A method and system for evaluating the operation safety of a construction equipment for road maintenance

Abstract

The application discloses a kind of construction equipment operation safety evaluation method and system of highway maintenance, it is related to equipment safety evaluation technical field, comprising: acquisition equipment multi-source operating condition data and normalization processing, form standardization working condition vector sequence;With each time series vector in working condition vector sequence as graph node, construct weight adjacency matrix to generate working condition evolution state atlas;According to the demand of task to be executed, construct task feature vector and match atlas node, calculate path comprehensive score and filter optimal evolution path;Each node in optimal evolution path is mapped to construction area, and the path comprehensive score is fused and corrected by environmental factor;The score after correction is classified and output safety level and control strategy by grading classification.This application realizes the closed-loop intelligent decision of construction safety by dynamic risk correction and evolution path prediction, improves the timeliness of early warning and environmental adaptability.

Description

Technical Field

[0001] This invention relates to the field of equipment safety evaluation technology, and in particular to a method and system for evaluating the operational safety of construction equipment used in highway maintenance. Background Technology

[0002] Safety evaluation technology for highway maintenance and construction equipment has gradually moved towards intelligentization in recent years. Existing technologies mainly rely on IoT sensors to collect equipment operating parameters in real time (such as vibration spectrum, oil temperature, and current fluctuations), combined with threshold early warning mechanisms to achieve basic fault diagnosis. With the penetration of machine learning technology, some studies have attempted to classify and evaluate equipment status using static models such as Support Vector Machines (SVM) and Random Forests. Meanwhile, the introduction of digital twin technology has made the visualization and analysis of equipment operating scenarios possible, mapping the physical entity's state through 3D modeling.

[0003] However, current technological focus remains on offline health assessment of single devices, lacking in-depth exploration of adaptability to dynamic construction tasks and multi-source temporal state evolution patterns; existing methods mostly employ discrete state snapshot analysis and have not yet established a collaborative evaluation system covering the entire chain of "device-task-environment", making it difficult to support real-time safety decision-making under complex working conditions. Summary of the Invention

[0004] This invention relates to the field of safety evaluation technology for highway maintenance and construction equipment. In view of the above-mentioned problems, this invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that existing methods for evaluating the safety of construction equipment suffer from the following problems: discretized state assessment lacks temporal evolution correlation and static models cannot dynamically couple task requirements with geographical environmental risks.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for evaluating the operational safety of construction equipment for highway maintenance, which includes acquiring multi-source operational status data of the construction equipment during task execution, normalizing the multi-source operational status data, and obtaining a working condition vector sequence.

[0008] By using each time-series vector in the working condition vector sequence as a graph node, a directed graph structure is established and a weighted adjacency matrix is ​​constructed to generate a working condition evolution state map.

[0009] Based on the requirements of the task to be executed, a task feature vector is constructed. The working condition evolution map is matched and scored with the task feature vector. A path task matching function is constructed, a comprehensive path score is calculated, and the optimal evolution path is selected.

[0010] Map each node in the optimal evolution path to the actual construction area, construct an environmental risk correction function, correct the comprehensive score of the path, and obtain the environmentally corrected score;

[0011] The environmental correction score is classified according to the preset scoring range, and the corresponding operational safety level label is output. Based on the different levels, corresponding control strategy suggestions are also output.

[0012] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the steps of acquiring multi-source operational status data of the construction equipment during task execution, normalizing the multi-source operational status data, and obtaining a working condition vector sequence are as follows.

[0013] Synchronously trigger and collect data from the sensors deployed on the construction equipment to obtain multi-source operating status data of the construction equipment during task execution;

[0014] The multi-source operational status data is aligned according to a unified timestamp and then normalized to generate a multi-source operational status data matrix.

[0015] Each parameter in the original matrix of multi-source operational status data is normalized to generate a multi-source operational status data matrix.

[0016] During task execution, the multi-source operational status data matrix is ​​vectorized to form a multi-source operational status data vector sequence.

[0017] Perform data consistency checks on each time-matter vector of the multi-source operating status data vector sequence and sort them according to time to form an operating condition vector sequence.

[0018] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the specific steps for generating a working condition evolution state graph are as follows: Each time-series vector in the working condition vector sequence is used as a graph node to establish a directed graph structure and construct a weighted adjacency matrix.

