Construction early warning method and system for digging and anchoring all-in-one machine and medium

Abstract

The invention discloses a construction early warning method and system for a digging and anchoring all-in-one machine and a medium, and relates to the technical field of digging and anchoring all-in-one machines. The method comprises the steps that whether the digging and anchoring all-in-one machine is in an operation switching state or not is recognized; if the heading assembly is in the switching state, pose modeling is conducted on the heading assembly and the anchoring assembly based on the sensing data; a dynamic safety buffer area algorithm is adopted to analyze pose data, and the collision risk level between the assemblies is evaluated; and when the risk level is greater than or equal to a preset threshold value, an early warning response module is triggered to adjust postures of related components. Therefore, the technical effects of dynamically monitoring the switching state, carrying out risk assessment and early warning in real time, and improving the construction safety are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of roadheader-anchoring machines, and particularly to a construction warning method, system and medium for roadheader-anchoring machines. Background Art

[0002] During actual operation, a roadheader-anchoring machine needs to frequently switch between a tunneling mode and an anchoring mode to complete different construction tasks. During the switching process, the poses of the tunneling component and the anchoring component will change. However, due to the lack of real-time monitoring and risk analysis of the switching state in the prior art, specifically, the prior art cannot dynamically evaluate the collision risk between the tunneling component and the anchoring component, resulting in the equipment being damaged due to collision or the construction being forced to interrupt due to the inability to give an early warning during the operation mode switching, which affects the construction efficiency and the service life of the equipment. Summary of the Invention

[0003] The present invention provides a construction warning method, system and medium for a roadheader-anchoring machine to solve the technical problem in the prior art that the lack of real-time monitoring and warning of the roadheader-anchoring machine affects the safety of the equipment and the construction, and to achieve the technical effects of dynamically monitoring the switching state, real-time risk assessment and warning, and further improving the construction safety.

[0004] In a first aspect, the present invention provides a construction warning method for a roadheader-anchoring machine, wherein the construction warning method for the roadheader-anchoring machine includes: Identifying whether the current operation state of the roadheader-anchoring machine is in a switching state according to a sensing and perception module.

[0005] If the roadheader-anchoring machine is in a switching state, pose modeling is performed on the roadheader-anchoring machine according to the sensing data of the sensing and perception module to obtain the pose data of the tunneling component and the pose data of the anchoring component.

[0006] Performing risk analysis on the pose data of the tunneling component and the pose data of the anchoring component based on a dynamic safety buffer algorithm to obtain the collision risk level between the tunneling component and the anchoring component.

[0007] Judging whether the collision risk level of the tunneling component and the anchoring component is greater than or equal to a preset risk threshold. If the collision risk level is greater than or equal to the preset risk threshold, the warning response module adjusts the postures of the tunneling component and the anchoring component.

[0008] In a feasible implementation manner, the sensing and perception module is connected to a state classification model, and whether the current operation state of the roadheader-anchoring machine is in a switching state is identified according to the state classification model, wherein the roadheader-anchoring machine includes a tunneling state, an anchoring state and a switching state.

[0009] In a feasible implementation manner, the method for constructing the state classification model includes: Obtain the heading component sample data and the anchoring component sample data in the heading state, the anchoring state, and the switching state respectively.

[0010] Extract feature vectors based on the heading component sample data and the anchoring component sample data, where the feature vectors include time series features, spatial features, and behavior features.

[0011] Extract key features from the feature vectors to obtain the speed change of the heading component, the angle change of the anchoring component, and the action overlap degree of the heading and anchoring components in each state.

[0012] Use a support vector machine to perform model training on the speed change of the heading component, the angle change of the anchoring component, and the action overlap degree of the heading and anchoring components in each state to obtain a trained state classification model.

[0013] In a feasible implementation manner, perform risk analysis on the pose data of the heading component and the pose data of the anchoring component based on the dynamic safety buffer algorithm. The method includes: Obtain the device data and the task paths of the heading component and the anchoring component.

[0014] Define a heading safety buffer and an anchoring safety buffer based on the device data of the heading component and the anchoring component and the task paths of the heading component and the anchoring component.

[0015] Perform risk analysis on the pose data of the heading component and the pose data of the anchoring component under the heading safety buffer and the anchoring safety buffer based on the dynamic safety buffer algorithm to obtain a collision risk level.

[0016] In a feasible implementation manner, perform risk analysis on the pose data of the heading component and the pose data of the anchoring component. The method includes: Calculate a first distance based on the pose data of the heading component and the pose data of the anchoring component, where the first distance is the minimum distance between the heading component and the anchoring component.

[0017] Obtain a safety distance based on the heading safety buffer and the anchoring safety buffer.

[0018] Compare the first distance with the safety distance and output a collision risk level.

[0019] In a feasible implementation manner, compare the first distance with the safety distance and output a collision risk level.

[0020] Wherein, when the ratio of the first distance to the safety distance is greater than or equal to 1, the collision risk level is output according to the ratio.

[0021] When the ratio of the first distance to the safety distance is less than 1, a safety signal is sent to the warning response module.

[0022] In a feasible implementation manner, the warning response module adjusts the postures of the tunneling assembly and the anchoring assembly. The method includes: Obtain the movement spaces of the tunneling assembly and the anchoring assembly.

