Multi-modal risk sensing method and device for well drilling automation system

Abstract

The invention provides a multi-modal risk sensing method and device for a well drilling automation system. The method comprises the following steps: acquiring a risk interval value of a first-level risk index; converting the risk interval value of each first-level risk indicator to obtain a first-level cloud feature parameter; converting the first-level cloud feature parameter to obtain a second-level cloud feature parameter, wherein the first-level risk index belongs to a second-level risk index; converting the second-level cloud feature parameter to obtain a third-level cloud feature parameter, wherein the second-level risk index belongs to a misoperation risk index; and comparing the third-level cloud feature parameters with standard cloud feature parameters of different misoperation risk levels, and determining the misoperation risk level of the current operator. According to the method, the cloud feature parameters of the misoperation risk indexes can be obtained according to various risk indexes, the misoperation risk grade of the current operator can be accurately identified by comparing the cloud feature parameters with the standard cloud feature parameters, and a guarantee is provided for safe operation of a well site.

Description

Technical Field

[0001] The present application belongs to the field of safe operations at a well site, and specifically, relates to a multimodal risk perception method and device for a drilling automation system. Background Art

[0002] The intelligent construction of well sites (drilling and oil production work sites) has realized the unmanned and less-manned operation of well site operations, while the well site information is concentrated on the operators at the control console. Excessive concentration of information will increase the work intensity and pressure of operators, and the risk of operational errors will also increase. Therefore, it is necessary to conduct multi-dimensional risk perception and monitoring of operator misoperations at intelligent well sites to ensure the safety of intelligent well site operators.

[0003] However, the perception and detection of operator misoperation is a complex process, which is affected by many factors. Most of the factors are ambiguous and uncertain, making it difficult to conduct quantitative analysis. Currently, the commonly used methods for the perception and monitoring of operator misoperation risks include safety table inspection method, hazard and operability analysis method, hierarchical analysis method, etc. The obvious problems of these methods are that most factors cannot be quantitatively analyzed or they rely too much on expert scoring, resulting in poor accuracy of misoperation risk perception and monitoring results, which is not conducive to the safety rectification of drilling operators. Summary of the invention

[0004] In view of the above problems, the present application aims to provide a multimodal risk perception method and device for a drilling automation system, which is used to solve the problem of poor risk monitoring accuracy caused by the inability to quantify the risk factors existing in the existing well site misoperation.

[0005] In a first aspect, the present application provides a multimodal risk perception method for a drilling automation system, comprising:

[0006] Obtaining a risk interval value of the first-level risk indicator, wherein the risk interval value is determined according to the degree of influence of the first-level risk indicator on the operating personnel;

[0007] Performing a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain the first-level cloud feature parameter corresponding to the first-level risk indicator;

[0008] Performing a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to the second-level risk indicators, wherein the first-level risk indicators are subordinate to the second-level risk indicators;

[0009] Performing a third digital feature conversion on the second-level cloud feature parameters to obtain third-level cloud feature parameters corresponding to the misoperation risk indicator, wherein the second-level risk indicator belongs to the misoperation risk indicator;

[0010] The third-level cloud characteristic parameters are compared with the standard cloud characteristic parameters of different risk levels of misoperation to determine the misoperation risk level of the current operator.

[0011] Based on the above technical solution, the present application can also make the following improvements:

[0012] In a possible implementation, performing a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain a first-level cloud feature parameter corresponding to the first-level risk indicator includes:

[0013] Determine the corresponding expectation, entropy and super entropy of each first-level risk indicator according to the risk interval value of each first-level risk indicator;

[0014] The first-level cloud characteristic parameters corresponding to each first-level risk indicator are determined according to the expectation, entropy and super entropy corresponding to each first-level risk indicator.

[0015] In a possible implementation, performing a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to the second-level risk indicators includes:

[0016] Obtain the weight coefficient of each first-level risk indicator;

[0017] Determine the expectation, entropy and super entropy corresponding to each second-level risk indicator according to the first-level cloud characteristic parameters of each first-level risk indicator and the weight coefficient of the corresponding first-level risk indicator;

[0018] The second-level cloud characteristic parameters corresponding to each second-level risk indicator are determined according to the expectation, entropy and super entropy corresponding to each second-level risk indicator.

[0019] In a possible implementation, obtaining a weight coefficient of each first-level risk indicator includes:

[0020] Rank the importance of the first-level risk indicators that belong to the same second risk indicator, and assign scores to the first-level risk indicators;

[0021] Perform regression analysis on the scoring results of the above first-level risk indicators to obtain the complex correlation coefficient of each first-level risk indicator;

[0022] The complex correlation coefficients of the above-mentioned first-level risk indicators are normalized to determine the weight coefficient of each first-level risk indicator.

