A smart detection device and anomaly handling method for key equipment at construction sites

Abstract

This invention discloses an intelligent detection device and anomaly handling method for key equipment at construction sites, belonging to the field of safety monitoring and anomaly handling for construction site equipment. It includes collecting operational data of key equipment at the construction site through a multimodal sensor array. The operational data includes at least several of the following: vibration signals, tilt signals, load signals, temperature signals, current signals, hydraulic pressure signals, and environmental risk signals. A time-series input tensor is constructed. By unifying the heterogeneous signals of vibration, attitude, load, temperature, current, hydraulic pressure, and environmental risks of the key equipment at the construction site into a unified time-series feature tensor, and performing differential processing with the equipment operation state model prediction data, a residual tensor is formed to identify abnormal deviations. This allows early anomalies of key equipment at the construction site to be identified in a timely manner under multi-source state fusion conditions, thereby solving the problem that single-threshold alarms are difficult to detect anomalies in a timely manner under complex construction conditions.

Description

Technical Field

[0001] This invention relates to the field of equipment safety monitoring and anomaly handling technology, and more specifically, to an intelligent detection device and anomaly handling method for key equipment at construction sites. Background Technology

[0002] With the intelligent development of building construction, municipal construction, energy facility construction and chemical project construction, the operational safety of key equipment at construction sites has a significant impact on project progress and on-site personnel safety. During the operation of tower cranes, construction hoists, concrete pumping equipment, hydraulic piling equipment, welding equipment, temporary power distribution equipment and hoisting, installation and commissioning equipment at chemical project construction sites, the equipment status is easily affected by load changes, attitude deviations, hydraulic fluctuations, abnormal temperature rises, environmental disturbances and cross-operation interference.

[0003] Existing equipment monitoring methods at construction sites mostly rely on single sensor alarms or manual inspections. While these methods can alert users to out-of-limit conditions, they struggle to model equipment operating status, environmental disturbances, node linkages, and anomaly handling paths in a unified manner. Especially in scenarios where multiple critical pieces of equipment operate collaboratively, anomalies often do not manifest as single-point failures but rather propagate continuously along equipment nodes, edge control nodes, and the work area. Existing methods lack the ability to dynamically evaluate the effectiveness of anomaly propagation links and handling paths, resulting in untimely early anomaly identification, reliance on manual experience for handling path selection, and easily delayed on-site responses. Summary of the Invention

[0004] To address the problems mentioned in the background section, the present invention provides the following technical solution:

[0005] A smart detection device for key equipment at a construction site, comprising:

[0006] The multimodal data acquisition module is used to collect vibration signals, sound signals, temperature signals, environmental risk signals, and pressure change signals generated by key equipment at the construction site during operation, and to construct the acquisition results into a time-series-based multimodal feature input tensor.

[0007] The residual generation and trend recognition module is used to generate a prediction tensor based on the equipment operation status model and historical operation data, and perform differential processing with the input tensor to form a residual tensor, further constructing a scoring residual trend tensor and identifying scoring fluctuation characteristics.

[0008] The anomaly propagation graph construction module is used to construct an anomaly propagation path graph based on the multidimensional distribution and temporal characteristics of the residual tensor, and to identify key response nodes and linkage path structures within it.

[0009] The strategy path generation module is used to construct a feedback-driven strategy path candidate set based on the state sequence and historical handling paths of key response nodes, and to select the optimal anomaly handling path by minimizing perturbation and restoring stability objective functions.

[0010] The virtual simulation and scoring evaluation module is used to simulate candidate paths in a simulation environment containing multiple potential fault evolution characteristics, collect feedback indicators of the paths in terms of response speed, anomaly suppression efficiency and stable recovery time, and calibrate the current optimal handling path based on the comprehensive scoring function.

[0011] The edge node scheduling and linkage module is used to map the optimal anomaly handling path to edge nodes, generate linkage isolation control sequences based on topology, resource status and priority relationship, and perform path migration, task pruning and residual suppression scheduling between nodes.

[0012] The scoring function evolution and path stability evaluation module is used to trigger the scoring function structure reconstruction mechanism when the scoring deviation exceeds the threshold, adjust the scoring factor weights and penalty parameters based on the scoring residual trend tensor, and solidify the alternative path as a long-term scheduling candidate path when the scoring trend of the alternative path stabilizes.

[0013] The disturbance feedback and parameter adaptive update module is used to synchronously update the path selection parameters, level discrimination threshold and scoring function structure based on the disturbance residuals, score fluctuations and node state change trends generated during the execution process, so as to realize the periodic reconstruction and evolution optimization of the anomaly handling strategy.

[0014] A method for handling anomalies in intelligent detection of key equipment at a construction site includes the following steps:

[0015] S1. Collect multimodal state data generated by key equipment at the target construction site during operation. The multimodal state data includes at least several of the following: vibration signals, tilt angle signals, load signals, temperature signals, current signals, hydraulic pressure signals, and environmental risk signals. Construct a unified multimodal feature input tensor based on the time series. ;

[0016] S2. Constructing a prediction tensor based on equipment operation status model and historical operation data. The predicted tensor is then differentially processed with the currently acquired tensor to form a residual tensor. To capture any possible abnormal offset patterns;

[0017] S3. Based on the multidimensional structural distribution and temporal variation characteristics of the residual tensor, construct an anomaly propagation path map and identify the linkage path nodes in the propagation chain to characterize the diffusion trend of anomalies among equipment components or subsystems.

[0018] S4. Based on the state sequence of key response nodes identified in the anomaly propagation chain and their historical handling behavior paths, construct a feedback-driven strategy update path. Based on the execution effect of the strategy path in multiple feedback cycles, establish a dynamic evaluation function with the goal of minimizing disturbances and achieving stable recovery. Calculate the expected value and select the best alternative for multiple candidate handling paths to generate an adaptive and variable optimal anomaly handling path sequence.

[0019] S5. Among the multiple candidate anomaly handling paths generated, a virtual simulation environment containing multiple potential fault evolution characteristics is constructed. Each path is sequentially mapped to the simulation environment for trial operation. Multi-dimensional feedback indicators such as response speed, anomaly suppression efficiency and stable recovery time of the handling path under simulation conditions are collected. The optimal path is determined based on the path comprehensive scoring function and marked as the current anomaly handling execution path.

[0020] S6. Based on the historical anomaly trigger frequency, current anomaly level and structural position of the target node in the anomaly propagation chain, combined with the simulation scoring results in S5, construct a multi-factor fusion anomaly level weight model, and update the strategy allocation order according to node priority to realize the early execution of high-risk node handling paths and dynamic buffer scheduling of low-weight node paths.

[0021] S7. After the current anomaly handling path is completed, based on the changing trends of the disturbance response residual, simulation score deviation and edge node environmental disturbance factor during the handling process, a disturbance parameter correction function is constructed and the path scoring model, level discrimination threshold and path optimization strategy parameters are updated synchronously to improve the adaptability and convergence of the strategy path in multi-cycle anomaly environment.

[0022] Further includes:

[0023] When the generated anomaly handling path contains multiple critical response nodes, a policy path mapping function is constructed based on the current edge node topology and response latency characteristics. The key response actions in the anomaly handling path are mapped to the corresponding edge nodes, and a linkage isolation control sequence is generated based on the execution coupling relationship and priority weight between nodes to form a distributed edge execution path;

[0024] The linkage isolation control sequence is dynamically trimmed based on environmental disturbance factors, its own state residuals, and task conflict factors to ensure the executability and stability of the path under edge conditions.

