Automated in situ testing method, system, program product, and electronic device
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NORTHWEST ENGINEERING CORPORATION LIMITED
- Filing Date
- 2025-10-30
- Publication Date
- 2026-07-21
Smart Images
Figure CN121275520B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of in-situ testing technology, and more specifically, to an automated in-situ testing method, an automated in-situ testing system, a computer program product, and an electronic device. Background Technology
[0002] In-situ testing is a key technology for obtaining relevant survey data for offshore wind power, and standard penetration testing is a widely used in-situ testing method.
[0003] The standard penetration test (SPT) method uses a specified mass of weight to fall freely from a fixed height, driving a penetration hammer into the soil. By recording the number of blows required for the penetration hammer to reach a fixed depth in the soil, the engineering characteristics of the soil layer are indirectly reflected.
[0004] In related technologies, during standard penetration testing, the penetration hammer cannot disengage in time, causing the probe rod to be pulled up and deviate from the hole position, resulting in poor accuracy. Summary of the Invention
[0005] The purpose of this disclosure is to provide an automated in-situ testing method, an automated in-situ testing system, a computer program product, and an electronic device, thereby overcoming, to at least a certain extent, the problem that the penetration hammer cannot be disengaged in a timely manner due to the limitations and defects of related technologies.
[0006] According to one aspect of this disclosure, an automated in-situ testing method is provided, comprising:
[0007] The winch in the standard penetration method is detected to start lifting the penetration hammer, and the stroke displacement of the winch is monitored in real time by a displacement sensor installed on the winch.
[0008] The displacement sensor detects that the travel displacement of the winch has reached the upper limit position. When the lifting state of the penetrating hammer is stable, the unhooking mechanism is triggered to release the penetrating hammer according to the first verification result and the second verification result.
[0009] When the displacement sensor detects that the travel displacement of the winch has reached the lower limit position, it sends an indication signal to the control system, so that the control system drives the unhooking mechanism to release the penetrating hammer.
[0010] In one exemplary embodiment of this disclosure, triggering the release mechanism to release the penetration hammer based on the first verification result and the second verification result includes:
[0011] Acceleration and tension are collected in real time by an acceleration sensor installed in the penetrating hammer and a tension sensor in the wire rope.
[0012] A first verification result is obtained by performing dual verification based on the acceleration and the tension.
[0013] The soil type, penetration data, and state data of the penetrator are obtained, and the soil type, penetration data, and state data are fitted by a first machine learning model to obtain a second verification result.
[0014] Based on the first verification result and the second verification result, the penetration hammer is released at the target release time.
[0015] In one exemplary embodiment of this disclosure, the step of performing dual verification based on the acceleration and the tension to obtain a first verification result includes:
[0016] If the detected acceleration is the first value, the tension remains unchanged at the second value, the lifting state is the hovering state, and the first verification result is that the release condition is met.
[0017] In an exemplary embodiment of this disclosure, the state data includes tensile fluctuation amplitude and acceleration fluctuation amplitude; the step of fitting the soil type, penetration data, and state data using a first machine learning model to obtain a second verification result includes:
[0018] Determine the stability characteristics of the state based on the amplitude of tension fluctuation and acceleration fluctuation in the state data;
[0019] The soil type, the penetration data, the state data, and the stability features are integrated into the input features, and the first machine learning model is used to perform a convolution operation on the input features to obtain the dynamic threshold.
[0020] The state data is compared with the dynamic threshold to determine the second verification result.
[0021] In one exemplary embodiment of this disclosure, the step of integrating the soil type, the penetration data, the state data, and the stability features into input features, and then performing a convolution operation on the input features using the first machine learning model to obtain a dynamic threshold, includes:
[0022] Local feature extraction is performed on the input features to obtain multiple local features;
[0023] The local features are fused together, and the fused features are then convolved to extract higher-order features.
[0024] The higher-order features are mapped to obtain the predicted dynamic threshold;
[0025] The predicted dynamic threshold is determined by performing boundary verification based on the standard penetration parameters, and the dynamic threshold includes an upper limit threshold.
[0026] In one exemplary embodiment of this disclosure, releasing the penetration hammer at the target release timing based on the first verification result and the second verification result includes:
[0027] Based on the first verification result and the second verification result, it is determined that decoupling is allowed, and the standard decoupling time is determined as the target release timing, and the penetration hammer is released.
[0028] Based on the first verification result and the second verification result, it is determined that decoupling is prohibited. A delay time is added to the standard decoupling time to determine the release timing of the target and trigger the release of the penetration hammer.
[0029] In one exemplary embodiment of this disclosure, the method further includes:
[0030] The key data is input into the second machine learning model, which outputs the danger probability of the travel displacement, and determines the upper or lower limit of the prediction position based on the danger probability.
