A method, system, device and medium for attitude measurement of a rotary steering system

Abstract

The application provides a posture measurement method, system, device and medium of a rotary steering system, and relates to the technical field of data processing.In the application, firstly, internal semantic mining is performed on a first acceleration component sequence and a second acceleration component sequence respectively, and the results of the semantic mining are associated and fused to form a target acceleration semantic feature; then, decoding output is performed based on the target acceleration semantic feature to obtain a third acceleration component and a fourth acceleration component; further, the first acceleration component is corrected based on the third acceleration component to form a first corrected acceleration component, and the second acceleration component is corrected based on the fourth acceleration component to form a second corrected acceleration component; finally, an inclination angle is determined based on the first corrected acceleration component and the second corrected acceleration component.Based on the above, the problem that the reliability of posture measurement is relatively low in the prior art can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a pose measurement method, system, device and medium of a rotary steering system. BACKGROUND

[0002] The rotary steering system (RSS) is a guided drilling system that can complete the steering function in real time while the drill string is rotating. The rotary steering drilling system is the most advanced and highest-end technical equipment in the field of petroleum engineering, and is a key tool for achieving geological targets, improving oil and gas drilling success rate, and reducing costs and increasing efficiency. It can make the drill bit complete the direction control function in real time while the drill string is rotating. In the drilling process, especially in the geological environment where the direction of the drill bit needs to be accurately controlled, the rotary steering system plays a crucial role. In order to ensure that the steering system can complete the direction control in real time, pose measurement is particularly important. Pose measurement needs to provide real-time monitoring of the pose of the drill string (including inclination angle, azimuth angle, etc.) to achieve high-precision direction control. However, the inventors have found that in the prior art, the reliability of pose measurement is relatively low. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a pose measurement method, system, device and medium of a rotary steering system to improve the problem of relatively low reliability of pose measurement in the prior art.

[0004] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0005] A pose measurement method of a rotary steering system, comprising:

[0006] obtaining a first acceleration component and a second acceleration component of an accelerometer in a target rotary steering system at a target time, wherein the accelerometer is installed inside the drill string, and the first acceleration component belongs to the horizontal direction, and the second acceleration component belongs to the gravity direction;

[0007] obtaining a first acceleration component sequence and a second acceleration component sequence of the accelerometer within a target time period, wherein the target time period includes the target time;

[0008] respectively performing internal semantic mining on the first acceleration component sequence and the second acceleration component sequence, and performing associated fusion on the results of semantic mining to form a target acceleration semantic feature;

[0009] decoding and outputting based on the target acceleration semantic feature to obtain a third acceleration component and a fourth acceleration component, wherein the third acceleration component belongs to the horizontal direction, and the fourth acceleration component belongs to the gravity direction;

[0010] correcting the first acceleration component based on the third acceleration component to form a corresponding first corrected acceleration component, and correcting the second acceleration component based on the fourth acceleration component to form a corresponding second corrected acceleration component;

[0011] determining the inclination angle of the drill string based on a ratio between the first corrected acceleration component and the second corrected acceleration component.

[0012] In a preferred selection of the present application, in the attitude measurement method of the rotary steerable system, the step of respectively performing internal semantic mining on the first acceleration component sequence and the second acceleration component sequence, and correlatively fusing the results of semantic mining to form a target acceleration semantic feature, comprises:

[0013] performing multi-dimensional semantic mining on the first acceleration component sequence to form a plurality of first acceleration semantic features;

[0014] performing multi-dimensional semantic mining on the second acceleration component sequence to form a plurality of second acceleration semantic features;

[0015] for each of the first acceleration semantic features, performing first correlational fusion on the first acceleration semantic feature, other-dimensional first acceleration semantic features, and second acceleration semantic features of the same dimension to form a corresponding fused acceleration semantic feature;

[0016] performing second correlational fusion on the fused acceleration semantic feature corresponding to each of the first acceleration semantic features to form a target acceleration semantic feature.

[0017] In a preferred selection of the present application, in the attitude measurement method of the rotary steerable system, the step of performing multi-dimensional semantic mining on the first acceleration component sequence to form a plurality of first acceleration semantic features, comprises:

[0018] performing convolution mining on the first acceleration component sequence to form a first acceleration convolution feature;

[0019] performing frequency domain conversion on the first acceleration component sequence to form a first acceleration frequency spectrum;

[0020] performing convolution mining on the first acceleration frequency spectrum to form a first frequency spectrum convolution feature;

[0021] determining the first acceleration convolution feature and the first frequency spectrum convolution feature as first acceleration semantic features respectively to form a plurality of first acceleration semantic features.

[0022] In the preferred selection of the present application, in the attitude measurement method of the rotary steering system, the step of convoluting the first acceleration frequency spectrum to form the first frequency spectrum convolution feature includes:

[0023] masking the first acceleration frequency spectrum with low frequency offset to form a masked acceleration frequency spectrum;

[0024] respectively performing convolution processing on the first acceleration frequency spectrum and the masked acceleration frequency spectrum to form acceleration global semantic features and acceleration masked semantic features;

[0025] respectively performing compression operations of multiple sizes on the acceleration global semantic features and the acceleration masked semantic features to form acceleration global compressed features of multiple sizes and acceleration masked compressed features of multiple sizes;

[0026] for each size of the acceleration global compressed features, based on the corresponding size of the acceleration masked compressed features, performing attention processing on the acceleration global compressed features to form acceleration attention features corresponding to the acceleration global compressed features;

[0027] performing gated mapping on the fusion features of the acceleration attention features corresponding to each size of the acceleration global compressed features to form gated mapping parameters;

[0028] based on the gated mapping parameters, performing semantic information screening on the acceleration global semantic features to form the first frequency spectrum convolution feature.

