A method and system for evaluating multi-element blasting effects based on point cloud data

Abstract

The present invention discloses a method and system for multivariate blasting effect evaluation based on point cloud data, which relates to the field of blasting effect evaluation using drilling and blasting methods. The present invention uses a three-dimensional laser scanner to scan a point cloud after tunnel blasting, and uses the Canupo algorithm to classify the blasting pile point cloud, the face point cloud, and the tunnel point cloud; by processing the blasting pile point cloud, the face point cloud, and the tunnel point cloud, the large block rate, the throwing distance, the excavation footage, the blasthole utilization rate, the tunnel half-hole, and the over-excavation index parameters are obtained respectively; the blasting effect evaluation score is obtained by combining the weights and the scores of the various index parameters, and the blasting effect evaluation is obtained. The present invention can accurately obtain multiple blasting effect evaluation indicators based on the point cloud data obtained by three-dimensional laser scanning, and quantitatively evaluate the blasting effect, saving a lot of manpower, improving the efficiency and accuracy of blasting effect evaluation, and providing a reference for the improvement of subsequent blasting design.

Description

Technical Field

[0001] The present invention relates to the field of blasting effect evaluation using a drilling and blasting method, and in particular to a method and system for multivariate blasting effect evaluation based on point cloud data. Background Art

[0002] Drill and blast tunnel excavation refers to a construction method that excavates tunnels by drilling holes, loading explosives, and blasting rocks. Drill and blast tunnel excavation has the characteristics of low cost and strong geological applicability.

[0003] The current drilling and blasting blasting effect evaluation technology faces problems such as insufficient accuracy and difficulty in obtaining blasting effect evaluation parameters. Through three-dimensional laser scanning technology, multiple blasting effect evaluation parameters can be obtained quickly and accurately, and data processing can be quickly realized to generate blasting effect evaluation, and blasting design can be adjusted in real time accordingly.

[0004] Point cloud data is a data structure composed of a large number of coordinate information points in three-dimensional space. Point cloud data can truly reflect the three-dimensional geometric shape and surface features of an object, and has the characteristics of high precision and high density. Point cloud data can be obtained through three-dimensional laser scanning and other surveying and mapping technologies, and is usually used in geographic information systems and surveying and mapping, construction and civil engineering, cultural relics protection and other fields. Summary of the Invention

[0005] In order to solve the problems existing in the prior art, the purpose of the present invention is to provide a method for multivariate blasting effect evaluation based on point cloud data. The present invention can obtain multiple blasting effect evaluation indicators based on the point cloud after tunnel blasting, and proposes a method for blasting effect evaluation based on the extracted indicators. The method has the characteristics of high efficiency, intelligence, high precision, low labor cost, and quantification of blasting effect evaluation.

[0006] To achieve the above objectives, the technical solutions adopted by the present invention are specifically as follows:

[0007] A method for multivariate blasting effect evaluation based on point cloud data comprises the following steps:

[0008] S1. Scan the tunnel after blasting with a 3D laser scanner to obtain point cloud data. Use the Canupo algorithm to classify the obtained point cloud data into tunnel face point cloud, blast pile point cloud, and tunnel body point cloud.

[0009] S2. Calculate the shortest distance between the tunnel face point cloud obtained from the current scan and the tunnel face point cloud obtained from the previous blasting to obtain the excavation footage for this blasting. Then, based on the actual blasting design and excavation footage, determine the blasthole utilization rate.

[0010] S3. Process the blast pile point cloud to output the blast pile fragmentation distribution data. Based on actual project data, determine the threshold for determining the large fragment rate, and then obtain the large fragment rate index. Determine the throwing distance based on the relationship between the blast pile point cloud and the tunnel face point cloud.

[0011] S4. Process the tunnel point cloud to generate a semi-hole point cloud. Based on engineering practice, obtain the semi-hole ratio. Generate a tunnel design contour model based on the actual tunnel design. Compare the obtained point cloud with the tunnel design contour model to determine the amount of tunnel over-excavation or under-excavation.

[0012] S5. Determine the qualified and expected values for each parameter based on the tunnel blasting design and engineering practice, and assign scores to the semi-hole ratio, blasthole utilization rate, excavation footage, large block ratio, throwing distance, and tunnel over-excavation and under-excavation indicators; calculate the blasting effect evaluation score through weighted calculation, and evaluate the blasting effect based on the evaluation score.