[0023] In a possible implementation, the second-level cloud feature parameters are subjected to a third digital feature conversion to obtain third-level cloud feature parameters corresponding to the misoperation risk indicator, including:

[0024] Obtain the weight coefficient of each second-level risk indicator;

[0025] Determine the expectation, entropy and super entropy corresponding to the misoperation risk indicator according to the second-level cloud characteristic parameters corresponding to each second-level risk indicator and the weight coefficient of the corresponding second-level risk indicator;

[0026] According to the expectation, entropy and super entropy corresponding to the misoperation risk indicator, the third-level cloud characteristic parameters corresponding to the misoperation risk indicator are determined.

[0027] In a possible implementation, obtaining the weight coefficient of each second-level risk indicator includes:

[0028] Rank the importance of the second-level risk indicators belonging to the misoperation risk indicators, and assign scores to the second-level risk indicators;

[0029] Perform regression analysis on the scoring results of the above second-level risk indicators to obtain the complex correlation coefficient of each second-level risk indicator;

[0030] The complex correlation coefficients of the above-mentioned second-level risk indicators are normalized to determine the weight coefficients of the second-level risk indicators.

[0031] In a possible implementation, the second-level risk indicators include human indicators and environmental indicators, and the first-level risk indicators include emotional state, psychological stress, fatigue level and workload belonging to human indicators, and temperature parameters and noise parameters belonging to environmental indicators;

[0032] The step of obtaining the risk interval value of the first-level risk indicator includes:

[0033] Determine the risk interval value of the operator's emotional state, psychological stress, fatigue level and workload based on the real-time collection of the operator's physiological signals and behavioral data;

[0034] The risk interval values ​​of the temperature parameters and the noise parameters are determined according to the segmented intervals of the temperature parameters and the noise parameters collected in real time at the operation site.

[0035] In a second aspect, the present application also provides a multi-modal risk perception device for a drilling automation system, comprising:

[0036] An acquisition module, used to acquire a risk interval value of a first-level risk indicator, wherein the risk interval value is determined according to the degree of influence of the first-level risk indicator on the operator;

[0037] A first digital feature conversion module, used for performing a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain a first-level cloud feature parameter corresponding to the first-level risk indicator;

[0038] A second digital feature conversion module is used to perform a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to second-level risk indicators, wherein the first-level risk indicators are subordinate to the second-level risk indicators;

[0039] A third digital feature conversion module is used to perform a third digital feature conversion on the second-level cloud feature parameter to obtain a third-level cloud feature parameter corresponding to the misoperation risk indicator, wherein the second-level risk indicator belongs to the misoperation risk indicator;

[0040] The determination module is used to compare the third-level cloud characteristic parameters with the standard cloud characteristic parameters of different risk levels of misoperation to determine the misoperation risk level of the current operator.

[0041] In a third aspect, the present application further provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0042] The memory stores computer-executable instructions;

[0043] The processor executes the computer-executable instructions stored in the memory to implement the multimodal risk perception method of the drilling automation system as described in any one of the first aspects above.

[0044] In a fourth aspect, the present application further provides a computer storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the multimodal risk perception method for a drilling automation system as described in any one of the first aspects above.

[0045] The present application provides a multimodal risk perception method and device for a drilling automation system, which first obtains the risk interval value of the first-level risk indicator; then converts the risk interval value of each first-level risk indicator to obtain the first-level cloud feature parameter corresponding to the first-level risk indicator; converts the first-level cloud feature parameter to obtain the second-level cloud feature parameter corresponding to the second-level risk indicator; converts the second-level cloud feature parameter to obtain the cloud feature parameter of the misoperation risk indicator; finally, the cloud feature parameter of the misoperation risk indicator is compared with the standard cloud feature parameter of different risk levels of misoperation to determine the misoperation risk level of the current operator. In specific monitoring, since the first-level risk indicator is converted into a quantifiable risk interval value, and then the corresponding cloud feature parameter is output based on the cloud model, and then the weight coefficients of the indicators at each level are used to push from the low level to the high level, the cloud feature parameter of the misoperation risk indicator is obtained, and finally it is compared with the standard cloud feature parameter, so that the misoperation risk level of the current operator can be more accurately identified, providing a guarantee for safe operation of the well site. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] Figure 1 A specific application scenario diagram of the multimodal risk perception method for a drilling automation system provided in an embodiment of the present application;

[0048] Figure 2 A cloud diagram of the risk levels of misoperation provided in the embodiment of the present application;

[0049] Figure 3 A flow chart of a multi-modal risk perception method for a drilling automation system provided in an embodiment of the present application;

[0050] Figure 4 A flowchart of another multi-modal risk perception method for a drilling automation system provided in an embodiment of the present application;

[0051] Figure 5 This is a schematic diagram comparing the third-level cloud characteristic parameters of this application with the cloud diagrams of various risk level standards for misoperation;

[0052] Figure 6 A schematic diagram of the structure of a multi-modal risk perception device for a drilling automation system provided in an embodiment of the present application;

[0053] Figure 7 A hardware structure diagram of an electronic device provided in an embodiment of the present application.

[0054] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments.

