Data analysis-driven special equipment safety risk assessment method and system

Abstract

The invention discloses a data analysis-driven special equipment safety risk assessment method and system, and relates to the technical field of data processing, and the method comprises the steps: carrying out the safety operation demand analysis of target special equipment, determining the safety operation factor, analyzing a detection point according to the safety operation factor, and laying a sensor group to form a sensing module; target equipment fault data is collected, and a safety risk data set is generated through evaluation and fused into an evaluation tree; and monitoring multi-point operation data of the equipment by using the sensing module, and performing feature analysis and risk assessment in combination with the assessment tree to obtain a safety risk assessment coefficient of the special equipment. The technical problems that in the prior art, potential faults of the special equipment are difficult to monitor and identify in real time through a traditional method, and the real-time performance and accuracy of risk assessment are poor are solved, the potential faults are accurately identified by monitoring the running state of the special equipment in real time, and the risk assessment efficiency is improved. And the real-time performance and the accuracy of safety risk assessment of the special equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a special equipment safety risk assessment method and system driven by data analysis. Background Art

[0002] With the development of social economy and the acceleration of urbanization, the application of special equipment, such as elevators, in industrial production and daily life is becoming more and more extensive. These devices involve complex mechanical, electrical and environmental factors during operation, and their safe operation is directly related to the life safety of personnel and the operation efficiency of the devices. However, due to the complex structure and changing operating environment of special equipment, traditional special equipment fault detection relies on regular manual inspections and single-point monitoring, often unable to timely and accurately detect potential faults during equipment operation, easily leading to sudden equipment failures and safety accidents. Summary of the Invention

[0003] This application provides a special equipment safety risk assessment method and system driven by data analysis, which is used to solve the technical problems that traditional methods in the prior art are difficult to monitor and identify potential faults of special equipment in real time, and the real-time performance and accuracy of risk assessment are poor.

[0004] In the first aspect of this application, a special equipment safety risk assessment method driven by data analysis is provided. The method includes: analyzing the safety operation requirements of the target special equipment to obtain equipment safety operation factors, parsing the detection points of the target special equipment according to the equipment safety operation factors to obtain a set of equipment factor detection points; determining factor detection sensors according to the equipment safety operation factors, and arranging a sensor group according to the factor detection sensors for the set of equipment factor detection points to obtain a special equipment perception module; collecting a special equipment fault data set, and performing associated sampling based on the target special equipment and the special equipment fault data set to obtain a target equipment fault data set; extracting fault features and performing safety risk assessment on the target equipment fault data set to obtain an equipment safety risk data set, and performing cascade fusion on the equipment safety risk data set to generate a special equipment safety risk assessment tree; monitoring and collecting multi-point operation data streams of special equipment through the special equipment perception module, and using the special equipment safety risk assessment tree to perform feature analysis and risk assessment on the multi-point operation data streams of special equipment to obtain a special equipment safety risk assessment coefficient.

[0005] In the second aspect of the present application, a special equipment safety risk assessment system driven by data analysis is provided. The system includes: a detection point analysis module, which is used to analyze the safety operation requirements of the target special equipment, obtain the equipment safety operation factors, and parse the detection points of the target special equipment according to the equipment safety operation factors to obtain a set of equipment factor detection points; a sensor group layout module, which is used to determine factor detection sensors according to the equipment safety operation factors, and layout a sensor group for the set of equipment factor detection points according to the factor detection sensors to obtain a special equipment perception module; an associated sampling module, which is used to collect and obtain a special equipment failure data set, and perform associated sampling based on the target special equipment and the special equipment failure data set to obtain a target equipment failure data set; a safety risk assessment tree construction module, which is used to extract failure features and perform safety risk assessment on the target equipment failure data set to obtain an equipment safety risk data set, and perform cascade fusion on the equipment safety risk data set to generate a special equipment safety risk assessment tree; a safety risk assessment module, which is used to monitor and collect multi-point operation data streams of special equipment through the special equipment perception module, and use the special equipment safety risk assessment tree to perform feature analysis and risk assessment on the multi-point operation data streams of special equipment to obtain a special equipment safety risk assessment coefficient.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages: A special equipment safety risk assessment method and system driven by data analysis provided in the present application relates to the technical field of data processing. For special equipment, first analyze its safety operation requirements, determine the detection points and sensor layout to form a perception module, then collect failure data, extract features and evaluate risks to generate a risk assessment tree, and finally use the perception module to monitor data and combine the assessment tree to perform risk assessment to obtain a safety risk assessment coefficient. It solves the technical problems that in the prior art, it is difficult for traditional methods to monitor and identify potential failures of special equipment in real time, and the real-time performance and accuracy of risk assessment are poor, and realizes the technical effect of accurately identifying potential failures by monitoring the operation status of special equipment in real time and improving the real-time performance and accuracy of special equipment safety risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0008] Figure 1 Schematic flowchart of a special equipment safety risk assessment method driven by data analysis provided by an embodiment of the present application; Figure 2 Schematic flowchart of obtaining a set of equipment factor detection points through detection point analysis in a special equipment safety risk assessment method driven by data analysis provided by an embodiment of the present application; Figure 3 Schematic structural diagram of a special equipment safety risk assessment system driven by data analysis provided by an embodiment of the present application.

