A substation engineering monitoring method based on intelligent perception

Abstract

The present invention belongs to the technical field of substation engineering monitoring, and relates to a substation engineering monitoring method based on intelligent perception. The method dynamically generates a lifting trajectory envelope space including a specified crane boom body and a lifting object based on historical motion inertia characteristics, current operation target constraints, and real-time position feedback, associates the lifting trajectory envelope spaces of other cranes on the substation site, calibrates the intersection domain of the envelope space as a tangible collision risk domain, synchronously monitors the spatial distribution of the electromagnetic field strength of the substation electric field source, dynamically calculates the safety distance margin threshold between the end of the specified crane boom and the nearest electric field source based on the field strength gradient change rate and the boom posture parameters, calibrates the spatial coverage domain of the nearest electric field source that is less than the margin threshold as an intangible collision risk domain, and triggers a graded warning signal when the specified crane enters the tangible collision risk domain or the intangible collision risk domain, thereby significantly improving the application and accuracy of substation crane lifting collision monitoring.

Description

Technical Field

[0001] The present invention belongs to the technical field of substation engineering monitoring, and relates to a substation engineering monitoring method based on intelligent perception. Background Art

[0002] With the advancement of smart grid construction, substations, as core hubs of the power system, are attracting significant attention for their safety, reliability, and efficiency. Large equipment hoisting operations, due to the complex nature of multi-step coordination, present significant safety risks such as collisions and tilting. Traditional monitoring methods based on manual experience are unable to predict these risks in real time. Therefore, implementing hoisting collision warning monitoring is of irreplaceable importance for ensuring equipment and personnel safety, improving construction efficiency, and ensuring project quality.

[0003] There are also some solutions related to substation hoisting collision monitoring in the existing technology. For example, China Patent Publication No. CN118877752A is a substation crane anti-collision control method and system. It uses spherical electric field sensors and lidar to monitor the position and distance of charged obstacles, and uses image acquisition modules to identify and provide obstacle avoidance solutions, thereby improving the degree of observation automation, avoiding human visual errors and blind spots, and accurately monitoring the distance between the boom and obstacles in real time to prevent hoisting accidents.

[0004] Another Chinese patent, with publication number CN116692690A, describes a crane anti-collision warning method, device, equipment, and medium. When a crane is detected entering the operating area, its position, boom length, and inclination angle are obtained, and the three-dimensional coordinates of the vertex are obtained. A safety coordinate set is constructed based on a preset safety distance. The risk obstacle is determined based on the three-dimensional coordinates of the obstacle, and the distance between the boom and the obstacle is calculated. A collision alarm is issued when it is less than the safety distance. When an electric field is detected around the boom, the industrial frequency electric field strength corresponding to the electric field is determined. If the electric field strength exceeds the threshold, an electric shock alarm is issued, effectively preventing crane collisions and electric shocks.

[0005] Although the above scheme proposes some solutions related to substation hoisting collision monitoring, the existing technology still has the following limitations, specifically: 1. The existing technology has the defect of discretization of collision risk domain modeling, relies on discrete point cloud of lidar to detect obstacles, simplifies the boom into a single-point monitoring target at the end, fails to effectively construct the continuous motion envelope space of crane hoisting, ignores the swing envelope domain caused by inertia of the hoisting load and the offset factors caused by human operation, makes it difficult to accurately assess the risk of dynamic operations, and has the potential for monitoring blind spots and misjudgment.

[0006] 2. The existing technology ignores the coupling effect between the metal conductor of the boom and the electric field, and does not consider its dynamic distortion effect on the surrounding electromagnetic field strength distribution. It only relies on a preset fixed electric field strength threshold to trigger the alarm, which cannot accurately reflect the actual energized risk status of the boom. As a result, the alarm mechanism has lags or misjudgment risks, making it difficult to adapt to the real-time safety monitoring needs in complex electromagnetic environments. Summary of the Invention

[0007] In view of this, in order to solve the problems raised in the above background technology, a substation engineering monitoring method based on intelligent perception is proposed.