[0055] Description of reference numerals:

[0056] 101-Human body index collection equipment; 102-Environmental index collection equipment; 103-Cloud server;

[0057] 601 - acquisition module; 602 - first digital feature conversion module; 603 - second digital feature conversion module; 604 - third digital feature conversion module; 605 - determination module. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] The perception and detection of operator misoperation at the well site is a complex process, which is affected by many factors. Most of the factors are ambiguous and uncertain, making it difficult to conduct quantitative analysis. Currently, the commonly used methods for the perception and monitoring of operator misoperation risks include safety table inspection method, hazard and operability analysis method, hierarchical analysis method, etc. Most of the factors in these methods cannot be quantitatively analyzed or are overly dependent on expert scoring, resulting in poor accuracy in the perception and monitoring of misoperation risks.

[0060] In order to solve the above problems, the embodiments of the present application provide a multimodal risk perception method and device for a drilling automation system, so as to accurately identify the risk level of misoperation of the current operator and provide guarantee for safe operation at the well site.

[0061] Figure 1 The figure shows a specific application scenario diagram of the multimodal risk perception method of the drilling automation system of the embodiment of the present application, including a human indicator collection device 101 for collecting misoperation risk indicators and an environmental indicator collection device 102 for collecting environmental parameters, and a cloud server 103 for receiving and processing the misoperation risk indicators, wherein the human indicator collection device 101 is used to collect human parameters of operators, and can output the human indicators of operators based on the collected human parameters, and the environmental indicator collection device 102 collects environmental parameters and outputs environmental indicators.

[0062] The cloud server 103 is used to receive the human indicators and environmental indicators sent by the human indicator collection device 101 and the environmental indicator collection device 102, and output the misoperation risk level of the current operator based on these misoperation risk indicators.

[0063] The human index collection device 101 can be a wearable electronic device such as a bracelet, smart clothing, etc., and the environmental index collection device 102 can be an outdoor sensor or monitoring device. The above devices are not specifically limited in this application.

[0064] A specific embodiment is given below to illustrate:

[0065] The human index collection device 101 is a multi-modal bracelet worn by the staff, which is used to collect the pulse wave, skin electricity, acceleration, angular velocity and other physiological signals and behavioral data of the staff in real time. Through these physiological signals and behavioral data, the emotional state, psychological pressure, fatigue level and workload of the staff can be measured. The specific measurement process is as follows:

[0066] First, the collected pulse wave, skin electricity, acceleration, angular velocity and other physiological signals and behavioral data are matched with the corresponding feature data in the database. Then, feature layer classification is performed based on the support vector machine. All the feature values ​​extracted from a single physiological signal are fused and classified. The basic probability distribution value (BPA) required by the DS evidence theory is calculated through the delayed probability and confusion matrix. Finally, the BPA values ​​of all physiological signals are fused to determine the physiological and psychological state level of the operator.

[0067] Table 1 Misoperation risk indicators

[0068]

[0069] The environmental index collection device 102 collects environmental parameters such as temperature, humidity, noise, etc. that may easily affect the operators, and these environmental parameters may be obtained through corresponding sensors. Table 1 shows the risk indicators of misoperation at various levels in this embodiment.

[0070] Of course, as needed, supplements can be made to the human indicators and environmental indicators. For example, the working space can be added as the first-level risk indicator in the environmental indicators. Other first- and second-level risk indicators can also be added, such as organizational indicators (second-level risk indicators) and corresponding safety education, safety rewards and punishments, safety atmosphere (first-level risk indicators), equipment indicators (second-level risk indicators) and corresponding storage rationality, equipment reliability, protective measures and safety warning design (first-level risk indicators).

[0071] The cloud server 103 obtains the current operator's misoperation risk level through the misoperation risk index. Before monitoring and determining the misoperation risk level, the cloud server 103 also needs to determine standard cloud characteristic parameters of different misoperation risk levels.

[0072] In one embodiment, the embodiment divides the risk value of erroneous operation of intelligent well site operators into five levels, namely, Level I (9-10 points) is a major risk, Level II (7-8 points) is a large risk, Level III (5-6 points) is a medium risk, Level IV (3-4 points) is a relatively low risk, and Level V (1-2 points) is a low risk.

[0073] The cloud characteristic parameters (expected Ex, entropy En, and super entropy He) corresponding to the misoperation risk level are obtained through the divided misoperation risk level. The specific calculation formula is as follows:

[0074] Ex=(Y max +Y min ) / twenty one)

[0075] En=(Y max -Y min ) / 6 (2)

[0076] He=kEn (3)

[0077] Among them, Y max and Y min are the upper and lower limits of the misoperation risk level scores, for example, level I is a major risk, Y max is 10, Y min is 9; k is a constant, which is determined according to the fuzziness of the evaluation index and is taken as 0.1 here based on parameter characteristics and experience.