[0009] Explanation of reference numerals: Detection point analysis module 11, Sensor group layout module 12, Correlation sampling module 13, Safety risk assessment tree construction module 14, Safety risk assessment module 15. Detailed implementation manners

[0010] The present application provides a special equipment safety risk assessment method and system driven by data analysis, which is used to solve the technical problems that in the prior art, traditional methods are difficult to monitor and identify potential faults of special equipment in real time, and the real-time performance and accuracy of risk assessment are poor.

[0011] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0012] It should be noted that the terms "first", "second", etc. in the specification and the above-mentioned accompanying drawings of the present application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules not clearly listed or inherent to these processes, methods, products, or devices.

[0013] Embodiment 1, as Figure 1 shown, the present application provides a special equipment safety risk assessment method driven by data analysis, and the method includes: P10: Analyze the safety operation requirements of the target special equipment to obtain the equipment safety operation factors, and parse the detection points of the target special equipment according to the equipment safety operation factors to obtain the equipment factor detection point set.

[0014] Further, as Figure 2 shown, step P10 of the embodiment of the present application further includes: P11: Obtain the structural distribution information of the target special equipment, perform three-dimensional modeling based on the structural distribution information to generate a special equipment spatial structure model; P12: Perform finite element mesh division on the special equipment spatial structure model to obtain an equipment spatial finite element mesh model, and perform regional structure marking on the equipment spatial finite element mesh model; P13: Perform associated structure mapping on the equipment spatial finite element mesh model after regional structure marking according to the equipment safety operation factors respectively to obtain an associated factor equipment structure set; P14: Perform key detection point analysis on the associated factor equipment structure set respectively to obtain the equipment factor detection point set.

[0015] It should be understood that a detailed analysis of the safety operation requirements of the target special equipment, such as an elevator, is carried out to determine the equipment safety operation factors under different operating conditions, and further parse out the equipment detection point set. This process helps to clarify the monitoring requirements of the key parts of the equipment and ensure its operation within a safe range.

[0016] Specifically, first obtain the structural distribution information of the target special equipment, that is, the positions and layouts of each component inside the equipment. This information can be obtained through means such as design drawings, CAD models, or laser scanning. Based on this structural distribution information, perform three-dimensional modeling on the target equipment to generate a three-dimensional spatial structure model of the equipment, that is, a special equipment spatial structure model. This model completely shows the arrangement relationship of each structural component of the equipment in three-dimensional space and provides a basis for subsequent analysis.

[0017] Next, perform finite element mesh division on the special equipment spatial structure model to form an equipment spatial finite element mesh model. Finite element mesh division is a process of discretizing a complex structure into small units (mesh units), which is commonly used to analyze the stress and deformation of each part of the equipment under external loads or during operation. Through this process, the stress and deformation characteristics of the equipment under different working conditions can be simulated more carefully. Subsequently, perform regional structure marking on these mesh units, that is, identify the key areas of the equipment (such as load-bearing components, suspension devices, etc.) for key analysis.

