Wellhead safety remote control method and control system for marine ship drilling system

Abstract

The invention discloses a marine ship drilling system wellhead safety remote control method which comprises the following steps: arranging a plurality of groups of sensors at a wellhead, acquiring wellhead data in real time and sending the wellhead data to a ground control center; filtering the wellhead data; kalman filtering is carried out; performing data cleaning and preprocessing to obtain processed data; performing data conversion and standardization on the processed data by taking a preset standard value as a zero point and a preset threshold value as an upper limit and a lower limit; establishing a data reference model through historical data and expert knowledge, inputting the converted and standardized data into the data reference model, and comparing the converted and standardized data with data in the data reference model to obtain abnormal data in the converted and standardized data; according to characteristics and relevance of the data, similar data in different data sources are matched and aligned, and weight construction formulas of different sensors are introduced; and carrying out Huffman coding on the aligned data. According to the invention, the data processing accuracy and the storage efficiency are enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of remote control and data processing of wellhead safety systems, and particularly relates to a method and a control system for remote control of wellhead safety in an offshore ship drilling system. Background Art

[0002] The wellhead safety system of an offshore ship drilling system is a crucial device in the offshore oil and gas industry, used to monitor and control the operating status of the wellhead to ensure the safety of personnel and the environment. Traditional wellhead safety systems usually rely on on-site operators for manual control and monitoring, which may have some limitations and risks, such as: personnel safety risks, operational efficiency, data collection and analysis. To solve these problems, the remote control technology of wellhead safety systems has received extensive attention and application. The remote control technology can communicate and control the wellhead safety system with a central control room or a remote monitoring center in real time through a network connection. In short, the remote control technology of wellhead safety systems can improve personnel safety, improve operational efficiency, and achieve real-time data collection and analysis, thus bringing higher safety, efficiency and sustainable development to the oil and gas industry.

[0003] However, the current remote control method for wellhead safety has a low degree of intelligence, only meets data collection and partial logic control, and only has a certain emergency response ability when an emergency has occurred, and cannot perform complex processing of data. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and a control system for remote control of wellhead safety in an offshore ship drilling system, which improve the accuracy and reliability of data processing, enhance the data processing and storage efficiency, and enhance the intelligent anomaly detection and processing ability.

[0005] To solve the above technical problems, the technical solution of the present invention is: a method for remote control of wellhead safety in an offshore ship drilling system, comprising the following steps:

[0006] S1. Set several groups of sensors at the wellhead to collect wellhead data in real time and send them to the ground control center respectively; the wellhead data includes at least the pressure, temperature, flow rate and liquid level of the wellhead;

[0007] S2. After the ground control center receives the wellhead data, filter the wellhead data from different data sources respectively; wherein, a single sensor is used as a data source;

[0008] S3. Perform Kalman filtering on the data after filtering processing;

[0009] S4. Clean and preprocess the data processed by Kalman filtering to obtain processed data; the preprocessing includes at least removing duplicate data, handling missing values and outliers;

[0010] S5. Use a preset standard value as the zero point and a preset threshold as the upper and lower limits to perform data conversion and standardization on the processed data;

[0011] S6. Establish a data benchmark model through historical data and expert knowledge, input the data after data conversion and standardization into the data benchmark model, compare it with the data in the data benchmark model, and obtain the abnormal data in the data after data conversion and standardization to monitor whether there is an abnormal state at the wellhead;

[0012] S7. According to the characteristics and correlations of the data, match and align the similar data in different data sources, and introduce a weight construction formula for different sensors;

[0013] S8. Perform Huffman coding on the aligned data for local storage or remote transmission.

[0014] It also includes the following steps: Set a visual sensor at the wellhead, after processing the video data collected by the visual sensor according to the steps described in S1 - S7, perform wavelet compression on the processed video data for local storage or remote transmission.