[0025] Furthermore, the control execution mechanism based on the anomaly handling path at the edge nodes further includes:

[0026] In a multi-edge node environment, a dynamic graph of path execution residuals is constructed. The graph is based on the execution residual sequence, resource occupancy status and task response stability index formed by different edge nodes in multiple historical feedback cycles. The residual trend tensor is extracted and a node behavior stability prediction model is constructed.

[0027] Based on the stability prediction model, a migration scheduling mapping relationship for candidate disposal paths is established, and the current preferred path is mapped to an edge node with sufficient remaining resources and high predicted stability according to the strategy scoring result.

[0028] During execution, path migration decisions are dynamically adjusted based on changes in node resource load and response delay after migration. A feedback update mechanism is constructed to achieve dynamic scheduling of disposal paths among edge nodes, execution residual suppression, and collaborative stability control, thereby improving the overall robustness and response consistency of anomaly disposal paths.

[0029] Furthermore, the dynamic scheduling mechanism for the anomaly handling path among edge nodes further includes:

[0030] After completing the construction of the path execution residual dynamic graph, the path segments corresponding to the high-frequency offset nodes in the graph are extracted, and the resource consumption weight and response stability index of the path segment in multiple feedback cycles are calculated.

[0031] Construct a path segment pruning priority function It is used to dynamically prune each path segment based on resource constraints, response bias, and residual weights.

[0032] The remaining path segments are constructed with residual minimization and stability maximization as joint optimization objective functions. The disposal paths are reorganized based on the graph structure shortest path algorithm, and the corrected disposal paths are executed according to the new node scheduling priority sequence to improve overall execution efficiency and multi-node response stability.

[0033] Furthermore, if the preset scoring threshold is not reached within two or more consecutive scheduling cycles of the feedback scoring function, the path scoring residual sequence is extracted based on the path execution residual map, and a residual trend tensor for trend analysis is constructed.

[0034] Based on the score decay pattern identified in the residual trend tensor, a preset path structure template library is retrieved, and candidate path templates with a similarity to the current path structure features that is higher than a threshold value are selected.

[0035] The key node sequence in the candidate path template is fine-tuned to form alternative path candidates that can adapt to the current edge node state characteristics;

[0036] Alternative path candidates are incorporated into the scheduling path scoring system and evaluated in real time through a feedback scoring function. Once the continuous scoring meets the stability requirements, they are solidified as the main execution path for the current scheduling cycle to replace the original path in execution.

[0037] Furthermore, after the adaptive alternative path is loaded into the task scheduling sequence of the current edge node, a scoring residual trend tensor is constructed based on the scoring residual change trend and scoring fluctuation characteristics of the alternative path in historical periods.

[0038] Based on the aforementioned scoring residual trend tensor, the residual attribution sequence of each scoring factor in the scoring function is extracted, and the penalty parameter and stability evaluation criterion of the feedback scoring function are dynamically adjusted accordingly.

[0039] When the deviation of the scoring standard exceeds the preset tolerance threshold within two consecutive scheduling cycles, the evolution mechanism of the scoring function structure is triggered, the evaluation dimension of the scoring function is reconstructed, and a scoring adjustment factor based on the residual fluctuation frequency is introduced.

[0040] The scoring adjustment factor is applied to the current scoring function to re-evaluate the adaptive alternative path. When the scoring trend stabilizes and the scoring confidence interval converges to the target interval, the alternative path is marked as a long-term scheduling candidate path, and a stability index is generated for reference in subsequent scheduling cycles.

[0041] Furthermore, after the adaptive alternative path is loaded into the scheduling sequence of the edge node, a scoring residual trend tensor is constructed based on the scoring residual change trend and scoring fluctuation frequency of the alternative path in continuous historical cycles, in order to identify the feedback lag of the current scoring mechanism to path stability.

[0042] Based on the scoring residual trend tensor, the residual attribution sequence of each scoring factor in the scoring function is extracted, its offset magnitude and contribution ratio are calculated, and the penalty parameter and path stability evaluation dimension in the scoring function are dynamically adjusted according to the attribution results.

[0043] When the deviation of the stability judgment result of the scoring function exceeds the preset tolerance threshold in two consecutive scheduling cycles, the evolution mechanism of the scoring function structure is triggered, the evaluation sub-dimension of the scoring function is reconstructed, and a scoring adjustment factor based on the fluctuation frequency of the scoring residual is introduced to enhance the sensitivity of the scoring function to path behavior anomalies.

[0044] The scoring adjustment factor is modeled by weighting the residual fluctuation period, maximum amplitude and delay trend of each scoring factor, and is applied to the current scoring function to re-score the alternative path;

[0045] When the re-scoring result converges to the target interval within a continuous period and the scoring trend meets the stability criterion, the alternative path is marked as a long-term scheduling candidate path, and a stability index parameter is generated for reference in subsequent task scheduling cycles.

[0046] In summary, the present invention has the following beneficial effects:

[0047] By unifying heterogeneous signals such as vibration, attitude, load, temperature, current, hydraulic pressure, and environmental risks of key equipment at the construction site into a time-series feature tensor, and performing differential processing with the equipment operation state model prediction data to form a residual tensor to identify abnormal deviations, early anomalies of key equipment at the construction site can be identified in a timely manner under multi-source state fusion conditions, thereby solving the problem that single threshold alarms are difficult to detect anomalies in a timely manner under complex construction conditions.

[0048] By analyzing the temporal changes and structural distribution of residual tensors, an anomaly propagation path map is constructed to identify the propagation chain and key response nodes of anomalies among critical equipment, edge nodes, and work areas. This enables anomaly handling to be transformed from single-point alarms to linked path analysis, thereby solving the problem of difficulty in locating anomaly propagation paths in multi-equipment collaborative construction scenarios.

[0049] By introducing a virtual simulation environment to pre-run and score multiple anomaly handling paths, and combining execution feedback to update the path scoring model, node priority, and scoring function structure, the anomaly handling paths can be dynamically adjusted according to on-site load, environmental disturbances, and execution residuals, thereby solving the problems of relying on human experience and path response lag in anomaly handling at construction sites. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. 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.

[0051] Figure 1 This is a schematic diagram of the overall structure of the intelligent detection device for key equipment at the construction site according to the present invention;

[0052] Figure 2 This is a flowchart illustrating the construction process of the residual trend tensor for the scoring of key equipment at the construction site in this invention.

[0053] Figure 3 This is a flowchart illustrating the construction and path identification process for the anomaly propagation pattern of key equipment at the construction site, as described in this invention.

[0054] Figure 4This is a diagram of the strategy path generation and edge execution feedback mechanism for key equipment at the construction site in this invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Example:

[0057] The following is in conjunction with the appendix Figure 1-4 The present invention will be described in further detail below.

[0058] Please see Figure 1-4 This invention provides a technical solution: an intelligent detection device for key equipment at construction sites, such as... Figure 1-4 As shown, it includes:

[0059] The multimodal data acquisition module is used to collect vibration signals, sound signals, temperature signals, environmental risk signals, and pressure change signals generated by key equipment at the construction site during operation, and to construct the acquisition results into a time-series-based multimodal feature input tensor.