[0031] The time series data corresponding to the key data is input into the long short-term memory network model to extract time series features, and combined with the equipment parameters of the winch, the dynamic correction coefficient is determined.
[0032] The upper or lower prediction limit position is adjusted according to the dynamic correction parameters to obtain the adjusted upper or lower prediction limit position.
[0033] The upper limit position is determined based on the predicted upper limit position and the adjusted upper limit position, and the lower limit position is determined based on the predicted lower limit position and the adjusted lower limit position.
[0034] According to one aspect of this disclosure, an automated in-situ testing system is provided, comprising:
[0035] The stroke displacement monitoring module is used to detect the start of the winch lifting the penetration hammer in the standard penetration method, and monitors the stroke displacement of the winch in real time through the displacement sensor installed on the winch.
[0036] The first release module is used to trigger the unhooking mechanism to release the penetrating hammer when the displacement sensor detects that the travel displacement of the winch has reached the upper limit position and the lifting state of the penetrating hammer is stable, based on the first verification result and the second verification result.
[0037] The second release module is used to send an indication signal to the control system when the displacement sensor detects that the travel displacement of the winch has reached the lower limit position, so that the control system drives the unhooking mechanism to release the penetration hammer.
[0038] According to one aspect of this disclosure, a computer program product is provided, which, when executed by a processor, implements the automated in-situ testing method described in any of the preceding claims.
[0039] According to one aspect of this disclosure, an electronic device is provided, comprising:
[0040] processor;
[0041] Memory for storing the executable instructions of the processor;
[0042] The processor is configured to implement the automated in-situ testing method described above by executing the executable instructions.
[0043] In the technical solution provided in this embodiment, by comparing the stroke displacement of the winch with the upper and lower limit positions, the unhooking structure can be triggered in time to release the penetration hammer, avoiding the problems of the penetration hammer not being able to unhook in time and deviating from the hole position in related technologies, thus improving the accuracy and reliability of the penetration hammer release.
[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.
[0046] Figure 1 The schematic diagram illustrates the process flow of the automated in-situ testing method in an embodiment of this disclosure.
[0047] Figure 2 This diagram illustrates the determination of the upper and lower limit positions in an embodiment of the present disclosure.
[0048] Figure 3 The flowchart illustrating the release of the penetrating hammer is shown in an embodiment of this disclosure.
[0049] Figure 4 A schematic block diagram of an automated in-situ testing system according to an embodiment of this disclosure is shown.
[0050] Figure 5 A schematic block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation
[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.
[0052] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0053] Based on this, this disclosure provides an automated in-situ testing method that can be applied to the release of the penetration hammer in in-situ testing. Figure 1 The diagram illustrates an automated in-situ testing method. (See reference...) Figure 1 As shown, the method mainly includes the following steps:
[0054] Step S110: It is detected that the winch in the standard penetration method starts to lift the penetration hammer, and the stroke displacement of the winch is monitored in real time by the displacement sensor installed on the winch.
[0055] Step S120: The displacement sensor detects that the travel displacement of the winch has reached the upper limit position. When the lifting state of the penetrating hammer is stable, the unhooking mechanism is triggered to release the penetrating hammer according to the first verification result and the second verification result.
[0056] In step S130, when the displacement sensor detects that the travel displacement of the winch has reached the lower limit position, it sends an indication signal to the control system so that the control system drives the unhooking mechanism to release the penetrating hammer.
[0057] Next, the automated in-situ testing method in the embodiments of this disclosure will be described in detail with reference to the examples.
[0058] In step S110, it is detected that the winch in the standard penetration method starts to lift the penetration hammer, and the stroke displacement of the winch is monitored in real time by the displacement sensor installed on the winch.
[0059] In this embodiment, the standard penetration method includes the following steps: First, a hole is drilled to a depth of 15-30 cm above the target soil layer to avoid disturbing the test soil layer. After cleaning the hole, the penetration hammer is placed at the bottom of the hole and driven into the soil to a depth of 15 cm to perform the pre-penetration stage. The purpose is to eliminate the influence of loose soil layers or disturbance at the bottom of the hole and ensure that subsequent tests are conducted in undisturbed soil. The number of blows required for the penetration hammer to continue driving into the soil to a depth of 30 cm is recorded, and this value is the standard penetration hammer blow count (N value). If the number of blows exceeds 50 and the soil has not penetrated to a depth of 30 cm, the test is stopped, and information such as the standard penetration hammer blow count, soil layer name, depth, and groundwater level is recorded simultaneously. During the standard penetration process, the penetration hammer generates impact energy through free fall, which is transmitted to the penetration hammer through the probe rod, driving the penetration hammer to drive into the soil.