[0013] Furthermore, the step S3 specifically includes the following sub-steps:

[0014] S301. Segment the blast pile point cloud using a clustering algorithm to obtain a segmented blast pile block point cloud;

[0015] S302. The three-dimensional distance between the two farthest points in the segmented point cloud of each blast pile block is the block size of the corresponding block; according to the scale of the shovel equipment used in actual engineering, set the threshold value of the large block rate;

[0016] S303. Compare the blockiness of each block with the threshold to obtain a large block ratio index.

[0017] Furthermore, the step S4 specifically includes the following sub-steps:

[0018] S401. A semi-circle fitting process is performed on the tunnel body point cloud to obtain a half-hole point cloud;

[0019] S402. Measure the total length of the remaining half-hole using the half-hole point cloud. Compare this with the total length of the actual pre-set blasthole to obtain the half-hole ratio.

[0020] S403. Generate a tunnel design contour model based on the actual tunnel design, and use the distance difference between the obtained point cloud and the tunnel design contour as the tunnel over-excavation amount;

[0021] S404. Based on the tunnel excavation footage, obtain the average linear overbreak and the average linear underbreak of the tunnel.

[0022] Furthermore, in step S5, the specific process of assigning points is as follows: assigning points to each extracted blasting effect evaluation parameter, determining the expected value and qualified value of each indicator based on the tunnel blasting design and engineering practice, using the semi-hole rate, blasthole utilization rate, and excavation footage as positive indicators, and the large block rate, throwing distance, and tunnel over-excavation and under-excavation as negative indicators, to assign points to each indicator. The score calculation process for positive and negative indicators is specifically expressed as follows:

[0023] Positive indicator scoring: ;

[0024] Reverse indicator scoring: ;

[0025] Among them, the Represents various evaluation index parameters, Indicates the qualified values corresponding to various indicator parameters, To express the expected value corresponding to each indicator parameter, the indicator parameters include half-hole rate, blasthole utilization rate, excavation footage, large block rate, throwing distance and tunnel over-excavation and under-excavation indicators.

[0026] Furthermore, in step S5, the specific process of weighted calculation of the blasting effect evaluation score is as follows:

[0027] S501. Determine the weight of the extracted blasting effect evaluation parameters in the blasting effect evaluation model, and determine the subjective weight of each evaluation parameter in the blasting effect evaluation according to the expert evaluation method. ;

[0028] S502. According to the CRITIC method, objective weights are determined, and blasting effect evaluation parameters extracted after multiple blasting are used to standardize each indicator to obtain a standardized indicator.

[0029] S503. Construct a decision matrix based on the extracted indicators of large block rate, casting distance, half-hole rate, average linear overbreak of the tunnel, average linear underbreak of the tunnel, excavation footage, and blasthole utilization rate. ;

[0030] S504. Based on the standard deviation between various indicators Calculate the correlation coefficient and covariance, and determine the amount of information contained in each indicator;

[0031] S505. Determine the objective weight of each indicator based on the amount of information contained in each indicator ; and according to the minimum discriminant information principle, the objective weights of each indicator are combined to obtain the combined weight.

[0032] Furthermore, in step S503, the decision matrix Specifically expressed as:

[0033] ;

[0034] Among them, the Indicates the The first sample The value of the indicator, Indicates the total number of samples.

[0035] Furthermore, in step S504, the calculation process of the correlation coefficient is specifically expressed as follows:

[0036] ;

[0037] The calculation process for determining the amount of information contained in each indicator is specifically expressed as follows:

[0038] ;

[0039] Among them, the Indicates the Indicators and The correlation coefficient between the indicators is Indicates the Indicators and The covariance of the indicators, Represents the standard deviation of the j-th indicator, Indicates the amount of information contained in the j-th indicator.

[0040] Furthermore, in step S505, the objective weight calculation process is specifically expressed as follows:

[0041] ;

[0042] The combined weight is obtained according to the minimum discriminant information principle , where the calculation process of the combined weight is specifically expressed as:

[0043] ;

[0044] Among them, the Indicates the combined weight of the jth indicator in the evaluation. Indicates the subjective weight of the jth indicator in the evaluation. It represents the objective weight of the jth indicator in the evaluation.

[0045] Furthermore, in step S5, the blasting effect evaluation score The calculation process is specifically expressed as follows:

[0046] ;

[0047] based on The blasting effect judgment standard of the value is: When the blasting effect is good, When the blasting effect is better, When the blasting effect is poor, When the blasting effect is poor.