[0019] Extract the working condition vectors one by one in ascending order of time and define them as graph nodes to form a graph node set;

[0020] Based on the temporal relationship and state difference between two adjacent graph nodes in the graph node set, calculate the state transition weight and generate the graph edge set and its corresponding weight.

[0021] The set of graph nodes and the set of graph edges are structurally merged to construct a directed graph structure;

[0022] The weights of the edges in the directed graph are mapped to matrix form according to the node index position to generate a weighted adjacency matrix.

[0023] The graph node set, graph edge set, directed graph structure, and weighted adjacency matrix are uniformly encapsulated to generate a working condition evolution state map.

[0024] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the steps of constructing a task feature vector based on the requirements of the task to be performed, matching and scoring the working condition evolution map with the task feature vector, and constructing a path-task matching function are as follows:

[0025] The specific construction information and working condition vectors of the task to be performed are uniformly normalized into task feature vectors.

[0026] Based on the working condition evolution state map, all path combinations with a fixed depth are extracted from the graph node set to form a construction path set as a task matching and scoring object set.

[0027] Construct a path task matching function to match and score the task feature vector with the work condition vector corresponding to each node of each path in the path set of task matching scoring objects, and record the task matching score of each path.

[0028] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the specific steps for calculating the comprehensive score of the calculation path and selecting the optimal evolution path are as follows:

[0029] The rate of change of path conditions is calculated based on the state difference between consecutive nodes in each path;

[0030] Calculate the overall path score for each path based on the task matching score and the rate of change of working conditions between nodes in the path.

[0031] The path with the highest overall score is selected as the optimal evolutionary path for task execution.

[0032] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the specific steps for mapping each node in the optimal evolution path to the actual construction area and constructing an environmental risk correction function are as follows:

[0033] Each working condition vector node in the optimal evolution path of task execution is mapped to the construction time segment in the task plan in chronological order, thus forming the time mapping sequence of the optimal evolution path of task execution.

[0034] Based on the time mapping sequence of the optimal evolution path of task execution, environmental factor information is obtained to form a construction environmental factor matrix;

[0035] Based on the mapping relationship between the working condition vector nodes and the construction environmental factor matrix in the same time segment in the optimal evolution path of task execution, an environmental adaptation combination sequence is constructed. Based on the interference degree characteristics of environmental factors in the environmental adaptation combination sequence, an exponential environmental risk correction function is established to obtain the environmental risk correction value of all nodes in the optimal evolution path.

[0036] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the specific steps for correcting the comprehensive path score to obtain an environment-corrected score are as follows:

[0037] Arrange the environmental risk correction values ​​of all nodes in the optimal evolution path of task execution in the order of the path to obtain the sequence of environmental risk correction values ​​for the optimal evolution path of task execution.

[0038] Based on the correspondence between the comprehensive path score of each node in the optimal evolution path of task execution and the environmental risk correction value of each node in the optimal evolution path, a path environment correction score sequence is formed.

[0039] The average score of each node in the score sequence after path environment correction is calculated and used as the environment-corrected score of the optimal evolution path corresponding to task execution.

[0040] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the steps of classifying the environmentally corrected score according to a preset scoring interval and outputting the corresponding operational safety level label are as follows:

[0041] The score after correcting the optimal evolution path environment for task execution is compared with the preset score segment interval to determine the score interval and assign a security level label.

[0042] As a preferred embodiment of the method for evaluating the operational safety of construction equipment for highway maintenance as described in this invention, the specific steps for outputting corresponding control strategy suggestions based on different levels are as follows:

[0043] Based on the operational safety level label, and according to the preset operational control strategy table, output control strategy suggestions that match the operational safety level label.

[0044] Secondly, the present invention provides a safety evaluation system for the operation of construction equipment in highway maintenance, including a data normalization module for acquiring multi-source operating status data of construction equipment during task execution, normalizing the multi-source operating status data, and obtaining a working condition vector sequence.

[0045] The graph construction module is used to take each time-series vector in the working condition vector sequence as a graph node, establish a directed graph structure and construct a weighted adjacency matrix to generate a working condition evolution state graph.