[0023] If the movement spaces of both the tunneling assembly and the anchoring assembly are less than the preset movement space, the warning response module performs collaborative posture adjustment on the tunneling assembly and the anchoring assembly.

[0024] If the movement space of the tunneling assembly is greater than or equal to the preset movement space, the warning response module adjusts the posture of the tunneling assembly.

[0025] If the movement space of the anchoring assembly is greater than or equal to the preset movement space, the warning response module adjusts the posture of the anchoring assembly.

[0026] If the movement spaces of both the tunneling assembly and the anchoring assembly are greater than or equal to the preset movement space, the warning response module adjusts the posture of the tunneling assembly or the anchoring assembly.

[0027] In a feasible implementation manner, the warning response module adjusts the postures of the tunneling assembly and the anchoring assembly. The method further includes: The warning response module determines the posture adjustment object, and the posture adjustment object includes a tunneling assembly, an anchoring assembly, and a tunneling-anchoring assembly.

[0028] According to the posture adjustment object, a posture adjustment strategy is generated. The posture adjustment strategy includes the backward and forward displacements and angles of the tunneling assembly, and the deployment, retraction time, and angles of the anchoring assembly.

[0029] In a second aspect, the present invention further provides a construction warning system for a roadheader-anchoring machine. Among them, the construction warning system for the roadheader-anchoring machine includes: An operation state recognition unit, configured to identify whether the current operation state of the roadheader-anchoring machine is in a switching state according to the sensing and perception module.

[0030] A pose modeling unit, configured to, if the roadheader-anchoring machine is in a switching state, perform pose modeling on the roadheader-anchoring machine according to the sensing data of the sensing and perception module, and obtain the pose data of the tunneling assembly and the pose data of the anchoring assembly.

[0031] A collision risk analysis unit is configured to perform risk analysis on the pose data of the tunneling assembly and the pose data of the anchoring assembly based on a dynamic safety buffer algorithm, and obtain the collision risk level between the tunneling assembly and the anchoring assembly.

[0032] A risk judgment and adjustment unit is configured to judge whether the collision risk level of the tunneling assembly and the anchoring assembly is greater than or equal to a preset risk threshold. If the collision risk level is greater than or equal to the preset risk threshold, an early warning response module adjusts the postures of the tunneling assembly and the anchoring assembly.

[0033] In a third aspect, the present invention further provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the construction early warning method for a roadheader-anchoring machine provided by the present invention.

[0034] The present invention discloses a construction early warning method, system and medium for a roadheader-anchoring machine, including: identifying whether the current operation state of the roadheader-anchoring machine is in a switching state through a sensing and perception module; if in the switching state, performing pose modeling on the roadheader-anchoring machine according to sensing data to obtain the pose data of the tunneling assembly and the anchoring assembly; subsequently, performing risk analysis on the pose data of the two based on a dynamic safety buffer algorithm to judge their collision risk level; if the collision risk level is greater than or equal to a preset risk threshold, an early warning response module adjusts the postures of the tunneling assembly and the anchoring assembly. The construction early warning method, system and medium for a roadheader-anchoring machine disclosed by the present invention solve the technical problem of lack of real-time monitoring and early warning for a roadheader-anchoring machine, which affects equipment and construction safety, and realizes dynamic monitoring of the switching state, real-time risk assessment and early warning, thereby improving the technical effect of construction safety. Description of the Drawings

[0035] Figure 1 It is a schematic flow chart of the construction early warning method for a roadheader-anchoring machine according to the present invention.

[0036] Figure 2 It is a schematic structural diagram of the construction early warning system for a roadheader-anchoring machine according to the present invention.

[0037] Description of the reference numerals: The operation state identification unit 11, the pose modeling unit 12, the collision risk analysis unit 13, and the risk judgment and adjustment unit 14. Detailed Embodiments

[0038] The above technical solution will be described in detail below in combination with the specification drawings and specific embodiments to better understand the above technical solution. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments only for explaining the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention. In addition, it should be noted that for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0039] Embodiment 1, as Figure 1 is a schematic flowchart of the construction warning method for the roadheader-anchoring machine of the present invention. Among them, the construction warning method for the roadheader-anchoring machine includes: S100: Identify whether the current operation state of the roadheader-anchoring machine is in a switching state according to the sensing and perception module.

[0040] Specifically, first, activate the sensing and perception module to monitor the real-time state information of the target roadheader-anchoring machine, especially whether the roadheader-anchoring machine is in a switching state; among them, the switching state refers to the transitional state when the roadheader-anchoring machine switches from the tunneling mode to the anchoring mode or from the anchoring mode to the tunneling mode. During the switching process, the positions and postures of the tunneling component and the anchoring component will change, and there is a risk of collision.

[0041] Exemplarily, the sensing and perception module communicates with the control end of the roadheader-anchoring machine through the interactive CAN bus or the wireless communication module to read the control signal, and the control signal includes the current operation mode (tunneling, anchoring or switching) of the device and related action instructions (such as the tunneling component retreating, the anchoring component unfolding, etc.); at the same time, the sensing and perception module combines the sensor data collected in real time (such as the displacement, speed and angle of the tunneling component, the unfolding angle and retracting speed of the anchoring component, etc.), and combines the above control signal to identify the switching state. For example, when the roadheader-anchoring machine switches from the tunneling mode to the anchoring mode, the control signal will trigger the actions of the tunneling component retreating and the anchoring component unfolding. Then, the sensing and perception module can judge whether the device is in the switching state by reading the control signal and the sensor data and verifying the consistency.