[0060] In standard penetration testing, a winch is used to pull the penetration hammer via a wire rope, achieving a "lift-positioning-unhooking" cycle. The winch needs to work in conjunction with sensors, an unhooking mechanism, and a control system. The specific linkage process is as follows: start-up phase, unhooking phase, and reset phase. Upon receiving a lifting command, the winch can be started, and the wire rope pulls the penetration hammer upwards. Unhooking phase: When the stroke displacement reaches the final upper limit position and the tension and speed are stable, a release command is sent to the unhooking mechanism, and the winch is stopped from lifting. Reset phase: After the hammer strike is completed, the winch is lowered until the penetration hammer resets, the stroke displacement reaches the lower limit position, and preparation for the next strike is made.
[0061] First, the start-up phase will be explained. A displacement sensor can be deployed in the winch. This sensor can be a high-precision magnetostrictive displacement sensor, whose range covers the entire stroke displacement of the winch. For example, the displacement sensor can be fixed parallel to the winch's drum support, and linked to the wire rope traction end via a magnetic ring slider to monitor the winch's displacement changes in real time, thus determining the winch's stroke displacement. Specifically, the displacement sensor can monitor the number of rotations of the winch drum or the length of the wire rope winding / unwinding in real time to determine the winch's stroke displacement.
[0062] To prevent displacement sensor failure, a backup sensor can be deployed in the winch. The backup sensor can be the same type as the displacement sensor. When the displacement sensor fails, the backup sensor automatically monitors the number of rotations of the winch drum or the length of the wire rope to determine the winch's travel displacement.
[0063] In step S120, the displacement sensor detects that the travel displacement of the winch has reached the upper limit position. When the lifting state of the penetrating hammer is stable, the unhooking mechanism is triggered to release the penetrating hammer according to the first verification result and the second verification result.
[0064] In this embodiment of the disclosure, the upper and lower limits of the winch are set according to the process requirements of the standard penetration method. The upper limit is the hammer impact position, and the lower limit is the unhooking position. The lower limit can be lower than the upper limit. In some embodiments, the upper limit can be determined based on the displacement value corresponding to the designed drop distance of the standard penetration hammer and a safety value, where the safety value can be 10cm. The lower limit can be determined based on the difference between the displacement value of the probe reset reference point and the anti-pull-off buffer amount, where the anti-pull-off buffer amount can be, for example, 20cm.
[0065] In some embodiments, the upper and lower limits can also be determined based on a first machine learning model. Key data can be integrated into a PLC (Programmable Logic Controller) and interact with an artificial intelligence analysis module via the Modbus protocol to dynamically determine the upper and lower limits. For example, key data related to the operation of the winch can be acquired, including the displacement of the displacement sensor, the winch's equipment parameters, the tension and wear of the wire rope, the load weight, and environmental parameters.
[0066] Figure 2 The diagram illustrates a flowchart for determining the upper and lower limit positions. (Reference) Figure 2 As shown, the main steps include:
[0067] Step S210: Input the key data into the second machine learning model, output the danger probability of the travel displacement, and determine the upper limit position or the lower limit position of the prediction based on the danger probability;
[0068] Step S220: Input the time series data corresponding to the key data into the long short-term memory network model to extract time series features, and combine it with the equipment parameters of the winch to determine the dynamic correction coefficient;
[0069] Step S230: Adjust the upper limit position or lower limit position of the prediction according to the dynamic correction parameters to obtain the adjusted upper limit position or lower limit position;
[0070] Step S240: Determine the upper limit position based on the predicted upper limit position and the adjusted upper limit position, and determine the lower limit position based on the predicted lower limit position and the adjusted lower limit position.
[0071] In this embodiment, key data is input into a second machine learning model, which outputs the probability of danger in the travel displacement. Based on the probability of danger, the upper or lower prediction limit position is determined. Specifically, when the probability of danger is greater than a probability threshold, the travel displacement corresponding to that probability can be determined as the upper or lower prediction limit position.
[0072] The time-series data corresponding to key data is processed through a Long Short-Term Memory (LSTM) network model. This time-series data may include the rate of change of travel displacement and tension fluctuations. The time-series data is input into the LSTM network model to extract time-series features. Combined with equipment parameters, dynamic correction coefficients are output. The upper or lower limit position is adjusted based on these dynamic correction parameters to obtain the adjusted upper or lower limit position. Equipment parameters refer to the hoist's equipment parameters, including the mechanical top rail limit, minimum drum diameter, equipment service life, and wire rope rated tension. For example, the basic time-series features are determined through a first-layer LSTM. These features, along with the equipment parameters, are input into a second-layer LSTM to obtain a fused time-series feature. The fused time-series feature is then compressed through a first fully connected layer. This compressed feature is then input into a second fully connected layer for linear mapping to obtain the dynamic correction coefficients.