[0060] The residual generation and trend recognition module is used to generate a prediction tensor based on the equipment operation status model and historical operation data, and perform differential processing with the input tensor to form a residual tensor, further constructing a scoring residual trend tensor and identifying scoring fluctuation characteristics.

[0061] The anomaly propagation graph construction module is used to construct an anomaly propagation path graph based on the multidimensional distribution and temporal characteristics of the residual tensor, and to identify key response nodes and linkage path structures within it.

[0062] The strategy path generation module is used to construct a feedback-driven strategy path candidate set based on the state sequence and historical handling paths of key response nodes, and to select the optimal anomaly handling path by minimizing perturbation and restoring stability objective functions.

[0063] The virtual simulation and scoring evaluation module is used to simulate candidate paths in a simulation environment containing multiple potential fault evolution characteristics, collect feedback indicators of the paths in terms of response speed, anomaly suppression efficiency and stable recovery time, and calibrate the current optimal handling path based on the comprehensive scoring function.

[0064] The edge node scheduling and linkage module is used to map the optimal anomaly handling path to the edge node, generate linkage isolation control sequence based on topology, resource status and priority relationship, and perform path migration, task pruning and residual suppression scheduling between nodes.

[0065] The scoring function evolution and path stability evaluation module is used to trigger the scoring function structure reconstruction mechanism when the scoring deviation exceeds the threshold, adjust the scoring factor weights and penalty parameters based on the scoring residual trend tensor, and solidify the alternative path as a long-term scheduling candidate path when the scoring trend of the alternative path stabilizes.

[0066] The disturbance feedback and parameter adaptive update module is used to synchronously update the path selection parameters, level discrimination threshold and scoring function structure based on the disturbance residuals, score fluctuations and node state change trends generated during the execution process, so as to realize the periodic reconstruction and evolution optimization of the anomaly handling strategy.

[0067] In this embodiment, the device is suitable for monitoring the status and handling anomalies of critical equipment at construction sites, municipal construction sites, energy facility construction sites, and chemical project construction sites. The critical equipment includes tower cranes, construction hoists, concrete pumping equipment, hydraulic piling equipment, temporary power distribution equipment, and key operational equipment used for hoisting, installation, and commissioning at chemical project construction sites. The device synchronously collects data on the load-bearing status, attitude changes, vibration characteristics, temperature rise, hydraulic pressure, current changes, and environmental risk signals of the critical equipment to construct a multimodal feature input pattern for the construction site operation process.

[0068] The multimodal data acquisition module collects various signals such as vibration, sound waves, temperature, environmental risks, hydraulic pressure and load changes during equipment operation by deploying MEMS vibration sensors, high-sensitivity acoustic wave sensors, tilt sensors, load sensors, K-type thermocouple arrays, current transformers, hydraulic pressure sensors and dust concentration or harmful gas detection sensors at key parts of key equipment on the construction site.

[0069] This module adopts an edge-synchronized timestamp and modality alignment mechanism, and constructs a time series input tensor based on a 5-second cycle with dimensions of (N×M×T), where N is the modality type, M is the number of sensing points per modality, and T is the sequence length;

[0070] The residual generation and trend recognition module is based on the data-driven equipment operation status model deployed in the device and the periodically updated historical operation benchmark tensor. It uses a three-dimensional difference operator to calculate the tensor residual for each period, and further uses exponential sliding weighted filtering to extract the scoring residual trend sequence.

[0071] This module identifies fluctuation characteristics in the output of the scoring function through residual kurtosis analysis and local range dynamic fluctuation function, which is used to identify the unstable state of the scoring system at an early stage.

[0072] The anomaly propagation graph construction module uses a structured projection algorithm based on multidimensional tensor residuals to construct a weighted graph structure within the same period, where nodes represent detection points and edges represent response delays or linkage strengths.

[0073] By calculating the normalized weighted length of the propagation path and analyzing information centrality, key response nodes and abnormal linkage paths are extracted, and a dynamic propagation graph is generated for subsequent strategy generation.

[0074] The strategy path generation module uses key response nodes as the starting point of the graph structure. Combining historical anomaly handling records and an expert rule base, it generates multiple feedback-driven strategy path candidates through a dual-objective optimization function that optimizes both the shortest recovery time and disturbance suppression strength. The candidate paths are prioritized and passed to the simulation module for verification. The virtual simulation and scoring evaluation module performs multiple rounds of simulation on the candidate path set within the constructed digital twin simulation environment. Each round of simulation collects key indicators such as response latency (ms), suppression efficiency (%), energy consumption level (J), and recovery stabilization time (s), using a composite scoring function.

[0075] ;

[0076] Where: the above scoring function This represents the comprehensive performance score of the candidate path during the virtual simulation evaluation process, and its construction principle is a weighted ratio of maximizing response efficiency and minimizing stability fluctuations; where, Indicates the first The weights of each scoring factor are determined by fitting historical scheduling data. Common scoring factors include response time, suppression efficiency, energy consumption level, and recovery time. Indicates the first The normalized deviation value of the item scoring factor is defined as the normalized result of the difference between the current value of the factor and the optimal reference value, and the value range is [0,1]. The weighting coefficient for the stability fluctuation penalty term is usually set between 0.5 and 2, and is used to adjust the system's tolerance for scoring instability; Indicates the first The absolute value of the second derivative of each simulation score result on the time axis is used to quantify the fluctuation intensity of the score curve, where This represents the score sequence of a candidate path within the simulation cycle. This represents the total number of rating factors. Indicates the number of scoring sequences in the simulation cycle; scoring value The larger the value, the better the candidate path performs under multi-objective conditions. Its score is directly used to drive the selection of the optimal anomaly handling path.

[0077] The path is scored, and the path with the highest score is selected as the optimal treatment path.

[0078] The edge node scheduling and linkage module adopts a multilateral topology mapping mechanism to map selected paths to physical edge nodes according to node type and task response requirements. It uses a multi-constraint scheduler to generate task pruning plans and path migration sequences, and uses suppression synchronization instructions to trigger multiple nodes to achieve linkage control and resource isolation according to predetermined control logic, ensuring the real-time response of the abnormal handling process.

[0079] The scoring function evolution and path stability assessment module automatically triggers the scoring function evolution mechanism when the scoring result deviates from the stable interval for two consecutive cycles (i.e., the confidence interval boundary exceeds ±10%).

[0080] This mechanism reconstructs the dimensions of the scoring function, introduces a residual fluctuation frequency factor and a path switching frequency penalty term, and ensures that the scoring is more in line with long-term stability indicators.

[0081] When the alternative path score converges and the variance is less than 0.005, the path is marked as a long-term scheduling candidate path and a stability index (SI) record is generated.

[0082] The disturbance feedback and parameter adaptive update module continuously tracks the disturbance residual (the error between the response time and the expected response time), the volatility of the scoring function output, and the trajectory of node state changes during task execution. Based on multivariate regression and Bayesian optimization algorithms, it periodically reconstructs and optimizes the strategy parameter set (path selection weight, scoring function factor, node priority) to achieve adaptive evolution of abnormal strategies in the system.