[0078] Table 2 Classification of risk levels of misoperation and cloud characteristic parameters

[0079] Evaluation Criteria Level classification Cloud characteristic parameters Low risk [1，2] (1.5，0.1667，0.0167) Lower risk [3，4] (3.5，0.1667，0.0167) Medium risk [5，6] (5.5，0.1667，0.0167) Greater risk [7，8] (7.5，0.1667，0.0167) Significant risks [9，10] (9.5，0.1667，0.0167)

[0080] Table 2 shows the cloud characteristic parameters corresponding to the five levels of misoperation risk. Figure 2 The standard cloud map of each risk level of misoperation provided in the embodiment of the present application is input into the prepared algorithm by inputting the cloud feature parameters corresponding to different risk levels of misoperation into the prepared algorithm, and the following can be obtained: Figure 2 The standard cloud diagrams of various risk levels of misoperation shown are used as standard cloud characteristic parameters of different risk levels of misoperation.

[0081] Therefore, the goal of this application is to obtain the current staff misoperation risk indicator cloud feature parameters based on the currently collected misoperation risk indicators and compare them with the standard cloud feature parameters to determine the current misoperation risk level.

[0082] Figure 3 A flowchart of a multi-modal risk perception method for a drilling automation system provided in an embodiment of the present application. Figure 3 As shown, a multimodal risk perception method for a drilling automation system is applied to a cloud server 103 to determine the current risk level of misoperation. Figure 1 As shown, the cloud server 103 here can also be other mobile terminals, control backgrounds, etc. The multimodal risk perception method of the drilling automation system includes:

[0083] S301: Obtain the risk interval value of the first-level risk indicator, which is determined according to the impact of the first-level risk indicator on the operator.

[0084] In this embodiment, the first-level risk indicators shown in Table 1 may be collected, and the risk interval value of each first-level risk indicator may be determined according to the degree of influence of the first-level risk indicator on the operator.

[0085] S302: Perform a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain the first-level cloud feature parameter corresponding to the first-level risk indicator

[0086] After obtaining the risk interval value of each first-level risk indicator, the first digital feature conversion can be performed according to formulas (1) to (3) to calculate the corresponding expectation, entropy and super entropy of each first-level risk indicator, and then the first-level cloud feature parameters (expectation Ex, entropy En, super entropy He) corresponding to each first-level risk indicator can be obtained based on the corresponding expectation, entropy and super entropy of each first-level risk indicator.

[0087] S303: Perform a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to the second-level risk indicators. The first-level risk indicators are subordinate to the second-level risk indicators.

[0088] S304: Perform a third digital feature conversion on the second-level cloud feature parameters to obtain the third-level cloud feature parameters corresponding to the misoperation risk index. The second-level risk index belongs to the misoperation risk index.

[0089] In each of the above steps, there are multiple ways to convert digital features. Formulas (1) to (3) are relatively common digital feature conversion methods for the risk interval values ​​of the first-level risk indicators.

[0090] S305: Compare the third-level cloud characteristic parameters with standard cloud characteristic parameters of different risk levels of misoperation to determine the misoperation risk level of the current operator.

[0091] The simplest way to compare the third-level cloud characteristic parameters with the standard cloud characteristic parameters is to directly observe the expectations of the two and see within which level of misoperation risk the expectations of the third-level cloud characteristic parameters fall.

[0092] The multimodal risk perception method of the drilling automation system provided in the above embodiment first obtains the risk interval value of the first-level risk indicator; then converts the risk interval value of each first-level risk indicator to obtain the first-level cloud feature parameter corresponding to the first-level risk indicator; converts the first-level cloud feature parameter to obtain the second-level cloud feature parameter corresponding to the second-level risk indicator; converts the second-level cloud feature parameter to obtain the cloud feature parameter of the misoperation risk indicator; finally, the cloud feature parameter of the misoperation risk indicator is compared with the standard cloud feature parameter of different risk levels of misoperation to determine the misoperation risk level of the current operator. In specific monitoring, since the first-level risk indicator is converted into a quantifiable risk interval value, and then the corresponding cloud feature parameter is output based on the cloud model, and then the weight coefficients of the indicators at each level are used to push from the low level to the high level, the cloud feature parameter of the misoperation risk indicator is obtained, and finally it is compared with the standard cloud feature parameter, so that the misoperation risk level of the current operator can be more accurately identified, providing a guarantee for safe operation of the well site.

[0093] Figure 4 Another flowchart of a multi-modal risk perception method for a drilling automation system provided in an embodiment of the present application is as follows: Figure 4 As shown, the multimodal risk perception method of the drilling automation system includes:

[0094] S401: Obtain the risk interval value of the first-level risk indicator, which is determined according to the impact of the first-level risk indicator on the operator.

[0095] The following is a specific example to illustrate:

[0096] For each first-level risk indicator belonging to human body indicators (emotional state, psychological stress, fatigue level, workload), the cloud server can obtain the corresponding characteristic data based on the original data (human parameters collected by the human body indicator collection device) and match it in the database, and finally obtain the measurement results of the operator's emotional state, psychological stress, fatigue level, workload and other physiological and psychological states, and convert the measurement levels of the operator's physiological and psychological states into different integer ranges of 1-10 as the risk interval values ​​of risk indicators.