[0042] By monitoring the operation state of the roadheader-anchoring machine and accurately identifying the switching state, it provides a basis for subsequent risk analysis and attitude adjustment, ensuring that the device can be adjusted in time during the switching process to avoid collision and construction interruption.

[0043] In some embodiments, the sensing module is connected to the state classification model to identify whether the current operating state of the tunneling and bolting machine is in a switching state according to the state classification model, where the tunneling and bolting machine includes a tunneling state, an anchoring state, and a switching state.

[0044] Specifically, the state classification model is used to classify and identify the operating states (such as tunneling, anchoring, and switching) of the tunneling and bolting machine. Optionally, the state classification model is constructed and trained based on a machine learning algorithm; among them, the switching state includes two types: from the tunneling state to the anchoring state and from the anchoring state to the tunneling state.

[0045] Specifically, the sensing module is connected to the state classification model, so that the acquired sensing data can be input into the state classification model in real time for state classification; through the collaborative work of the sensing module and the state classification model, the operating state of the tunneling and bolting machine, especially the switching state, can be identified in real time and accurately, providing reliable data support for subsequent risk analysis and early warning.

[0046] In some implementation manners, the method for constructing the state classification model includes: Obtain the sample data of the tunneling components and the sample data of the anchoring components in the tunneling state, the anchoring state, and the switching state respectively; extract the feature vectors according to the sample data of the tunneling components and the sample data of the anchoring components, where the feature vectors include time series features, spatial features, and behavior features; perform key feature extraction on the feature vectors to obtain the speed change of the tunneling components, the angle change of the anchoring components, and the action overlap degree of the tunneling and anchoring components in each state; use a support vector machine to perform model training on the speed change of the tunneling components, the angle change of the anchoring components, and the action overlap degree of the tunneling and anchoring components in each state to obtain a trained state classification model.

[0047] Specifically, the sample data of the tunneling components includes the operation data of the tunneling components of the tunneling and bolting machine in the tunneling state, the anchoring state, and the switching state, such as the displacement, speed, angle, etc. of each part in the tunneling components; correspondingly, the sample data of the anchoring components includes multiple groups of operation data of the anchoring components of the tunneling and bolting machine in the tunneling state, the anchoring state, and the switching state respectively, such as the deployment angle, retraction speed, etc. of each part in the anchoring components.

[0048] Specifically, the feature vector is a vectorized representation of the features extracted from the sample data of the tunneling components and the sample data of the anchoring components, where different vector dimensions correspond to different feature items, specifically including time series features (such as speed change rate), spatial features (such as pose data), and behavior features (such as action overlap degree).

[0049] Specifically, first, collect the original operation data of the tunneling component and the anchoring component in the tunneling state, the anchoring state, and the switching state from the control instruction log or the experimental data respectively; then, preprocess the obtained tunneling component sample data and the anchoring component sample data to improve the data quality, and perform feature engineering on the preprocessed sample data to extract time series features such as the running speed change rate, the start / stop time difference, etc., spatial features such as the advancing distance, the telescopic length of the cylinder, etc., and behavior features such as the component action sequence, the collaborative operation sequence, etc.; then, construct the corresponding feature vectors according to the obtained multi-dimensional features.

[0050] Specifically, through statistical analysis or feature selection algorithms such as correlation analysis method, covariance matrix or principal component analysis, further extract the key features that can significantly distinguish the states in the feature vectors. Preferably, the key features include the speed change of the tunneling component, the angle change of the anchoring component, and the action overlap degree of the tunneling and anchoring components.

[0051] Furthermore, mark the state categories of the extracted feature vectors, and use the marked feature vectors as the input sample data and input them into the classification model constructed based on the support vector machine (SVM). Use the radial basis function (RBF) as the kernel function, set the kernel function parameter γ = 0.5, and the penalty factor C = 10, and perform supervised training on the state classification model until the prediction performance of the model meets the preset requirements or the training iteration times meet the preset termination conditions.

[0052] By the above method, extracting the key features from the sample data and using the support vector machine for training helps the state classification model to accurately distinguish the tunneling, anchoring, and switching states and reduce the misjudgment rate.

[0053] S200: If the roadheader-anchoring machine is in the switching state, perform pose modeling on the roadheader-anchoring machine according to the sensing data of the sensing and perception module to obtain the pose data of the tunneling component and the pose data of the anchoring component.

[0054] Specifically, if the classification result shows that the current roadheader-anchoring machine is in the switching state, based on the sensing data obtained by the sensing and perception module, construct the corresponding pose model of the roadheader-anchoring machine through the digital modeling method, so as to intuitively calculate the pose data of the tunneling component and the pose data of the anchoring component through the digital model. Among them, the above-mentioned pose data includes the three-dimensional spatial position and motion posture information of the key components of the roadheader-anchoring machine.