[0083] Therefore, the detection device is adapted to heterogeneous network edge environments, has high redundancy and high fault tolerance, and can also achieve high-precision anomaly detection and rapid response path deployment for key equipment on construction sites under resource constraints, thus providing a solid guarantee for safe operation and maintenance under complex working conditions.

[0084] A method for handling anomalies in intelligent detection of key equipment at a construction site includes the following steps:

[0085] S1. Collect operational data of key equipment at the construction site using a multimodal sensor array. The operational data includes at least several of the following: vibration signals, tilt angle signals, load signals, temperature signals, current signals, hydraulic pressure signals, and environmental risk signals. Construct a unified multimodal feature input tensor based on the time series. ;

[0086] S2. Generating prediction tensors based on the operational status model of key equipment at the construction site. The predicted tensor is then differentially processed with the currently acquired tensor to form a residual tensor. To capture any possible abnormal offset patterns;

[0087] S3. Based on the multidimensional structural distribution and temporal variation characteristics of the residual tensor, construct an anomaly propagation path map and identify the linkage path nodes in the propagation chain to characterize the diffusion trend of anomalies among equipment components or subsystems.

[0088] S4. Based on the state sequence of key response nodes identified in the anomaly propagation chain and their historical handling behavior paths, construct a feedback-driven strategy update path. Based on the execution effect of the strategy path in multiple feedback cycles, establish a dynamic evaluation function with the goal of minimizing disturbances and achieving stable recovery. Calculate the expected value and select the best alternative for multiple candidate handling paths to generate an adaptive and variable optimal anomaly handling path sequence.

[0089] S5. Among the multiple candidate anomaly handling paths generated, a virtual simulation environment containing multiple potential fault evolution characteristics is constructed. Each path is sequentially mapped to the simulation environment for trial operation. Multi-dimensional feedback indicators such as response speed, anomaly suppression efficiency and stable recovery time of the handling path under simulation conditions are collected. The optimal path is determined based on the path comprehensive scoring function and marked as the current anomaly handling execution path.

[0090] S6. Based on the historical anomaly trigger frequency, current anomaly level and structural position of the target node in the anomaly propagation chain, combined with the simulation scoring results in S5, construct a multi-factor fusion anomaly level weight model, and update the strategy allocation order according to node priority to realize the early execution of high-risk node handling paths and dynamic buffer scheduling of low-weight node paths.

[0091] S7. After the current anomaly handling path is completed, based on the changing trends of the disturbance response residual, simulation score deviation and edge node environmental disturbance factor during the handling process, construct a disturbance parameter correction function and synchronously update the path scoring model, level discrimination threshold and path optimization strategy parameters to improve the adaptability and convergence of the strategy path in a multi-cycle anomaly environment.

[0092] The anomaly handling method proposed in this embodiment is applicable to the automatic monitoring and anomaly response control of key equipment during continuous operation at construction sites. Typical scenarios include tower crane swaying, abnormal vibration of construction hoists, abnormal concrete pumping pressure, hydraulic pressure fluctuations in hydraulic piling equipment, abnormal temperature rise of temporary power distribution equipment, and exceeding environmental risk limits in confined space operations at chemical project construction sites.

[0093] Distributed edge nodes are used to collect real-time data on the operating status of multiple target devices. The collected parameters include, but are not limited to:

[0094] Vibration acceleration signal, sampling frequency 5kHz;

[0095] Airborne sound wave signals, frequency band from 1Hz to 2kHz;

[0096] Thermistor temperature data, accuracy ±0.1°C;

[0097] Gas concentration (selecting three types of gas sensors: H2S, NH3, and CO);

[0098] Pipe pressure fluctuation data, sampling period 100ms;

[0099] After all data is synchronized with local timestamps, it is normalized and encoded using a tensor structure to construct a third-order input feature tensor with dimensions of sensor type × time window × data channel.

[0100] Using the LSTM-GRU hybrid prediction model deployed on the main control platform, a prediction tensor is generated based on historical 12-hour sliding window data;

[0101] Subsequently, element-wise difference operations are performed between the current input tensor and the prediction tensor to generate the residual tensor;

[0102] The portion of the residual value that is greater than the set threshold (mean + 2 × standard deviation) is marked as a potential outlier region.

[0103] The temporal evolution trend of the residual tensor is modeled using a structural graph. The linked nodes in each residual propagation chain are extracted using GAT (Graph Attention Network) to form an anomaly propagation map.

[0104] When multiple nodes exhibit continuous propagation of residual peaks within 20 seconds, identify the chain as the main propagation path and lock the node with the shortest response delay in the path as the key response node.

[0105] Using the three most recent anomaly handling records of key response nodes as state sequence inputs, a feedback update path based on the policy evolution function is constructed.

[0106] The function employs an improved reinforcement learning algorithm to perturb the index. and recovery time The path is scored for the objective function, and the scoring formula is as follows:

[0107] ;

[0108] in This represents the cumulative value of the residuals from abnormal disturbances along the current path. The time taken for the abnormal state to recover to a steady state is expressed in seconds. The path with the highest score is selected to form the optimal treatment path sequence.

[0109] Based on the selected path, a digital twin simulation environment is constructed to simulate three typical fault scenarios:

[0110] The tower crane is experiencing abnormal swaying during lifting.

[0111] The construction hoist was vibrating abnormally during operation;

[0112] Abnormal temperature rise in temporary power distribution equipment;

[0113] During the simulation, the response time, suppression magnitude, and system stabilization time for each path are recorded, and the current execution path is determined based on the comprehensive simulation score.

[0114] Historical anomaly levels, trigger frequencies, and structural locations in the propagation graphs of each device node are collected, normalized, and then a priority scoring model is constructed using a multi-factor weighted function.

[0115] ;

[0116] by The value prioritizes all paths to be processed, so that high-risk nodes are scheduled first, while low-priority paths are included in the buffer queue.

[0117] After the disposal path is executed, the residual of process disturbance and simulation deviation are recorded. The strategy scoring model and threshold function parameters are updated using the minimum mean square error (MSE) function. The path scoring strategy is adjusted synchronously according to changes in external meteorological disturbances, such as humidity changes exceeding 15% or wind speed fluctuations exceeding 20%, in order to achieve adaptive learning and long-term optimization.

[0118] like Figure 1-4 As shown, it further includes:

[0119] When the generated anomaly handling path contains multiple critical response nodes, a policy path mapping function is constructed based on the current edge node topology and response latency characteristics. The system maps each key response action in the exception handling path to the corresponding edge node, and generates a linkage isolation control sequence based on the execution coupling relationship and priority weight between nodes, thus forming a distributed edge execution path.

[0120] The linkage isolation control sequence is dynamically trimmed based on environmental disturbance factors, its own state residuals, and task conflict factors to ensure the executability and stability of the path under edge conditions.

[0121] In this embodiment: Based on the anomaly handling path sequence generated in step S4, a control mapping relationship is constructed for the edge execution nodes in multiple key equipment at the construction site, including the following specific steps:

[0122] S4-1: Establishing an edge node topology diagram based on the physical connection structure and control response hierarchy of chemical equipment. , where nodes This refers to various execution units, such as valve controllers, emergency sprinkler systems, and ventilation control modules, etc. This indicates the response dependency or control latency channel between nodes;

[0123] Each node is allocated a processing latency coefficient. With resource state vector This is used to indicate the load feasibility of the current node;

[0124] S4-2: Handle each step of the strategy path. Mapped to edge control action sequences ,in Indicates the type of physical operation to be performed on the corresponding node;

[0125] The sequence of control actions must satisfy the temporal dependencies and safety constraints between operations. Candidate paths are filtered by judging the following mapping feasibility function:

[0126] ;

[0127] S4-3: For all action sequences filtered by mapping, establish the action scheduling matrix for edge nodes:

[0128] ;

[0129] in and Calculated based on system latency and priority;

[0130] If a task conflict is detected, such as two tasks being scheduled to the same node at the same time, the scheduling will be restructured using the conflict penalty function.