[0029] In the preferred selection of the present application, in the attitude measurement method of the rotary steering system, the step of convoluting the first acceleration frequency spectrum to form the first frequency spectrum convolution feature includes:

[0030] for each of the first acceleration semantic features, respectively performing linear mapping on the first acceleration semantic feature and the first acceleration semantic features of other dimensions to form corresponding first linear mapping features and second linear mapping features, and performing gated mapping on the second linear mapping features to form corresponding gated mapping parameters, and then based on the gated mapping parameters, performing semantic information screening on the first linear mapping features to form intra-dimension fusion semantic features;

[0031] based on the second acceleration semantic features of the same dimension, performing attention processing on the intra-dimension fusion semantic features to form corresponding fusion acceleration semantic features.

[0032] In the preferred selection of the present application, in the attitude measurement method of the rotary steering system, the step of performing second associated fusion on the fusion acceleration semantic feature corresponding to each first acceleration semantic feature to form a target acceleration semantic feature comprises:

[0033] determining an attention weight parameter based on the fusion acceleration semantic feature corresponding to the first acceleration semantic feature, and performing weighted summation calculation on the fusion acceleration semantic feature corresponding to the second first acceleration semantic feature based on the first attention weight parameter to obtain a first associated semantic feature;

[0034] mapping based on the first attention weight parameter to form a second attention weight parameter, and performing weighted summation calculation on the fusion acceleration semantic feature corresponding to the first first acceleration semantic feature based on the second attention weight parameter to obtain a second associated semantic feature;

[0035] splicing, adding or mean calculating the first associated semantic feature and the second associated semantic feature to form a target acceleration semantic feature.

[0036] In the preferred selection of the present application, in the attitude measurement method of the rotary steering system, the step of performing second associated fusion on the fusion acceleration semantic feature corresponding to each first acceleration semantic feature to form a target acceleration semantic feature comprises:

[0037] performing full connection processing on the target acceleration semantic feature to form a full connection semantic feature, wherein the size of the full connection semantic feature is 1*2 or 2*1;

[0038] performing linear mapping or identity mapping on the full connection semantic feature to form a target mapping parameter, and determining a first parameter included in the target mapping parameter as a third acceleration component and a second parameter included in the target mapping parameter as a fourth acceleration component.

[0039] The present application also provides a rotary steering system attitude measurement system, comprising:

[0040] An acceleration component acquisition module is configured to acquire a first acceleration component and a second acceleration component of an accelerometer in a target rotary steering system at a target time, wherein the accelerometer is installed in the interior of a drill string, and the first acceleration component belongs to a horizontal direction and the second acceleration component belongs to a gravity direction;

[0041] obtain a first acceleration component sequence and a second acceleration component sequence of the accelerometer in a target time period, wherein the target time period comprises the target moment;

[0042] perform internal semantic mining on the first acceleration component sequence and the second acceleration component sequence respectively, and perform correlation fusion on the results of the semantic mining to form a target acceleration semantic feature;

[0043] decode and output based on the target acceleration semantic feature to obtain a third acceleration component and a fourth acceleration component, wherein the third acceleration component belongs to a horizontal direction and the fourth acceleration component belongs to a gravity direction;

[0044] correct the first acceleration component based on the third acceleration component to form a corresponding first corrected acceleration component, and correct the second acceleration component based on the fourth acceleration component to form a corresponding second corrected acceleration component;

[0045] determine the inclination angle of the drill string based on the ratio between the first corrected acceleration component and the second corrected acceleration component.

[0046] On the basis of the above, the present application further provides an electronic device comprising:

[0047] a memory for storing a computer program;

[0048] a processor connected with the memory for executing the computer program stored in the memory to realize the attitude measurement method of the rotary steerable system.

[0049] On the basis of the above, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program runs to execute the steps of the attitude measurement method of the rotary steerable system.

[0050] The application provides a posture measurement method, system, device and medium of a rotary steering system. First, a first acceleration component and a second acceleration component of an accelerometer in a target rotary steering system at a target time are obtained. Second, a first acceleration component sequence and a second acceleration component sequence of the accelerometer within a target time period are obtained. Then, internal semantic mining is performed on the first acceleration component sequence and the second acceleration component sequence respectively, and the results of the semantic mining are associated and fused to form a target acceleration semantic feature. After that, the target acceleration semantic feature is decoded and output to obtain a third acceleration component and a fourth acceleration component. Further, the first acceleration component is corrected based on the third acceleration component to form a corresponding first corrected acceleration component, and the second acceleration component is corrected based on the fourth acceleration component to form a corresponding second corrected acceleration component. Finally, the inclination angle of the drill string is determined based on the ratio between the first corrected acceleration component and the second corrected acceleration component. Based on the above, after the first acceleration component and the second acceleration component at the target time are obtained, the inclination angle is not directly determined based on the two acceleration components, but the semantic mining and association and fusion are performed based on the first acceleration component sequence and the second acceleration component sequence of the target time period including the target time, so as to realize the capture and mining of potential semantic information and realize the association constraint of the semantic information of different acceleration components. In this way, the richness and representation accuracy of the semantic information can be taken into account, and the reliability of the acceleration component correction based on the decoded output acceleration component can be ensured, so as to obtain a reliable inclination angle, and thus the problem of relatively low reliability of posture measurement in the prior art can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to make the above objectives, characteristics and advantages of the application more apparent and easy to understand, the following preferred embodiments are specifically described below with reference to the accompanying drawings.

[0052] Figure 1 The structural block diagram of the electronic device provided by the embodiments of the application is shown.

[0053] Figure 2 The schematic diagram of the posture measurement method of the rotary steering system provided by the embodiments of the application is shown.

[0054] Figure 3 The schematic diagram of the multi-dimensional semantic mining provided by the embodiments of the application is shown.

[0055] Figure 4 The schematic diagram of the convolution mining provided by the embodiments of the application is shown.

[0056] Figure 5 The schematic diagram of the posture measurement system of the rotary steering system provided by the embodiments of the application is shown. DETAILED DESCRIPTION

[0057] The technical solutions and advantages of the embodiments of the present application will be more apparent from the following description of the embodiments of the present application in conjunction with the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations.

[0058] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work are within the scope of protection of the present application.

[0059] As shown in Figure 1 The embodiments of the present application provide an electronic device. The electronic device can include a memory, a processor, and a pose measurement system of a rotary steerable system.