[0097] For each first-level risk indicator (temperature parameter, noise parameter) belonging to the environmental indicator, the cloud server can divide the risk interval value of the original data (collected by the environmental indicator collection device) according to the upper and lower limits of the historical parameters. Specifically, if the highest and lowest temperatures at the work site are T max and T min , then T max -T min The difference is divided into 10 segment intervals to determine the risk interval value of the real-time temperature. If the real-time temperature exceeds T max, then the corresponding risk interval value is located at 10. If the real-time temperature is less than T min , the corresponding risk interval value is positioned at 1.

[0098] S402: Perform a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain the first-level cloud feature parameter corresponding to the first-level risk indicator

[0099] After obtaining the risk interval value of each first-level risk indicator, the first digital feature conversion can be performed according to formulas (1) to (3) to calculate the corresponding expectation, entropy and super entropy of each first-level risk indicator, and then the first-level cloud feature parameters (expectation Ex, entropy En, super entropy He) corresponding to each first-level risk indicator can be obtained based on the corresponding expectation, entropy and super entropy of each first-level risk indicator.

[0100] S403: Obtaining the weight coefficient of each first-level risk indicator;

[0101] Different risk indicators have different effects on the final misoperation risk. In order to better reflect the impact of risk indicators, combined with accidents caused by human misoperation and the characteristics of intelligent well sites, the importance of the first-level risk indicators belonging to the same second risk indicator is ranked and the first-level risk indicators are scored. The risk indicator importance score range is 1 to 10 points, and the scores are assigned from low to high according to the degree of importance.

[0102] In order to calculate the weight coefficients of different risk indicators, the weight coefficients of the first-level risk indicators are taken as an example for explanation below.

[0103] First, regression analysis is performed on the scoring results of the first-level risk indicators to obtain the complex correlation coefficient of each first-level risk indicator. The first-level risk indicators are emotional state, psychological pressure, fatigue level, and workload, which are also human body indicators.

[0104]

[0105] Among them, R is the multiple correlation coefficient, β is the value of one of the first-level risk indicators after the importance is assigned, is the average value of the importance of each first-level risk indicator, is the value after regression analysis of the importance score of each first-level risk indicator, β 1 , β 2 ...β n The value after assigning the importance of each first-level risk indicator, k i is the regression parameter.

[0106] Normalize the complex correlation coefficients of the above first-level risk indicators to determine the weight coefficient of each first-level risk indicator:

[0107]

[0108] Among them, w i is the weight coefficient of each first-level risk indicator, R i is the complex correlation coefficient of each first-level risk indicator, n is the number of first-level risk indicators belonging to human body indicators, which is 4 here.

[0109] Similarly, according to the above method, the weight coefficients of the first-level risk indicators (temperature parameters, noise parameters) that are also environmental indicators can be obtained.

[0110] Accordingly, the second-level risk indicators (human indicators and environmental indicators) are used as lower-level risk indicators under the misoperation risk indicator, and the weight coefficients corresponding to the corresponding second-level risk indicators are calculated according to the above method, which can be applied to step S405. The specific process is as follows:

[0111] Rank the importance of the second-level risk indicators belonging to the misoperation risk indicators, and assign scores to the second-level risk indicators;

[0112] Perform regression analysis on the scoring results of the above second-level risk indicators to obtain the complex correlation coefficient of each second-level risk indicator;

[0113] The complex correlation coefficients of the above-mentioned second-level risk indicators are normalized to determine the weight coefficients of the second-level risk indicators.

[0114] Table 3 Weight coefficients of risk indicators at all levels

[0115]

[0116] Table 3 is a description of the weight coefficients corresponding to the indicators at each level in Table 1, where each weight coefficient satisfies:

[0117] w 1 +w 2 =1,w 11 +w 12 +w 13 +w 14 =1,w 21 +w 22 =1.

[0118] S404: Determine the expectation, entropy and super entropy corresponding to each second-level risk indicator according to the first-level cloud characteristic parameters of each first-level risk indicator and the weight coefficient of the corresponding first-level risk indicator

[0119] For the first-level cloud characteristic parameters corresponding to each first-level risk indicator obtained in step S402 and the weight coefficients corresponding to each first-level risk indicator obtained in step S403 (see Table 3), the expected Ex, entropy En and super entropy He corresponding to each second-level risk indicator can be calculated by the following formula:

[0120]

[0121] Where: m is the first-level risk index included in each second-level risk index. Specifically, if the expected Ex of human index A is calculated 1 , Entropy 1 and super entropy He 1 ,but:

[0122] Ex 1 =Ex 11 w 11 +Ex 12 w 13 +Ex 13 w 13 +Ex 14 w 14

[0123]

[0124] Expected Ex of Environmental Indicator B 2 , Entropy 2 and super entropy He 2 It can also be obtained by the above formula.

[0125] S405: Determine the second-level cloud characteristic parameters corresponding to each second-level risk indicator according to the expectation, entropy, and super entropy corresponding to each second-level risk indicator

[0126] The human body index cloud characteristic parameters (Ex 1 ,En 1 , He 1 ) and environmental index cloud characteristic parameters (Ex 2 ,En 2 , He 2 ) can determine the second-level cloud characteristic parameters corresponding to the second-level risk indicators (human indicators and environmental indicators).