[0046] The path matching decision module is used to construct a task feature vector based on the requirements of the task to be executed, match and score the working condition evolution map with the task feature vector, construct a path task matching function, calculate the comprehensive path score, and select the optimal evolution path.

[0047] The path score correction module is used to map each node in the optimal evolution path to the actual construction area, construct an environmental risk correction function, correct the comprehensive path score, and obtain the environmentally corrected score.

[0048] The control strategy suggestion module is used to classify the environmental correction score according to the preset score segment range, output the corresponding operation safety level label, and output the corresponding control strategy suggestion according to different levels.

[0049] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the method for evaluating the operational safety of construction equipment for highway maintenance as described in the first aspect of the present invention.

[0050] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for evaluating the operational safety of construction equipment for highway maintenance as described in the first aspect of the present invention.

[0051] The beneficial effects of this invention are as follows: by constructing a weighted adjacency matrix using time-series vectors to generate a working condition evolution state map, the dynamic evolution path of equipment operation status is quantitatively predicted; by coupling task feature vector matching with environmental risk correction functions, dynamic safety adaptability under complex construction scenarios is achieved; and by generating a hierarchical control strategy through preset scoring intervals, closed-loop linkage between risk decision-making and execution control is realized. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart of a method for evaluating the operational safety of construction equipment used in highway maintenance.

[0054] Figure 2 This is a schematic diagram of a safety evaluation system for construction equipment used in highway maintenance.

[0055] Figure 3 A schematic diagram for constructing the state map of the working condition evolution.

[0056] Figure 4 This is a schematic diagram of the path comprehensive scoring and environmental correction process. Detailed Implementation

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0060] Reference Figures 1-4 As one embodiment of the present invention, this embodiment provides a method for evaluating the operational safety of highway maintenance construction equipment, comprising the following steps:

[0061] S1: Obtain multi-source operating status data of construction equipment during task execution, normalize the multi-source operating status data, and obtain the working condition vector sequence.

[0062] The sensors deployed on the construction equipment are synchronously triggered to acquire multi-source operating status data of the construction equipment during task execution.

[0063] Furthermore, before the task is executed, the electrical, mechanical, thermal, and control parameters of the construction equipment during the task execution process are obtained by collecting data from the sensors deployed on the construction equipment.

[0064] The synchronous triggering of the data acquisition operation is specifically as follows:

[0065] The sensor parameters are aligned according to a unified timestamp to form multi-source operating status data of the construction equipment during the task execution process.

[0066] Furthermore, the electrical, mechanical, thermal, and control parameters of the construction equipment during task execution are aligned using a unified timestamp to construct multi-source operational status data.

[0067] Each parameter in the multi-source operational status data is normalized to generate a multi-source operational status data matrix.

[0068] Furthermore, each electrical parameter, mechanical parameter, thermal parameter, and control behavior parameter in the multi-source operating status data is subjected to maximum and minimum normalization processing to generate a multi-source operating status data matrix.

[0069] For example, each indicator is normalized to the [0,1] interval according to its historical maximum and minimum values, thus obtaining a normalized multi-source operating status data matrix.

[0070] During task execution, the multi-source operational status data matrix is ​​vectorized to generate a multi-source operational status data vector sequence.

[0071] Furthermore, the multi-source operational status data matrix is ​​reconstructed in segments using the sliding time window method to construct a multi-source operational status data time series set. Each time window in the multi-source operational status data time series set is converted into an ordered vector in chronological order to form a multi-source operational status data vector sequence.

[0072] Perform data consistency checks on each time-matter vector of the multi-source operating status data vector sequence and sort them according to time to form an operating condition vector sequence.

[0073] Furthermore, using the multi-source operational status data vector sequence as input, the electrical parameter sequence, mechanical parameter sequence, thermal parameter sequence, and control behavior parameter sequence of the construction equipment during task execution are extracted according to dimensions. Based on the electrical parameter sequence, mechanical parameter sequence, thermal parameter sequence, and control behavior parameter sequence of the construction equipment during task execution, the maximum and minimum values ​​of each parameter dimension within the historical window are calculated to construct a parameter normalization interval table. Subsequently, for each dimension parameter in the multi-source operational status data vector sequence, according to the maximum and minimum values ​​corresponding to the parameter in the parameter normalization interval table, max-min normalization processing is performed to generate a normalized multi-source operational status data vector sequence. The vectors at each time point in the normalized multi-source operational status data vector sequence are then checked for consistency according to data continuity rules, for example, sampling points with a mutation rate exceeding 50% are removed. Finally, the normalized multi-source operational status data vector sequences that satisfy the continuity rules are arranged in chronological order to generate the operating condition vector sequence of the construction equipment during task execution.