[0015] The method of data conversion and standardization in S5 is specifically as follows:

[0016]

[0017] Among them, t is time; r is the sensor acquisition value, and its value depends on time t; (r1, r2) is the safety value neighborhood; B(r) is the excess of the conversion standard value; O(B) is the standardized value after introducing a second - order function and setting upper and lower limits;

[0018]

[0019] Among them, r 3 、r 4 are respectively the upper and lower limits of the set dangerous values; a and α are both quadratic - term coefficients for data conversion by introducing a second - order function; b and β are both linear - term coefficients for data conversion by introducing a second - order function; c and γ are both constant - term coefficients for data conversion by introducing a second - order function.

[0020] The method of introducing a weight construction formula for different sensors in S7 is specifically as follows:

[0021] Construct a weight formula M for two inputs (O 1(t) and O 2(t) , that is, there are two sensors for wellhead safety monitoring(t) and N (t) , expressed as:

[0022]

[0023] There is:

[0024]

[0025] F = μO 1(t) + ∈O 2(t)

[0026] where M is the standard value of the incorrect acquisition by the first sensor, N is the standard value of the incorrect acquisition by the second sensor; O 1(t) and O 2(t) respectively correspond to the O of the two sensors (t) value; μ 1 corresponds to the weight of the fluctuation of the first sensor, ε 1 respectively correspond to the weights of the fluctuations of the second sensor; m is a weight of the importance of the first sensor in the whole system, n is a weight of the importance of the second sensor in the whole system, m, n ∈ (0, 1); μ is the weight of the first sensor after normalization processing, ∈ is the weight of the first sensor after normalization processing; F is the final calculated value, used to judge whether an accident occurs.

[0027] 5. According to the method for remotely controlling the wellhead safety of an offshore marine drilling system described in claim 1, characterized in that, in S2, the wellhead data is filtered by a Butterworth low-pass filter.

[0028] There is also provided a wellhead safety remote control system for an offshore marine drilling system, including a sensor group and a remote control module; wherein,

[0029] Several groups of sensors are arranged at the wellhead for real-time collecting wellhead data and respectively sending it to the remote control module; the wellhead data includes at least the pressure, temperature, flow rate, liquid level and video data of the wellhead;

[0030] The remote control module is set in the ground control center and is used to filter the wellhead data from different data sources respectively after receiving the wellhead data; where a single sensor is regarded as a data source; perform Kalman filtering on the filtered data; perform data cleaning and preprocessing on the data after Kalman filtering to obtain processed data; the preprocessing includes at least removing duplicate data, handling missing values and outliers; taking a preset standard value as the zero point and a preset threshold as the upper and lower limits, perform data conversion and standardization on the processed data; establish a data benchmark model through historical data and expert knowledge, input the data after data conversion and standardization into the data benchmark model, compare it with the data in the data benchmark model, and obtain the abnormal data in the data after data conversion and standardization to monitor whether there is an abnormal state at the wellhead; according to the characteristics and correlations of the data, match and align the similar data in different data sources, and introduce the weight construction formula of different sensors; perform Huffman coding on the aligned data for local storage or remote transmission; perform wavelet compression on the aligned video data for local storage or remote transmission.

[0031] The method of data conversion and standardization is specifically as follows:

[0032]

[0033] Where t is time; r is the sensor acquisition value, and its value depends on time t; (r1, r2) is the safety value neighborhood; B(r) is the transition amount of the conversion standard value; O(B) is the standardized value after introducing a second-order function and setting upper and lower limits;

[0034]

[0035] Where r 3 、r 4 are respectively the upper and lower limits of the set dangerous values; a and α are both quadratic term coefficients for data conversion by introducing a second-order function; b and β are both linear term coefficients for data conversion by introducing a second-order function; c and γ are both constant term coefficients for data conversion by introducing a second-order function.

[0036] The method of introducing the weight construction formula of different sensors is specifically as follows:

[0037] Construct a two-input (O 1(t) and O 2(t) , that is, when there are two sensors for wellhead safety monitoring, the weight formulas M (t) and N (t) , which are expressed as:

[0038]

[0039] There are:

[0040]

[0041]

[0042] F = μO 1(t) + ∈O 2(t)

[0043] Wherein, M is the standard value of the incorrect acquisition by the first sensor, N is the standard value of the incorrect acquisition by the second sensor; O 1(t) and O 2(t) respectively correspond to the O (t) values of the two sensors; μ 1 corresponds to the weight of the fluctuation of the first sensor, ε 1 respectively correspond to the weights of the fluctuations of the second sensor; m is a weight of the importance of the first sensor in the whole system, n is a weight of the importance of the second sensor in the whole system, m, n ∈ (0, 1); μ is the weight of the first sensor after normalization processing, ∈ is the weight of the first sensor after normalization processing; F is the final calculated value, used to judge whether an accident occurs.