[0018] Furthermore, according to the marked regional structure, correlation structure mapping is performed on different equipment safe operation factors (such as temperature, vibration, tension, acceleration, etc.). Correlation structure mapping refers to matching the equipment safe operation factors with the corresponding regions in the spatial structure model of the equipment to determine the action regions of each factor in the equipment structure. For example, the vibration factor may be closely related to the driving components and suspension components of the equipment, while the temperature factor may affect the working stability of the electrical components. Through this correlation structure mapping, the influence ranges of different factors inside the equipment can be clarified, and a set of equipment structures with associated factors is generated.

[0019] Finally, key detection point analysis is performed on the above-obtained set of equipment structures with associated factors to determine the optimal monitoring positions of each associated factor on the equipment. Key detection points refer to those positions that can reflect the operating state of the equipment, are easily affected by safe operation factors, and are easy to monitor. For example, for tension monitoring, the tension concentration part of the suspension rope should be preferentially selected as the detection point; for temperature monitoring, the motor and control cabinet and other areas prone to heat generation should be selected as the detection points. By analyzing the characteristics of each structural region and the influence positions of the associated factors, a set of equipment factor detection points is finally obtained.

[0020] The above process forms a multi-dimensional monitoring layout for special equipment through the acquisition of structural distribution information, solid modeling, finite element mesh division, correlation factor mapping, and key detection point analysis. It not only improves the understanding of the equipment operating state but also lays a technical foundation for subsequent sensor layout, real-time monitoring, and risk assessment, helping to improve the safety and reliability of special equipment (such as elevators).

[0021] Furthermore, step P14 of the embodiment of the present application further includes: P14-1: Uniformly mark the detection points of the set of equipment structures with associated factors respectively to obtain a set of optional detection points for the equipment factor structures; P14-2: Design test parameters and perform orthogonal arrangement of parameters according to the equipment safe operation factors respectively to obtain a parameter table of equipment safe operation test scenarios; P14-3: Based on the parameter table of equipment safe operation test scenarios, test records are made for the set of optional detection points for the equipment factor structures to obtain a set of test parameters for the optional detection points, and the set of test parameters for the optional detection points includes detection sensitivity and detection accuracy; P14-4: Optimize the detection points of the set of optional detection points for the equipment factor structures according to the set of test parameters for the optional detection points to obtain the set of equipment factor detection points.

[0022] Optionally, further refine the generation process of the equipment factor detection point set. Through multi-step analysis and screening, ensure the scientificity and accuracy of the detection points. Specifically, first, uniformly mark the detection points for the set of associated factor equipment structures, that is, within the associated factor areas of the equipment structures, distribute possible detection points evenly according to certain rules and distance intervals, thereby forming a set of optional detection points for the equipment factor structure. This set includes all potential points in the equipment that can be used for monitoring, making the subsequent selection of detection points more comprehensive and scientific.

[0023] After the uniform marking is completed, for each equipment safe operation factor (such as temperature, vibration, tension, etc.), design test parameters respectively and perform orthogonal arrangement of the parameters. The test parameter design refers to designing different test conditions according to the characteristics of each factor (such as the range of temperature change, the change of vibration frequency, etc.). The orthogonal arrangement of parameters is an optimization design method. By selecting a limited number of test combinations, with fewer experimental times, obtain as much data as possible on the impact of factor changes on the equipment, thereby forming a parameter table for the equipment safe operation test scenario. This table records the operating status of the equipment under different test conditions and provides a reference for subsequent tests.

[0024] Next, based on the parameter table of the equipment safe operation test scenario, conduct test records on the set of optional detection points for the equipment factor structure. Specifically, in each test scenario, monitor the optional detection points and record the test results of each point under different conditions, forming a set of test parameters for the optional detection points. The set of test parameters for the optional detection points includes detection sensitivity and detection accuracy. Detection sensitivity refers to the response degree of the detection point to the change of the operation factor, reflecting the sensitivity of the point to minute changes. Detection accuracy indicates the matching degree between the detection result and the actual equipment state.