[0008] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a substation engineering monitoring method based on intelligent perception, including: dynamically generating the lifting trajectory envelope space of a specified crane based on historical motion inertia characteristics, current operation target constraints and real-time position feedback, including the boom body envelope space and the lifting object envelope space.

[0009] The hoisting trajectory envelope spaces of other cranes at the substation site are associated, and the intersection domain of the envelope spaces is calibrated as the tangible collision risk domain.

[0010] The spatial distribution of electromagnetic field strength of the substation's electric field source is synchronously monitored. The safety distance margin threshold between the end of the crane's boom and the nearest electric field source is dynamically calculated based on the field strength gradient change rate and the boom posture parameters. The spatial coverage area of ​​the nearest electric field source that is less than the margin threshold is calibrated as the invisible collision risk area.

[0011] When a designated crane enters the tangible collision risk zone or the intangible collision risk zone, a graded warning signal is triggered.

[0012] Compared with the existing technology, the beneficial effects of the present invention are as follows: (1) The present invention integrates the inertial characteristics of historical actions, the current operation target constraints and real-time position feedback to construct a lifting trajectory envelope space that integrates the boom body and the hoisted object and is updated adaptively with the operation status. Through multi-dimensional data coupling, it realizes accurate modeling of dynamic factors such as inertial swing and human operation offset during the lifting process, and significantly improves the continuous and three-dimensional monitoring accuracy of the collision risk domain under complex working conditions.

[0013] (2) The present invention incorporates a static obstacle avoidance mechanism into the process of constructing the envelope space of the hoisted object, and combines it with the dynamic correlation analysis of the intersection area of ​​the envelope space of multiple cranes to achieve the prediction of the tangible collision risk of the entire trajectory of the hoisting operation, significantly improving the safety and collaborative efficiency of the hoisting operation under complex working conditions, and providing a systematic collision prevention solution for multi-device linkage scenarios.

[0014] (3) The present invention simultaneously monitors the spatial distribution of the electromagnetic field strength of the electric field source in the substation, and through the coupling analysis of the dynamic distribution of the electromagnetic field and the posture of the equipment, accurately quantifies the safety critical values ​​of different working positions, realizes the real-time dynamic matching of safety standards with the environment and working conditions, significantly improves the refinement and response sensitivity of the electric shock risk warning in complex electromagnetic environments, and effectively avoids the delayed alarm or misjudgment problem caused by fixed thresholds. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 The present invention is a flowchart of the steps for implementing the method.

[0017] Figure 2 A logic schematic diagram is dynamically generated for the hoisting trajectory envelope space of the designated crane of the present invention.

[0018] Figure 3 A logic diagram for calculating the safety distance margin threshold between the end of the crane boom and the nearest electric field source is specified for the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] See also Figure 1 As shown, the present invention provides a substation engineering monitoring method based on intelligent perception, including: S11. Based on historical action inertia characteristics, current operation target constraints and real-time position feedback, dynamically generate the lifting trajectory envelope space of the specified crane, including the boom body envelope space and the lifting object envelope space.

[0021] See also Figure 2 As shown, in a preferred embodiment of the present invention, the dynamic generation process of the hoisting trajectory envelope space of the specified crane includes: obtaining the rated weight percentage of the current hoisting load of the specified crane, and retrieving the corresponding historical operating inertia parameters of the specified crane according to the percentage interval, including the historical maximum lateral swing margin and the historical longitudinal inertia moment extreme value.

[0022] It should be noted that the above-mentioned inertia parameters corresponding to the historical operation of the specified crane are retrieved according to the percentage interval, which specifically refers to the historical operation database of the specified crane. The percentage interval includes the low load interval, the medium load interval and the heavy load interval. The percentage range of each interval can be set as follows. 、 、 .

[0023] Connect the current operation starting point and the placement point to generate a basic path line, and load the substation site static obstacle coordinate library to generate multiple feasible obstacle avoidance trajectories.

[0024] The historical maximum lateral swing margin is expanded along each feasible obstacle avoidance trajectory to form a lateral envelope, and the historical longitudinal moment of inertia extreme values ​​are superimposed to form a continuous object envelope space.