[0060] In detail, the memory and the processor are directly or indirectly electrically connected to realize data transmission or interaction. For example, the memory and the processor can be electrically connected through one or more communication buses or signal lines. The pose measurement system of the rotary steerable system includes at least one software function module stored in the memory in the form of software or firmware. The processor is configured to execute the executable computer programs stored in the memory, for example, the software function modules and computer programs included in the pose measurement system of the rotary steerable system, to realize the pose measurement method of the rotary steerable system provided by the embodiments of the present application.

[0061] Alternatively, the memory can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (EPROM), an electrically erasable programmable read only memory (EEPROM), etc.

[0062] The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc., and can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0063] It can be understood that Figure 1 The structure shown is only schematic, and the electronic device can further include more or fewer components than those shown in the figures, or have a different configuration from that shown in the figures, for example, it can further include a communication unit for information interaction with other devices (such as an accelerometer, etc.). Figure 1 It can be understood that Figure 1 The structure shown is only schematic, and the electronic device can further include more or fewer components than those shown in the figures, or have a different configuration from that shown in the figures, for example, it can further include a communication unit for information interaction with other devices (such as an accelerometer, etc.).

[0064] In combination with Figure 2 The embodiments of the present application also provide a posture measurement method of a rotary steering system applicable to the electronic device. The method steps defined by the flow of the posture measurement method of the rotary steering system can be implemented by the electronic device.

[0065] The specific flow shown in Figure 2 will be described in detail below.

[0066] In step S110, the first acceleration component and the second acceleration component of an accelerometer in a target rotary steering system at a target time are obtained.

[0067] In the embodiments of the present application, the electronic device can obtain the first acceleration component and the second acceleration component of an accelerometer in a target rotary steering system at a target time. The accelerometer is installed inside a drill string, and the first acceleration component is in the horizontal direction and the second acceleration component is in the gravity direction. It should be noted that the target time can be the current time (correspondingly, the first acceleration component at the target time is the last horizontal direction acceleration component output by the accelerometer, and the second acceleration component at the target time is the last gravity direction acceleration component output by the accelerometer), or other time.

[0068] In step S120, the first acceleration component sequence and the second acceleration component sequence of the accelerometer in a target time period are obtained.

[0069] In the embodiments of the present application, the electronic device can further acquire a first acceleration component sequence and a second acceleration component sequence of the accelerometer in a target time period. The target time period includes the target moment, for example, the target moment can be the last moment in the target time period, the first moment, or any intermediate moment. In addition, it should be noted that the first acceleration component of the target moment can be extracted from the first acceleration component sequence or acquired separately, and the second acceleration component of the target moment can be extracted from the second acceleration component sequence or acquired separately.

[0070] In step S130, internal semantic mining is performed on the first acceleration component sequence and the second acceleration component sequence respectively, and the results of semantic mining are associated and fused to form a target acceleration semantic feature.

[0071] In the embodiments of the present application, after the first acceleration component sequence and the second acceleration component sequence are acquired, the electronic device can further perform internal semantic mining on the first acceleration component sequence and the second acceleration component sequence respectively, and associate and fuse the results of semantic mining to form a target acceleration semantic feature. That is, internal semantic mining can be performed on the first acceleration component sequence to form a first semantic mining result, and internal semantic mining can be performed on the second acceleration component sequence to form a second semantic mining result. Then, the first semantic mining result and the second semantic mining result can be associated and fused to form a target acceleration semantic feature.

[0072] In step S140, decoding output is performed based on the target acceleration semantic feature to obtain a third acceleration component and a fourth acceleration component.

[0073] In the embodiments of the present application, after the target acceleration semantic feature is formed, the electronic device can perform decoding output based on the target acceleration semantic feature to obtain a third acceleration component and a fourth acceleration component. The third acceleration component belongs to the horizontal direction (i.e., the first acceleration component corresponding to the target moment, the first acceleration component sequence), and the fourth acceleration component belongs to the gravity direction (i.e., the second acceleration component corresponding to the target moment, the second acceleration component sequence).

[0074] In step S150, the first acceleration component is corrected based on the third acceleration component to form a corresponding first corrected acceleration component, and the second acceleration component is corrected based on the fourth acceleration component to form a corresponding second corrected acceleration component.

[0075] In the embodiments of the present application, after the third acceleration component is obtained with respect to the first acceleration component, the electronic device can correct the first acceleration component based on the third acceleration component, form a corresponding first corrected acceleration component, and correct the second acceleration component based on the fourth acceleration component, form a corresponding second corrected acceleration component. That is, the actual acceleration component is corrected based on the predicted acceleration component.

[0076] In step S160, the inclination angle of the drill string is determined based on the ratio between the first corrected acceleration component and the second corrected acceleration component.

[0077] In the embodiments of the present application, after the first corrected acceleration component and the second corrected acceleration component are obtained, the electronic device can determine the inclination angle of the drill string based on the ratio between the first corrected acceleration component and the second corrected acceleration component.

[0078] Based on the above, after the first acceleration component and the second acceleration component at the target moment are obtained, the inclination angle is not directly determined based on the two acceleration components, but semantic mining and correlation fusion are performed based on the first acceleration component sequence and the second acceleration component sequence of the target time period including the target moment, so as to realize the capture and mining of potential semantic information, and realize the correlation constraint of the semantic information of different acceleration components. In this way, the richness and representation accuracy of semantic information can be taken into account, and the reliability of the acceleration component correction based on the decoding output can be ensured, so that a reliable inclination angle is obtained. Therefore, the problem that the reliability of the attitude measurement in the prior art is relatively low can be improved.

[0079] In the first aspect, it needs to be explained that the specific manner of obtaining the first acceleration component and the second acceleration component of the accelerometer in the target rotary steering system at the target moment is not limited, and can be selected according to actual needs.