[0127] S406: Perform a third digital feature conversion on the second-level cloud feature parameters to obtain the third-level cloud feature parameters corresponding to the misoperation risk index. The second-level risk index belongs to the misoperation risk index.

[0128] After obtaining the second-level cloud characteristic parameters corresponding to each second-level risk indicator, the third-level cloud characteristic parameters can be obtained by referring to steps S403 to S405, as follows:

[0129] Obtain the weight coefficient of each second-level risk indicator;

[0130] Determine the expectation, entropy and super entropy corresponding to the misoperation risk indicator according to the second-level cloud characteristic parameters corresponding to each second-level risk indicator and the weight coefficient of the corresponding second-level risk indicator;

[0131] According to the expectation, entropy and super entropy corresponding to the misoperation risk indicator, the third-level cloud characteristic parameters corresponding to the misoperation risk indicator are determined.

[0132] The process of obtaining the weight coefficient of each second-level risk indicator can refer to the description in S403. Specifically, the weight coefficient w of the second-level risk indicator (human indicator and environmental indicator) is 1 、w 2 It can be obtained from Table 3 according to step S403.

[0133] The expectation, entropy and super entropy corresponding to the misoperation risk indicator are determined according to the second-level cloud characteristic parameters corresponding to each second-level risk indicator and the weight coefficient corresponding to the second-level risk indicator. The calculation method of the expectation Ex, entropy En and super entropy He corresponding to the misoperation risk indicator can refer to the method for calculating the second-level risk indicator in step S404.

[0134] The third-level cloud characteristic parameters (Ex, En, He) corresponding to the misoperation risk index can be determined by the obtained expectation Ex, entropy En and super entropy He, which are referred to as misoperation risk index cloud characteristic parameters.

[0135] S407: Compare the third-level cloud characteristic parameters with standard cloud characteristic parameters of different risk levels of misoperation to determine the misoperation risk level of the current operator.

[0136] Figure 5 This is a schematic diagram of the comparison between the third-level cloud feature parameters and the cloud map of each risk level standard of misoperation. In addition to the direct comparison method mentioned in step S305, the cloud map comparison method provided by this embodiment can also be used. This method is more conducive to intuitively determining the risk level of misoperation. The specific process is to first convert the third-level cloud feature parameters into a cloud map, and then compare it with Figure 2 The cloud chart of risk level of misoperation shown in the figure provides a more intuitive comparison. Figure 5 It can be seen from the cloud chart that the risk level of misoperation obtained by real-time monitoring is a relatively high risk.

[0137] For different levels of misoperation risk: when the misoperation risk level is low risk, it means that the operation complies with the specification standards, and the result of the operation error is within the controllable range; when the misoperation risk level is relatively low risk, it means that the operation does not meet the specification standards, and the result of the operation error is not within the controllable range, and timely rectification is required; when the misoperation risk level is medium risk, it means that the misoperation will lead to certain consequences, and timely rectification is required and the operation site should be supervised; when the misoperation risk level is relatively high risk, it means that the misoperation will lead to more serious consequences, and the operation process needs to be improved and the operation site needs to be supervised; when the misoperation risk level is high risk, it means that the misoperation will lead to serious consequences, and it is necessary to immediately stop the on-site production work, improve the operation process, and train the operators.

[0138] The following example illustrates the calculation process of the risk interval value:

[0139] The second-level risk indicators include human indicators and environmental indicators. The first-level risk indicators include emotional state, psychological stress, fatigue level and workload belonging to human indicators, and temperature parameters and noise parameters belonging to environmental indicators.

[0140] Obtaining the risk interval value of the first-level risk indicator includes: determining the risk interval value of the operator's emotional state, psychological stress, fatigue level and workload based on the real-time collection of the operator's physiological signals and behavioral data; determining the risk interval value of the temperature parameter and noise parameter based on the segmented interval of the real-time collection of the temperature parameter and noise parameter of the operation site. For the specific process, please refer to Figure 1 Relevant description of the specific application scenario diagram shown.

[0141] Figure 6 A structural schematic diagram of a multimodal risk perception device for a drilling automation system provided in an embodiment of the present application, the device may be in the form of software and / or hardware, and the multimodal risk perception device for a drilling automation system includes: an acquisition module 601, a first digital feature conversion module 602, a second digital feature conversion module 603, a third digital feature conversion module 604 and a determination module 605.

[0142] The acquisition module 601 is used to obtain the risk interval value of the first-level risk indicator, and the risk interval value is determined according to the impact degree of the first-level risk indicator on the operating personnel.

[0143] The first digital feature conversion module 602 is used to perform a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain a first-level cloud feature parameter corresponding to the first-level risk indicator;

[0144] The second digital feature conversion module 603 is used to perform a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to the second-level risk indicators, and the first-level risk indicators are subordinate to the second-level risk indicators.