[0025] The boom pitch angle and boom length are inversely solved for the coordinates of the trajectory points of each feasible obstacle avoidance trajectory, and a continuous boom envelope space is formed with the crane rotation center as the vertex.

[0026] It should be noted that the specific process of inversely solving the boom pitch angle and arm length from the above trajectory point coordinates is: taking the vertical coordinate difference between the trajectory point and the crane rotation center as the numerator, and the horizontal coordinate difference as the denominator, and substituting the ratio operation result into the inverse tangent function to obtain the boom pitch angle.

[0027] The vertical coordinate difference and horizontal coordinate difference between the trajectory point and the crane rotation center are squared respectively, and then summed, and then the square root of the sum is taken to obtain the boom length.

[0028] The continuous boom envelope space is a conical space formed by taking the sum of the boom pitch angle and the preset safety margin angle as the cone angle and the boom length as the radius.

[0029] The continuous objects and boom envelope spaces of all feasible obstacle avoidance trajectories are integrated to form the initial lifting trajectory envelope space of the specified crane.

[0030] The real-time coordinates of the hoisted object and the end of the boom are obtained through the hook and boom end position sensors respectively. The real-time coordinate comparison is used to determine whether the reconstruction standard is met. If so, the subsequent trajectory envelope space is reconstructed based on the current position. Otherwise, the initial hoisting trajectory envelope space is kept valid.

[0031] In a preferred embodiment of the present invention, the process of generating multiple obstacle avoidance feasible trajectories includes:

[0032] According to the outer contour boundary coordinate set of each static obstacle recorded in the static obstacle coordinate library, the minimum circumscribed space volume of each static obstacle at the substation site is planned and a safety expansion process is performed.

[0033] It should be noted that the above-mentioned safety expansion processing can adopt the isometric expansion method or the proportional expansion method, wherein the isometric expansion method is to set a safety expansion distance, and for each surface of the minimum circumscribed space body of each static obstacle, translate the safety expansion distance outward along the normal direction.

[0034] The proportional expansion method is to set an expansion proportional coefficient and expand the dimensions of the minimum circumscribed space of each static obstacle by the expansion proportional coefficient on the original basis.

[0035] In the free space around the basic path line, candidate path points are screened according to the predefined sampling density. Obstacle collision detection is performed on the lines connecting the candidate points using the separating axis theorem. Path segments that intersect with any static obstacle space after expansion are filtered out, and a collision-free topological path diagram is constructed between the current operation starting point and the placement point.

[0036] It should be noted that the above-mentioned predefined sampling density follows the following rules: when the relative distance to the static obstacle is less than the preset standard distance, the basic sampling density is used to screen the path candidate points; when the relative distance is greater than or equal to the standard distance, the sampling density is adjusted to a set multiple higher than the basic value to screen the path candidate points.

[0037] It should also be noted that the above-mentioned separating axis theorem points out that for two convex bodies, if there is a straight line in two-dimensional space or a plane in three-dimensional space so that the projections of the two convex bodies on the straight line or plane do not overlap, then this straight line or plane is the separating axis, which is used to determine that the two convex bodies have not collided. When the two convex bodies collide, such a separating axis that can make their projections non-overlapping cannot be found in any direction. The present invention can perform obstacle collision detection on the lines between candidate points under the separating axis theorem through Matlab software.

[0038] The specified crane motion constraints are checked for each path in the collision-free topological path graph, the motion compliance of each path is quantified, and the paths are arranged in descending order of motion compliance to select a preset number of paths as feasible obstacle avoidance trajectories.

[0039] In a preferred embodiment of the present invention, the specified crane motion constraint verification of each path in the collision-free topological path graph includes: detecting the direction angle change rate between adjacent path segments in the path, and counting the number of sudden change path segments that exceed the preset response threshold of the crane mechanism.

[0040] The extreme value of the crane load swing angle along the entire path is calculated based on the change in path elevation.