[0080] For example, in an alternative implementation, the acceleration components of an accelerometer in the horizontal direction and the gravity direction at the target moment can be obtained, so as to obtain the first acceleration component and the second acceleration component. For another example, in another alternative implementation, the acceleration components of multiple accelerometers in the horizontal direction and the gravity direction at the target moment can be obtained, and then mean value calculation is performed, so as to obtain the first acceleration component and the second acceleration component.

[0081] In the second aspect, it needs to be explained that the specific manner of obtaining the first acceleration component sequence and the second acceleration component sequence of the accelerometer in the target time period is not limited, and can be selected according to actual requirements.

[0082] For example, in an alternative implementation, the first acceleration component at each time point obtained before can be combined to form the first acceleration component sequence, and the second acceleration component at each time point obtained before can be combined to form the second acceleration component sequence, that is, the target time period can be a time period from when the drill string starts to work to the current time point. For another example, in another alternative implementation, the first acceleration component in a recent period of time obtained before can be combined to form the first acceleration component sequence, and the second acceleration component in the recent period of time obtained before can be combined to form the second acceleration component sequence, that is, the target time period can be a recent time period, and the specific time length is not limited and can be configured according to actual requirements. For example, in consideration of the amount of calculation, the time length of the target time period can be small, and in consideration of the calculation accuracy, the time length of the target time period can be large to ensure that more potential semantic information can be mined.

[0083] In the third aspect, it needs to be explained that the specific manner of forming the target acceleration semantic feature is not limited and can be selected according to actual requirements.

[0084] For example, in an alternative implementation, in order to ensure that the target acceleration semantic feature formed can represent the acceleration components in two directions and also take into account the richness and accuracy of semantic information, the above-mentioned step S130 can further include steps S131, S132, S133 and S134, and the specific contents of each step are as follows.

[0085] Step S131: performing multi-dimensional semantic mining in the first acceleration component sequence to form a plurality of first acceleration semantic features.

[0086] In the embodiments of the present application, multi-dimensional semantic mining can be performed in the first acceleration component sequence to form a plurality of first acceleration semantic features. For example, semantic mining can be performed in the time domain to form a corresponding first acceleration semantic feature, and for another example, semantic mining can be performed in the frequency domain to form a corresponding first acceleration semantic feature.

[0087] Step S132: performing multi-dimensional semantic mining in the second acceleration component sequence to form a plurality of second acceleration semantic features.

[0088] In the embodiments of the present application, multi-dimension semantic mining can be performed on the second acceleration component sequence to form a plurality of second acceleration semantic features. For example, semantic mining can be performed in the time domain to form a corresponding second acceleration semantic feature. For another example, semantic mining can be performed in the frequency domain to form a corresponding second acceleration semantic feature. It should be noted that the manner of performing multi-dimension semantic mining in step S132 can be the same as the manner of performing multi-dimension semantic mining in step S131, and the specific mining manner can be referred to the relevant description hereinafter.

[0089] In step S133, for each first acceleration semantic feature, the first acceleration semantic feature, other-dimension first acceleration semantic features, and same-dimension second acceleration semantic features are first associated and fused to form a corresponding fused acceleration semantic feature.

[0090] In the embodiments of the present application, after obtaining the plurality of first acceleration semantic features and the plurality of second acceleration semantic features, for each first acceleration semantic feature, the first acceleration semantic feature, other-dimension first acceleration semantic features, and same-dimension second acceleration semantic features can be first associated and fused to form a corresponding fused acceleration semantic feature. For example, for a time-domain first acceleration semantic feature, the first acceleration semantic feature, a frequency-domain first acceleration semantic feature, and a time-domain second acceleration semantic feature can be first associated and fused to form a first fused acceleration semantic feature. For another example, for a frequency-domain first acceleration semantic feature, the first acceleration semantic feature, a time-domain first acceleration semantic feature, and a frequency-domain second acceleration semantic feature can be first associated and fused to form a second fused acceleration semantic feature.

[0091] In step S134, the fused acceleration semantic features corresponding to each first acceleration semantic feature are second associated and fused to form a target acceleration semantic feature.

[0092] In the embodiments of the present application, after obtaining the fused acceleration semantic features corresponding to each first acceleration semantic feature, the fused acceleration semantic features corresponding to each first acceleration semantic feature can be second associated and fused to form a target acceleration semantic feature. For example, the first fused acceleration semantic feature and the second fused acceleration semantic feature can be second associated and fused to form a target acceleration semantic feature.

[0093] It can be understood that the specific manner of performing multi-dimensional semantic mining in step S131 is not limited, for example, in an alternative embodiment, in order to ensure that the plurality of first acceleration semantic features mined can represent more detailed information, step S131 can further include steps S131a, S131b, S131c and S131d, the specific content of each step is described below, combined with Figure 3

[0094] Step S131a, performing convolution mining on the first acceleration component sequence to form a first acceleration convolution feature.

[0095] In the embodiment of the present application, the first acceleration component sequence can be subjected to convolution mining to form a first acceleration convolution feature. Illustratively, the convolution mining can be implemented through a convolution neural network layer, which can include convolution layer 1, pooling layer 1, fully connected layer 1, convolution layer 2, pooling layer 2 and fully connected layer 2 connected in turn. Based on this, semantic mining of the first acceleration component sequence in the time domain dimension can be achieved.

[0096] Step S131b, performing frequency domain conversion on the first acceleration component sequence to form a first acceleration frequency spectrum.

[0097] In the embodiment of the present application, the first acceleration component sequence can be subjected to frequency domain conversion to form a first acceleration frequency spectrum. Illustratively, the first acceleration component sequence can be subjected to Fourier transform to form a first acceleration frequency spectrum.

[0098] Step S131c, performing convolution mining on the first acceleration frequency spectrum to form a first frequency spectrum convolution feature.

[0099] In the embodiment of the present application, after obtaining the first acceleration frequency spectrum, convolution mining can be performed on the first acceleration frequency spectrum to form a first frequency spectrum convolution feature. Based on this, semantic mining of the first acceleration component sequence in the frequency domain dimension can be achieved.

[0100] Step S131d, determining the first acceleration convolution feature and the first frequency spectrum convolution feature as first acceleration semantic features, respectively, to form a plurality of first acceleration semantic features.