[0131] ;

[0132] S4-4: If multiple resource conflicting nodes or resource overload occurs, a scoring function is used to prune candidate paths.

[0133] ;

[0134] High-scoring paths are retained, while paths with high resource costs and large response delays are discarded to generate the final executable linkage control sequence;

[0135] S4-5: Send the actions in the final scheduling matrix to each edge node in a timely manner, and execute them by the local controller;

[0136] During execution, each node sends back its response time, action completion status, and local disturbance impact value, and updates the path execution log.

[0137] If an execution failure or abnormal feedback exceeds the threshold, the backup control path switching mechanism is triggered.

[0138] like Figure 1-4 As shown, the control execution mechanism based on the anomaly handling path at the edge node further includes:

[0139] In a multi-edge node environment, a dynamic graph of path execution residuals is constructed. The graph is based on the execution residual sequence, resource occupancy status and task response stability index formed by different edge nodes in multiple historical feedback cycles. The residual trend tensor is extracted and a node behavior stability prediction model is constructed.

[0140] Based on the stability prediction model, a migration scheduling mapping relationship for candidate disposal paths is established, and the current preferred path is mapped to the edge node with sufficient remaining resources and high predicted stability according to the strategy scoring results.

[0141] During execution, the path migration decision is dynamically adjusted based on changes in node resource load and response delay after migration. A feedback update mechanism is constructed to realize dynamic scheduling of the handling path among edge nodes, execution residual suppression and collaborative stability control, so as to improve the overall robustness and response consistency of the abnormal handling path.

[0142] In this embodiment, to enhance the stability and adaptability of the exception handling path during execution at edge nodes, the following implementation steps are adopted:

[0143] First, for each edge node In multiple feedback cycles During the execution of the exception handling path within the system, the response indicator residuals after each round of path execution are collected, and an execution residual sequence tensor is constructed:

[0144] ;

[0145] in Indicates the first Round path execution in The response error value at any given time, such as disturbance suppression residual, recovery offset residual, etc.;

[0146] Next, for each node ,exist Extracting the maximum offset from the residual sequence of each period Residual mean square deviation With stability index function The execution stability score of the computing node:

[0147] ;

[0148] By inputting the stability scores of each edge node into the scheduling mapping function Generate a node migration priority vector:

[0149] ;

[0150] in Represents a node The path migration priority is determined by the score; the lower the score, the higher the priority.

[0151] Subsequently, the task execution path of the node with the lowest current score is migrated to the adjacent node with the higher score. For example: if Then Node path migration to Execute the operation, and simultaneously collect new residual data after execution to update the tensor. And feed it back to the mapping function. Dynamic reallocation is performed during this process, resulting in the following closed-loop path migration map:

[0152] ;

[0153] The above methods can achieve dynamic scheduling, execution optimization, and adaptive stability improvement of anomaly handling paths without significantly increasing edge load, and can be integrated into the main controller strategy evolution module to participate in the next round of path optimization strategy selection.

[0154] like Figure 1-4 As shown, the dynamic scheduling mechanism for anomaly handling paths among edge nodes further includes:

[0155] After completing the construction of the path execution residual dynamic graph, the path segments corresponding to the high-frequency offset nodes in the graph are extracted, and the resource consumption weight and response stability index of the path segment in multiple feedback cycles are calculated.

[0156] Construct a path segment pruning priority function It is used to dynamically prune each path segment based on resource constraints, response bias, and residual weights.

[0157] The remaining path segments are constructed with residual minimization and stability maximization as the joint optimization objective function. The disposal path is reorganized based on the graph structure shortest path algorithm, and the modified disposal path is executed according to the new node scheduling priority sequence to improve the overall execution efficiency and multi-node response stability.

[0158] In this embodiment, in order to verify the effectiveness of the edge node dynamic scheduling strategy based on the abnormal handling path pruning and reconstruction mechanism in the abnormal handling scenario of remote equipment in industrial and chemical industry, a set of simulation experiments were designed.

[0159] The experimental environment uses a virtual edge computing network simulation platform to simulate six heterogeneous edge nodes, and deploy historical task datasets and different resource load models respectively.

[0160] The simulated task is the execution scheduling task after an abnormal temperature control alarm in a chemical plant. This task has moderate resource consumption fluctuations and real-time requirements, making it suitable for verification in this embodiment.

[0161] First, four different anomaly handling paths were constructed as a comparison group: existing path A (traditional scheduling strategy), path B (residual optimization strategy), path C (node ​​priority scheduling mechanism), and path D (the pruning and reconstruction joint mechanism proposed in this invention).

[0162] Each path is simulated for 20 rounds of scheduling tasks under the same period. During the process, the resource utilization rate, execution residual (expressed as the standard deviation between path feedback and predicted response), path switching delay time (ms), stability score (comprehensively considering node response jitter, feedback stability and residual gradient) and task completion efficiency improvement ratio (based on path A) of each node are recorded in real time.

[0163] In this process, path D constructs a high-frequency offset node feature map based on the execution residual map, extracts resource consumption weights and response stability scores for multi-cycle path segments, and jointly constructs a pruning priority function. And execute the strategy compression;

[0164] The path segments are then regrouped and sorted based on the joint score of residuals and resource indicators, and mapped to the node with the best stability prediction score.

[0165] During path execution, a migration feedback correction mechanism is constructed to automatically suppress residual jumps and dynamically schedule path segments, thereby achieving pruning and reconstruction between edge nodes. See the table for details.

[0166] Experimental data table of abnormal handling path pruning and reconstruction

[0167] Parameters / Test Subjects Average resource utilization rate (%) Mean of residuals (unit: standard deviation) Path switching delay (ms) Node stability score (out of 10) Task completion efficiency improved (%) Path A (Existing Strategy) 82.5 2.1 125 6.1 0.0 Path B (Residual Optimization Strategy) 71.3 1.6 103 7.8 8.3 Path C (Node Priority Scheduling) 68.9 1.3 97 8.2 11.7 Path D (Pruning and Reconstruction Strategy of this Invention) 59.7 0.7 89 9.3 19.4

[0168] According to the table above, by constructing a dynamic graph with path residual as the driving parameter, the system can identify abnormal fluctuation trends in the execution path in advance, and on this basis guide the pruning and optimization process to converge towards the dual indicators of resource consumption rate and path deviation amplitude.

[0169] The pruning process is not carried out in isolation, but is further coupled with the historical stability score results of the execution nodes, so that the optimal path not only has the ability to compress resources, but also shows strong adaptability in task response.

[0170] Subsequently, the system uses the execution deviation trend function derived from the prediction model to reconstruct and adjust the candidate path set, forming a more balanced execution distribution pattern.