[0145] The third digital feature conversion module 604 is used to perform a third digital feature conversion on the second-level cloud feature parameters to obtain third-level cloud feature parameters corresponding to the misoperation risk index, and the second-level risk index belongs to the misoperation risk index.

[0146] The determination module 605 is used to compare the third-level cloud characteristic parameters with standard cloud characteristic parameters of different risk levels of misoperation to determine the misoperation risk level of the current operator.

[0147] The multimodal risk perception device for a drilling automation system provided in the embodiment of the present application has the same implementation principle and technical effects as those in the aforementioned embodiment of the multimodal risk perception method for a drilling automation system. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned embodiment of the multimodal risk perception method for a drilling automation system.

[0148] In some embodiments, the specific process of the first digital feature conversion module 602 is: determine the corresponding expectation, entropy and super entropy of each first-level risk indicator according to the risk interval value of each first-level risk indicator; determine the first-level cloud feature parameters corresponding to each first-level risk indicator according to the corresponding expectation, entropy and super entropy of each first-level risk indicator.

[0149] In some embodiments, the specific process of the second digital feature conversion module 603 is: obtaining the weight coefficient of each first-level risk indicator; determining the expectation, entropy and super entropy corresponding to each second-level risk indicator according to the first-level cloud feature parameters of each first-level risk indicator and the weight coefficient of the corresponding first-level risk indicator; determining the second-level cloud feature parameters corresponding to each second-level risk indicator according to the expectation, entropy and super entropy corresponding to each second-level risk indicator.

[0150] Among them, the weight coefficient of each first-level risk indicator is obtained, including:

[0151] Rank the importance of the first-level risk indicators that belong to the same second risk indicator, and assign scores to the first-level risk indicators;

[0152] Perform regression analysis on the scoring results of the above first-level risk indicators to obtain the complex correlation coefficient of each first-level risk indicator;

[0153] The complex correlation coefficients of the above-mentioned first-level risk indicators are normalized to determine the weight coefficient of each first-level risk indicator.

[0154] In some embodiments, the specific process of the third digital feature conversion module 604 is: obtaining the weight coefficient of each second-level risk indicator; determining the expectation, entropy and super entropy corresponding to the misoperation risk indicator according to the second-level cloud feature parameters corresponding to each second-level risk indicator and the weight coefficient of the corresponding second-level risk indicator; determining the third-level cloud feature parameters corresponding to the misoperation risk indicator according to the expectation, entropy and super entropy corresponding to the misoperation risk indicator.

[0155] Among them, the weight coefficient of each second-level risk indicator is obtained, including:

[0156] Rank the importance of the second-level risk indicators belonging to the misoperation risk indicators, and assign scores to the second-level risk indicators;

[0157] Perform regression analysis on the scoring results of the above second-level risk indicators to obtain the complex correlation coefficient of each second-level risk indicator;

[0158] The complex correlation coefficients of the above-mentioned second-level risk indicators are normalized to determine the weight coefficients of the second-level risk indicators.

[0159] In some embodiments, the second-level risk indicators include human indicators and environmental indicators, and the first-level risk indicators include emotional state, psychological stress, fatigue level and workload belonging to human indicators, and temperature parameters and noise parameters belonging to environmental indicators;

[0160] The risk interval values ​​for obtaining the first-level risk indicators include:

[0161] Determine the risk interval value of the operator's emotional state, psychological stress, fatigue level and workload based on the real-time collection of the operator's physiological signals and behavioral data;

[0162] The risk interval values ​​of the temperature parameters and the noise parameters are determined according to the segmented intervals of the temperature parameters and the noise parameters collected in real time at the operation site.

[0163] Figure 7 A hardware structure diagram of an electronic device provided in an embodiment of the present application, the embodiment provides an electronic device, including: a processor 701, and a memory 702 communicatively connected to the processor 701; the memory 702 stores computer execution instructions; the processor 701 executes the computer execution instructions stored in the memory 702, so as to implement the description of the multimodal risk perception method of the drilling automation system in the corresponding embodiment above.

[0164] Figure 7 The electronic device shown further includes a communication interface 703 and a communication bus 704 , wherein the processor 701 , the memory 702 and the communication interface 703 communicate with each other via the communication bus 704 .

[0165] The memory 702 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication bus 704 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of communication bus.

[0166] The communication interface 703 is used to connect to at least one user terminal and other network units through a network interface, and send the encapsulated IPv4 message or IPv4 message to the user terminal through the network interface.

[0167] The processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 701. The above processor 701 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 72, and the processor 71 reads the information in the memory 72 and completes the steps of the method of the above embodiment in combination with its hardware.

[0168] The embodiment of the present application also provides a computer storage medium, in which a computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the description of the multimodal risk perception method of the drilling automation system in the corresponding embodiment above, and therefore, will not be repeated here. In addition, the description of the beneficial effects of using the same method will not be repeated. For technical details not disclosed in the computer storage medium embodiment involved in the present invention, please refer to the description of the method embodiment of the present invention.