[0041] It should be noted that the specific process of calculating the extreme value of the crane load swing angle throughout the entire path based on the change in path elevation is as follows: collecting the path elevation data sequence and constructing a fitting function, performing a second-order derivative of the fitting function to obtain the real-time vertical acceleration of the path, substituting the ratio of the vertical acceleration to the acceleration of gravity into the inverse tangent function to obtain the predicted degree of the crane load swing angle in real time, and screening the maximum value among them as the extreme value of the crane load swing angle throughout the path.

[0042] It should also be noted that the specific quantification process of the motion conformity of the above-mentioned paths includes: adding the ratio of the crane load swing angle extreme value throughout the path to the preset safety swing angle threshold of the specified crane, and the proportion of the number of sudden path segments that exceed the preset response threshold of the crane mechanism, and substituting the accumulated value into the preset standard attenuation function to obtain the motion conformity.

[0043] In a preferred embodiment of the present invention, the reconstruction standard includes the following contents: setting a set of key feature points for each feasible obstacle avoidance trajectory according to a preset spacing, obtaining the spatial offset vector of the real-time coordinates of the hoisted object and its nearest key feature point, and when the spatial offset modulus is continuously sampled for a preset number of times greater than a preset tolerance spacing threshold and the change rate of the spatial offset modulus is greater than a first preset change rate, it is determined that the hoisted object trajectory offset phenomenon exists.

[0044] The shortest distance between the real-time coordinates of the boom end and the envelope space of the initial hoisting trajectory is calculated. If the shortest distance is less than the preset warning distance and the change rate of the shortest distance is less than the second preset change rate, it is determined that the boom boundary approach phenomenon is established.

[0045] It should be noted that the above-mentioned first preset change rate and second preset change rate can refer to the relevant recommended values ​​or limit values ​​in the operating specifications and safety standards of similar crane systems or automated lifting applications, where the first preset change rate is a positive value and the second preset change rate is a negative value.

[0046] If any of these phenomena is judged to be true, then the reconstruction standard is met.

[0047] In a preferred embodiment of the present invention, reconstructing the subsequent trajectory envelope space based on the current position includes: using the current position as a new operation starting point and generating a three-dimensional sector scanning area at a preset reconstruction angle toward the original placement point.

[0048] A modified feasible trajectory set is generated based on the static obstacle distribution in the three-dimensional sector-shaped scanning area.

[0049] The spatial offset vector between the coordinates of the hoisted object and its nearest key feature point in the previous trajectory is extracted, and the maximum lateral offset modulus and the maximum longitudinal offset modulus are screened. The maximum lateral offset modulus is expanded along each corrected feasible trajectory to form a lateral envelope, and the maximum longitudinal offset modulus is superimposed to form the subsequent object envelope space.

[0050] Similarly, the boom pitch angle and boom length corresponding to the feasible trajectory are corrected by inverse solution to form the subsequent boom envelope space.

[0051] Integrate all objects and boom envelope spaces of the corrected feasible trajectories and reconstruct the subsequent trajectory envelope space.

[0052] The embodiment of the present invention integrates the inertial characteristics of historical actions, current operation target constraints and real-time position feedback to construct a lifting trajectory envelope space that integrates the boom body and the hoisted object and is adaptively updated according to the operation status. Through multi-dimensional data coupling, it realizes accurate modeling of dynamic factors such as inertial swing and human operation offset during the lifting process, and significantly improves the continuous and three-dimensional monitoring accuracy of the collision risk domain under complex working conditions.

[0053] S12. Associate the hoisting trajectory envelopes of other cranes at the substation site and calibrate the intersection of the envelopes as the tangible collision risk domain.

[0054] The embodiment of the present invention incorporates a static obstacle avoidance mechanism into the process of constructing the envelope space of the hoisted object, and combines it with the dynamic correlation analysis of the intersection area of ​​the envelope spaces of multiple cranes to achieve the prediction of tangible collision risks for the entire trajectory of the hoisting operation, significantly improving the safety and collaborative efficiency of hoisting operations under complex working conditions, and providing a systematic collision prevention solution for multi-device linkage scenarios.