[0025] Finally, based on the set of test parameters for the optional detection points, conduct optimization of the set of optional detection points for the equipment factor structure. By analyzing the detection sensitivity and detection accuracy of each point, screen out the points with the highest monitoring effect. The optimization process takes into account the overall performance of the points under different test conditions, selects those points that can not only accurately reflect the equipment state change with high precision but also quickly respond to equipment anomalies, and finally obtains the equipment factor detection point set, thereby ensuring that the detection point setting of special equipment has a scientific basis and can meet the actual monitoring requirements.

[0026] P20: Determine the factor detection sensor according to the equipment safe operation factor, and deploy the sensor group according to the factor detection sensor for the equipment factor detection point set to obtain the special equipment perception module.

[0027] Specifically, based on the equipment safety operation factors determined in the previous step, corresponding detection sensors are selected. For each operation factor, the appropriate sensor types and models are chosen. For example, for the temperature factor, a high-precision temperature sensor can be selected; for the vibration factor, a triaxial acceleration sensor may be required; for the monitoring of tension, a strain gauge or a tensile force sensor can be used. The selection of sensors needs to consider their measurement range, accuracy, sensitivity, and environmental adaptability to ensure normal operation under various working conditions.

[0028] Next, the sensors are detected according to the selected factors, and a sensor group is arranged on the set of equipment factor detection points obtained previously. Appropriate sensors are installed at each detection point to achieve comprehensive monitoring of each key part of the equipment. In this process, the layout scheme of the sensors needs to be optimized according to the specific distribution characteristics and monitoring requirements of the detection points. For example, in the parts of the equipment with strong vibration, acceleration sensors can be densely arranged to capture more vibration detail data; in the parts with small temperature changes but high accuracy requirements, a small number of high-precision temperature sensors can be used to save costs.

[0029] When arranging the sensor group, the fixing method and installation position of the sensors also need to be considered to ensure the stability and accuracy of the measurement results. For example, it should be ensured that the sensors are installed in areas on the equipment surface that are stable and not easily loosened to avoid data deviation caused by equipment movement or vibration. At the same time, to avoid the influence of environmental factors such as humidity and dust on the sensor performance, a protective cover or a sealing device can be equipped when necessary.

[0030] Through the selection and reasonable arrangement of sensors, a special equipment perception module is formed, that is, a monitoring system composed of multiple different types of sensors. These sensors are arranged at each key detection point of the equipment to achieve real-time perception and data collection of the safe operation state of the equipment. This module can continuously obtain multi-dimensional operation data of the equipment, not only ensuring efficient monitoring of the equipment operation state, but also being able to timely detect abnormal situations in the equipment operation, thereby improving the overall safety and stability of the equipment.

[0031] P30: Collect and obtain a special equipment failure data set, and perform associated sampling based on the target special equipment and the special equipment failure data set to obtain a target equipment failure data set.

[0032] Furthermore, step P30 of the embodiment of the present application further includes: P31: Classify the target special equipment according to its specification attributes and scenario attributes to obtain equipment specification attribute information and equipment application scenario attribute information; P32: Perform feature correlation matching on the obtained equipment specification attribute information and equipment application scenario attribute information with the special equipment failure dataset to obtain a primary failure dataset; P33: Traverse the primary failure dataset to collect similar feature data in the special equipment failure dataset to obtain a secondary failure dataset; P34: Based on the secondary failure dataset, perform P-level similar data collection in the special equipment failure dataset to obtain a P-level failure dataset, where 2 ≤ P ≤ 5; P35: Hierarchically integrate the primary failure dataset, the secondary failure dataset, and up to the P-level failure dataset to obtain the target equipment failure dataset.

[0033] It should be understood that through the associated sampling method, the target failure dataset of special equipment is gradually constructed to provide accurate data support for subsequent risk assessment.

[0034] First, classify the target special equipment according to its specification attributes and scenario attributes. Specification attribute classification refers to classification based on the physical characteristics and technical parameters of the equipment (such as model, load capacity, size, etc.); scenario attribute classification refers to classification based on the application scenario of the equipment (such as commercial, residential, industrial sites, etc.). Through this process, the equipment specification attribute information and application scenario attribute information are obtained, which helps to more accurately locate the failure characteristics of the equipment in a specific environment.