[0169] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The above-mentioned storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0170] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A multimodal risk perception method for a drilling automation system, characterized in that: include: Obtaining a risk interval value of the first-level risk indicator, wherein the risk interval value is determined according to the degree of influence of the first-level risk indicator on the operating personnel; Performing a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain the first-level cloud feature parameter corresponding to the first-level risk indicator; Performing a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to the second-level risk indicators, wherein the first-level risk indicators are subordinate to the second-level risk indicators; Performing a third digital feature conversion on the second-level cloud feature parameters to obtain third-level cloud feature parameters corresponding to the misoperation risk indicator, wherein the second-level risk indicator belongs to the misoperation risk indicator; The third-level cloud characteristic parameters are compared with the standard cloud characteristic parameters of different risk levels of misoperation to determine the misoperation risk level of the current operator.

2. The method according to claim 1, characterized in that The step of performing a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain a first-level cloud feature parameter corresponding to the first-level risk indicator includes: Determine the corresponding expectation, entropy and super entropy of each first-level risk indicator according to the risk interval value of each first-level risk indicator; The first-level cloud characteristic parameters corresponding to each first-level risk indicator are determined according to the expectation, entropy and super entropy corresponding to each first-level risk indicator.

3. The method according to claim 1, characterized in that: The step of performing a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to the second-level risk indicators includes: Obtain the weight coefficient of each first-level risk indicator; Determine the expectation, entropy and super entropy corresponding to each second-level risk indicator according to the first-level cloud characteristic parameters of each first-level risk indicator and the weight coefficient of the corresponding first-level risk indicator; The second-level cloud characteristic parameters corresponding to each second-level risk indicator are determined according to the expectation, entropy and super entropy corresponding to each second-level risk indicator.

4. The method according to claim 3, characterized in that The step of obtaining the weight coefficient of each first-level risk indicator includes: Rank the importance of the first-level risk indicators that belong to the same second risk indicator, and assign scores to the first-level risk indicators; Perform regression analysis on the scoring results of the above first-level risk indicators to obtain the complex correlation coefficient of each first-level risk indicator; The complex correlation coefficients of the above-mentioned first-level risk indicators are normalized to determine the weight coefficient of each first-level risk indicator.

5. The method according to claim 1, characterized in that The third step of performing a third digital feature conversion on the second-level cloud feature parameters to obtain the third-level cloud feature parameters corresponding to the misoperation risk index includes: Obtain the weight coefficient of each second-level risk indicator; Determine the expectation, entropy and super entropy corresponding to the misoperation risk indicator according to the second-level cloud characteristic parameters corresponding to each second-level risk indicator and the weight coefficient of the corresponding second-level risk indicator; According to the expectation, entropy and super entropy corresponding to the misoperation risk indicator, the third-level cloud characteristic parameters corresponding to the misoperation risk indicator are determined.

6. The method according to claim 5, characterized in that The step of obtaining the weight coefficient of each second-level risk indicator includes: Rank the importance of the second-level risk indicators belonging to the misoperation risk indicators, and assign scores to the second-level risk indicators; Perform regression analysis on the scoring results of the above second-level risk indicators to obtain the complex correlation coefficient of each second-level risk indicator; The complex correlation coefficients of the above-mentioned second-level risk indicators are normalized to determine the weight coefficients of the second-level risk indicators.

7. The method according to claim 1, characterized in that The second-level risk indicators include human indicators and environmental indicators, and the first-level risk indicators include emotional state, psychological stress, fatigue level and workload belonging to human indicators, and temperature parameters and noise parameters belonging to environmental indicators; The step of obtaining the risk interval value of the first-level risk indicator includes: Determine the risk interval value of the operator's emotional state, psychological stress, fatigue level and workload based on the real-time collection of the operator's physiological signals and behavioral data; The risk interval values ​​of the temperature parameters and the noise parameters are determined according to the segmented intervals of the temperature parameters and the noise parameters collected in real time at the operation site.

8. A multi-modal risk perception device for a drilling automation system, comprising: An acquisition module, used to acquire a risk interval value of a first-level risk indicator, wherein the risk interval value is determined according to the degree of influence of the first-level risk indicator on the operator; A first digital feature conversion module, used for performing a first digital feature conversion on the risk interval value of each first-level risk indicator to obtain a first-level cloud feature parameter corresponding to the first-level risk indicator; A second digital feature conversion module is used to perform a second digital feature conversion on the first-level cloud feature parameters to obtain second-level cloud feature parameters corresponding to the second-level risk indicators, wherein the first-level risk indicators are subordinate to the second-level risk indicators; A third digital feature conversion module, used for performing a third digital feature conversion on the second-level cloud feature parameter to obtain a third-level cloud feature parameter corresponding to the misoperation risk indicator, wherein the second-level risk indicator belongs to the misoperation risk indicator; The determination module is used to compare the third-level cloud characteristic parameters with the standard cloud characteristic parameters of different risk levels of misoperation to determine the misoperation risk level of the current operator.

9. An electronic device, comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images