[0074] S2: Using each time-series vector in the working condition vector sequence as a graph node, establish a directed graph structure and construct a weighted adjacency matrix to generate a working condition evolution state map.

[0075] The working condition vectors are extracted one by one in chronological order and defined as graph nodes to form a graph node set.

[0076] Furthermore, each working condition vector in the working condition vector sequence is extracted one by one in chronological order, and each working condition vector is used as an independent node to form a graph node set.

[0077] Based on the temporal relationship and state difference between two adjacent graph nodes in the graph node set, the state transition weight is calculated, and the graph edge set and corresponding weights are generated.

[0078] Furthermore, the graph edge weights are calculated based on the temporal order relationship between every two adjacent graph nodes in the graph node set and the Euclidean distance between the state vectors.

[0079] Based on the state differences and time-varying relationships between operating condition vectors, a similarity weight for state transitions is constructed, expressed as:

[0080] ;

[0081] in, Indicates from node To the node The similarity weight of state transitions, Represents the first in the working condition vector sequence The working condition vector at each moment, Represents the first in the working condition vector sequence The working condition vector at each moment, This represents the temperature factor, with a value range of (0, +∞), and is determined by comparing different... The changing trend of state transition weights under the given value For state to state The time difference experienced.

[0082] Construct a graph edge set and corresponding weights for construction equipment during task execution.

[0083] The set of graph nodes and the set of graph edges are structurally merged to construct a directed graph structure.

[0084] Furthermore, the graph node set and graph edge set are structurally connected to construct a directed graph structure of the construction equipment during the task execution process.

[0085] The weights of the edges in the directed graph are mapped to matrix form according to the node index position, generating a weighted adjacency matrix.

[0086] Furthermore, the weight of each edge in the directed graph structure is filled into a matrix according to the index positions of the start and end points in the graph node set, generating a weighted adjacency matrix.

[0087] The graph node set, graph edge set, directed graph structure, and weighted adjacency matrix are uniformly encapsulated to generate a state evolution graph of construction equipment during task execution.

[0088] Furthermore, the graph node set, graph edge set, directed graph structure, and construction equipment in the weighted adjacency matrix are taken as input and processed uniformly through structured encapsulation to generate a working condition evolution state map of the construction equipment during task execution.

[0089] S3: Construct a task feature vector based on the requirements of the task to be executed, match and score the working condition evolution map with the task feature vector, construct a path task matching function, calculate the comprehensive path score, and select the optimal evolution path.

[0090] The specific construction information and working condition vectors of the task to be performed are uniformly normalized into task feature vectors.

[0091] Furthermore, based on the construction plan documents and information such as the construction objectives, construction objects, load requirements, operational stability indicators, and duration indicators of the tasks to be executed in the historical task database, a task feature vector with the same dimension as the working condition vector is constructed. The indicators in the task feature vector are normalized using the minimax method. For example, the load stability indicator is normalized to the range of [0.0, 1.0] to form the task feature vector.

[0092] Based on the working condition evolution state map, all path combinations with a fixed depth are extracted from the graph node set to form a construction path set as the task matching and scoring object set.

[0093] Furthermore, based on the working condition evolution map of the construction equipment during task execution, a depth-first traversal is performed from any node in the graph node set at a fixed depth according to a fixed depth parameter. Under the constraint of the directed edge structure of the graph, all continuous directed paths starting from the starting point and with a length not exceeding the specified depth are extracted. Each working condition node sequence containing time sequence and with no repetition of nodes constitutes a path combination. All path combinations are collected to construct the path set as the task matching and scoring object set.

[0094] A path-task matching function is constructed based on the multidimensional feature similarity between the working condition vectors of the constructed path nodes and the task feature vectors. The function performs a one-by-one matching and scoring of the working condition vectors corresponding to each node of each path in the path set of task matching scoring objects, and records the task matching score of each path.