[0055] S13. Synchronously monitor the spatial distribution of the electromagnetic field strength of the electric field source of the substation, dynamically calculate the safety distance margin threshold between the end of the crane boom and the nearest electric field source based on the field strength gradient change rate and the boom posture parameters, and calibrate the spatial coverage area of ​​the nearest electric field source that is less than the margin threshold as the invisible collision risk area.

[0056] In a preferred embodiment of the present invention, the monitoring of the spatial distribution of electromagnetic field strength of the electric field source of the substation includes: obtaining the equipment type identification, spatial coordinates and real-time operating voltage level of each electric field source based on the live topology monitoring unit at the substation site.

[0057] By using the preset electromagnetic field strength distribution model library and associating equipment types with operating voltage levels, the basic electromagnetic field strength and spatial coverage of each electric field source under rated operating conditions are obtained to achieve spatial distribution monitoring of electromagnetic field strength of substation electric field sources.

[0058] See also Figure 3As shown, in a preferred embodiment of the present invention, the calculation of the safety distance margin threshold between the end of the designated crane boom and the nearest electric field source includes: dynamically determining the electric field source target closest to the end of the designated crane boom based on the real-time coordinates of the boom end and the spatial coverage domain scope under the rated working conditions of each electric field source.

[0059] The spatial dielectric coefficient is determined according to the real-time environmental humidity parameter of the substation site, and the image charge corresponding to the metal conductor of the boom is introduced at the electromagnetic symmetrical position of the target closest to the electric field source.

[0060] The disturbed composite field strength of the nearest electric field source target under the coupling of the basic electromagnetic field strength and the image charge is calculated, and the time series variation interval of the disturbed composite field strength is recorded to obtain the gradient variation rate of the electromagnetic field strength of the nearest electric field source target.

[0061] It should be noted that the calculation process of the disturbed composite field strength of the aforementioned nearest electric field source target under the coupling of the basic electromagnetic field strength and the image charge can refer to the following calculation formula: ,in As the basic electromagnetic field strength, is the spatial medium coefficient, is the image charge corresponding to the metal conductor of the boom, is the electromagnetic symmetric position spacing and the corresponding unit vector, is a preset constant.

[0062] The tilt sensor installed at the end of the boom collects the boom elevation angle data in real time and converts it into a standard arc measurement value.

[0063] According to the field intensity gradient change rate and the boom elevation angle arc value, the preset reference safety distance is dynamically compensated and corrected to generate a real-time updated safety distance margin threshold.

[0064] It should be noted that the above safety distance margin threshold can be calculated by referring to the formula ,in They represent the boom elevation angle radian value and the field intensity gradient change rate respectively. Respectively represent the pre-calibrated elevation angle influence coefficient and field intensity gradient influence coefficient, It is the preset benchmark safety distance.

[0065] In a preferred embodiment of the present invention, the process of determining the electric field source target closest to the end of the designated crane boom includes: calculating the geometric spatial distance from the real-time coordinates of the boom end to all position points on the boundary of the spatial coverage domain under the rated working conditions of each electric field source.

[0066] Filter specific location points in the electric field source coverage area of ​​the entire station that have the minimum geometric space distance from the real-time coordinates of the boom end.

[0067] The electric field source to which a specific location point belongs is taken as the nearest electric field source target.

[0068] The embodiment of the present invention synchronously monitors the spatial distribution of the electromagnetic field strength of the substation electric field source, and through the coupling analysis of the dynamic distribution of the electromagnetic field and the equipment posture, accurately quantifies the safety critical values ​​of different working positions, realizes real-time dynamic matching of safety standards with the environment and working conditions, significantly improves the refinement and response sensitivity of electric shock risk warning in complex electromagnetic environments, and effectively avoids the delayed alarm or misjudgment problem caused by fixed thresholds.

[0069] S14. When the designated crane enters the tangible collision risk zone or the intangible collision risk zone, a graded warning signal is triggered.

[0070] In a preferred embodiment of the present invention, the graded warning signal includes a first-level warning signal for entering the tangible collision risk domain and a second-level warning signal for entering the intangible collision risk domain, and the response process is as follows: outputting sound and light alarms and operation prohibitions through the human-computer interaction interface.

[0071] Send the equipment locking command code to the power control unit.