[0073] Furthermore, the minimum of the predicted upper limit position and the adjusted upper limit position can be used as the upper limit position, and the maximum of the predicted lower limit position and the adjusted lower limit position can be used as the lower limit position.
[0074] In this embodiment, when the winch's travel displacement reaches the upper limit position, indicating that the hammering operation has been reached or the normal operating range is about to be exceeded, the penetration hammer should fall freely, allowing for release by unhooking. When the winch's travel displacement reaches the lower limit position, it indicates that it may be in an abnormally low displacement state, which may pose a serious threat to equipment or operational safety. The lower limit position refers to the dangerous position where the probe rod may be pulled up. At this time, the system should trigger unhooking, cut off the power supply, and send an alarm message.
[0075] First, let's explain the situation when the upper limit position is reached. When the winch reaches the upper limit position, the release mechanism can be triggered to release the penetrating hammer based on its lifting status. For example, acceleration and tension are collected in real time using an acceleration sensor installed in the penetrating hammer and a tension sensor in the wire rope; a first verification result is obtained by double verification based on the acceleration and tension; the soil type, penetration data, and state data of the penetrating hammer are acquired, and a second verification result is obtained by fitting the soil type, penetration data, and state data using a first machine learning model; based on the first and second verification results, the penetrating hammer is released at the target release time.
[0076] First, if the detected acceleration is less than the first value, it indicates that the hammer is stable and there is no wobbling or jamming; the tension remains constant at the second value, so the hammer's lifting state can be considered stable, and the first verification result can be considered to meet the release condition. If the detected acceleration is greater than or equal to the first value, or the tension change does not remain constant at the second value, the hammer's lifting state can be considered to be in a changing state. Since a changing state indicates that the hammer's state is not yet stable, the first verification state can be considered to not meet the release condition. When the first verification state meets the release condition, disengagement is allowed; when the first verification state does not meet the release condition, disengagement is prohibited.
[0077] Next, a second verification can be performed based on the first machine learning model. Based on this, soil type, penetration data, and state data can be input into the first machine learning model. The first machine learning model then fits the soil type, penetration data, and state data to obtain the second verification result.
[0078] In some embodiments, state stability features can be determined based on the tensile force fluctuation amplitude and acceleration fluctuation amplitude in the state data; soil type, penetration data, state data, and state stability features are integrated into input features, and a dynamic threshold is obtained by performing a convolution operation on the input features through a first machine learning model; the state data is compared with the dynamic threshold to determine the second verification result. The soil type can be hard soil, etc. The penetration data can be the current penetration depth, cumulative hammer blows, etc. The state data includes the tensile force fluctuation amplitude and acceleration fluctuation amplitude.
[0079] First, the state stability characteristics are determined based on the standard deviations of the tensile force fluctuation amplitude and the acceleration fluctuation amplitude at multiple sampling points in the state data. The state stability characteristics can be either stable or fluctuating. When the standard deviation gradually decreases, the state stability characteristics can be considered stable; when the standard deviation gradually increases, the state stability characteristics can be considered fluctuating.
[0080] Soil type, penetration data, state data, and state stability features are integrated into input features. These input features are then fed into a first machine learning model, which can be a convolutional neural network. By performing convolution operations on the input features, local features between adjacent parameters are obtained, such as the local features between soil type and current penetration depth.
[0081] Furthermore, convolution operations can be performed on local features. Specifically, multiple local features can be fused, and then convolution operations can be performed on the fused features to extract higher-order features. For example, a second convolution operation can be performed on the output local features to fuse cross-channel associated features. The resulting higher-order features can be, for example, a combination of hard soil, depth, and tensile strength features, used to reflect the effect of increasing depth on tensile strength in soil types.
[0082] Next, pooling and fully connected operations can be performed on the higher-order features. The pooled higher-order features are then mapped to output values using a weight matrix. These output values refer to the predicted dynamic thresholds, which can be multiple and represent the upper limits of the state data. When the state data consists of tension fluctuation amplitude and velocity fluctuation amplitude, the predicted dynamic thresholds can be the upper limits of the tension fluctuation amplitude and acceleration fluctuation amplitude, respectively. Furthermore, boundary checks can be performed on the predicted dynamic thresholds output by the model to avoid exceeding the allowable range of the equipment or test specifications, thus obtaining boundary-checked predicted dynamic thresholds. For example, when the predicted dynamic threshold is higher than the standard ingress parameter, the standard ingress parameter is determined as the dynamic threshold. When the predicted dynamic threshold is lower than the standard ingress parameter, the predicted dynamic threshold is determined as the dynamic threshold.