[0095] Furthermore, the task feature vector and the working condition vector corresponding to each node in each path in the path set are scored node by node through the path task matching function to obtain the task matching score.

[0096] The path task matching function is fitted using an exponential decay function representing the feature differences between the task feature vector and the working condition vector across all dimensions. The expression is as follows:

[0097] ;

[0098] in, This represents the score of the path task matching function. This represents the number of dimensions of the task's feature vector. Indicates the first The weight coefficients for each feature dimension, with values ​​ranging from [0,1]. Indicates the first A sensitivity factor for each feature dimension, with values ​​ranging from (0, +∞). Indicates the first Feature values ​​of nodes in the working condition path in each dimension Indicates the first The expected feature values ​​of the task to be executed in each dimension. This indicates that the actual state in the task path and the task requirements are at the [number]th [position]. The absolute difference across each feature dimension. For example, if the feature value of a node represents the current speed in the device's operating path as 40 km / h, then... =40, the desired speed is 50 km / h, then =50.

[0099] It should be noted that, By analyzing a large amount of historical task execution data, regression analysis is used to calculate the sensitivity of each dimension to changes in scores, and weights are assigned accordingly. Using weights with values ​​in the range of [0,1] can avoid numerical instability caused by excessive differences in dimension scores.

[0100] Record the task matching score for each task path.

[0101] The path condition change rate is calculated based on the state difference between consecutive nodes in each task path.

[0102] Furthermore, the rate of change of path conditions between adjacent nodes is expressed as:

[0103] ;

[0104] in, Indicates the first and the The rate of change of operating conditions between the two nodes Indicates the first The working condition vector of each node, Indicates the first The working condition vector of each node, Indicates the first and the The time difference between two nodes.

[0105] Among them, the task path The expression for the overall rate of change of operating conditions is:

[0106] ;

[0107] in, Indicates the task path The overall rate of change of operating conditions Indicates the task path The total number of nodes in the middle.

[0108] The overall path score for each path is calculated based on the task matching score and the rate of change of working conditions between nodes in the task path.

[0109] Furthermore, the expression for calculating the comprehensive score of the calculation path is:

[0110] ;

[0111] in, Indicates the task path of Overall route score Indicates the task path of Task matching score This represents the weighting coefficient for the task matching score, with a value range of [0,1]. The weighting coefficient represents the rate of change of operating conditions, and its value ranges from [0,1].

[0112] It should be noted that, =1, and Task matching scores are evaluated by collecting historical task data and using regression analysis. and rate of change of operating conditions Weights on the impact on the final performance metrics.

[0113] By calculating the overall path score for all task paths, the path with the highest score is selected as the optimal evolution path.

[0114] S4: Map each node in the optimal evolution path to the actual construction area, construct an environmental risk correction function, correct the comprehensive score of the path, and obtain the environmentally corrected score.

[0115] Each working condition vector node in the optimal evolution path of task execution is mapped to a construction time segment in the task plan in chronological order, thus forming the time mapping sequence of the optimal evolution path of task execution.

[0116] Based on the time mapping sequence of the optimal evolution path of task execution, environmental factor information is obtained to form a construction environmental factor matrix.

[0117] Furthermore, based on each construction time segment in the optimal evolution path time mapping sequence corresponding to task execution, environmental factor information such as terrain slope, surface humidity, wind speed and direction, particulate matter concentration and geological disturbance index in the corresponding construction area is obtained, and a construction environmental factor matrix is ​​constructed.

[0118] Based on the mapping relationship between the working condition vector nodes and the environmental factors of the construction environmental factor matrix in the same time segment in the optimal evolution path of task execution, an environmental adaptation combination sequence is constructed, and an exponential environmental risk correction function is established based on the interference degree characteristics of environmental factors in the environmental adaptation combination sequence.