[0055] Exemplarily, in a certain set of data, the IMU (Inertial Measurement Unit) measures the instantaneous attitude change angle of the tunneling assembly: Δθ = 0.25°, the lidar measures the spatial offset between the front of the tunneling part and the anchoring part: Δx = 85 mm, Δz = 35 mm, and the angle sensor detects that the anchoring leg is retracting, with a retraction angular velocity of approximately 10° / min; then, a pose solution coordinate system is established, with the reference point of the tunneling assembly as the origin, and the tunneling assembly and the anchoring assembly are abstracted as two rigid bodies. Each rigid body consists of multiple components, and the pose state equation is constructed by combining the IMU and the structural parameters of the roadheader-anchoring machine, and the relative pose of the two is constrained by the sensor data; furthermore, the pose data of the tunneling assembly and the anchoring assembly at a predetermined time node is obtained according to the constructed pose state equation.

[0056] Through the above pose modeling, the pose data of the tunneling assembly and the anchoring assembly of the roadheader-anchoring machine in the switching state can be obtained in real time and accurately, thus providing reliable basic data for subsequent risk analysis and early warning.

[0057] S300: Perform risk analysis on the pose data of the tunneling assembly and the pose data of the anchoring assembly based on the dynamic safety buffer algorithm, and obtain the collision risk level between the tunneling assembly and the anchoring assembly.

[0058] Specifically, the dynamic safety buffer algorithm is used to calculate the required safety distance between devices according to real-time dynamic parameters such as the current state of the device (i.e., the pose data of the tunneling group and the anchoring assembly), its own size, inertial trend, environmental factors, etc. The dynamic safety buffer algorithm can dynamically adjust the buffer range according to the pose change, so as to achieve a more accurate risk level discrimination. Among them, the collision risk level is a quantitative assessment of the potential contact conflict between devices. Exemplarily, it can be divided into low risk, medium risk, high risk and other levels according to factors such as proximity, relative speed and remaining buffer ratio.

[0059] In some embodiments, performing risk analysis on the pose data of the tunneling assembly and the pose data of the anchoring assembly based on the dynamic safety buffer algorithm, the method includes: Obtain the device data and task paths of the tunneling assembly and the anchoring assembly; define the tunneling safety buffer and the anchoring safety buffer based on the device data of the tunneling assembly and the anchoring assembly and the task paths of the tunneling assembly and the anchoring assembly; perform risk analysis on the pose data of the tunneling assembly and the pose data of the anchoring assembly under the tunneling safety buffer and the anchoring safety buffer based on the dynamic safety buffer algorithm, and obtain the collision risk level.

[0060] Specifically, the equipment data refers to the inherent physical parameters of the tunneling component and the anchoring component, including shape dimensions, weight, degrees of freedom, etc.; the task path is the path planning that the roadheader-anchor rig needs to execute during construction, including the tunneling path and the anchoring path. In particular, the task path includes the spatial position time-series data (such as G-code) of the tunneling component and the anchoring component, that is, the spatial position states of the tunneling component and the anchoring component at different time nodes. This spatial position time-series data can indirectly reflect the motion states of the tunneling component and the anchoring component.

[0061] Specifically, the tunneling safety buffer zone is a dynamic spatial range surrounding the tunneling component, which is used to ensure that the tunneling component maintains a safe distance from other components during movement. In other words, if the tunneling safety buffer zone is empty, it can be considered that the tunneling component is safe. Correspondingly, the anchoring safety buffer zone is another dynamic spatial range surrounding the anchoring component, which is used to ensure that the anchoring component maintains a safe distance from other components during movement.

[0062] Specifically, first, obtain the equipment data of the tunneling component and the anchoring component from the control system of the roadheader-anchor rig, including dimensions, weight, movement range, etc. At the same time, obtain the task path of the roadheader-anchor rig, including the tunneling path and the anchoring path; then, define the tunneling safety buffer zone and the anchoring safety buffer zone through existing preset rules (such as the technical requirements of the equipment manufacturer, the equipment manual, or the general safety requirements of the target scenario).

[0063] Exemplarily, taking the tunneling component as an example, assuming the maximum speed is 0.5 m / s and the maximum allowable deceleration is 0.6 m / s², then the equipment braking distance ; at the same time, considering the additional movement of 0.15 m caused by the control response lag and considering the environmental disturbance margin (±0.1 m), then the dynamic safety buffer zone of the final tunneling component can be defined as a three-dimensional space envelope with a radius of 0.46 m.

[0064] Further, taking the above-defined tunneling safety buffer zone and anchoring safety buffer zone as the reference safety zones, using the dynamic safety buffer zone algorithm, the safety zone correction coefficient between the tunneling component and the anchoring component is calculated in real time to correct the above-mentioned tunneling safety buffer zone and anchoring safety buffer zone, and then the collision risk level based on the pose data of the tunneling component and the pose data of the anchoring component is determined according to the corrected tunneling safety buffer zone and anchoring safety buffer zone. In other words, the above-defined tunneling safety buffer zone and anchoring safety buffer zone as the reference safety zones can be considered as the buffer zone configurations that can ensure absolute safety under standard conditions, and corrections need to be made through the dynamic safety buffer zone algorithm in subsequent discrimination. For example, if the pose data of the tunneling component and the pose data of the anchoring component show that the movement speed of the component is low or already in a decelerating state at that time, the above safety zone correction coefficient can be set to a value less than 1. If the pose data of the tunneling component and the pose data of the anchoring component show that the movement speed of the component is speeding or the component is aging (resulting in a decrease in braking ability), the above safety zone correction coefficient can be set to a value greater than 1.