[0048] A system for multivariate blasting effect evaluation based on point cloud data, the system being implemented based on any of the above-mentioned methods for multivariate blasting effect evaluation based on point cloud data, comprising:

[0049] Data acquisition module, used to obtain point cloud data of the tunnel after blasting through 3D laser scanning;

[0050] The data pre-processing module is used to reduce noise in the point cloud data and classify the blasting point cloud, tunnel point cloud, and face point cloud;

[0051] The evaluation index extraction module is used to process point cloud data and, based on engineering practice, obtain blasting effect evaluation parameters such as large block rate, throwing distance, average linear over-break and under-break of tunnels, blasting footage, and explosive consumption per unit.

[0052] The index parameter evaluation module is used to assign points to the extracted blasting effect evaluation index parameters and determine the weight of each index in the blasting effect evaluation;

[0053] The blasting effect evaluation module is used to obtain a blasting effect evaluation score based on the score of each evaluation indicator and the weight of each indicator, and to obtain a blasting effect evaluation based on the obtained blasting effect evaluation score.

[0054] The beneficial effects of the present invention are:

[0055] The present invention can accurately obtain multiple blasting effect evaluation indicators at one time based on the point cloud data obtained by three-dimensional laser scanning, and quantitatively evaluate the blasting effect, saving a lot of manpower and improving the efficiency of blasting effect evaluation. At the same time, it also avoids the problems of incomplete data collection, low accuracy, high time cost, etc. caused by manual data collection, and provides a reference for the improvement of subsequent blasting design. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a flow chart of a method according to an embodiment of the present invention;

[0057] Figure 2 2 is a system block diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The embodiments of the present invention are described in detail below with reference to the accompanying drawings. Example

[0059] like Figure 1 As shown, a method for multivariate blasting effect evaluation based on point cloud data includes the following steps:

[0060] A method for multivariate blasting effect evaluation based on point cloud data comprises the following steps:

[0061] S1. Scan the tunnel after blasting with a 3D laser scanner to obtain point cloud data. Use the Canupo algorithm to classify the obtained point cloud data into tunnel face point cloud, blast pile point cloud, and tunnel body point cloud.

[0062] S2. Calculate the shortest distance between the tunnel face point cloud obtained from the current scan and the tunnel face point cloud obtained from the previous blasting to obtain the excavation footage for this blasting. Then, based on the actual blasting design and excavation footage, determine the blasthole utilization rate.

[0063] S3. Process the blast pile point cloud to output the blast pile fragmentation distribution data. Based on actual project data, determine the threshold for determining the large fragment rate, and then obtain the large fragment rate index. Determine the throwing distance based on the relationship between the blast pile point cloud and the tunnel face point cloud.

[0064] S4. Process the tunnel point cloud to generate a semi-hole point cloud. Based on engineering practice, obtain the semi-hole ratio. Generate a tunnel design contour model based on the actual tunnel design. Compare the obtained point cloud with the tunnel design contour model to determine the amount of tunnel over-excavation or under-excavation.

[0065] S5. Determine the qualified and expected values for each parameter based on the tunnel blasting design and engineering practice, and assign scores to the semi-hole ratio, blasthole utilization rate, excavation footage, large block ratio, throwing distance, and tunnel over-excavation and under-excavation indicators; calculate the blasting effect evaluation score through weighted calculation, and evaluate the blasting effect based on the evaluation score.

[0066] Specifically, the process principle of step S1 is as follows: A 3D laser scanner uses time-of-flight (TOF) or phase difference detection technology to accurately measure 3D coordinates by emitting a high-frequency laser beam at the target area and capturing the time delay or phase difference of the reflected signal. The resulting point cloud data is high-density and highly accurate, fully reflecting the geometry and characteristics of the tunnel's interior surface. After preliminary processing, the point cloud data is classified using the Canupo algorithm. The Canupo algorithm uses a multi-scale feature extraction method based on the local geometric features of the points and constructs a support vector machine (SVM) classifier to automatically classify the point cloud.

[0067] Exemplarily, an implementation process of automatic classification is proposed: within the neighborhood of each point, by calculating its normal vector, curvature and statistical characteristics of local point distribution, a multidimensional feature vector describing the point cloud morphology is extracted; by gradually expanding the neighborhood range, the features of the point cloud at different scales are extracted, and these features are integrated into a high-dimensional feature space to describe the local geometric properties of the point cloud; based on manually annotated sample data, a classifier is constructed using a support vector machine (SVM), and the classification hyperplane is optimized to maximize the interval between categories; the trained classifier is applied to the entire point cloud dataset, and it is divided into a face point cloud, a blast pile point cloud and a tunnel body point cloud according to its geometric characteristics.