[0083] After obtaining the dynamic threshold, the state data can be compared with the corresponding dynamic threshold to determine the second verification result. For example, the tension fluctuation amplitude in the state data is compared with the upper limit of the tension fluctuation amplitude to determine the first comparison result; the acceleration fluctuation amplitude in the state data is compared with the upper limit of the acceleration fluctuation amplitude to determine the second comparison result. The second verification result is further determined based on the first and second comparison results. When the first comparison result is that the tension fluctuation amplitude does not exceed the upper limit of the tension fluctuation amplitude, and the second comparison result is that the acceleration fluctuation amplitude does not exceed the upper limit of the acceleration fluctuation amplitude, the second verification result can be considered as a suggestion to decouple; when the first comparison result is that the tension fluctuation amplitude exceeds the upper limit of the tension fluctuation amplitude, or when the second comparison result is that the acceleration fluctuation amplitude exceeds the upper limit of the acceleration fluctuation amplitude, the second verification result can be considered as a prohibition to decouple.
[0084] When both the first and second verification results indicate that disengagement is permitted, the disengagement mechanism can be triggered to activate the penetration hammer. If either the first or second verification result indicates that disengagement is prohibited, the disengagement mechanism cannot be triggered to activate the penetration hammer. If disengagement is permitted, the penetration hammer can be released within the standard disengagement time. The standard disengagement time can be logically calculated based on the start time, the stroke displacement reference value, the initial stroke displacement, the lifting speed, and the response delay of the disengagement mechanism. The start time refers to the time when the winch begins lifting; the initial stroke displacement refers to the length of the wire rope at the start of lifting; and the stroke displacement reference value refers to the free fall distance of the penetration hammer required by the standard penetration method. It should be noted that the standard disengagement time can be dynamically adjusted according to soil type. For example, in hard soil, to avoid the hammer getting stuck due to soil reaction force, the standard disengagement time can be shortened. In soft soil, the standard disengagement time can be increased, for example, by delaying disengagement by 10-20 ms.
[0085] If the unhooking mechanism is prohibited or cannot trigger the penetration hammer, a delay time can be added to the standard unhooking time until the unhooking condition is met, so as to trigger the release of the penetration hammer.
[0086] The delay time can be determined as follows: Identify the anomaly type, and then determine the initial delay time based on the anomaly type. The anomaly type can be either the degree of tension anomaly or the degree of acceleration anomaly. The degree of tension anomaly or acceleration anomaly is positively correlated with the initial delay time. When either tension or acceleration is abnormal, the initial delay time can be determined based on the degree of tension or acceleration anomaly. When both tension and acceleration are abnormal, the maximum value of the initial delay times determined by the degree of tension or acceleration anomaly is determined as the final initial delay time.
[0087] Next, correction coefficients can be determined, and the initial delay time is corrected based on these coefficients to obtain the delay time. For example, a tension correction coefficient and an acceleration correction coefficient are determined. The tension is compared to the normal tension range of the penetration hammer to determine the tension deviation value, and the tension correction coefficient is determined based on this deviation value. The acceleration is compared to the normal acceleration range of the penetration hammer to determine the acceleration deviation value, and the acceleration correction coefficient is determined based on this deviation value. Tension weights and acceleration weights are determined, and the initial delay time is logically processed based on the first weighted sum of the tension weight and the tension correction coefficient, and the second weighted sum of the acceleration weight and the acceleration correction coefficient, to obtain the delay time. The tension weight can be greater than the acceleration weight.
[0088] If the first and second verification results determine that the unhooking mechanism cannot trigger the penetration hammer, the standard unhooking time can be delayed until the unhooking condition is met, in order to trigger the release of the penetration hammer.
[0089] In step S130, when the displacement sensor detects that the travel displacement of the winch has reached the lower limit position, it sends an indication signal to the control system so that the control system drives the unhooking mechanism to release the penetrating hammer.
[0090] In this embodiment, the indication signal can be a drive signal, which can be an electrical signal, a hydraulic signal, or other form of power signal, specifically determined according to the type of unhooking mechanism. For example, if the unhooking mechanism is an electromagnetic unhooker, the control system will send a pulse signal to energize the electromagnetic unhooker, generating magnetic force or other forces to release the penetration hammer; if it is a hydraulic unhooking mechanism, the control system will control the opening or closing of the hydraulic valve, causing changes in the flow direction and pressure of the hydraulic oil, thereby driving the unhooking mechanism to move and release the penetration hammer. When the unhooking mechanism receives the indication signal, it immediately triggers the release of the penetration hammer, separating the penetration hammer from the winch or other connecting parts. The penetration hammer then begins to fall under the action of gravity or other external forces to carry out subsequent work, such as conducting soil penetration tests, etc.