[0065] Exemplarily, by comparing the real-time minimum distance determined according to the pose data of the tunneling component and the pose data of the anchoring component with the above-mentioned corrected tunneling safety buffer zone and anchoring safety buffer zone, and calculating the overlapping ratio between the safety buffer zones, the corresponding collision risk level is determined. Exemplarily, if the overlapping volume exceeds 20% of any buffer zone, it is determined as a medium risk; if it exceeds 50%, it is determined as a high risk.

[0066] Through the above process, combining the task path and the operating state, dynamically adjusting the buffer zone helps to improve the accuracy of risk detection; the collision risk level can provide a quantitative result for subsequent executions such as braking, decelerating or path adjustment, and thus helps to improve the system intelligence level and operation safety during the operation process.

[0067] In some implementation manners, risk analysis is performed on the pose data of the tunneling component and the pose data of the anchoring component. The method includes: According to the pose data of the tunneling component and the pose data of the anchoring component, a first distance is calculated, where the first distance is the minimum distance between the tunneling component and the anchoring component; according to the tunneling safety buffer zone and the anchoring safety buffer zone, a safety distance is obtained; and the first distance is compared with the safety distance to output the collision risk level.

[0068] Specifically, the first distance refers to the minimum spatial distance between the tunneling component and the anchoring component, which is used to measure the physical proximity between the two. Exemplarily, the first distance can be calculated according to three-dimensional envelope modeling using the shortest boundary distance algorithm. The safety distance is the combined minimum boundary value of the respective safety buffer zones of the two components, which is equivalent to the minimum spatial distance required to keep the safety envelopes of the two components non-contact.

[0069] Specifically, the relationship between the first distance and the safety distance is correspondingly assigned to multiple collision risk levels. For example: the first distance ≥ safety distance, it is a low risk; the first distance < 70% of the safety distance, it is a medium risk; the first distance < 40% of the safety distance, it is a high risk.

[0070] Exemplarily, first, taking the currently collected pose data as input, a rigid body simplified model (such as approximated by a cuboid or a cylinder) of the tunneling component and the anchoring component is established in space, and then the minimum distance (such as 0.45) between the two is calculated using a boundary collision detection algorithm (such as AABB or OBB); then, according to the predefined tunneling safety buffer zone radius (such as 0.30m) and the anchoring safety buffer zone radius (such as 0.35m), the sum of the two is calculated as the safety distance (such as 0.65m); furthermore, the first distance is compared with the safety distance: the current distance of 0.45m is less than the safety distance of 0.65m, and 0.45 / 0.65 ≈ 69.2%, which is in the interval [40%, 70%], and the collision risk level is determined to be medium risk.

[0071] Through the above process, the collision risk between the tunneling component and the anchoring component can be evaluated in real time and dynamically, providing a reliable basis for early warning and control.

[0072] In some implementation manners, the first distance is compared with the safety distance to output the collision risk level; wherein, when the ratio of the first distance to the safety distance is greater than or equal to 1, the ratio is output as the collision risk level; when the ratio of the first distance to the safety distance is less than 1, a safety signal is sent to the early warning response module.

[0073] Optionally, according to the collision possibility level determined by the ratio of the first distance to the safety distance, if the ratio is greater than or equal to 1, the ratio is directly output as the collision risk level; if the ratio is less than 1, it can be considered that the equipment spacing is within the safe range, and a safety signal is sent to the early warning response module to confirm that the current state is safe.

[0074] S400: Determine whether the collision risk levels of the tunneling component and the anchoring component are greater than or equal to a preset risk threshold. If the collision risk level is greater than or equal to the preset risk threshold, the early warning response module adjusts the postures of the tunneling component and the anchoring component.

[0075] Specifically, the preset risk threshold is used to determine whether it is necessary to respond to the current collision risk level, such as adjusting the postures of the tunneling component and the anchoring component to avoid collisions. Optionally, the preset risk threshold is determined through statistical analysis. For example, based on the construction data of the past year, the probability of collisions occurring during the switching process of the tunneling component and the anchoring component is statistically analyzed, and the risk level corresponding to a collision confidence level of 0.8 is set as the preset risk threshold.

[0076] Specifically, if the collision risk level is greater than or equal to the preset risk threshold, the warning response module is triggered to generate corresponding control signals according to the risk level to adjust the postures of the tunneling component and the anchoring component. Among them, the adjustment strategies include the backward and forward displacements and angle adjustments of the tunneling component, as well as the deployment, retraction time, and angle adjustments of the anchoring component. Through the above process, the collision risks of the tunneling component and the anchoring component can be evaluated and responded to in a timely and accurate manner, ensuring the safety of the equipment during the switching process.

[0077] In some embodiments, the warning response module adjusts the postures of the tunneling component and the anchoring component. The method includes: Obtaining the action spaces of the tunneling component and the anchoring component; if the action spaces of both the tunneling component and the anchoring component are smaller than the preset action space, the warning response module performs coordinated posture adjustment on the tunneling component and the anchoring component; if the action space of the tunneling component is greater than or equal to the preset action space, the warning response module adjusts the posture of the tunneling component; if the action space of the anchoring component is greater than or equal to the preset action space, the warning response module adjusts the posture of the anchoring component; if the action spaces of both the tunneling component and the anchoring component are greater than or equal to the preset action space, the warning response module adjusts the posture of either the tunneling component or the anchoring component.