[0044] There is also provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the control method as described in any one of the above are implemented.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] Through real-time acquisition and logical judgment by sensors, the present invention reduces the errors in data acquisition and transmission, and further processes the data by using Butterworth low-pass filters and Kalman filters, improving the reliability of the data; through data cleaning and preprocessing mechanisms, the waste of storage space is reduced, and Huffman coding and wavelet compression technologies are adopted to save local storage space and shorten the time for remote data transmission, enhancing the data processing and storage efficiency; based on a benchmark model of historical data and expert knowledge, intelligent detection of abnormal data is realized by using normalization and matching alignment technologies, and local logical judgment is performed by fusing multiple sensor modules, improving the system response ability and enhancing the intelligent abnormal detection and processing ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic flowchart of an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0049] The technical solution of the present invention is: a method for remotely controlling the wellhead safety of an offshore ship drilling system, including the following steps:

[0050] S1. Sensors collect information such as pressure, temperature, flow rate, and liquid level of the wellhead in real time. The various sensor modules can be interconnected to perform some simple logical judgments, and are transmitted to a nearby ground control center through a local area network.

[0051] S2. After the ground control center receives the data, the data receiver is connected to a Butterworth filter for low-pass filtering.

[0052] S3. Transmit the data processed in the previous step into the MCU (main control unit) for Kalman filtering.

[0053] S4. Clean and preprocess the data from the previous step, including removing duplicate data, handling missing values and outliers, etc.

[0054] S5. Take the neighborhood of the set value as the zero point, and use the threshold as the upper and lower limits to convert and standardize the data from different data sources.

[0055]

[0056] Where t is time; r is the sensor acquisition value, and its value depends on time t; (r1, r2) is the neighborhood of the safety value; B(r) is the excess amount of the conversion standard value; O(B) is the standardized value after introducing a second-order function and setting upper and lower limits;

[0057]

[0058] Where r 3 、r 4 are respectively the upper and lower limits of the set dangerous value. Solving the two equations can obtain the values of a, b, c, α, β, and γ. Where a and α are both the quadratic term coefficients for introducing a second-order function for data conversion; b and β are both the linear term coefficients for introducing a second-order function for data conversion; c and γ are both the constant term coefficients for introducing a second-order function for data conversion.

[0059] S6. In this embodiment, by using the logging data extracted from the cloud databases of the intelligent drilling platform data centers in Tianjin, Shenzhen, and Hainan by Ma Lianrui of China University of Petroleum in "Drilling Condition Identification and Application Based on Logging Data", and inputting the data after conversion and standardization into the data benchmark model, information such as the data distribution and variation range under normal conditions can be obtained. In this way, the collected data can be compared with the benchmark model to discover abnormal data that is inconsistent with the normal situation.

[0060] S7. According to the characteristics and correlations of the data, similar data in different data sources are matched and aligned, and a formula for constructing the weights of different sensors is introduced.

[0061] Here, a weight formula for two inputs (O 1(t) and O 2(t) , that is, there are two sensors for wellhead safety monitoring) is constructed

[0062]

[0063]

[0064] F = μO 1(t) + ∈O 2(t)

[0065] where M is the standard value of incorrect acquisition by the first sensor, N is the standard value of incorrect acquisition by the second sensor; O 1(t) and O 2(t) correspond to the O (t) values of the two sensors respectively; μ 1 corresponds to the weight of the first sensor's fluctuation, ε 1 corresponds to the weight of the second sensor's fluctuation respectively; m is a weight representing the importance of the first sensor in the entire system, n is a weight representing the importance of the second sensor in the entire system, m, n ∈ (0, 1); μ is the weight of the first sensor after standardization processing, ∈ is the weight of the first sensor after standardization processing; F is the final calculated value, used to determine whether an accident occurs.