[0072] Upload the risk domain field strength topology map to the remote monitoring terminal in real time.

[0073] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0074] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0075] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0076] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0077] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0078] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A substation engineering monitoring method based on intelligent perception, characterized in that: include: Based on the historical motion inertia characteristics, current operation target constraints and real-time position feedback, the hoisting trajectory envelope space of the specified crane is dynamically generated, including the boom body envelope space and the hoisted object envelope space; Specify the dynamic generation process of the crane's hoisting trajectory envelope space, including: Obtain the percentage of the rated weight of the current hoisting load of the specified crane, and retrieve the corresponding historical operating inertia parameters of the specified crane based on the percentage range, including the historical maximum lateral swing margin and the historical extreme value of the longitudinal moment of inertia; Connect the current operation starting point and placement point to generate a basic path line, and load the substation site static obstacle coordinate library to generate multiple obstacle avoidance feasible trajectories; Expanding the historical maximum lateral swing margin along each feasible obstacle avoidance trajectory to form a lateral envelope, and superimposing the historical extreme values ​​of the longitudinal moment of inertia to form a continuous object envelope space; The boom pitch angle and boom length are inversely solved for the coordinates of the trajectory points of each feasible obstacle avoidance trajectory, and a continuous boom envelope space is formed with the crane rotation center as the vertex; Integrate the continuous objects and boom envelope spaces of all feasible obstacle avoidance trajectories to form the initial hoisting trajectory envelope space of the specified crane; The real-time coordinates of the hoisted object and the end of the boom are obtained through the hook and boom end position sensors respectively. The real-time coordinate comparison is used to determine whether the reconstruction standard is met. If so, the subsequent trajectory envelope space is reconstructed based on the current position. Otherwise, the initial hoisting trajectory envelope space is kept valid. The hoisting trajectory envelopes of other cranes at the substation site are associated, and the intersection of the envelopes is calibrated as the tangible collision risk domain. The electromagnetic field intensity spatial distribution of the substation's electric field source is synchronously monitored. Based on the field intensity gradient change rate and boom posture parameters, a safety margin threshold between the crane boom end and the nearest electric field source is dynamically calculated. The spatial coverage area of ​​the nearest electric field source that is less than the margin threshold is calibrated as an invisible collision risk area. When a designated crane enters the tangible collision risk zone or the intangible collision risk zone, a graded warning signal is triggered.

2. The substation engineering monitoring method based on intelligent perception according to claim 1 is characterized in that: The process of generating multiple obstacle avoidance feasible trajectories includes: According to the outer contour boundary coordinate set of each static obstacle recorded in the static obstacle coordinate library, the minimum circumscribed space volume of each static obstacle at the substation site is planned and a safety expansion process is performed; In the free space around the basic path line, candidate path points are screened according to a predefined sampling density. Obstacle collision detection is performed on the lines connecting the candidate points using the separating axis theorem. Path segments that intersect with any static obstacle space after expansion are filtered out, and a collision-free topological path diagram is constructed between the current operation start point and the placement point. The specified crane motion constraints are checked for each path in the collision-free topological path graph, the motion compliance of each path is quantified, and the paths are arranged in descending order of motion compliance to select a preset number of paths as feasible obstacle avoidance trajectories.

3. The substation engineering monitoring method based on intelligent perception according to claim 2 is characterized by: The checking of the specified crane motion constraints on each path in the collision-free topological path graph includes: Detect the rate of change of azimuth angles between adjacent path segments in the path and count the number of sudden path segments that exceed the preset response threshold of the crane mechanism; The extreme value of the crane load swing angle along the entire path is calculated based on the change in path elevation.

4. The substation engineering monitoring method based on intelligent perception according to claim 1 is characterized in that: The reconstruction criteria include the following: A set of key feature points is set for each feasible obstacle avoidance trajectory according to a preset spacing, and a spatial offset vector between the real-time coordinates of the hoisted object and its nearest key feature point is obtained. When the spatial offset modulus is continuously greater than a preset tolerance spacing threshold for a preset number of sampling times and the spatial offset modulus change rate is greater than a first preset change rate, it is determined that the hoisted object trajectory offset phenomenon exists; Calculating the shortest distance between the real-time coordinates of the boom end and the envelope space of the initial hoisting trajectory; if the shortest distance is less than a preset warning distance and the rate of change of the shortest distance is less than a second preset rate of change, determining that the boom boundary approach phenomenon is established; If any of these phenomena is judged to be true, then the reconstruction standard is met.