[0078] Specifically, the action spaces of the tunneling component and the anchoring component refer to the actual movement ranges in which the tunneling component or the anchoring component can perform posture adjustment during operation. This space is jointly determined by the equipment design parameters (equipment degrees of freedom), the current working state, and the control strategy; the preset action space is the minimum effective adjustment range defined during the safe adjustment process. In other words, the preset action space is the basic movement amplitude for avoiding collisions or optimizing the operation path.

[0079] Specifically, when the action spaces of both devices (the tunneling component and the anchoring component) are insufficient for effective adjustment alone, the warning response module adjusts both of them simultaneously, that is, a greater movement amplitude is achieved through coordinated actions. The total adjustment amplitude of the coordinated actions effectively adjusts the relative positions of the two, thereby ensuring that the overall action space compensation reaches or exceeds the preset range.

[0080] Specifically, if the action space of a single device (tunneling component or anchoring component) is greater than or equal to the preset action space, the early warning response module only performs separate attitude adjustment on the corresponding device.

[0081] Specifically, if the action spaces of both (tunneling component and anchoring component) are greater than or equal to the preset action space, either of the two devices can be arbitrarily selected for adjustment to achieve overall safety control.

[0082] Optionally, after the attitude adjustment is executed, the pose and action space data of the tunneling component and the anchoring component are obtained again, and the collision risk level is recalculated. If the risk level is lower than the preset safety threshold, the adjustment is exited; if it is still higher than the threshold, additional adjustment is performed or the operator is notified to intervene.

[0083] Through the above process, the attitude adjustment strategy can be flexibly adjusted according to the action spaces of the tunneling component and the anchoring component, ensuring the safety and efficiency of the equipment in different environments.

[0084] In some embodiments, the early warning response module performs attitude adjustment on the tunneling component and the anchoring component, and the method further includes: The early warning response module determines the attitude adjustment object, and the attitude adjustment object includes a tunneling component, an anchoring component, and a tunneling-anchoring component; according to the attitude adjustment object, an attitude adjustment strategy is generated, and the attitude adjustment strategy includes the backward, forward displacement and angle of the tunneling component, and the deployment, retraction time and angle of the anchoring component.

[0085] Specifically, according to the discrimination result of the above early warning response module, the attitude adjustment object is determined. Among them, if the action spaces of the tunneling component and the anchoring component are both insufficient for effective adjustment alone, the attitude adjustment object is the tunneling-anchoring component; otherwise, the attitude adjustment object is a designated one (the action space of a single device is greater than or equal to the preset action space) or any one (the action spaces of both devices are greater than or equal to the preset action space) of the tunneling component and the anchoring component.

[0086] Furthermore, the attitude adjustment strategy is adaptively configured based on the determined attitude adjustment object, including the backward, forward displacement and angle of the tunneling component, and the deployment, retraction time and angle of the anchoring component. Exemplarily, if the attitude adjustment object is the tunneling-anchoring component, the attitude adjustment strategy includes: allocating the preset action space to the tunneling component and the anchoring component according to the ratio of the action spaces of the tunneling component and the anchoring component as the attitude adjustment strategy (for example, each adjusts 50% of the preset action space).

[0087] By determining different attitude adjustment objects, the above process can specifically adopt individual or collaborative adjustment strategies to generate matching adjustment strategies, which helps to achieve more refined risk control, making risk adjustment more comprehensive and the dynamic response faster, thus significantly reducing the collision risk.

[0088] In summary, the construction warning method for the roadheader-anchoring machine provided by the present invention has the following technical effects: The sensing and perception module is used to identify whether the current operation state of the roadheader-anchoring machine is in a switching state. If it is in a switching state, the pose modeling of the roadheader-anchoring machine is carried out according to the sensing data to obtain the pose data of the tunneling component and the anchoring component. Subsequently, based on the dynamic safety buffer algorithm, risk analysis is carried out on the pose data of the two to judge their collision risk levels. If the collision risk level is greater than or equal to the preset risk threshold, the warning response module adjusts the postures of the tunneling component and the anchoring component, thereby realizing the technical effects of dynamically monitoring the switching state, real-time risk assessment and warning, and further improving the construction safety.

[0089] Embodiment 2, as Figure 2 is a schematic structural diagram of the construction warning system for the roadheader-anchoring machine of the present invention. For example, Figure 1 In the flow schematic diagram of the construction warning method for the roadheader-anchoring machine of the present invention can be realized by a structure such as Figure 2 shown.

[0090] Based on the same concept as the construction warning method for the roadheader-anchoring machine in the above embodiment, the construction warning system for the roadheader-anchoring machine provided by the present invention further includes: An operation state recognition unit 11, configured to identify whether the current operation state of the roadheader-anchoring machine is in a switching state according to the sensing and perception module.

[0091] A pose modeling unit 12, configured to perform pose modeling on the roadheader-anchoring machine according to the sensing data of the sensing and perception module to obtain the pose data of the tunneling component and the pose data of the anchoring component if the roadheader-anchoring machine is in a switching state.

[0092] A collision risk analysis unit 13, configured to perform risk analysis on the pose data of the tunneling component and the pose data of the anchoring component based on the dynamic safety buffer algorithm to obtain the collision risk level between the tunneling component and the anchoring component.