[0035] Next, perform feature correlation matching on the special equipment failure dataset according to the obtained equipment specification attribute information and application scenario attribute information. Feature correlation matching means screening out the most similar failure data in the special equipment failure dataset according to the specification and scenario attributes of the target equipment, thereby generating a primary failure dataset. The primary failure dataset contains failure samples with similar attributes and operating environments to the target equipment and is the basis for further data mining.

[0036] Further analyze the data in the primary failure dataset. By traversing the primary failure dataset, collect data with similar features in the special equipment failure dataset. Similar feature data collection means finding data samples in the dataset with a high degree of feature matching with the primary dataset to ensure the relevance and consistency of the data. Through this process, a secondary failure dataset is generated, which contains more data samples that conform to the characteristics of the target equipment.

[0037] Based on the secondary fault dataset, further multi-level similar data collection is carried out, that is, P-level similar data collection of the secondary fault dataset is performed in the special equipment fault dataset. The P-level similar data collection refers to performing multiple iterative analyses on the similarity of data. Each iteration starts from level 2 and gradually expands to levels 3, 4, and finally 5 (i.e., 2 ≤ P ≤ 5). In each round of similar data collection, on the basis of the previous round, data samples with a higher similarity to the target device are further added, thereby generating a P-level fault dataset. This process ensures the extensiveness and diversity of the fault dataset, making the data analysis results more comprehensive and reliable.

[0038] Finally, the primary fault dataset, the secondary fault dataset, and each P-level fault dataset are hierarchically integrated, that is, by merging and deduplicating datasets at different levels, a target device fault dataset containing comprehensive fault information is generated. This target device fault dataset fully reflects the performance of the target device under various fault scenarios, providing a solid data foundation for subsequent equipment risk assessment, fault prediction, and preventive maintenance.

[0039] P40: Extract fault features and conduct safety risk assessment on the target device fault dataset to obtain an equipment safety risk dataset, and perform cascaded fusion on the equipment safety risk dataset to generate a special equipment safety risk assessment tree.

[0040] Specifically, extract fault features from the target device fault dataset, that is, identify the typical manifestations and key parameters of the device when a fault occurs from the fault data, such as temperature fluctuations, vibration amplitude changes, and abnormal tension when a fault occurs. Then, conduct safety risk assessment based on the extracted fault features, that is, analyze the impact of each fault feature on the overall safe operation of the device. The assessment process takes into account the frequency of fault occurrence, severity, and the degree of harm that may be caused to the device and personnel, thereby forming an equipment safety risk dataset. This dataset reflects the safety risk situation of the device under various operating conditions and can help identify high-risk operating states.

[0041] After obtaining the equipment safety risk dataset, perform cascaded fusion on these data, that is, integrate different types of risk data according to their relevance, and through the layer-by-layer fusion of data, form a multi-level risk assessment model, that is, a special equipment safety risk assessment tree. The assessment tree is a tree-structured model, where each node represents a specific risk feature or fault type, and each path represents the relationship and influence degree between different risk factors. The special equipment safety risk assessment tree can be used to analyze the operating state of the equipment in real time, quickly assess the current safety level of the equipment, and provide a decision-making basis for the preventive maintenance and fault management of the equipment.

[0042] Further, for the step P40 of obtaining the device security risk dataset in the embodiments of the present application, it further includes: P41: Extract fault features from the target device fault dataset to obtain a device-associated fault feature set, where the device-associated fault feature set includes fault types, generation causes, and fault levels; P42: Based on the device-associated fault feature set, extract associated operation features from the target device fault dataset to obtain a device-associated multi-point operation feature set; P43: According to the special equipment security risk assessment standard, conduct a security risk assessment on the device-associated fault feature set to obtain a device security risk assessment coefficient set; P44: Map and associate the device-associated fault feature set, the device-associated multi-point operation feature set, and the device security risk assessment coefficient set to obtain the device security risk dataset.

[0043] In a possible embodiment of the present application, the process of obtaining the device security risk dataset is further refined. Through multi-step analysis and association, a comprehensive assessment from fault features to security risks is achieved.