5. The substation engineering monitoring method based on intelligent perception according to claim 1 is characterized in that: The reconstructing of the subsequent trajectory envelope space based on the current position includes: Taking the current position as the new operation starting point, a three-dimensional sector scanning area is generated at a preset reconstruction angle in the direction of the original placement point; Generating a modified feasible trajectory set based on static obstacle distribution within the three-dimensional sector scanning area; Extract the spatial offset vector between the coordinates of the hoisted object and its nearest key feature point in the previous trajectory, select the maximum lateral offset modulus and the maximum longitudinal offset modulus, expand the maximum lateral offset modulus along each corrected feasible trajectory to form a lateral envelope, and superimpose the maximum longitudinal offset modulus to form the subsequent object envelope space; Inversely solve and correct the boom pitch angle and boom length corresponding to the feasible trajectory according to the method for dynamically generating the hoisting trajectory envelope space of the specified crane to form a subsequent boom envelope space; Integrate all objects and boom envelope spaces of the corrected feasible trajectories and reconstruct the subsequent trajectory envelope space.

6. The method for monitoring a substation project based on intelligent perception according to claim 1, characterized in that: The monitoring of the spatial distribution of the electromagnetic field strength of the electric field source of the substation includes: Based on the live topology monitoring unit at the substation site, the device type identification, spatial coordinates and real-time operating voltage level of each electric field source are obtained; By using the preset electromagnetic field strength distribution model library and associating equipment types with operating voltage levels, the basic electromagnetic field strength and spatial coverage of each electric field source under rated operating conditions are obtained to achieve spatial distribution monitoring of electromagnetic field strength of substation electric field sources.

7. The method for monitoring a substation project based on intelligent perception according to claim 6, characterized in that: The calculation specifies a safety distance margin threshold between the end of the crane boom and the nearest electric field source, including: Dynamically determine the electric field source target closest to the designated crane boom end based on the real-time coordinates of the boom end and the spatial coverage of each electric field source under rated working conditions; Determine the spatial dielectric coefficient based on the real-time environmental humidity parameter of the substation site, and introduce the image charge corresponding to the metal conductor of the boom at the electromagnetic symmetrical position of the target closest to the electric field source; Calculating the disturbed composite field strength of the nearest electric field source target under the coupling effect of the basic electromagnetic field strength and the image charge, and recording the time series variation interval of the disturbed composite field strength to obtain the gradient change rate of the electromagnetic field strength of the nearest electric field source target; The tilt sensor installed at the end of the boom collects the boom elevation angle data in real time and converts it into a standard arc measurement value; According to the field intensity gradient change rate and the boom elevation angle arc value, a preset reference safety distance is dynamically compensated and corrected to generate a real-time updated safety distance margin threshold.

8. The method for monitoring a substation project based on intelligent perception according to claim 7, characterized in that: The process of determining the electric field source target closest to the end of the designated crane boom includes: Calculating the geometric spatial distances from the real-time coordinates of the boom end to all position points on the boundary of the spatial coverage domain under the rated working conditions of each electric field source; Screening the specific location point with the smallest distance from the real-time coordinate geometric space of the boom end in the electric field source coverage area of ​​the entire station; The electric field source to which a specific location point belongs is taken as the nearest electric field source target.

9. The method for monitoring a substation project based on intelligent perception according to claim 1, characterized in that: The graded warning signal includes a first-level warning signal for entering the tangible collision risk domain and a second-level warning signal for entering the intangible collision risk domain, and the response process is as follows: outputting an audible and visual alarm and an operation prohibition through a human-computer interaction interface; Sending equipment locking instruction code to the power control unit; Upload the risk domain field strength topology map to the remote monitoring terminal in real time.

Images