[0093] A risk judgment and adjustment unit 14, configured to judge whether the collision risk levels of the tunneling component and the anchoring component are greater than or equal to a preset risk threshold. If the collision risk level is greater than or equal to the preset risk threshold, the warning response module adjusts the postures of the tunneling component and the anchoring component.

[0094] In some embodiments, the sensing and perception module of the operation status recognition unit 11 is connected to the status classification model, and whether the current operation status of the roadheader-anchoring machine is in a switching state is recognized according to the status classification model, wherein the roadheader-anchoring machine includes a tunneling state, an anchoring state, and a switching state.

[0095] In some embodiments, the operation status recognition unit 11 includes a classification model construction sub-unit, which is configured to: obtain the tunneling component sample data and the anchoring component sample data in the tunneling state, the anchoring state, and the switching state respectively. Extract feature vectors according to the tunneling component sample data and the anchoring component sample data, where the feature vectors include time series features, spatial features, and behavior features. Perform key feature extraction on the feature vectors to obtain the speed change of the tunneling component, the angle change of the anchoring component, and the action overlap degree of the tunneling and anchoring components in each state. Use a support vector machine to perform model training on the speed change of the tunneling component, the angle change of the anchoring component, and the action overlap degree of the tunneling and anchoring components in each state to obtain a trained status classification model.

[0096] In some embodiments, the collision risk analysis unit 13 includes: An equipment data and task path acquisition sub-unit, which is configured to acquire the equipment data and the task path of the tunneling component and the anchoring component.

[0097] A safety buffer definition sub-unit, which is configured to define a tunneling safety buffer and an anchoring safety buffer based on the equipment data of the tunneling component and the anchoring component and the task paths of the tunneling component and the anchoring component.

[0098] A collision risk analysis sub-unit, which is configured to perform risk analysis on the pose data of the tunneling component and the pose data of the anchoring component under the tunneling safety buffer and the anchoring safety buffer based on the dynamic safety buffer algorithm to obtain the collision risk level.

[0099] In some implementation manners, the execution steps of the collision risk analysis sub-unit in the collision risk analysis unit 13 further include: calculating a first distance according to the pose data of the tunneling component and the pose data of the anchoring component, where the first distance is the minimum distance between the tunneling component and the anchoring component. Obtain a safety distance according to the tunneling safety buffer and the anchoring safety buffer. Compare the first distance with the safety distance and output the collision risk level.

[0100] In some implementations, the execution steps of the collision risk analysis subunit in the collision risk analysis unit 13 further include: when the ratio of the first distance to the safety distance is greater than or equal to 1, outputting the collision risk level at the ratio. A safety signal sending unit, configured to send a safety signal to the warning response module when the ratio of the first distance to the safety distance is less than 1.

[0101] In some embodiments, the risk judgment and adjustment unit 14 includes: An action space acquisition subunit, configured to acquire the action spaces of the tunneling assembly and the anchoring assembly.

[0102] A collaborative attitude adjustment decision subunit, configured to, if the action spaces of the tunneling assembly and the anchoring assembly are both less than a preset action space, perform collaborative attitude adjustment on the tunneling assembly and the anchoring assembly by the warning response module.

[0103] A tunneling assembly attitude adjustment decision subunit, configured to, if the action space of the tunneling assembly is greater than or equal to the preset action space, perform attitude adjustment on the tunneling assembly by the warning response module.

[0104] An anchoring assembly attitude adjustment decision subunit, configured to, if the action space of the anchoring assembly is greater than or equal to the preset action space, perform attitude adjustment on the anchoring assembly by the warning response module.

[0105] A single-component attitude adjustment decision subunit, configured to, if the action spaces of the tunneling assembly and the anchoring assembly are both greater than or equal to the preset action space, perform attitude adjustment on the tunneling assembly or the anchoring assembly by the warning response module.

[0106] In some embodiments, the risk judgment and adjustment unit 14 further includes: An attitude adjustment object determination subunit, configured to determine an attitude adjustment object by the warning response module, where the attitude adjustment object includes a tunneling assembly, an anchoring assembly, and a tunneling-anchoring assembly.

[0107] An attitude adjustment strategy generation subunit, configured to generate an attitude adjustment strategy according to the attitude adjustment object, where the attitude adjustment strategy includes the backward and forward displacements and angles of the tunneling assembly, and the deployment, retraction times and angles of the anchoring assembly.

[0108] Embodiment 3, the present invention further provides a computer-readable storage medium, which can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the construction warning method for a roadheader-anchoring machine in the embodiments of the present invention, so as to implement the above-mentioned construction warning method for a roadheader-anchoring machine.

[0109] It should be understood that the disclosed embodiments of the present invention and the above descriptions enable those skilled in the art to implement the present invention. At the same time, the present invention is not limited to the above-mentioned part of the embodiments. It should be understood that ordinary skilled in the art can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A construction warning method for a continuous miner, characterized in that Including: Identifying whether the current operation state of the roadheader-anchoring machine is in a switching state according to the sensing and perception module; If the roadheader-anchoring machine is in a switching state, performing pose modeling on the roadheader-anchoring machine according to the sensing data of the sensing and perception module to obtain the pose data of the tunneling component and the pose data of the anchoring component; Performing risk analysis on the pose data of the tunneling component and the pose data of the anchoring component based on the dynamic safety buffer algorithm to obtain the collision risk level between the tunneling component and the anchoring component; Judging whether the collision risk levels of the tunneling component and the anchoring component are greater than or equal to a preset risk threshold. If the collision risk level is greater than or equal to the preset risk threshold, the warning response module adjusts the postures of the tunneling component and the anchoring component.