[0091] Meanwhile, to ensure safety, when the displacement sensor detects that the winch's travel displacement has reached the lower limit position, the power supply to the winch can be immediately cut off and an audible and visual alarm can be activated to send alarm information.
[0092] In this embodiment, the disengagement status of the penetration hammer can be displayed on the screen interface of the video monitoring platform. The screen interface may include a main video monitoring area and a disengagement status display area. Specifically, the main video monitoring area may include a real-time video stream, displaying real-time images of the penetration hammer and the disengagement mechanism. The real-time image displays a disengagement status label, which can be in text or other formats. It can also respond to zoom operations on the real-time video stream, enlarging or reducing the stream. The disengagement status display area can display detailed information and auxiliary data predicted by a machine learning model. The detailed information includes the disengagement time, the disengagement height of the penetration hammer, and the cause of the anomaly, etc. The cause of the anomaly may be, for example, hook jamming. The auxiliary data may include the opening and closing angle of the disengagement mechanism, the initial height of the penetration hammer, etc.
[0093] Figure 3 The flowchart illustrating the release of the penetration hammer is shown in the figure. (Refer to...) Figure 3 As shown, the main steps include:
[0094] Step S310: The displacement sensor monitors the travel displacement of the winch in real time.
[0095] Step S320: Determine if the travel displacement is greater than the upper limit position. If yes, proceed to step S330; otherwise, proceed to step S350.
[0096] Step S330: Trigger the unhooking mechanism to unhook.
[0097] Step S340: Release the penetrating hammer.
[0098] Step S350: Continue to raise the penetration hammer.
[0099] Step S360: Determine if the stroke displacement is less than the lower limit position. If yes, proceed to step S370; otherwise, proceed to step S310.
[0100] Step S370: Disconnect the power supply and send an alarm message.
[0101] In this embodiment, by comparing the travel displacement of the winch with the upper and lower limit positions, the unhooking structure can be triggered in a timely manner to release the penetration hammer, avoiding the problems of the penetration hammer not being able to unhook in time and deviating from the hole position in related technologies, thus improving the accuracy and reliability of the penetration hammer release.
[0102] This disclosure also provides an automated in-situ testing system, with reference to... Figure 4 As shown, the automated in-situ testing system 400 includes:
[0103] The stroke displacement monitoring module 401 is used to detect the start of the winch to lift the penetration hammer in the standard penetration method, and to monitor the stroke displacement of the winch in real time through the displacement sensor installed on the winch.
[0104] The first release module 402 is used to trigger the unhooking mechanism to release the penetrating hammer when the displacement sensor detects that the travel displacement of the winch has reached the upper limit position and the lifting state of the penetrating hammer is stable, based on the first verification result and the second verification result.
[0105] The second release module 403 is used to send an indication signal to the control system when the displacement sensor detects that the travel displacement of the winch has reached the lower limit position, so that the control system drives the unhooking mechanism to release the penetration hammer.
[0106] In one exemplary embodiment of this disclosure, triggering the release mechanism to release the penetration hammer based on the first verification result and the second verification result includes:
[0107] Acceleration and tension are collected in real time by an acceleration sensor installed in the penetrating hammer and a tension sensor in the wire rope.
[0108] A first verification result is obtained by performing dual verification based on the acceleration and the tension.
[0109] The soil type, penetration data, and state data of the penetrator are obtained, and the soil type, penetration data, and state data are fitted by a first machine learning model to obtain a second verification result.
[0110] Based on the first verification result and the second verification result, the penetration hammer is released at the target release time.
[0111] In one exemplary embodiment of this disclosure, the step of performing dual verification based on the acceleration and the tension to obtain a first verification result includes:
[0112] If the detected acceleration is the first value, the tension remains unchanged at the second value, the lifting state is the hovering state, and the first verification result is that the release condition is met.
[0113] In an exemplary embodiment of this disclosure, the state data includes tensile fluctuation amplitude and acceleration fluctuation amplitude; the step of fitting the soil type, penetration data, and state data using a first machine learning model to obtain a second verification result includes:
[0114] Determine the stability characteristics of the state based on the amplitude of tension fluctuation and acceleration fluctuation in the state data;
[0115] The soil type, the penetration data, the state data, and the stability features are integrated into the input features, and the first machine learning model is used to perform a convolution operation on the input features to obtain the dynamic threshold.
[0116] The state data is compared with the dynamic threshold to determine the second verification result.
[0117] In one exemplary embodiment of this disclosure, the step of integrating the soil type, the penetration data, the state data, and the stability features into input features, and then performing a convolution operation on the input features using the first machine learning model to obtain a dynamic threshold, includes:
[0118] Local feature extraction is performed on the input features to obtain multiple local features;
[0119] The local features are fused together, and the fused features are then convolved to extract higher-order features.