[0119] Furthermore, each working condition vector node in the optimal evolution path of task execution is combined with the environmental factors of the same time segment in the construction environmental factor matrix to form the optimal evolution path environment adaptation combination sequence corresponding to task execution. Then, based on the degree of interference of each environmental factor in the optimal evolution path environment adaptation combination sequence corresponding to task execution on the stability of equipment operation, an environmental risk correction function is constructed, expressed as:

[0120] ;

[0121] in, Represents the optimal evolution path The corresponding environmental risk correction value, This indicates the number of environmental factors involved in the risk correction calculation. Indicates the first The weighting coefficients for each environmental factor range from [-5, 5]. Represents the optimal evolution path In the Environmental assessment values ​​under each environmental factor dimension This indicates a product operation involving all environmental factor impact index terms;

[0122] It should be noted that, It uses a multivariate regression method based on a large amount of historical task execution data to calculate various environmental factors. The correlation with the equipment operation stability index is considered, and to avoid the extreme impact of certain environmental factors on the results, the value range is limited to [-5, 5].

[0123] Among them, environmental assessment value The expression is:

[0124] ;

[0125] in, For the first The sensitivity coefficients for each environmental factor range from (0, 10). These are the standardized environmental factor values.

[0126] It should be noted that, It uses regression modeling to calculate the contribution of each environmental factor to risk change and maps the contribution to a value. The value range is (0, 10) to control the variation of the exponential function term during the calculation process, and to avoid the value being too large or too small, which may interfere with the subsequent scoring calculation.

[0127] For example, for each node The mapped construction area collected multiple environmental factors, the first... The actual observed values ​​of each environmental factor are ,right Standardized environmental factor values ​​are obtained after max-min normalization. .

[0128] Arrange the environmental risk correction values ​​of all nodes in the optimal evolution path of task execution in the order of the path to obtain the sequence of environmental risk correction values ​​for the optimal evolution path of task execution.

[0129] Based on the correspondence between the comprehensive path score of each node in the optimal evolution path of task execution and the environmental risk correction value of each node in the optimal evolution path, a path environment correction score sequence is formed.

[0130] Furthermore, for each node in the optimal evolution path corresponding to task execution, the path comprehensive score of the corresponding node in the path comprehensive score and the environmental risk correction value of the corresponding node in the environmental risk correction function sequence of the optimal evolution path corresponding to task execution are obtained respectively, forming the environmental correction score sequence of the optimal evolution path corresponding to task execution, as shown below:

[0131] ;

[0132] in, Indicates the first The score after environmental correction for each node This is represented as the first in the overall path score. The overall path score for each node. This represents the sequence of environmental risk correction functions for the optimal evolution path corresponding to task execution. Environmental risk correction value for each node.

[0133] Calculate the average value of the environment-corrected scores of each node in the path environment-corrected score sequence, and use the average value of the path environment-corrected score sequence as the environment-corrected score of the optimal evolution path corresponding to task execution.

[0134] S5: Classify the environmental correction score according to the preset score segment interval, output the corresponding operation safety level label, and output corresponding control strategy suggestions according to different levels.

[0135] The score after the optimal evolution path environment correction is compared with the preset score segment interval to determine the score interval of the optimal evolution path environment correction score and assign a security level label.

[0136] Furthermore, the preset scoring intervals are multiple continuous and non-overlapping real-number closed intervals set after the scoring is corrected for the optimal evolution path environment of task execution. The interval threshold is the boundary value between each adjacent scoring interval, and the value range is [0,1].

[0137] The boundary values ​​between each adjacent scoring interval are determined based on project objectives and safety requirements.

[0138] The score after correcting the optimal evolution path environment corresponding to the task execution is compared with the preset score segment interval.

[0139] For example, when the score after environmental correction for the optimal evolutionary path corresponding to the task execution is greater than 0.85, it is in the highest score range; when the score after environmental correction for the optimal evolutionary path corresponding to the task execution is between 0.55 and 0.70, it is in the middle score range; and when the score after environmental correction for the optimal evolutionary path corresponding to the task execution is less than 0.55, it is in the lowest score range.

[0140] The corresponding operational safety level label is assigned to the score segment interval where the score is located after the optimal evolution path environment corresponding to the task execution is corrected.

[0141] For example, the highest score range corresponds to a safe operational safety level label, the middle score range corresponds to a low risk operational safety level label, and the lowest score range corresponds to a high risk operational safety level label.

[0142] Based on the operational safety level label, search the preset operational control strategy table and output control strategy suggestions that match the operational safety level label.