[0066] S8. Perform Huffman coding on the already processed data for storage locally or remote transmission to the client, thereby establishing a hierarchical monitoring and early warning mechanism, which can prevent the occurrence of safety problems to the greatest extent.

[0067] S9. Perform wavelet compression on the video data for storage locally or remote transmission to the client. Using video monitoring technology can visually observe the actual operating conditions of the wellhead, monitor the status of personnel and equipment around the wellhead, which is beneficial to protecting oilfield materials. More importantly, it can promptly detect accidents such as leaks and explosions occurring at the wellhead. Conduct corresponding intelligent verification analysis with the remotely processed data to improve the accuracy of remote diagnosis.

[0068] Among them, each sensor module can be interconnected to perform some simple logical judgments without sending requests to the control center, thus shortening the response time. After the data detected for wellhead pressure, flow rate, and temperature are transmitted to the nearby ground control center through the local area network, the Butterworth filter (Butterworth low-pass filter) can filter out high-frequency interference during data acquisition or transmission. Through Kalman filtering for sensor state estimation, it can quickly respond to the moment when a sensor fails and correct it to a certain extent. At the same time, the elimination of data duplicates makes the data near the outliers more obvious, not only saving storage space but also shortening the communication time. After further standardizing the data, the set value or the normal value without interference is set as zero, upper and lower limit thresholds are set, and abnormal occurrences are accurately and intelligently judged by referring to historical data and expert knowledge. Finally, Huffman coding is used to compress the data, and wavelet compression is used to compress the video, which can not only save local storage memory but also shorten the remote transmission time.

[0069] It is easy for those skilled in the art to understand that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for remotely controlling the wellhead safety of an ocean vessel drilling system, characterized in that: The following steps are involved: S1. Several groups of sensors are set at the wellhead to collect wellhead data in real time and send them to the ground control center respectively; the wellhead data at least includes the pressure, temperature, flow rate and liquid level of the wellhead; S2. After receiving the wellhead data, the ground control center filters the wellhead data from different data sources respectively; a single sensor is used as a data source; S3, performing Kalman filtering on the filtered data; S4, performing data cleaning and preprocessing on the data processed by the Kalman filter to obtain processed data; the preprocessing at least includes removing duplicate data, processing missing values ​​and outliers; S5. Using the preset standard value as the zero point and the preset thresholds as the upper and lower limits, the processed data is converted and standardized; S6. Establish a data benchmark model through historical data and expert knowledge, input the converted and standardized data into the data benchmark model, compare it with the data in the data benchmark model, and obtain abnormal data in the converted and standardized data to monitor whether there is an abnormal state at the wellhead; S7. According to the characteristics and relevance of the data, similar data from different data sources are matched and aligned, and the weights of different sensors are introduced to construct formulas; S8. Perform Huffman encoding on the aligned data for local storage or remote transmission.

2. A method for remotely controlling the wellhead safety of an ocean vessel drilling system according to claim 1, characterized in that: The following steps are also included: A visual sensor is arranged at the wellhead, and the video data collected by the visual sensor is processed as described in steps S1-S7, and then the processed video data is subjected to wavelet compression for local storage or remote transmission.

3. A method for remotely controlling a wellhead of an ocean vessel drilling system according to claim 1, characterized in that: The method of data conversion and standardization in S5 is specifically as follows: Where t is time; r is the sensor acquisition value, whose value depends on the time t; (r1, r2) is the safety value neighborhood; B(r) is the transition value of the conversion standard value; O(B) is the standardized value after the second-order function is introduced and the upper and lower limits are set; Among them, r3 and r4 are the upper and lower limits of the set risk value respectively; a and α are the quadratic term coefficients of the second-order function introduced for data conversion; b and β are the linear term coefficients of the second-order function introduced for data conversion; c and γ are the constant term coefficients of the second-order function introduced for data conversion.