[0101] ​In the embodiments of the present application, after the first acceleration convolution feature and the first frequency spectrum convolution feature are obtained, the first acceleration convolution feature and the first frequency spectrum convolution feature can be determined as first acceleration semantic features respectively to form a plurality of first acceleration semantic features. It should be noted that the first acceleration convolution feature can be a first acceleration semantic feature in the time domain dimension, and the first frequency spectrum convolution feature can be a first acceleration semantic feature in the frequency domain dimension.

[0102] It can be understood that the specific manner of convolution mining of the first acceleration frequency spectrum in the above step S131c is not limited. For example, in an alternative embodiment, in order to capture more detailed information in the process of convolution mining and avoid the problem of semantic distortion caused by the drift of the accelerometer, the above step S131c can further include steps c1, c2, c3, c4, c5 and c6, the specific contents of each step are as follows, in combination with Figure 4

[0103] Step c1, the first acceleration frequency spectrum is subjected to low-frequency offset masking to form a masked acceleration frequency spectrum.

[0104] In the embodiments of the present application, the first acceleration frequency spectrum can be subjected to low-frequency offset masking to form a masked acceleration frequency spectrum. For example, a low-frequency threshold can be configured according to actual conditions, and then the region corresponding to the low-frequency threshold in the first acceleration frequency spectrum can be masked, such as being multiplied by a masking matrix (the size of which is the same as that of the first acceleration frequency spectrum), the value of the region corresponding to the low-frequency threshold in the masking matrix is 0, and the value of the other regions is 1.

[0105] Step c2, the first acceleration frequency spectrum and the masked acceleration frequency spectrum are subjected to convolution processing respectively to form acceleration global semantic features and acceleration masked semantic features.

[0106] In the embodiments of the present application, after the masked acceleration frequency spectrum is formed, the first acceleration frequency spectrum and the masked acceleration frequency spectrum can be subjected to convolution processing respectively to form acceleration global semantic features and acceleration masked semantic features. For example, the first acceleration frequency spectrum can be subjected to convolution processing (which can be realized by a convolution layer, a pooling layer and a full connection layer) to obtain acceleration global semantic features, and the masked acceleration frequency spectrum can be subjected to convolution processing to obtain acceleration masked semantic features.

[0107] ​Step c3, performing compression operations of multiple sizes on the acceleration global semantic feature and the acceleration occlusion semantic feature respectively to form acceleration global compressed features of multiple sizes and acceleration occlusion compressed features of multiple sizes.

[0108] In the embodiments of the present application, after obtaining the acceleration global semantic feature and the acceleration occlusion semantic feature, compression operations of multiple sizes can be performed on the acceleration global semantic feature and the acceleration occlusion semantic feature respectively to form acceleration global compressed features of multiple sizes and acceleration occlusion compressed features of multiple sizes. For example, based on a first downsampling parameter, downsampling processing can be performed on the acceleration global semantic feature and the acceleration occlusion semantic feature to obtain acceleration global compressed features of a first size and acceleration occlusion compressed features of the first size. For another example, based on a second downsampling parameter, downsampling processing can be performed on the acceleration global semantic feature and the acceleration occlusion semantic feature to obtain acceleration global compressed features of a second size and acceleration occlusion compressed features of the second size.

[0109] Step c4, for each size of the acceleration global compressed feature, based on the acceleration occlusion compressed feature of the corresponding size, attention processing is performed on the acceleration global compressed feature to form an acceleration attention feature corresponding to the acceleration global compressed feature.

[0110] In the embodiments of the present application, after obtaining the acceleration global compressed features of multiple sizes and the acceleration occlusion compressed features of multiple sizes, for each size of the acceleration global compressed feature, based on the acceleration occlusion compressed feature of the corresponding size, attention processing can be performed on the acceleration global compressed feature to form an acceleration attention feature corresponding to the acceleration global compressed feature. For example, based on the acceleration occlusion compressed feature of the first size, attention processing can be performed on the acceleration global compressed feature of the first size to form a first acceleration attention feature. For another example, based on the acceleration occlusion compressed feature of the second size, attention processing can be performed on the acceleration global compressed feature of the second size to form a second acceleration attention feature.

[0111] Step c5, performing gating mapping on a fusion feature of the acceleration attention feature corresponding to each size of the acceleration global compressed feature to form a gating mapping parameter.

[0112] In the embodiments of the present application, after obtaining the acceleration attention feature, the fusion feature of the acceleration attention feature corresponding to the acceleration global compression feature of each size can be mapped by a gating mechanism to form a gating mapping parameter. For example, the acceleration attention features corresponding to the acceleration global compression features of each size can be spliced, and the spliced result can be compressed to form a fusion feature. Then, the fusion feature can be linearly mapped by a fully connected layer (the size of the mapping result is the same as that of the acceleration global semantic feature), and finally, the linearly mapped result can be activated by a sigmiod function to form the gating mapping parameter.

[0113] In step c6, the acceleration global semantic feature is subjected to semantic information screening based on the gating mapping parameter to form a first spectral graph convolution feature.

[0114] In the embodiments of the present application, after forming the gating mapping parameter, the acceleration global semantic feature can be subjected to semantic information screening based on the gating mapping parameter to form a first spectral graph convolution feature. For example, the size of the gating mapping parameter can be the same as that of the acceleration global semantic feature, so that the gating mapping parameter and the acceleration global semantic feature can be multiplied by bit to form a corresponding first spectral graph convolution feature. Based on this, the first acceleration spectral graph and the masked acceleration spectral graph can be subjected to attention processing to mine associated semantic information, that is, to effectively capture important semantic information. Then, based on the captured important semantic information, the semantic information in the first acceleration spectral graph can be screened based on a gating mechanism. Thus, compared with a scheme of directly gating and screening two semantic features, the quality of the formed gating mapping parameter can be further improved, thereby realizing reliable semantic information screening and ensuring that the obtained first spectral graph convolution feature has high semantic representation accuracy.