[0171] The refactored structure continuously receives feedback signals during execution and dynamically fine-tunes itself based on real-time load conditions to ensure minimal path execution latency and a stable improvement in task scheduling success rate.

[0172] Verification showed that the selected path D outperformed paths A, B, and C in all five key performance indicators: its resource utilization was reduced to 59.7%, the path residual was controlled within 0.7, the response latency was reduced to 89ms, the path stability score reached 9.3 points, and the task completion rate was increased to 19.4%.

[0173] The above performance clearly demonstrates that the path optimization mechanism proposed in this embodiment can exhibit strong adaptability, high stability, and significant resource efficiency improvement in scenarios involving multi-task collaboration, high-pressure load on edge nodes, and sudden abnormal disturbances.

[0174] like Figure 1-4 As shown, if the preset scoring threshold is not reached within two or more consecutive scheduling cycles of the feedback scoring function, the path scoring residual sequence is extracted based on the path execution residual map, and a residual trend tensor for trend analysis is constructed.

[0175] Based on the score decay pattern identified in the residual trend tensor, a preset path structure template library is retrieved, and candidate path templates with similarity to the current path structure features above a threshold value are selected.

[0176] Fine-tune the key node sequence in the candidate path template to form alternative path candidates that can adapt to the current edge node state characteristics;

[0177] Alternative path candidates are incorporated into the scheduling path scoring system and evaluated in real time through a feedback scoring function. Once the continuous scoring meets the stability requirements, they are solidified as the main execution path for the current scheduling cycle to replace the original path in execution.

[0178] In this embodiment, it is necessary to further explain that the feedback scoring function refers to the function structure that dynamically adjusts the scoring parameters according to the path execution results during the task scheduling process. It has the characteristics of periodic feedback, adaptive adjustment and multi-dimensional scoring. This function not only considers static indicators such as path length or time delay, but also introduces dynamic evolution factors such as scoring residual fluctuation and stability change rate to guide path evolution.

[0179] The path execution residual graph is a multi-dimensional residual representation structure built around the difference between the path execution result and the expected score. The graph consists of a tensor graph with time and score dimensions to capture the performance degradation trend and local fluctuation pattern of the scheduling path in multiple cycles, supporting subsequent trend identification and template matching.

[0180] The residual trend tensor refers to a high-dimensional tensor structure extracted and constructed from the score residual map for trend modeling. Its dimensions can cover time windows, score factors, node positions, etc., to model the dynamic evolution of path scores in time series. This tensor supports tools such as singular value decomposition and Fourier analysis to perform pattern recognition of trends.

[0181] The path structure template library is a knowledge base containing predefined path structure information. It summarizes the structure based on historical execution data, expert experience and typical scenarios. Its role is to provide structural reference samples, support the efficient search for alternative paths in similar structural domains after the scheduling path fails, and has the ability to quickly match structures and abstract features.

[0182] Key node fine-tuning refers to making minor adjustments to the position, weight, or order of some key scheduling nodes in the candidate path template to better adapt them to the current edge node status (such as load, resource utilization, and latency sensitivity). This strategy significantly reduces scheduling costs and improves matching accuracy by dynamically adjusting the local structure rather than reconstructing the entire path.

[0183] Therefore, by constructing a score residual trend tensor, we can proactively identify the risk of score decay and sudden changes, which strengthens the feedforward control capability of the scheduling system. Furthermore, by using a structural template library and a trend alignment screening mechanism, we can avoid blindness and resource waste in the path replacement process.

[0184] Furthermore, by fine-tuning the key node strategy, the path structure can be reconstructed in a refined manner, significantly reducing scheduling costs and enhancing adaptability to edge environments. Finally, the path is solidified by a dynamic scoring function, ensuring the dual stability of the path in terms of local scoring and periodic performance, thus avoiding the problem of high scores and low reliability that is common in traditional methods.

[0185] like Figure 1-4 As shown, after the adaptive alternative path is loaded into the task scheduling sequence of the current edge node, a score residual trend tensor is constructed based on the score residual change trend and score fluctuation characteristics of the alternative path in the historical period.

[0186] Based on the scoring residual trend tensor, the residual attribution sequence of each scoring factor in the scoring function is extracted, and the penalty parameter and stability evaluation criterion of the feedback scoring function are dynamically adjusted accordingly.

[0187] When the deviation of the scoring standard exceeds the preset tolerance threshold within two consecutive scheduling cycles, the evolution mechanism of the scoring function structure is triggered, the evaluation dimension of the scoring function is reconstructed, and a scoring adjustment factor based on the residual fluctuation frequency is introduced.

[0188] The scoring adjustment factor is applied to the current scoring function to re-evaluate the adaptive alternative path. When the scoring trend stabilizes and the scoring confidence interval converges to the target interval, the alternative path is marked as a long-term scheduling candidate path, and a stability index is generated for reference in subsequent scheduling cycles.

[0189] In this embodiment, to verify the effectiveness of the scoring function reconstruction and long-term candidate path identification method based on the scoring residual trend tensor proposed in the above embodiments, a set of simulated edge node scheduling scenarios were constructed to test the impact of different scoring function configurations on the stability judgment and scoring trend of alternative paths.

[0190] The experimental scenario is set as a task scheduling node in a key equipment intelligent detection system at a construction site. The goal is to select the most stable alternative path to include in the long-term scheduling candidate in 30 consecutive scheduling cycles.

[0191] The experimental data includes four types of scoring function configurations:

[0192] Class A uses a traditional static scoring function with no scoring structure evolution mechanism;

[0193] Class B is the scoring function of this invention, which has a scoring residual trend tensor construction and function reconstruction mechanism;

[0194] Type C is a multi-factor weighted scoring function in the existing technology, which has a simple factor adjustment function;

[0195] Class D is a random rating function simulating a scenario where the rating trend is unstable;

[0196] Each type of function receives real-time path score input during the scheduling simulation process, and records the score trend changes, the convergence speed of the score confidence interval, the frequency of offset tolerance exceeding the threshold, and the final stability index.

[0197] The scoring residual trend tensor is constructed based on the periodic fluctuations in the historical scoring sequence of the path, with the periodic average difference as the tensor's basic dimension; the scoring adjustment factor is dynamically introduced based on the frequency domain analysis results to adjust the sensitivity coefficient of the feedback function and the weight of the evaluation factor; when the scoring trend deviates beyond the preset threshold (set as ±15% of the scoring mean) within two consecutive periods, the scoring function dimension is automatically reconstructed, and a new round of attribution factor feedback mechanism is introduced.

[0198] The experimental environment was built using a Python simulation platform, and a fixed path scoring perturbation model was used for uniform perturbation input to ensure the fairness and reproducibility of the experiment.

[0199] The experimental results are shown in the table below:

[0200] Comparison Table of Experimental Results on Trend Regulation of Scoring Function

[0201] Scoring function configuration Scoring trend stability (unit: σ) Convergence time (number of periods) of the scoring confidence interval Offset tolerance exceeding threshold frequency (times / 10 cycles) Stability index (0~1) Original scoring function A 2.3 15 4 0.52 The scoring function B of this invention 0.8 6 0 0.93 Traditional weighted function C 1.7 12 2 0.68 Random fluctuation function D 3.2 20 6 0.41

[0202] From the perspective of the stability of the scoring trend (measured by the standard deviation of the scoring), the scoring function B of this invention has the lowest fluctuation value in the scheduling period, which is only 0.8σ. This is significantly better than the traditional scoring function A (2.3σ) and the weighted function C (1.7σ), and much lower than the random function D (3.2σ) with significant scoring fluctuation. This indicates that the B scheme has better trend stability.