[0068] Specifically, the process of step S2 is as follows: The two scanned tunnel face point clouds are precisely aligned using the ICP (Iterative Closest Point) algorithm. The ICP algorithm iteratively minimizes the Euclidean distance between the two point clouds to find the optimal rigid body transformation matrix (including translation and rotation) to achieve spatial registration of the point clouds. After the point clouds are registered, a nearest neighbor search algorithm (such as KD-Tree) is used to calculate the shortest distance between the current point cloud and the previous point cloud. The KD-Tree structure efficiently searches for the closest point pairs in high-dimensional space. Based on the distribution of the shortest distances among all point pairs, the average or minimum displacement of the entire point cloud is calculated as the actual tunnel excavation progress. This method effectively filters out local noise points and ensures the accuracy of the calculation results.

[0069] Furthermore, the step S3 specifically includes the following sub-steps:

[0070] S301. Segment the blast pile point cloud using a clustering algorithm to obtain a segmented blast pile block point cloud;

[0071] S302. The three-dimensional distance between the two farthest points in the segmented point cloud of each blast pile block is the block size of the corresponding block; according to the scale of the shovel equipment used in actual engineering, set the threshold value of the large block rate;

[0072] S303. Compare the blockiness of each block with the threshold to obtain a large block ratio index.

[0073] Specifically, the point cloud is segmented using a clustering algorithm (such as DBSCAN or K-Means) to identify independent point cloud blocks. For example, DBSCAN leverages the density of point clouds to group neighboring points into the same cluster by defining a distance threshold and a minimum number of points. For point clouds with relatively uniform density, the K-Means algorithm iteratively optimizes the locations of cluster centers to partition the point cloud into a predefined number of blocks.

[0074] Furthermore, the step S4 specifically includes the following sub-steps:

[0075] S401. A semi-circle fitting process is performed on the tunnel body point cloud to obtain a half-hole point cloud;

[0076] S402. Measure the total length of the remaining half-hole using the half-hole point cloud. Compare this with the total length of the actual pre-set blasthole to obtain the half-hole ratio.

[0077] S403. Generate a tunnel design contour model based on the actual tunnel design, and use the distance difference between the obtained point cloud and the tunnel design contour as the tunnel over-excavation amount;

[0078] S404. Based on the tunnel excavation footage, obtain the average linear overbreak and the average linear underbreak of the tunnel.

[0079] Specifically, the semicircle fitting process in step S401 exemplarily involves fitting a circular arc to the hole point cloud using a fitting algorithm (e.g., the least squares method) to identify and extract the half-hole point cloud remaining from the blasting. The fitting model optimizes the arc parameters, namely, the center coordinates and radius, by minimizing the distance error between the point cloud and the circular arc.

[0080] Furthermore, in step S5, the specific process of assigning points is as follows: assigning points to each extracted blasting effect evaluation parameter, determining the expected value and qualified value of each indicator based on the tunnel blasting design and engineering practice, using the semi-hole rate, blasthole utilization rate, and excavation footage as positive indicators, and the large block rate, throwing distance, and tunnel over-excavation and under-excavation as negative indicators, to assign points to each indicator. The score calculation process for positive and negative indicators is specifically expressed as follows:

[0081] Positive indicator scoring: ;

[0082] Reverse indicator scoring: ;

[0083] Among them, the Represents various evaluation index parameters, Indicates the qualified values corresponding to various indicator parameters, To express the expected value corresponding to each indicator parameter, the indicator parameters include half-hole rate, blasthole utilization rate, excavation footage, large block rate, throwing distance and tunnel over-excavation and under-excavation indicators.

[0084] Furthermore, in step S5, the specific process of weighted calculation of the blasting effect evaluation score is as follows:

[0085] S501. Determine the weight of the extracted blasting effect evaluation parameters in the blasting effect evaluation model, and determine the subjective weight of each evaluation parameter in the blasting effect evaluation according to the expert evaluation method. ;

[0086] S502. According to the CRITIC method, objective weights are determined, and blasting effect evaluation parameters extracted after multiple blasting are used to standardize each indicator to obtain a standardized indicator.

[0087] S503. Construct a decision matrix based on the extracted indicators of large block rate, casting distance, half-hole rate, average linear overbreak of the tunnel, average linear underbreak of the tunnel, excavation footage, and blasthole utilization rate. ;

[0088] S504. Based on the standard deviation between various indicators Calculate the correlation coefficient and covariance, and determine the amount of information contained in each indicator;

[0089] S505. Determine the objective weight of each indicator based on the amount of information contained in each indicator ; and according to the minimum discriminant information principle, the objective weights of each indicator are combined to obtain the combined weight.