4. A method for remotely controlling a wellhead of an ocean vessel drilling system according to claim 1, characterized in that: The method of introducing the weights of different sensors to construct the formula in S7 is specifically: Construct two inputs (O 1(t) and O 2(t) , that is, the sensors used for wellhead safety monitoring have two weight formulas M (t) and N (t) , expressed as: have: F=μO 1(t) +∈O 2(t) Wherein, M is the standard value of the first sensor error acquisition, and N is the standard value of the second sensor error acquisition; 1(t) and O 2(t) Corresponding to the O of the two sensors (t) value; μ1 corresponds to the weight of the first sensor fluctuation, and ε1 corresponds to the weight of the second sensor fluctuation; m is the weight of the first sensor's importance in the entire system, and n is the weight of the second sensor's importance in the entire system, m,n∈(0,1); μ is the weight of the first sensor after standardization, and ∈ is the weight of the first sensor after standardization; F is the final calculated value, which is used to determine whether an accident has occurred.

5. A method for remotely controlling a wellhead of an ocean vessel drilling system according to claim 1, characterized in that: In the S2, the wellhead data is filtered by a Butterworth low-pass filter.

6. A control system using the offshore ship drilling system wellhead safety remote control method as claimed in claim 1, characterized in that: It includes a sensor group and a remote control module; wherein, Several groups of sensors are arranged at the wellhead, for collecting wellhead data in real time and sending them to the remote control module respectively; the wellhead data at least includes the pressure, temperature, flow, liquid level and video data of the wellhead; The remote control module is arranged in the ground control center, and is used to filter the wellhead data of different data sources respectively after receiving the wellhead data; wherein a single sensor is used as a data source; the filtered data is subjected to Kalman filtering; the data after Kalman filtering is cleaned and preprocessed to obtain processed data; the preprocessing at least includes removing duplicate data, processing missing values ​​and abnormal values; the processed data is converted and standardized with a preset standard value as the zero point and a preset threshold as the upper and lower limits; a data benchmark model is established through historical data and expert knowledge, the data after data conversion and standardization is input into the data benchmark model, and the data is compared with the data in the data benchmark model to obtain abnormal data in the data after data conversion and standardization to monitor whether there is an abnormal state at the wellhead; according to the characteristics and correlation of the data, similar data in different data sources are matched and aligned, and weight construction formulas of different sensors are introduced; the aligned data is Huffman encoded for local storage or remote transmission; the aligned video data is wavelet compressed for local storage or remote transmission.

7. The control system according to claim 6, characterized in that: The specific methods of data conversion and standardization are as follows: Where t is time; r is the sensor acquisition value, whose value depends on the time t; (r1, r2) is the safety value neighborhood; B(r) is the transition value of the conversion standard value; O(B) is the standardized value after the second-order function is introduced and the upper and lower limits are set; Among them, r3 and r4 are the upper and lower limits of the set risk value respectively; a and α are the quadratic term coefficients of the second-order function introduced for data conversion; b and β are the linear term coefficients of the second-order function introduced for data conversion; c and γ are the constant term coefficients of the second-order function introduced for data conversion.

8. The control system according to claim 6, characterized in that: The specific method of introducing the weight construction formula of different sensors is: Construct two inputs (O 1(t) and O 2(t) , that is, the sensors used for wellhead safety monitoring have two weight formulas M (t) and N (t) , expressed as: have: F=μO 1(t) +∈O 2(t) Wherein, M is the standard value of the first sensor error acquisition, and N is the standard value of the second sensor error acquisition; 1(t) and O 2(t) Corresponding to the O of the two sensors (t) value; μ1 corresponds to the weight of the first sensor fluctuation, and ε1 corresponds to the weight of the second sensor fluctuation; m is the weight of the first sensor's importance in the entire system, and n is the weight of the second sensor's importance in the entire system, m,n∈(0,1); μ is the weight of the first sensor after standardization, and ∈ is the weight of the first sensor after standardization; F is the final calculated value, which is used to determine whether an accident has occurred.

9. The control system according to claim 6, characterized in that: The wellhead data were filtered by a Butterworth low-pass filter.

10. 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 control method according to any one of claims 1 to 5 are implemented.

Images