[0203] In terms of the convergence time of the score confidence interval, Scheme B only requires 6 cycles to achieve score interval convergence, which is better than A (15 cycles) and C (12 cycles), demonstrating its faster adaptability to the changing trend of path scores.

[0204] Scheme D failed to stabilize after more than 20 cycles, indicating that the scoring function lacked effective control.

[0205] The frequency of deviation tolerance exceeding the threshold is a key indicator for measuring the deviation of the score from the target standard. Option B has 0 times, which shows that the method of the present invention has a strong error control capability in residual trend judgment and score function structure evolution.

[0206] In comparison, A and C have 4 and 2 offsets respectively, while D frequently crosses the boundary 6 times, making it the least reliable.

[0207] In terms of the final stability index, the proposed solution scored 0.93, which is much higher than A (0.52), C (0.68) and D (0.41), indicating that the method has higher accuracy in identifying long-term candidate paths in scheduling strategy optimization.

[0208] In summary, this embodiment effectively overcomes the shortcomings of traditional scoring mechanisms, such as scoring lag and inability to adapt to changing scoring trends, by constructing a dynamic evolution mechanism for the scoring residual trend tensor and the scoring function. It demonstrates significant technological progress and innovative effects in long-term stable scheduling path identification, especially in the evolution mechanism of the scoring function, the rapid convergence capability of the confidence interval, and the fine adjustment capability of residual attribution.

[0209] like Figure 1-4As shown, after the adaptive alternative path is loaded into the scheduling sequence of the edge node, a scoring residual trend tensor is constructed based on the scoring residual change trend and scoring fluctuation frequency of the alternative path in continuous historical cycles, in order to identify the feedback lag of the current scoring mechanism on path stability.

[0210] Based on the scoring residual trend tensor, the residual attribution sequence of each scoring factor in the scoring function is extracted, its offset magnitude and contribution ratio are calculated, and the penalty parameter and path stability evaluation dimension in the scoring function are dynamically adjusted according to the attribution results.

[0211] When the deviation of the stability judgment result of the scoring function exceeds the preset tolerance threshold in two consecutive scheduling cycles, the evolution mechanism of the scoring function structure is triggered, the evaluation sub-dimension of the scoring function is reconstructed, and a scoring adjustment factor based on the fluctuation frequency of the scoring residual is introduced to enhance the sensitivity of the scoring function to path behavior anomalies.

[0212] The scoring adjustment factor is modeled by weighting the residual fluctuation period, maximum amplitude and delay trend of each scoring factor, and is applied to the current scoring function to re-score the alternative path;

[0213] When the re-scoring result converges to the target interval within a continuous period and the scoring trend meets the stability criterion, the alternative path is marked as a long-term scheduling candidate path, and a stability index parameter is generated for reference in subsequent task scheduling cycles.

[0214] In this embodiment, to achieve dynamic tracking and stability evaluation of the scoring effect of adaptive alternative paths, firstly, after the alternative path is loaded into the task scheduling sequence of the current edge node, its scoring results over multiple historical scheduling cycles are collected. Then, a three-dimensional scoring residual trend tensor is constructed using scoring factors, such as response time, resource consumption, and anomaly suppression effect, as dimensions. ,in Indicates the rating factor number. Indicates the scheduling cycle number. Indicates the edge node number;

[0215] The scoring residual is defined as the difference between the current period's score and the baseline expected score, and its tensor element form is as follows:

[0216] ;

[0217] The scoring results are processed using a normalization method, and the value range is [value range missing]. The scoring residual is recorded once for each scheduling cycle, and the sample time window is 5 to 10 consecutive cycles;

[0218] Next, statistical analysis was performed on the tensor to extract the residual fluctuation standard deviation corresponding to each scoring factor. Compared with the reference expected mean Constructing a rating moderating factor This is used to correct the response strength of the current scoring function under different factor dimensions:

[0219] ;

[0220] in To prevent extremely small positive values ​​from being divided by zero;

[0221] Regulatory factors It is used to amplify or attenuate the factor weights in the current scoring function, thereby constructing a scoring function that strengthens the residual attribution mechanism. ;

[0222] If, within two or more consecutive scheduling cycles, the total score of the scoring function is lower than the set scoring threshold (e.g., 0.6), and the offset of each scoring factor exceeds the preset tolerance threshold... This triggers the evolution mechanism of the scoring function;

[0223] This mechanism retrieves the residual attribution sequence along the rating factor dimension and, based on the residual fluctuation frequency, automatically removes unstable factors or introduces new factors, such as "rating trend variance," to reconstruct the evaluation function structure for a new version. The specific evolutionary rules are shown in the table below:

[0224] Example table of evolutionary rules

[0225] Resource consumption rate yes Variance trend factor Weight reduced by 50% Response time no reserve Weights unchanged Stable suppression efficiency yes State offset Weight after replacement: 60%

[0226] Subsequently, the confidence interval of the newly constructed scoring function was evaluated;

[0227] With a confidence level of 95%, the following confidence interval is calculated for each rating factor:

[0228] ;

[0229] in The historical average rating For historical standard deviation, This represents the number of sampling periods. If the score value is within the confidence interval for three consecutive periods, and the interval width is less than 0.08, the score result is considered to have stabilized.

[0230] Once the above stability requirements are met, the alternative path is marked as a long-term scheduling candidate path. A stability index is then generated by combining the path's score trend volatility, mean stability, and score deviation over historical periods. The calculation method is as follows:

[0231] ;

[0232] in This represents the variance of the rating fluctuation. This represents the average score for the current period. The center value of the target scoring interval;

[0233] The stability index is used for path selection, priority setting, and dynamic scheduling judgment in subsequent scheduling strategies.

[0234] Through the above mechanism, this invention not only realizes the dynamic evolution and adaptive adjustment of the scoring mechanism, but also constructs a complete evaluation and decision-making link in multiple dimensions, such as scoring factors, trend changes, statistical confidence, and path labels, ensuring the high stability, high responsiveness, and continuous optimization capability of the anomaly handling path in different edge node environments.

[0235] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0236] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the present invention. Various changes and modifications can be made to the present invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed.

Claims

1. A method for handling anomalies in intelligent detection of key equipment at a construction site, characterized in that, Includes the following steps: S1. Collect operational data of key equipment at the construction site using a multimodal sensor array and construct a time-series input tensor; S2. Generate a prediction tensor and identify anomalies by performing a difference operation with the real-time tensor. S3. Construct an anomaly propagation map and identify key linkage nodes; S4. Generate candidate disposal paths and edge mapping strategies based on key node data; S5. Test the response metrics of each path in a virtual environment and collect residual data to select the optimal path; S6. Scheduling and processing order based on node priority; S7. Dynamically update model parameters and scoring function structure based on execution feedback.