[0143] It should be noted that the operation control strategy table is formulated based on the analysis results of historical operation data, equipment operation specifications, accident cases, and expert knowledge base.

[0144] Furthermore, based on the operational safety level label, the corresponding record row is searched in the operational control policy table. The operational control policy table pre-sets the control policy suggestion content corresponding to each level label. For example, when the operational safety level label is safe, the corresponding policy is "immediately stop and alarm", lower risk corresponds to "reduce load and start inspection process", and higher risk corresponds to "maintain current state and continue monitoring". After finding a matching row, the control policy suggestion field is extracted as the final output. If no matching item is found for the operational safety level label in the policy table, a default policy suggestion is output, such as "manual review" or "maintain current state and alarm", so as to realize the output of control policy suggestions based on the operational safety level label.

[0145] This embodiment also provides a safety evaluation system for the operation of construction equipment in highway maintenance, including:

[0146] The data normalization module is responsible for acquiring multi-source operating status data of construction equipment during task execution, normalizing the multi-source operating status data, and obtaining a working condition vector sequence.

[0147] The graph construction module uses each time-series vector in the working condition vector sequence as a graph node to establish a directed graph structure and construct a weighted adjacency matrix to generate a working condition evolution state graph.

[0148] The path matching decision module constructs a task feature vector based on the requirements of the task to be executed, matches and scores the working condition evolution map with the task feature vector, constructs a path task matching function, calculates the comprehensive path score, and selects the optimal evolution path.

[0149] The path score correction module is responsible for mapping each node in the optimal evolution path to the actual construction area, constructing an environmental risk correction function, correcting the comprehensive path score, and obtaining the environmentally corrected score.

[0150] The control strategy recommendation module classifies the environmental correction score according to the preset scoring range, outputs the corresponding operational safety level label, and outputs corresponding control strategy recommendations based on different levels.

[0151] This embodiment also provides a computer device applicable to a method for evaluating the operational safety of construction equipment for highway maintenance, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for evaluating the operational safety of construction equipment for highway maintenance as proposed in the above embodiment.

[0152] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0153] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements a method for evaluating the operational safety of construction equipment for highway maintenance as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0154] In summary, this invention achieves dynamic evolution path quantification and prediction of equipment operating status by constructing a weighted adjacency matrix from time-series vectors to generate an operating condition evolution state map; it achieves dynamic safety adaptability in complex construction scenarios by coupling task feature vector matching with environmental risk correction functions; and it achieves closed-loop linkage between risk decision-making and execution control by generating a hierarchical control strategy through preset scoring intervals.

[0155] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for evaluating the safety of a construction equipment operation for road maintenance, characterized by: The application relates to a construction equipment operation safety evaluation method and device. The method comprises the following steps: acquiring multi-source operation state data of construction equipment in a task execution process, normalizing the multi-source operation state data, and acquiring a working condition vector sequence; Each time sequence vector in the working condition vector sequence is taken as a graph node, a directed graph structure is established, a weighted adjacency matrix is constructed, and a working condition evolution state graph is generated; A task feature vector is constructed according to the requirements of a to-be-executed task, the working condition evolution graph is matched with the task feature vector, a path task matching function is constructed, a path comprehensive score is calculated, and an optimal evolution path is selected; Each node in the optimal evolution path is mapped to an actual construction area, an environment risk correction function is constructed, the path comprehensive score is corrected, and an environment-corrected score is acquired; The environment-corrected score is classified into different grades according to a preset score segmentation interval, a corresponding operation safety grade label is output, and a corresponding control strategy suggestion is output according to different grades. The working condition vector sequence is extracted in time sequence one by one, and is defined as a graph node to form a graph node set; Based on the time relationship and state difference between adjacent two graph nodes in the graph node set, the state transition weight is calculated, a graph edge set and the corresponding weight are generated; The graph node set and the graph edge set are structurally combined to construct a directed graph structure, and the graph edge weight in the directed graph is mapped to a matrix form according to the node index position to generate a weighted adjacency matrix; The graph node set, the graph edge set, the directed graph structure and the weighted adjacency matrix are uniformly encapsulated to generate a working condition evolution state graph of the construction equipment in the task execution process; The path comprehensive score is calculated, and the optimal evolution path is selected, and the specific steps are as follows: The path working condition change rate is calculated according to the state difference value between the continuous nodes in each path; The path comprehensive score of each path is calculated according to the task matching score and the path working condition change rate; The path with the highest score in the path comprehensive score is selected as the optimal evolution path for task execution; Each working condition vector node in the optimal evolution path for task execution is correspondingly mapped to a construction time segment in the task plan in time sequence to form an optimal evolution path time mapping sequence for task execution; Environment factor information is acquired to form a construction environment factor matrix; According to the environment factor mapping relationship between the working condition vector nodes in the optimal evolution path for task execution and the construction environment factor matrix in the same time segment, an environment adaptation combination sequence is constructed, and an exponential environment risk correction function is established based on the interference degree characteristics of the environment factors in the environment adaptation combination sequence to acquire the environment risk correction values of all the nodes in the optimal evolution path; The environment risk correction values of all the nodes in the optimal evolution path for task execution are arranged in sequence according to the path to acquire an optimal evolution path environment risk correction value sequence for task execution; ​ ​ ​ The path environment correction score sequence is formed based on a corresponding relationship between a path comprehensive score of each node in the optimal evolution path and an environment risk correction value of each node in the optimal evolution path; An average value of the scores of the nodes in the path environment correction score sequence is calculated as an environment correction score of the optimal evolution path corresponding to the task execution.