[0090] Furthermore, in step S501, the expert evaluation method is used to determine the evaluation parameters. For example, the Delphi method or the analytic hierarchy process (AHP) can be used to organize multiple blasting technology experts to score the importance of each indicator to form an expert scoring matrix.

[0091] Furthermore, in step S503, the decision matrix Specifically expressed as:

[0092] ;

[0093] Among them, the Indicates the The first sample The value of the indicator, Indicates the total number of samples.

[0094] Furthermore, in step S504, the calculation process of the correlation coefficient is specifically expressed as follows:

[0095] ;

[0096] The calculation process for determining the amount of information contained in each indicator is specifically expressed as follows:

[0097] ;

[0098] Among them, the Indicates the Indicators and The correlation coefficient between the indicators is Indicates the Indicators and The covariance of the indicators, Represents the standard deviation of the j-th indicator, Indicates the amount of information contained in the j-th indicator.

[0099] Furthermore, in step S505, the objective weight calculation process is specifically expressed as follows:

[0100] ;

[0101] The combined weight is obtained according to the minimum discriminant information principle , where the calculation process of the combined weight is specifically expressed as:

[0102] ;

[0103] Among them, the Indicates the combined weight of the jth indicator in the evaluation. Indicates the subjective weight of the jth indicator in the evaluation. It represents the objective weight of the jth indicator in the evaluation.

[0104] Furthermore, in step S5, the blasting effect evaluation score The calculation process is specifically expressed as follows:

[0105] ;

[0106] based on The blasting effect judgment standard of the value is: When the blasting effect is good, When the blasting effect is better, When the blasting effect is poor, When the blasting effect is poor.

[0107] Furthermore, as a preferred embodiment of this embodiment, a system for multivariate blasting effect evaluation based on point cloud data is also provided, such as Figure 2 Shown, including:

[0108] Data acquisition module: obtains point cloud data of the tunnel after blasting through 3D laser scanning;

[0109] Data pre-processing module: reduces noise on point cloud data and classifies blasting point cloud, tunnel point cloud, and face point cloud;

[0110] Evaluation index extraction module: used to process point cloud data and combine it with engineering practice to obtain blasting effect evaluation parameters such as large block rate, throwing distance, average linear over-break and under-break of tunnels, blasting footage, and explosive consumption per unit;

[0111] Index parameter evaluation module: assigns points to the extracted blasting effect evaluation index parameters and determines the weight of each index in the blasting effect evaluation;

[0112] Blasting effect evaluation module: The blasting effect evaluation score is obtained according to the score of each evaluation index and the weight of each index, and the blasting effect evaluation is obtained according to the obtained blasting effect evaluation score.

[0113] Furthermore, the specific implementation process principle of the above embodiment is as follows:

[0114] Using the Canupo algorithm, a classifier was constructed and trained based on the principle of multi-scale-dimensional feature analysis. The point cloud obtained after a tunnel blasting operation was manually segmented into samples of blast pile point clouds, tunnel face point clouds, and tunnel body point clouds. A classifier was trained based on these samples and applied to point clouds obtained after other tunnel blasting operations, thereby achieving classification of blast pile point clouds, tunnel body point clouds, and tunnel face point clouds.

[0115] The blast pile point cloud is segmented using a clustering algorithm to obtain the segmented blast pile block point cloud. The three-dimensional spatial distance between the two farthest points in each segmented blast pile block point cloud is used as the block size of the corresponding block. According to the scale of the shoveling equipment used in actual engineering, the threshold of the large block rate is obtained. The block size of each block is compared with the threshold to obtain the large block rate index.

[0116] The tunnel body point cloud is processed by semicircle fitting to obtain a half-hole point cloud. The total length of the remaining half-hole is measured and compared with the total length of the actual preset blastholes in the project to obtain the semi-porosity index. According to the actual tunnel design, a tunnel design contour model is generated. The difference in distance between the obtained point cloud and the tunnel design contour is used as the tunnel over-break and under-break. Combined with the tunnel excavation footage, the average linear over-break and average linear under-break of the tunnel are obtained.