2. The method for handling anomalies in intelligent detection of key equipment at a construction site according to claim 1, characterized in that, The edge mapping strategy includes: Based on the current topology and response latency characteristics of the edge nodes, a policy path mapping function is constructed. The key response actions in the anomaly handling path are mapped to the corresponding edge nodes, and a linkage isolation control sequence is generated based on the execution coupling relationship and priority weight between nodes to form a distributed edge execution path; The linkage isolation control sequence is dynamically trimmed based on environmental disturbance factors, its own state residuals, and task conflict factors.

3. The method for handling anomalies in intelligent detection of key equipment at a construction site according to claim 2, characterized in that, The control execution mechanism based on the anomaly handling path at the edge nodes further includes: In a multi-edge node environment, a dynamic graph of path execution residuals is constructed. The graph is based on the execution residual sequence, resource occupancy status and task response stability index formed by different edge nodes in multiple historical feedback cycles. The residual trend tensor is extracted and a node behavior stability prediction model is constructed. Based on the stability prediction model, a migration scheduling mapping relationship for candidate disposal paths is established, and the current preferred path is mapped to an edge node with sufficient remaining resources and high predicted stability according to the strategy scoring result. During execution, path migration decisions are dynamically adjusted based on changes in node resource load and response delays after migration. A feedback update mechanism is constructed to achieve dynamic scheduling of disposal paths among edge nodes, execution residual suppression, and collaborative stability control.

4. The method for handling anomalies in intelligent detection of key equipment at a construction site according to claim 3, characterized in that, The dynamic scheduling mechanism for the anomaly handling path among edge nodes further includes: After completing the construction of the path execution residual dynamic graph, the path segments corresponding to the high-frequency offset nodes in the graph are extracted, and the resource consumption weight and response stability index of the path segment in multiple feedback cycles are calculated. Construct a path segment pruning priority function It is used to dynamically prune each path segment based on resource constraints, response bias, and residual weights; The remaining path segments are constructed with residual minimization and stability maximization as joint optimization objective functions. The disposal paths are reorganized based on the graph structure shortest path algorithm, and the corrected disposal paths are executed according to the new node scheduling priority sequence to improve overall execution efficiency and multi-node response stability.

5. The method for handling anomalies in intelligent detection of key equipment at a construction site according to claim 4, characterized in that: When the output value of the node behavior stability prediction model is lower than the preset stability threshold for two consecutive scheduling cycles, the following steps are executed: Based on the constructed path execution residual dynamic graph, the path execution residual sequence is extracted; A residual trend tensor is constructed based on the residual sequence to identify stability decay patterns. The retrieval system uses a pre-stored path structure template library to filter candidate templates with a feature similarity of more than 85% to the current path. The key node sequences in the candidate template are fine-tuned in terms of position and weight to generate alternative paths that adapt to the edge node states; The alternative path is input into the stability prediction model for evaluation. Once the model meets the criteria for three consecutive evaluations, the original path is replaced and executed.

6. The method for handling anomalies in intelligent detection of key equipment at a construction site according to claim 5, characterized in that, After the adaptive alternative path is loaded into the task scheduling sequence of the current edge node, a scoring residual trend tensor is constructed based on the scoring residual change trend and scoring fluctuation characteristics of the alternative path in the historical period. Based on the aforementioned scoring residual trend tensor, the residual attribution sequence of each scoring factor in the scoring function is extracted, and the penalty parameter and stability evaluation criterion of the feedback scoring function are dynamically adjusted accordingly. When the deviation of the scoring standard exceeds the preset tolerance threshold within two consecutive scheduling cycles, the evolution mechanism of the scoring function structure is triggered, the evaluation dimension of the scoring function is reconstructed, and a scoring adjustment factor based on the residual fluctuation frequency is introduced. The scoring adjustment factor is applied to the current scoring function to re-evaluate the adaptive alternative path. When the scoring trend stabilizes and the scoring confidence interval converges to the target interval, the alternative path is marked as a long-term scheduling candidate path, and a stability index is generated for reference in subsequent scheduling cycles.

7. The method for handling anomalies in intelligent detection of key equipment at a construction site according to claim 6, characterized in that, After the adaptive alternative path is loaded into the scheduling sequence of the edge node, a scoring residual trend tensor is constructed based on the scoring residual change trend and scoring fluctuation frequency of the alternative path in continuous historical periods, in order to identify the feedback lag of the current scoring mechanism to the path stability. Based on the scoring residual trend tensor, the residual attribution sequence of each scoring factor in the scoring function is extracted, its offset magnitude and contribution ratio are calculated, and the penalty parameter and path stability evaluation dimension in the scoring function are dynamically adjusted according to the attribution results. When the deviation of the stability judgment result of the scoring function exceeds the preset tolerance threshold in two consecutive scheduling cycles, the evolution mechanism of the scoring function structure is triggered, the evaluation sub-dimension of the scoring function is reconstructed, and a scoring adjustment factor based on the fluctuation frequency of the scoring residual is introduced to enhance the sensitivity of the scoring function to path behavior anomalies. The scoring adjustment factor is modeled by weighting the residual fluctuation period, maximum amplitude and delay trend of each scoring factor, and is applied to the current scoring function to re-score the alternative path; When the re-scoring result converges to the target interval within a continuous period and the scoring trend meets the stability criterion, the alternative path is marked as a long-term scheduling candidate path, and a stability index parameter is generated for reference in subsequent task scheduling cycles.

8. An intelligent detection device for key equipment at a construction site, based on the method described in any one of claims 1-7, characterized in that, include: The multimodal data acquisition module is used to collect vibration signals, sound wave signals, tilt angle signals, load signals, temperature signals, current signals, hydraulic pressure signals and environmental risk signals generated by key equipment at the construction site during operation, and to construct the acquisition results into a time series-based multimodal feature input tensor; The residual generation and trend recognition module is used to generate a prediction tensor based on the equipment operation status model and historical operation data, and perform differential processing with the input tensor to form a residual tensor, further constructing a scoring residual trend tensor and identifying scoring fluctuation characteristics. The anomaly propagation graph construction module is used to construct an anomaly propagation path graph based on the multidimensional distribution and temporal characteristics of the residual tensor, and to identify key response nodes and linkage path structures within it. The strategy path generation module is used to construct a feedback-driven strategy path candidate set based on the state sequence and historical handling paths of key response nodes, and to select the optimal anomaly handling path by minimizing perturbation and restoring stability objective functions. The virtual simulation and scoring evaluation module is used to simulate candidate paths in a simulation environment containing multiple potential fault evolution characteristics, collect feedback indicators of the paths in terms of response speed, anomaly suppression efficiency and stable recovery time, and calibrate the current optimal handling path based on the comprehensive scoring function. The edge node scheduling and linkage module is used to map the optimal anomaly handling path to edge nodes, generate linkage isolation control sequences based on topology, resource status and priority relationship, and perform path migration, task pruning and residual suppression scheduling between nodes. The scoring function evolution and path stability evaluation module is used to trigger the scoring function structure reconstruction mechanism when the scoring deviation exceeds the threshold, adjust the scoring factor weights and penalty parameters based on the scoring residual trend tensor, and solidify the alternative path as a long-term scheduling candidate path when the scoring trend of the alternative path stabilizes. The disturbance feedback and parameter adaptive update module is used to synchronously update the path selection parameters, level discrimination threshold and scoring function structure based on the disturbance residuals, score fluctuations and node state change trends generated during the execution process, so as to realize the periodic reconstruction and evolution optimization of the anomaly handling strategy.

Images