

Description

Early warning method, device, equipment, medium and product for well drilling overflow Technical Field The application relates to the technical field of petroleum engineering, in particular to a method, a device, equipment, a medium and a product for early warning of well drilling overflow. Background In oil gas drilling engineering, overflow is used as an early sign of blowout, timely detection and control are needed, and the consequences of casualties, environmental pollution, equipment damage and the like caused by out-of-control blowout are avoided. As oil and gas resource development proceeds further, environmental uncertainty increases during drilling, thus leading to increased risk of flooding, requiring further detection of the risk of flooding. The overflow detection mode in the prior art mainly comprises the steps of collecting overflow related logging data generated in the drilling process in real time, and predicting whether overflow occurs in the drilling process in the future period based on the logging data in the current period. Because the prior art mainly relies on real-time data to predict the future drilling overflow condition, the situation of inaccurate prediction exists, and therefore the technical problem of low reliability of drilling overflow early warning exists in the prior art. Disclosure of Invention The embodiment of the application provides a method, a device, equipment, a medium and a product for early warning of well drilling overflow, which are used for achieving the technical effect of improving the reliability of early warning of well drilling overflow. In a first aspect, an embodiment of the present application provides a method for early warning of overflow of a drilling well, including: Generating second logging data in a second period based on the first logging data in the first period, wherein the first logging data refers to geological layer data and drilling equipment data when drilling is performed in the first period; Obtaining risk identification results of each moment in a first period and a second period according to the first logging data and the second logging data, wherein the risk identification results of each moment represent overflow risks at each moment; Based on risk identification results of all moments, carrying out evidence construction according to the moments to obtain evidences corresponding to different time steps, wherein the evidence with more time steps comprises evidence with less time steps, one time step corresponds to one moment, and each evidence comprises risk identification results corresponding to a plurality of time steps; And sending out early warning information when at least one of the lowest probability value and the highest probability value is greater than a preset threshold value, wherein the early warning information characterizes that overflow phenomenon can occur in a future second period. In one possible embodiment, obtaining a risk identification result at each moment in the first period and the second period according to the first logging data and the second logging data includes: Determining sub-data corresponding to each moment in a first period and a second period based on the first logging data and the second logging data; performing risk identification on the sub-data corresponding to each moment to obtain a risk identification result corresponding to the sub-data at each moment; the sub-data represent geological layer data and drilling equipment data when the drilling process is carried out at the corresponding moment, and the risk identification result refers to a predicted risk type corresponding to the sub-data at each moment. In a possible implementation manner, based on a plurality of evidences and a preset fusion rule, performing evidence fusion to obtain a lowest probability value and a highest probability value of overflow in the second period, where the method includes: Determining an original risk type corresponding to the sub-data at each moment based on the first logging data and the second logging data; Calculating the distribution probability of each original risk type in each risk recognition result based on the risk recognition result corresponding to the sub-data at each moment and the original risk type corresponding to the sub-data, wherein the distribution probability represents the reliability degree of the risk recognition result under different original risk types in a first period and a second period; determining the distribution probability of each overflow state in each risk identification result based on the mapping relation between the original risk type and the overflow state, and obtaining a distribution matrix composed of a plurality of distribution probabilities, wherein the distribution probabilities represent the reliability degree of the risk identification result in different overflow states in a first period and a second period; and calculating the lowest probability value and