[0117] Each extracted blasting effect evaluation parameter is scored. Tunnel blasting design and engineering practice require the determination of expected and qualified values for each indicator. The semi-hole rate, blasthole utilization rate, and excavation footage are used as positive indicators, while the large block rate, throwing distance, and tunnel over-excavation and under-excavation are used as negative indicators. Scores are assigned to each indicator. The following is a method for calculating the scores for positive and negative indicators:

[0118] Positive indicator scoring: ;

[0119] Reverse indicator scoring: ;

[0120] Among them, the Represents various evaluation index parameters, Indicates the qualified values corresponding to various indicator parameters, To express the expected value corresponding to each indicator parameter, the indicator parameters include half-hole rate, blasthole utilization rate, excavation footage, large block rate, throwing distance and tunnel over-excavation and under-excavation indicators.

[0121] Determine the weight of the extracted blasting effect evaluation parameters in the blasting effect evaluation model, and determine the subjective weight value of each evaluation parameter in the blasting effect evaluation according to the expert evaluation method ; According to the CRITIC method, the objective weight is determined, and the standardized index is obtained by standardizing each index based on the blasting effect evaluation parameters extracted after multiple blasting A decision matrix is constructed based on the extracted seven indicators: large block rate, throwing distance, half-hole rate, average linear overbreak of tunnel, average linear underbreak of tunnel, excavation footage, and blasthole utilization rate. , where the formula and decision matrix for indicator standardization are:

[0122] Normalization of positive indicators:

[0123] ;

[0124] Standardization of reverse indicators:

[0125] ;

[0126] Wherein, i represents the number of samples, j represents the index of the indicator, Represents a positive indicator after normalization. Represents the normalized inverse indicator.

[0127] Decision Matrix :

[0128] ;

[0129] Among them, the Indicates the The first sample The value of the indicator, Indicates the total number of samples.

[0130] According to the standard deviation between each indicator The correlation coefficient and covariance are used to calculate the information content of each indicator. The calculation formulas for the correlation coefficient and the information content are as follows:

[0131] ;

[0132] The calculation process for determining the amount of information contained in each indicator is specifically expressed as follows:

[0133] ;

[0134] Among them, the Indicates the Indicators and The correlation coefficient between the indicators is Indicates the Indicators and The covariance of the indicators, Represents the standard deviation of the j-th indicator, Indicates the amount of information contained in the j-th indicator.

[0135] The objective weight of each indicator is determined according to the amount of information contained in each indicator. The calculation formula of the objective weight is:

[0136] ;

[0137] The combination weight is obtained according to the minimum discriminant information principle, where the combination weight calculation formula is:

[0138] ;

[0139] Calculate the blasting effect evaluation score by combining the scores of each evaluation index with the weight , and based on The blasting effect evaluation is obtained by The calculation formula is:

[0140] ;

[0141] based on The blasting effect judgment standard of the value is: When the blasting effect is good, When the blasting effect is better, When the blasting effect is poor, When the blasting effect is poor.

[0142] Furthermore, as a preferred specific implementation of the above embodiment, a multi-objective evaluation method based on dynamic weights is proposed, which specifically includes the following steps:

[0143] S51. Based on the scores of the positive and negative indicators, construct a multi-objective optimization model, where the objective function is to maximize the positive indicator score and minimize the negative indicator score;

[0144] S52. Introducing the particle swarm optimization algorithm to dynamically adjust the weights of various indicators and optimize the objective function;

[0145] S53. Combined with the fuzzy comprehensive evaluation method, the scores of positive and negative indicators are mapped to fuzzy sets, and the comprehensive evaluation score is calculated through fuzzy reasoning;

[0146] S54. Calculate the blasting effect evaluation score based on the optimized weights and fuzzy inference results.

[0147] Furthermore, in step S51, the specific method for constructing the multi-objective optimization model includes:

[0148] Construct the objective function of the multi-objective optimization model:

[0149] Goal 1: Maximize the sum of positive indicator scores: , wherein the represents the objective function of maximizing the sum of positive indicator scores;

[0150] Goal 2: Minimize the sum of the inverse indicator scores: , wherein the represents the objective function of minimizing the sum of the inverse indicator scores;

[0151] Furthermore, in step S52, the particle swarm optimization algorithm is specifically expressed as:

[0152] ;

[0153] Among them, the represents the velocity of particle i at time t+1, represents the inertia weight, represents the velocity of particle i at time t, Indicates the step size of controlling the particle to move to the historical optimal position. represents a random number used to introduce randomness to the historical optimal position, Represents the step size of controlling the particle to move to the global optimal position, represents a random number used to introduce a random row to the global optimal position, represents the historical optimal position of particle i, Indicates that represents the position of particle i at time t, Represents the position of particle i at time t+1; the particles in the particle swarm optimization algorithm represent weight vectors, that is, the weights of various indicators in the blasting effect evaluation, and the position of each particle It represents a weight vector.