[0120] The higher-order features are mapped to obtain the predicted dynamic threshold;
[0121] The predicted dynamic threshold is determined by performing boundary verification based on the standard penetration parameters, and the dynamic threshold includes an upper limit threshold.
[0122] In one exemplary embodiment of this disclosure, releasing the penetration hammer at the target release timing based on the first verification result and the second verification result includes:
[0123] Based on the first verification result and the second verification result, it is determined that decoupling is allowed, and the standard decoupling time is determined as the target release timing, and the penetration hammer is released.
[0124] Based on the first verification result and the second verification result, it is determined that decoupling is prohibited. A delay time is added to the standard decoupling time to determine the release timing of the target and trigger the release of the penetration hammer.
[0125] In one exemplary embodiment of this disclosure, the system further includes:
[0126] The key data is input into the second machine learning model, which outputs the danger probability of the travel displacement, and determines the upper or lower limit of the prediction position based on the danger probability.
[0127] The time series data corresponding to the key data is input into the long short-term memory network model to extract time series features, and combined with the equipment parameters of the winch, the dynamic correction coefficient is determined.
[0128] The upper or lower prediction limit position is adjusted according to the dynamic correction parameters to obtain the adjusted upper or lower prediction limit position.
[0129] The upper limit position is determined based on the predicted upper limit position and the adjusted upper limit position, and the lower limit position is determined based on the predicted lower limit position and the adjusted lower limit position.
[0130] It should be noted that the specific details of each module in the above-mentioned automated in-situ testing system have been elaborated in the corresponding automated in-situ testing methods, and will not be repeated here.
[0131] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0132] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.
[0133] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.
[0134] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."
[0135] The following reference Figure 5 To describe an electronic device 500 according to such an embodiment of the present disclosure. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.
[0136] like Figure 5 As shown, the electronic device 500 is manifested in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), and a display unit 540.
[0137] The storage unit stores program code that can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 510 can perform actions such as... Figure 1 The steps are shown in the figure.
[0138] Storage unit 520 may include readable media in the form of volatile storage units, such as random access memory (RAM) 5201 and / or cache memory 5202, and may further include read-only memory (ROM) 5203.
[0139] Storage unit 520 may also include a program / utility 5204 having a set (at least one) program module 5205, such program module 5205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.
[0140] Bus 530 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.
[0141] Electronic device 500 can also communicate with one or more external devices 600 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with the electronic device 500, and / or with any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed through input / output (I / O) interface 550. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 560. Figure 5 As shown, network adapter 560 communicates with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0142] It should be noted that some embodiments of this disclosure also provide a computer program product, which includes a computer program that implements the above-described method when executed by a processor.
[0143] In one embodiment, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, NAND flash memory, etc. In one embodiment, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.
[0144] Computer program code can be written in one or more programming languages. Examples of programming languages include C, Java, and C++. Program code can execute entirely on the user's computing device, partially on the user's computing device, or as a standalone software package. It can also execute partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, such as a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via an internet connection provided by a mobile network operator).
[0145] Computer programs can be carried or transmitted via signals such as electrical, magnetic, optical, electromagnetic, and infrared rays. Electronic devices can convert signals carrying computer programs into digital signals, thereby running the computer programs. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, to be executed by the processor of the electronic device) the method steps of various exemplary embodiments of this disclosure.
[0146] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.
[0147] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.
[0148] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0149] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.
[0150] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. An automated in-situ testing method, characterized in that, include: The winch in the standard penetration method is detected to start lifting the penetration hammer, and the stroke displacement of the winch is monitored in real time by a displacement sensor installed on the winch. The displacement sensor detects that the travel displacement of the winch has reached the upper limit position. When the lifting state of the penetrating hammer is stable, the acceleration and tension are collected in real time by the acceleration sensor installed in the penetrating hammer and the tension sensor of the wire rope. The first verification result is obtained by double verification based on the acceleration and tension. The soil type, penetration data, and state data of the penetrator are obtained. The soil type, penetration data, and state data are fitted using a first machine learning model to obtain a second verification result. Based on the first verification result and the second verification result, the unhooking mechanism is triggered to release the penetrator at the target release time. When the displacement sensor detects that the travel displacement of the winch has reached the lower limit position, it sends an indication signal to the control system so that the control system drives the unhooking mechanism to release the penetrating hammer. The step of performing dual verification based on the acceleration and the tension to obtain the first verification result includes: If the detected acceleration is the first value, the tension remains unchanged at the second value, the lifting state is the hovering state, and the first verification result is that the release condition is met. The state data includes the amplitude of tensile force fluctuation and the amplitude of acceleration fluctuation; the second verification result obtained by fitting the soil type, penetration data, and state data through a first machine learning model includes: Determine the stability characteristics of the state based on the amplitude of tension fluctuation and acceleration fluctuation in the state data; The soil type, the penetration data, the state data, and the stability features are integrated into the input features, and the first machine learning model is used to perform a convolution operation on the input features to obtain the dynamic threshold. The state data is compared with the dynamic threshold to determine the second verification result; The process of integrating the soil type, the penetration data, the state data, and the stability features into input features, and then performing a convolution operation on the input features using the first machine learning model to obtain a dynamic threshold includes: Local feature extraction is performed on the input features to obtain multiple local features; The local features are fused together, and the fused features are then convolved to extract higher-order features. The higher-order features are mapped to obtain the predicted dynamic threshold; The predicted dynamic threshold is determined by performing boundary verification based on the standard penetration parameters, and the dynamic threshold includes an upper limit threshold.