2. The construction warning method for the roadheader-anchoring machine according to claim 1, wherein The sensing and perception module is connected to the state classification model, and identifies whether the current operation state of the roadheader-anchoring machine is in a switching state according to the state classification model. Among them, the roadheader-anchoring machine includes a tunneling state, an anchoring state, and a switching state.

3. The construction warning method for a tunneling and bolting machine according to claim 2, characterized in that, The method for constructing the state classification model includes: Obtaining the sample data of the tunneling component and the sample data of the anchoring component in the tunneling state, the anchoring state, and the switching state respectively; Extracting feature vectors according to the sample data of the tunneling component and the sample data of the anchoring component. The feature vectors include time series features, spatial features, and behavior features; Performing key feature extraction on the feature vectors to obtain the speed change of the tunneling component, the angle change of the anchoring component, and the action overlap degree of the tunneling and anchoring components in each state; Using a support vector machine to perform model training on the speed change of the tunneling component, the angle change of the anchoring component, and the action overlap degree of the tunneling and anchoring components in each state to obtain a trained state classification model.

4. The construction warning method for a roadheader-anchoring machine according to claim 1, wherein Performing risk analysis on the pose data of the tunneling component and the pose data of the anchoring component based on the dynamic safety buffer algorithm. The method includes: Obtaining the equipment data and task paths of the tunneling component and the anchoring component; Defining a tunneling safety buffer and an anchoring safety buffer based on the equipment data of the tunneling component and the anchoring component and the task paths of the tunneling component and the anchoring component; Performing risk analysis on the pose data of the tunneling component and the pose data of the anchoring component under the tunneling safety buffer and the anchoring safety buffer based on the dynamic safety buffer algorithm to obtain the collision risk level.

5. The construction warning method for a roadheader-anchoring machine according to claim 4, wherein, Performing risk analysis on the pose data of the tunneling component and the pose data of the anchoring component. The method includes: Calculating a first distance according to the pose data of the tunneling component and the pose data of the anchoring component, where the first distance is the minimum distance between the tunneling component and the anchoring component; Obtaining a safety distance according to the tunneling safety buffer and the anchoring safety buffer; Comparing the first distance with the safety distance and outputting the collision risk level.

6. The construction warning method for a roadheader-anchoring machine according to claim 5, characterized in that, Comparing the first distance with the safety distance and outputting the collision risk level; Wherein, when the ratio of the first distance to the safety distance is greater than or equal to 1, the collision risk level is output at the ratio; When the ratio of the first distance to the safety distance is less than 1, a safety signal is sent to the warning response module.

7. The construction warning method for the roadheader-anchoring machine according to claim 1, characterized in that, The warning response module adjusts the postures of the tunneling assembly and the anchoring assembly, and the method includes: Obtaining the action spaces of the tunneling assembly and the anchoring assembly; If the action spaces of both the tunneling assembly and the anchoring assembly are less than the preset action space, the warning response module performs coordinated posture adjustment on the tunneling assembly and the anchoring assembly; If the action space of the tunneling assembly is greater than or equal to the preset action space, the warning response module adjusts the posture of the tunneling assembly; If the action space of the anchoring assembly is greater than or equal to the preset action space, the warning response module adjusts the posture of the anchoring assembly; If the action spaces of both the tunneling assembly and the anchoring assembly are greater than or equal to the preset action space, the warning response module adjusts the posture of the tunneling assembly or the anchoring assembly.

8. The construction warning method for a roadheader-anchoring machine according to claim 7, characterized in that The warning response module adjusts the postures of the tunneling assembly and the anchoring assembly, and the method further includes: The warning response module determines the posture adjustment object, and the posture adjustment object includes a tunneling assembly, an anchoring assembly, and a tunneling-anchoring assembly; According to the posture adjustment object, a posture adjustment strategy is generated, and the posture adjustment strategy includes the backward and forward displacements and angles of the tunneling assembly, and the deployment, retraction time, and angles of the anchoring assembly.

9. The construction warning system for the roadheader-anchoring machine is characterized in that, For implementing the construction warning method for a roadheader-anchor rig according to any one of claims 1-8, it includes: An operation state recognition unit for identifying whether the current operation state of the roadheader-anchor rig is in a switching state according to the sensing and perception module; A pose modeling unit for, if the roadheader-anchor rig is in a switching state, performing pose modeling on the roadheader-anchor rig according to the sensing data of the sensing and perception module to obtain the pose data of the tunneling assembly and the pose data of the anchoring assembly; A collision risk analysis unit for performing risk analysis on the pose data of the tunneling assembly and the pose data of the anchoring assembly based on the dynamic safety buffer algorithm to obtain the collision risk level between the tunneling assembly and the anchoring assembly; A risk judgment and adjustment unit for judging whether the collision risk levels of the tunneling assembly and the anchoring assembly are greater than or equal to a preset risk threshold, and if the collision risk level is greater than or equal to the preset risk threshold, the warning response module adjusts the postures of the tunneling assembly and the anchoring assembly.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the construction warning method for a roadheader-anchor rig according to any one of claims 1 to 8.

Images