[0044] First, extract fault features from the target device fault dataset to identify the specific features of the device when a fault occurs and generate a device-associated fault feature set. This feature set includes three parts: fault types (such as mechanical faults, electrical faults, etc.), generation causes (for example, fault causes such as excessive temperature, abnormal vibration, etc.), and fault levels (reflecting the severity and urgency of the fault). These features can help accurately locate the sources and impacts of different types of faults and are the basis for subsequent risk assessment.

[0045] Next, based on the device-associated fault feature set, extract associated operation features from the target device fault dataset, that is, analyze the multi-point operation state features of the device in the context of the fault occurrence. For example, analyze the change trends of data such as temperature, vibration, and acceleration at each monitoring point when a specific fault type occurs in the device, so as to form a device-associated multi-point operation feature set. This feature set covers the operation features of the device in different fault scenarios and can provide support for the cause analysis and trend prediction of the fault occurrence.

[0046] Then, according to the special equipment security risk assessment standard, conduct a security risk assessment on the device-associated fault feature set. The assessment standard is usually formulated according to industry specifications and device characteristics and involves a comprehensive analysis of fault types, generation causes, and fault levels. Through the assessment, a security risk assessment coefficient can be calculated for each fault type, that is, the risk level of the device in different fault states, reflecting the potential threat degree of the fault to the safe operation of the device. Finally, a device security risk assessment coefficient set is obtained, where each coefficient corresponds to a specific fault feature and operation state.

[0047] Finally, map and associate the device - related fault feature set, the device - related multi - point operation feature set, and the device safety risk assessment coefficient set to generate a device safety risk data set. Mapping association means organically integrating the relationships between the above - mentioned data sets, and correlating each fault feature with its corresponding multi - point operation feature and risk assessment coefficient. For example, for a specific type of fault, the changes in its operation features at different monitoring points and its corresponding safety risk assessment coefficient can form a complete analysis path through mapping. Through this process, the device safety risk data set can comprehensively reflect the risk status of the device under various fault conditions, providing an important data basis for subsequent risk prediction, early warning, and decision - making support. Through this systematic analysis method, the safe operation of special equipment can be more effectively ensured, and the intelligent level of equipment management can be improved.

[0048] Further, in generating the special equipment safety risk assessment tree, step P40 of the embodiment of the present application further includes: P45: Perform fault level classification and associated topology analysis on the device - related fault feature set to obtain a device fault cascade feature set; P46: Perform logical mapping association on the device - related multi - point operation feature set and the device fault cascade feature set to obtain a fault judgment logic feature set; P47: Generate feature nodes based on the device fault cascade feature set and the fault judgment logic feature set to obtain a device fault feature recognition tree; P48: Perform risk assessment assignment on the device fault feature recognition tree based on the device safety risk assessment coefficient set to generate the special equipment safety risk assessment tree.

[0049] Optionally, the generation process of the special equipment safety risk assessment tree is further refined. This process forms a systematic assessment model through the analysis of fault features, the establishment of topological structures, and risk assessment assignment.

[0050] Specifically, first perform fault level classification and associated topology analysis on the device - related fault feature set to form a device fault cascade feature set. Among them, fault level classification means grading fault features according to the severity, influence range, and relevance of faults. For example, a minor fault may only affect a certain component, while a severe fault may cause the entire device to stop. Associated topology analysis is to construct a topological structure between fault features according to the causal relationship and mutual influence between fault features, which is used to describe the path and cascade effect of fault propagation. Through this analysis, the interaction and evolution process of different fault features during the operation of the device can be more comprehensively understood.

[0051] Next, a logical mapping association is performed between the device - associated multi - point operation feature set and the device fault cascade feature set to generate a fault judgment logical feature set. Logical mapping association means combining multi - point operation features (such as changes in temperature, vibration, etc. at different positions) with fault cascade features (such as the propagation path of a certain fault between different components) to form logical rules for fault judgment. For example, when the vibration amplitude at certain specific positions exceeds the threshold and the temperature rises, it may trigger the occurrence of a certain level of fault. Through this mapping association, a logical connection can be established between fault features and the device operation state, improving the accuracy of fault judgment.