[0115] It can be understood that in the above step S133, the specific manner of forming the corresponding fusion acceleration semantic feature by first association and fusion is not limited. For example, in an alternative embodiment, in order to ensure that the accuracy and computational complexity of semantic information fusion are taken into account, the above step S133 can further include steps S133a and S133b, and the specific contents of each step are described as follows.

[0116] Step S133a: For each of the first acceleration semantic features, the first acceleration semantic feature and the first acceleration semantic features of other dimensions are linearly mapped to form corresponding first linear mapping features and second linear mapping features. Then, the second linear mapping features are gated to form corresponding gated mapping parameters. Based on the gated mapping parameters, the first linear mapping features are semantically filtered to form intra-dimensional fused semantic features.

[0117] In this embodiment, for each first acceleration semantic feature, the first acceleration semantic feature (e.g., time domain dimension) and other dimensions of first acceleration semantic features (e.g., frequency domain dimension) can be linearly mapped (e.g., through a fully connected layer) to form corresponding first linear mapping features and second linear mapping features. Then, the second linear mapping features are gated (e.g., through functions such as sigmoid) to form corresponding gated mapping parameters. Based on the gated mapping parameters, the first linear mapping features are semantically filtered (e.g., by bitwise multiplication) to form intra-dimensional fused semantic features. In other words, for acceleration components in the same direction, since the semantic information is similar, fusion can be achieved through a gating mechanism.

[0118] Step S133b: Based on the second acceleration semantic features of the same dimension, attention processing is performed on the fused semantic features within the dimension to form corresponding fused acceleration semantic features.

[0119] In this embodiment, after forming the intra-dimensional fused semantic features, attention processing can be performed on the intra-dimensional fused semantic features based on the second acceleration semantic features of the same dimension (for example, when the first acceleration semantic features of other dimensions belong to the frequency domain dimension, the second acceleration semantic features of the same dimension belong to the time domain dimension), to form corresponding fused acceleration semantic features. In other words, an attention mechanism can be used to fuse acceleration components in different directions, ensuring the accuracy of the fusion.

[0120] It is understood that the specific method of performing the second association fusion to form the target acceleration semantic features in step S134 above is not limited. For example, in an alternative implementation, in order to balance the accuracy of semantic information fusion and the consumption of computing resources, step S134 above may further include steps S134a, S134b and S134c, the specific contents of each step are as follows.

[0121] Step S134a, determining an attention weight parameter based on the fusion acceleration semantic feature corresponding to the first first acceleration semantic feature, and performing weighted summation calculation on the fusion acceleration semantic feature corresponding to the second first acceleration semantic feature based on the first attention weight parameter to obtain a first associated semantic feature.

[0122] In the embodiment of the present application, the attention weight parameter can be determined based on the fusion acceleration semantic feature corresponding to the first first acceleration semantic feature, and the weighted summation calculation can be performed on the fusion acceleration semantic feature corresponding to the second first acceleration semantic feature based on the first attention weight parameter to obtain the first associated semantic feature.

[0123] Step S134b, mapping based on the first attention weight parameter to form a second attention weight parameter, and performing weighted summation calculation on the fusion acceleration semantic feature corresponding to the first first acceleration semantic feature based on the second attention weight parameter to obtain a second associated semantic feature.

[0124] In the embodiment of the present application, after obtaining the first attention weight parameter, the second attention weight parameter can also be obtained by mapping (such as linear mapping) based on the first attention weight parameter, and the weighted summation calculation can be performed on the fusion acceleration semantic feature corresponding to the first first acceleration semantic feature based on the second attention weight parameter to obtain the second associated semantic feature. That is, since the first attention weight parameter and the second attention weight parameter actually have a certain relationship, and the calculation amount is large by calculating the attention weight parameter again, the second attention weight parameter can be directly obtained by mapping, thereby reducing the calculation amount.

[0125] Step S134c, concatenating, adding or mean calculating the first associated semantic feature and the second associated semantic feature to form a target acceleration semantic feature.

[0126] In the embodiment of the present application, after obtaining the first associated semantic feature and the second associated semantic feature, the first associated semantic feature and the second associated semantic feature can be concatenated, added or mean calculated to form the target acceleration semantic feature.

[0127] For step S140, the specific manner of decoding and outputting based on the target acceleration semantic feature is not limited and can be selected according to actual requirements.

[0128] For example, in an alternative implementation, step S140 can further include the following content:

[0129] First, the target acceleration semantic feature can be fully connected to form a fully connected semantic feature, wherein the size of the fully connected semantic feature is 1*2 or 2*1.

[0130] Second, the fully connected semantic feature can be linearly mapped or identity mapped (such as y=x) to form a target mapping parameter, and a first parameter included in the target mapping parameter is determined as a third acceleration component and a second parameter included in the target mapping parameter is determined as a fourth acceleration component.

[0131] For step S150, the specific manner of correcting the acceleration components is not limited and can be selected according to actual requirements.

[0132] For example, in an alternative implementation, the third acceleration component and the first acceleration component can be calculated by mean or weighted summation to obtain a first corrected acceleration component. And the fourth acceleration component and the second acceleration component can be calculated by mean or weighted summation to obtain a second corrected acceleration component.

[0133] For step S160, the specific manner of determining the inclination angle of the drill string is not limited and can be selected according to actual requirements.

[0134] For example, in an alternative implementation, the ratio between the first corrected acceleration component and the second corrected acceleration component can be calculated, and then the ratio can be calculated based on an inverse tangent function to obtain the inclination angle of the drill string.

[0135] In combination Figure 5 The embodiments of the present application also provide a posture measurement system of a rotary steering system which can be applied to the electronic device. The posture measurement system of the rotary steering system can include an acceleration component acquisition module, a component sequence acquisition module, a semantic mining fusion module, a semantic feature decoding module, an acceleration component correction module, and an inclination angle determination module.