[0154] Furthermore, the step S52 specifically includes the following sub-steps:

[0155] S521. Randomly generate a set of particles, where the position of each particle represents a set of weights;

[0156] S522. Initialize the particle's velocity and historical optimal position; calculate the fitness value of each particle and determine the global optimal position;

[0157] S523. For each particle, calculate the new velocity and position according to the update formula; check whether the new position meets the constraints, and adjust if not;

[0158] S524. Calculate the fitness value of the new position; update the particle's historical optimal position and global optimal position; when the maximum number of iterations is reached or the fitness value converges, stop iteration and output the global optimal position, i.e., the optimal weight.

[0159] Furthermore, in S522, the fitness value of each particle is calculated by evaluating the quality of the weight vector through a fitness function. Based on the normalized index, the fitness function is defined as:

[0160] ;

[0161] Among them, the represents the fitness function, represents the weight vector.

[0162] Furthermore, the step S53 specifically includes the following sub-steps:

[0163] S531. For the scores of the positive and negative indicators, define the fuzzy membership function:

[0164] ;

[0165] Among them, the Represents the membership degree of the fuzzy set A, and Represents the boundary value of the fuzzy set;

[0166] S532. Generate comprehensive evaluation scores by reasoning using the fuzzy rule base:

[0167] S533. Use the centroid method to convert fuzzy scores into specific values:

[0168] ;

[0169] Among them, the represents the defuzzified value of the i-th indicator;

[0170] S534. Calculate the blasting effect evaluation score based on the weights optimized by the particle swarm optimization algorithm:

[0171] ;

[0172] Among them, the Indicates the blasting effect evaluation score.

[0173] As an example, a blasting effect evaluation method based on dynamic weights is given:

[0174] .

[0175] The above-described embodiments merely represent specific implementations of the present invention. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, and all such variations and improvements fall within the scope of protection of the present invention.

Claims

1. A method for multivariate blasting effect evaluation based on point cloud data, characterized in that: The following steps are involved: S1. Scan the tunnel after blasting with a 3D laser scanner to obtain point cloud data. Use the Canupo algorithm to classify the obtained point cloud data into tunnel face point cloud, blast pile point cloud, and tunnel body point cloud. S2. Calculate the shortest distance between the tunnel face point cloud obtained from the current scan and the tunnel face point cloud obtained from the previous blasting to obtain the excavation footage for this blasting. Then, based on the actual blasting design and excavation footage, determine the blasthole utilization rate. S3. Process the blast pile point cloud to output the blast pile fragmentation distribution data. Based on actual project data, determine the threshold for determining the large fragment rate, and then obtain the large fragment rate index. Determine the throwing distance based on the relationship between the blast pile point cloud and the tunnel face point cloud. S4. Process the tunnel point cloud to generate a semi-hole point cloud. Based on engineering practice, obtain the semi-hole ratio. Generate a tunnel design contour model based on the actual tunnel design. Compare the obtained point cloud with the tunnel design contour model to determine the amount of tunnel over-excavation or under-excavation. S5. Based on the tunnel blasting design and engineering practice, determine the acceptable and expected values for each parameter. Score the semi-hole ratio, blasthole utilization rate, excavation footage, large block ratio, casting distance, and tunnel over-excavation and under-excavation. Calculate the blasting effect evaluation score based on the score and weight of each evaluation indicator. Evaluate the blasting effect based on the resulting blasting effect evaluation score. The S3 specifically includes the following sub-steps: S301. Segment the blast pile point cloud using a clustering algorithm to obtain a segmented blast pile block point cloud; S302. The three-dimensional distance between the two farthest points in the segmented point cloud of each blast pile block is the block size of the corresponding block; according to the scale of the shovel equipment used in actual engineering, set the threshold value of the large block rate; S303. The blockiness of each block is compared with the threshold to obtain a large block rate indicator; The S4 specifically includes the following sub-steps: S401. A semi-circle fitting process is performed on the tunnel body point cloud to obtain a half-hole point cloud; S402. Measure the total length of the remaining half-hole using the half-hole point cloud. Compare this with the total length of the actual pre-set blasthole to obtain the half-hole ratio. S403. Generate a tunnel design contour model based on the actual tunnel design, and use the distance difference between the obtained point cloud and the tunnel design contour as the tunnel over-excavation amount; S404. Combined with the tunnel excavation footage, the average linear overbreak and the average linear underbreak of the tunnel are obtained; In S5, the specific scoring process is as follows: each extracted blasting effect evaluation parameter is scored, and the expected value and qualified value of each indicator are determined based on the tunnel blasting design and engineering practice. The semi-hole rate, blasthole utilization rate, and excavation footage are used as positive indicators, and the large block rate, throwing distance, and tunnel over-excavation and under-excavation are used as negative indicators. The score calculation process of the positive and negative indicators is specifically expressed as follows: Positive indicator scoring: ; Reverse indicator scoring: ; Among them, the Represents various evaluation index parameters, Indicates the qualified values corresponding to various indicator parameters, To express the expected value corresponding to each indicator parameter, the indicator parameters include half-hole rate, blasthole utilization rate, excavation footage, large block rate, throwing distance and tunnel over-excavation and under-excavation indicators.