2. The automated in-situ testing method according to claim 1, characterized in that, The step of triggering the unhooking mechanism to release the penetration hammer at the target release timing based on the first verification result and the second verification result includes: Based on the first verification result and the second verification result, it is determined that decoupling is allowed, and the standard decoupling time is determined as the target release timing, and the penetration hammer is released. Based on the first verification result and the second verification result, it is determined that decoupling is prohibited. A delay time is added to the standard decoupling time to determine the release timing of the target and trigger the release of the penetration hammer.
3. The automated in-situ testing method according to claim 1, characterized in that, The method further includes: The key data is input into the second machine learning model, which outputs the danger probability of the travel displacement, and determines the upper or lower limit of the prediction position based on the danger probability. The time series data corresponding to the key data is input into the long short-term memory network model to extract time series features, and combined with the equipment parameters of the winch, the dynamic correction coefficient is determined. The upper or lower prediction limit position is adjusted according to the dynamic correction parameters to obtain the adjusted upper or lower prediction limit position. The upper limit position is determined based on the predicted upper limit position and the adjusted upper limit position, and the lower limit position is determined based on the predicted lower limit position and the adjusted lower limit position.
4. An automated in-situ testing system, characterized in that, include: The stroke displacement monitoring module is used to detect the start of the winch lifting the penetration hammer in the standard penetration method, and monitors the stroke displacement of the winch in real time through the displacement sensor installed on the winch. The first release module is used to detect when the displacement sensor detects that the travel displacement of the winch has reached the upper limit position, and when the lifting state of the penetrating hammer is stable, to collect acceleration and tension in real time through an acceleration sensor installed in the penetrating hammer and a tension sensor in the wire rope; and to perform dual verification based on the acceleration and tension to obtain a first verification result. The soil type, penetration data, and state data of the penetrator are obtained. The soil type, penetration data, and state data are fitted using a first machine learning model to obtain a second verification result. Based on the first verification result and the second verification result, the unhooking mechanism is triggered to release the penetrator at the target release time. The second release module is used to send an indication signal to the control system when the displacement sensor detects that the travel displacement of the winch has reached the lower limit position, so that the control system drives the unhooking mechanism to release the penetrating hammer. The step of performing dual verification based on the acceleration and the tension to obtain the first verification result includes: If the detected acceleration is the first value, the tension remains unchanged at the second value, the lifting state is the hovering state, and the first verification result is that the release condition is met. The state data includes the amplitude of tensile force fluctuation and the amplitude of acceleration fluctuation; the second verification result obtained by fitting the soil type, penetration data, and state data through a first machine learning model includes: Determine the stability characteristics of the state based on the amplitude of tension fluctuation and acceleration fluctuation in the state data; The soil type, the penetration data, the state data, and the stability features are integrated into the input features, and the first machine learning model is used to perform a convolution operation on the input features to obtain the dynamic threshold. The state data is compared with the dynamic threshold to determine the second verification result; The process of integrating the soil type, the penetration data, the state data, and the stability features into input features, and then performing a convolution operation on the input features using the first machine learning model to obtain a dynamic threshold includes: Local feature extraction is performed on the input features to obtain multiple local features; The local features are fused together, and the fused features are then convolved to extract higher-order features. The higher-order features are mapped to obtain the predicted dynamic threshold; The predicted dynamic threshold is determined by performing boundary verification based on the standard penetration parameters, and the dynamic threshold includes an upper limit threshold.
5. A computer program product, characterized in that, When the computer program is executed by the processor, it implements the automated in-situ testing method according to any one of claims 1-3.
6. An electronic device, characterized in that, include: processor; Memory for storing the executable instructions of the processor; The processor is configured to implement the automated in-situ testing method according to any one of claims 1-3 by executing the executable instructions.