[0136] In detail, the acceleration component obtaining module can be configured to obtain a first acceleration component and a second acceleration component of an accelerometer in a target rotary steerable system at a target moment, wherein the accelerometer is installed in an interior of a drill string, and the first acceleration component belongs to a horizontal direction, and the second acceleration component belongs to a gravity direction. In the embodiment of the present application, the acceleration component obtaining module can be configured to execute Figure 2 The step S110 is shown, and the related content of the acceleration component obtaining module can be referred to the foregoing description of the step S110.

[0137] In detail, the component sequence obtaining module can be configured to obtain a first acceleration component sequence and a second acceleration component sequence of the accelerometer in a target time period, wherein the target time period includes the target moment. In the embodiment of the present application, the component sequence obtaining module can be configured to execute Figure 2 The step S120 is shown, and the related content of the component sequence obtaining module can be referred to the foregoing description of the step S120.

[0138] In detail, the semantic mining and fusion module can be configured to respectively perform internal semantic mining on the first acceleration component sequence and the second acceleration component sequence, and perform associated fusion on the results of the semantic mining to form a target acceleration semantic feature. In the embodiment of the present application, the semantic mining and fusion module can be configured to execute Figure 2 The step S130 is shown, and the related content of the semantic mining and fusion module can be referred to the foregoing description of the step S130.

[0139] In detail, the semantic feature decoding module can be configured to perform decoding output based on the target acceleration semantic feature to obtain a third acceleration component and a fourth acceleration component, wherein the third acceleration component belongs to a horizontal direction, and the fourth acceleration component belongs to a gravity direction. In the embodiment of the present application, the semantic feature decoding module can be configured to execute Figure 2 The step S140 is shown, and the related content of the semantic feature decoding module can be referred to the foregoing description of the step S140.

[0140] In detail, the acceleration component correction module can be configured to correct the first acceleration component based on the third acceleration component to form a corresponding first corrected acceleration component, and correct the second acceleration component based on the fourth acceleration component to form a corresponding second corrected acceleration component. In the embodiment of the present application, the acceleration component correction module can be configured to execute Figure 2 The step S150 is shown, and the related content of the acceleration component correction module can be referred to the foregoing description of the step S150.

[0141] In detail, the inclination angle determining module can be configured to determine the inclination angle of the drill string based on a ratio between the first corrected acceleration component and the second corrected acceleration component. In the embodiments of the present application, the inclination angle determining module can be configured to perform the following steps Figure 2 The step S160 is shown, and the related content of the inclination angle determining module can be referred to the foregoing description of the step S160.

[0142] In the embodiments of the present application, corresponding to the above-mentioned attitude measurement method applied to the rotary steerable system of the electronic device, a computer readable storage medium is also provided, and the computer readable storage medium stores a computer program. When the computer program runs, it executes each step of the attitude measurement method of the rotary steerable system.

[0143] In the embodiments of the present application, corresponding to the above-mentioned attitude measurement method applied to the rotary steerable system of the electronic device, a computer readable storage medium is also provided, and the computer readable storage medium stores a computer program. When the computer program runs, it executes each step of the attitude measurement method of the rotary steerable system.

[0144] In summary, the attitude measurement method, system, device and medium of the rotary steerable system provided by the present application, first, the first acceleration component and the second acceleration component of the accelerometer in the target rotary steerable system at the target time are obtained; secondly, the first acceleration component sequence and the second acceleration component sequence of the accelerometer in the target time period are obtained; then, the first acceleration component sequence and the second acceleration component sequence are respectively subjected to internal semantic mining, and the results of the semantic mining are associated and fused to form a target acceleration semantic feature; then, the target acceleration semantic feature is decoded and output to obtain a third acceleration component and a fourth acceleration component; further, the first acceleration component is corrected based on the third acceleration component to form a corresponding first corrected acceleration component, and the second acceleration component is corrected based on the fourth acceleration component to form a corresponding second corrected acceleration component; finally, the inclination angle of the drill string is determined based on the ratio between the first corrected acceleration component and the second corrected acceleration component. Based on the above, after obtaining the first acceleration component and the second acceleration component at the target time, the inclination angle is not directly determined based on the two acceleration components, but the first acceleration component sequence and the second acceleration component sequence of the target time period including the target time are subjected to semantic mining and associated fusion, so as to realize the capture and mining of potential semantic information, and realize the associated constraint of the semantic information of different acceleration components. In this way, the richness and representation accuracy of the semantic information can be taken into account, and the reliability of the acceleration component correction based on the decoding output can be ensured, so as to obtain a reliable inclination angle, and thus the problem of relatively low reliability of attitude measurement in the prior art can be improved.

[0145] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus and method embodiments described above are only illustrative. For example, the flowchart and block diagram in the drawings show the possible implementation architecture, function and operation of the apparatus, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, which includes one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different order from that shown in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the function involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for implementing the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0146] In addition, each functional module in the embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0147] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes. It should be noted that in this document, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the processes, methods, articles or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or device that includes the element.

[0148] The above descriptions are only the preferred embodiments of the present application, and are not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for measuring the attitude of a rotary guidance system, characterized in that, include: The first acceleration component and the second acceleration component of the accelerometer in the target rotation guidance system are obtained at the target time, wherein the accelerometer is installed inside the drill string, and the first acceleration component is in the horizontal direction and the second acceleration component is in the direction of gravity. Obtain the first acceleration component sequence and the second acceleration component sequence of the accelerometer within a target time period, wherein the target time period includes the target moment; Multi-dimensional semantic mining is performed within the first acceleration component sequence to form multiple first acceleration semantic features; multi-dimensional semantic mining is also performed within the second acceleration component sequence to form multiple second acceleration semantic features; for each first acceleration semantic feature, the first acceleration semantic feature, first acceleration semantic features of other dimensions, and second acceleration semantic features of the same dimension are first associated and fused to form a corresponding fused acceleration semantic feature; the fused acceleration semantic features corresponding to each first acceleration semantic feature are second associated and fused to form a target acceleration semantic feature; The target acceleration semantic features are processed by a fully connected layer to form fully connected semantic features; the fully connected semantic features are then mapped by a linear or identity mapping to form target mapping parameters; and the first parameter included in the target mapping parameters is determined as the third acceleration component and the second parameter included in the target mapping parameters is determined as the fourth acceleration component, wherein the third acceleration component belongs to the horizontal direction and the fourth acceleration component belongs to the gravitational direction. The first corrected acceleration component is obtained by averaging or weighted summing the third acceleration component and the first acceleration component, and the second corrected acceleration component is obtained by averaging or weighted summing the fourth acceleration component and the second acceleration component. The inclination angle of the drill string is determined based on the ratio between the first corrected acceleration component and the second corrected acceleration component.