2. The method of claim 1, wherein: The specific steps are as follows: The multi-source running state data of the construction equipment in the task execution process is acquired, and the multi-source running state data is normalized to obtain a working condition vector sequence. The multi-source running state data of the construction equipment in the task execution process is acquired through synchronous triggering and collection of the sensors arranged on the construction equipment. The multi-source running state data is time-aligned according to a uniform timestamp, and normalized to generate a multi-source running state data matrix. The multi-source running state data matrix is vectorized to generate a multi-source running state data vector sequence.

3. The method of claim 2, wherein: The vectors of each moment of the multi-source running state data vector sequence are subjected to data consistency verification and time sorting to form the working condition vector sequence. The specific steps are as follows: The specific construction information of the to-be-executed task and the working condition vector are uniformly normalized into a task feature vector. All path combinations of a fixed depth are extracted from the graph node set based on the working condition evolution state graph to construct a path set as a task matching score object set.

4. The method of claim 3, wherein: The path task matching function is constructed to match and score the working condition vectors corresponding to each node of the task feature vector and each path in the task matching score object set, and record the task matching scores of each path. The specific steps are as follows:

5. The method of claim 4, wherein: the road maintenance construction equipment is a snow plow. The optimal evolution path environment correction score of the task execution is compared with a preset score segmentation interval to determine the score interval of the optimal evolution path environment correction score and assign a safety level label. The specific steps are as follows:

6. A system for evaluating the operation safety of a road maintenance construction equipment, based on the method for evaluating the operation safety of a road maintenance construction equipment according to any one of claims 1 to 5, characterized in that: Based on the running safety level label, a control strategy suggestion matched with the running safety level label is output according to a preset running control strategy table. The specific steps are as follows: The specific steps are as follows: The data processing module is configured to acquire multi-source running state data of construction equipment in a task execution process, normalize the multi-source running state data, and obtain a working condition vector sequence. The graph construction module is configured to take each time sequence vector in the working condition vector sequence as a graph node, establish a directed graph structure, construct a weighted adjacency matrix, and generate a working condition evolution state graph. The path matching module is configured to construct a task feature vector according to a requirement of a to-be-executed task, match and score the working condition evolution state graph and the task feature vector, construct a path task matching function, calculate a path comprehensive score, and select an optimal evolution path. The specific steps are as follows: The path matching module is configured to construct a task feature vector according to a requirement of a to-be-executed task, match and score the working condition evolution state graph and the task feature vector, construct a path task matching function, calculate a path comprehensive score, and select an optimal evolution path. The path scoring module is configured to map each node in the optimal evolution path to an actual construction area, construct an environmental risk correction function, correct the comprehensive score of the path, and obtain an environmental correction score. The strategy suggestion module is configured to classify the environmental correction score according to a preset score segmentation interval, output a corresponding operation safety level label, and output a corresponding control strategy suggestion according to different levels.

Images