[0052] Furthermore, based on the device fault cascade feature set and the fault judgment logical feature set, feature nodes are generated for each fault feature and its associated operation features to construct a device fault feature recognition tree. Feature node generation means abstracting fault features and corresponding judgment logics into nodes in a tree - like structure, where each node represents a fault feature or an operation state. For example, a certain node can represent the manifestation characteristics of a specific fault type on a certain component. The device fault feature recognition tree intuitively shows the relationship between fault features and the device operation state through the hierarchical structure of these nodes and is the basic model for subsequent risk assessment.

[0053] Finally, based on the device safety risk assessment coefficient set, a risk assessment assignment is performed on the device fault feature recognition tree, that is, mapping the previously calculated safety risk assessment coefficients to each node of the fault feature recognition tree, so that each node not only reflects the corresponding fault feature but also carries the risk level corresponding to this feature, generating a special equipment safety risk assessment tree. Each branch and node of the assessment tree represents different fault evolution paths and risk degrees, and the potential risks of the device in various operation states can be shown from the root node to the leaf node.

[0054] Through this process, the special equipment safety risk assessment tree completely presents the risk structure of the device in various fault scenarios. It can not only intuitively display the relationship between fault features but also perform risk prediction and assessment based on the real - time operation data of the device. This model - based risk assessment method improves the fault recognition accuracy and safety monitoring ability of special equipment, helps to take preventive measures in a timely manner, and ensures the safe and stable operation of the device.

[0055] P50: The multi - point operation data stream of special equipment is monitored and collected through the special equipment perception module, and the special equipment safety risk assessment tree is used to perform feature analysis and risk assessment on the multi - point operation data stream of the special equipment to obtain the special equipment safety risk assessment coefficient.

[0056] It should be understood that through the special equipment perception module and the safety risk assessment tree, the multi-point operation status of special equipment is comprehensively monitored and analyzed to dynamically evaluate the safety risk status of the equipment.

[0057] First, through the special equipment perception module deployed on the special equipment, the multi-point data stream during the operation of the equipment is monitored and collected in real time. Among them, the special equipment perception module consists of multiple sensors, which are arranged at key positions of the equipment (such as motors, brakes, suspension devices, etc.) to obtain multi-dimensional operation data including temperature, vibration, tension, acceleration, etc. And the multi-point operation data stream refers to the data collected by these sensors at different positions simultaneously, reflecting the state changes of each part of the equipment during actual operation. For example, the vibration sensor can capture abnormal vibrations that occur during the operation of the equipment, and the temperature sensor can monitor the temperature fluctuations inside the equipment.

[0058] After collecting the multi-point operation data stream, the special equipment safety risk assessment tree is used to perform feature analysis and risk assessment on these data. Feature analysis refers to using the fault feature nodes defined in the assessment tree to match and analyze the multi-point operation data to identify features related to equipment failures. For example, if the acceleration data of a certain part exceeds the preset threshold, the assessment tree can judge that this may be a sign of a mechanical failure in this part. Through such feature analysis, the assessment tree can quickly locate abnormal phenomena during the operation of the equipment and compare and analyze these abnormalities with the historical fault features of the equipment.

[0059] On the basis of feature analysis, further risk assessment is carried out. Through its hierarchical structure, the assessment tree compares and calculates the real-time data with the fault risk coefficient of the equipment to generate the current safety risk assessment coefficient of the equipment. This coefficient is a risk quantification index of the equipment in the current state, reflecting the safety of the equipment during operation. The higher the assessment coefficient, the greater the fault risk faced by the equipment currently, and it may be necessary to immediately conduct inspections and maintenance; while a lower assessment coefficient indicates that the equipment is in good operating condition and the risk is small.

[0060] Through this process, the special equipment safety risk assessment tree can not only achieve dynamic analysis of the multi-point data stream, but also trigger real-time risk warnings when data anomalies occur. The equipment safety risk assessment coefficient provides intuitive risk quantification results for equipment management personnel, enabling them to quickly judge whether the equipment needs maintenance operations, thereby reducing potential safety hazards caused by equipment failures. By combining real-time data with the safety risk assessment model, accurate monitoring of the equipment operation status and dynamic risk management are achieved. Through the application of feature analysis and the assessment tree, risks that may occur during the operation of the equipment can be more effectively identified, improving the safe operation level and management efficiency of the equipment.