2. The attitude measurement method for a rotary guide system according to claim 1, characterized in that, The step of performing multi-dimensional semantic mining within the first acceleration component sequence to form multiple first acceleration semantic features includes: The first acceleration component sequence is subjected to convolution mining to form the first acceleration convolution feature; The first acceleration component sequence is frequency domain transformed to form a first acceleration spectrum. Convolution mining is performed on the first acceleration spectrum to form the first spectrum convolution feature; The first acceleration convolution feature and the first spectrogram convolution feature are respectively determined as the first acceleration semantic features to form multiple first acceleration semantic features.

3. The attitude measurement method for the rotary guide system according to claim 2, characterized in that, The step of performing convolution mining on the first acceleration spectrum to form convolutional features of the first spectrum includes: The first acceleration spectrum is masked by low-frequency offset to form a masked acceleration spectrum. The first acceleration spectrum map and the occluded acceleration spectrum map are convolved respectively to form global acceleration semantic features and acceleration occlusion semantic features; Multiple compression operations of different sizes are performed on the global acceleration semantic features and the acceleration occlusion semantic features respectively to form global acceleration compressed features of multiple sizes and acceleration occlusion compressed features of multiple sizes; For each size of the global acceleration compression feature, based on the corresponding size of the acceleration occlusion compression feature, attention processing is performed on the global acceleration compression feature to form the acceleration attention feature corresponding to the global acceleration compression feature; The fused features of acceleration attention features corresponding to the global acceleration compression features of each size are gated and mapped to form gated mapping parameters. Based on the gating mapping parameters, semantic information is filtered from the global semantic features of acceleration to form the first spectrogram convolutional features.

4. The attitude measurement method for a rotary guide system according to claim 1, characterized in that, The step of performing a first association fusion on each of the first acceleration semantic features, the first acceleration semantic features of other dimensions, and the second acceleration semantic features of the same dimension to form a corresponding fused acceleration semantic feature includes: For each of the first acceleration semantic features, the first acceleration semantic feature and the first acceleration semantic features of other dimensions are linearly mapped to form corresponding first linear mapping features and second linear mapping features. Then, the second linear mapping features are gated to form corresponding gated mapping parameters. Based on the gated mapping parameters, the first linear mapping features are filtered for semantic information to form intra-dimensional fused semantic features. Based on the second acceleration semantic features of the same dimension, attention processing is performed on the fused semantic features within the same dimension to form the corresponding fused acceleration semantic features.

5. The attitude measurement method for a rotary guide system according to claim 1, characterized in that, The step of performing a second association fusion on the fused acceleration semantic features corresponding to each of the first acceleration semantic features to form the target acceleration semantic features includes: Based on the fused acceleration semantic feature corresponding to the first first acceleration semantic feature, attention weights are determined for the fused acceleration semantic feature corresponding to the second first acceleration semantic feature to form a first attention weight parameter. Based on the first attention weight parameter, a weighted summation is performed on the fused acceleration semantic feature corresponding to the second first acceleration semantic feature to obtain a first associated semantic feature. Based on the first attention weight parameter, a second attention weight parameter is formed by mapping; and based on the second attention weight parameter, a weighted summation is performed on the fused acceleration semantic feature corresponding to the first first acceleration semantic feature to obtain the second associated semantic feature. The first associated semantic feature and the second associated semantic feature are concatenated, added, or averaged to form the target acceleration semantic feature.

6. An attitude measurement system for a rotary guidance system, characterized in that, include: An acceleration component acquisition module is used to acquire the first acceleration component and the second acceleration component of the accelerometer in the target rotation guidance system at the target time, wherein the accelerometer is installed inside the drill string, and the first acceleration component is in the horizontal direction, and the second acceleration component is in the direction of gravity. The component sequence acquisition module is used to acquire the first acceleration component sequence and the second acceleration component sequence of the accelerometer within a target time period, wherein the target time period includes the target time. The semantic mining and fusion module is used to perform multi-dimensional semantic mining within the first acceleration component sequence to form multiple first acceleration semantic features; and to perform multi-dimensional semantic mining within the second acceleration component sequence to form multiple second acceleration semantic features; for each first acceleration semantic feature, the module performs a first association fusion with the first acceleration semantic feature, other first acceleration semantic features of different dimensions, and second acceleration semantic features of the same dimension to form a corresponding fused acceleration semantic feature; and performs a second association fusion with the fused acceleration semantic features corresponding to each first acceleration semantic feature to form a target acceleration semantic feature. The semantic feature decoding module is used to perform fully connected processing on the target acceleration semantic features to form fully connected semantic features; to perform linear mapping or identity mapping on the fully connected semantic features to form target mapping parameters; and to determine the first parameter included in the target mapping parameters as the third acceleration component and the second parameter included as the fourth acceleration component, wherein the third acceleration component belongs to the horizontal direction and the fourth acceleration component belongs to the gravitational direction. An acceleration component correction module is used to calculate the mean or weighted summation of the third acceleration component and the first acceleration component to obtain a first corrected acceleration component, and to calculate the mean or weighted summation of the fourth acceleration component and the second acceleration component to obtain a second corrected acceleration component. The tilt angle determination module is used to determine the tilt angle of the drill string based on the ratio between the first corrected acceleration component and the second corrected acceleration component.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor connected to the memory is used to execute the computer program stored in the memory to implement the attitude measurement method of the rotary guide system according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains a computer program that, when executed, performs the attitude measurement method of the rotary guide system according to any one of claims 1-5.

Images