2. The method for multivariate blasting effect evaluation based on point cloud data according to claim 1, characterized in that: In S5, the specific process of calculating the blasting effect evaluation score by the scores of each evaluation index and the weight of each index is as follows: S501. Determine the weight of the extracted blasting effect evaluation parameters in the blasting effect evaluation model, and determine the subjective weight of each evaluation parameter in the blasting effect evaluation according to the expert evaluation method. ; S502. According to the CRITIC method to determine the objective weight, and based on the blasting effect evaluation parameters extracted after multiple blasting, each indicator is standardized to obtain a standardized indicator; S503. Construct a decision matrix based on the extracted indicators of large block rate, casting distance, half-hole rate, average linear overbreak of the tunnel, average linear underbreak of the tunnel, excavation footage, and blasthole utilization rate. ; S504. Based on the standard deviation between various indicators Calculate the correlation coefficient and covariance, and determine the amount of information contained in each indicator; S505. Determine the objective weight of each indicator based on the amount of information contained in each indicator ; And according to the minimum discriminant information principle, the objective weight of each indicator is combined to obtain the combined weight; In S504, the calculation process of the correlation coefficient is specifically expressed as follows: ； The calculation process for determining the amount of information contained in each indicator is specifically expressed as follows: ； Among them, the Indicates the Indicators and The correlation coefficient between the indicators is Indicates the Indicators and The covariance of the indicators, Represents the standard deviation of the j-th indicator, Indicates the amount of information contained in the j-th indicator; In S505, the calculation process of the objective weight is specifically expressed as follows: ； The combined weight is obtained according to the minimum discriminant information principle , where the calculation process of the combined weight is specifically expressed as: ； Among them, the Indicates the combined weight of the jth indicator in the evaluation. Indicates the subjective weight of the jth indicator in the evaluation. It represents the objective weight of the jth indicator in the evaluation.

3. The method for multivariate blasting effect evaluation based on point cloud data according to claim 2, characterized in that: In S503, the decision matrix Specifically expressed as: ； Among them, the Indicates the The first sample The value of the indicator, Indicates the total number of samples.

4. The method for multivariate blasting effect evaluation based on point cloud data according to claim 2, characterized in that: In S5, the blasting effect evaluation score The calculation process is specifically expressed as follows: ； based on The blasting effect judgment standard of the value is: When the blasting effect is good, When the blasting effect is better, When the blasting effect is poor, When the blasting effect is poor.

5. A system for multivariate blasting effect evaluation based on point cloud data, the system being implemented based on the method for multivariate blasting effect evaluation based on point cloud data according to any one of claims 1 to 4, characterized in that: include: Data acquisition module, used to obtain point cloud data of the tunnel after blasting through 3D laser scanning; The data pre-processing module is used to reduce noise in the point cloud data and classify the blasting point cloud, tunnel point cloud, and face point cloud; The evaluation index extraction module is used to process point cloud data and, based on engineering practice, obtain the semi-hole ratio, blasthole utilization rate, excavation footage, large block ratio, throwing distance, and tunnel over-excavation and under-excavation, and calculate blasting effect evaluation parameters; The indicator parameter evaluation module is used to assign scores to the extracted blasting effect evaluation parameters and determine the weight of each indicator in the blasting effect evaluation; The blasting effect evaluation module is used to obtain a blasting effect evaluation score based on the score of each evaluation indicator and the weight of each indicator, and to obtain a blasting effect evaluation based on the obtained blasting effect evaluation score.

Images