[0061] Furthermore, the embodiment of the present application further includes step P60, and step P60 further includes: P61: Obtain the feature information of the equipment leaf nodes according to the special equipment safety risk assessment tree; P62: Analyze the influence degree of the upper-level nodes on the feature information of the equipment leaf nodes in sequence to obtain the influence degree information of the equipment leaf nodes; P63: If the influence degree information of the equipment leaf nodes does not reach the preset influence degree threshold, generate a leaf node pruning instruction; P64: Based on the leaf node pruning instruction, prune and optimize the special equipment safety risk assessment tree.

[0062] Optionally, by optimizing the special equipment safety risk assessment tree, the accuracy and efficiency of risk assessment can be improved. First, according to the structure of the special equipment safety risk assessment tree, obtain the feature information of the equipment leaf nodes. The leaf nodes are the bottom-level nodes in the risk assessment tree and usually represent specific fault characteristics or operating states. By traversing the risk assessment tree, extract the feature information of all leaf nodes, and these information include fault types, fault levels, the possibility of fault occurrence, etc.

[0063] Next, analyze the influence degree of the upper-level nodes on the feature information of the equipment leaf nodes. Utilize the hierarchical relationship and logical mapping relationship in the risk assessment tree to calculate the influence degree of each leaf node on its upper-level node (i.e., the parent node). The calculation of the influence degree can be based on multiple factors, such as the severity of the fault characteristics, the frequency of fault occurrence, the impact of the fault on the overall operation of the equipment, etc. Through this step, obtain the influence degree information of the equipment leaf nodes. Leaf nodes with high influence degrees usually indicate that they have higher decision-making weights in the assessment tree, while leaf nodes with low influence degrees indicate that they have less impact on the overall risk assessment.

[0064] Then, judge the influence degree information of the equipment leaf nodes, that is, compare the influence degree information of the leaf nodes with the preset influence degree threshold. The preset influence degree threshold is set according to actual requirements and experience and is used to judge the necessity of leaf nodes in the risk assessment tree. If the influence degree of a certain leaf node does not reach the preset threshold, it means that the contribution of this node in the risk assessment is small, and its existence may increase the complexity and calculation amount of the assessment tree. Therefore, it is necessary to perform optimization processing on this leaf node through a pruning instruction.

[0065] Finally, based on the leaf node pruning instruction, the special equipment safety risk assessment tree is pruned and optimized. Pruning and optimization means removing the leaf nodes with low influence degrees to simplify the structure of the assessment tree and improve the efficiency of risk assessment. The pruning process needs to ensure that important fault information will not be lost, while simplifying the depth and the number of nodes of the tree, thereby reducing the calculation complexity and increasing the speed of real-time assessment. The assessment tree after pruning and optimization can focus more on high-risk and high-influence features, making the assessment process more targeted and accurate.

[0066] Through the above steps, the safety risk assessment tree of special equipment has been effectively streamlined and optimized, enabling the assessment tree to more accurately reflect the key risk points during equipment operation. This process not only improves the efficiency of risk assessment but also reduces the consumption of computing resources, contributing to the efficient management and real-time risk monitoring of special equipment in practical applications. The pruned assessment tree can quickly respond to changes in equipment status, enabling more timely risk warnings and maintenance decisions.

[0067] In summary, the embodiments of the present application at least have the following technical effects: The present application analyzes the safety operation requirements of the target special equipment to determine the safety operation factors, resolves the detection points accordingly, arranges a sensor group to form a sensing module, collects the fault data of the target equipment for safety assessment, generates a safety risk data set and integrates it into an assessment tree, uses the sensing module to monitor the operation data of multiple points of the equipment, combines with the assessment tree for feature analysis and risk assessment, and obtains the safety risk assessment coefficient of special equipment.

[0068] It achieves the technical effects of accurately identifying potential faults by real-time monitoring the operation status of special equipment, and improving the real-time performance and accuracy of the safety risk assessment of special equipment.

[0069] Embodiment 2, based on the same inventive concept as the method for safety risk assessment of special equipment driven by data analysis in the foregoing embodiment, as Figure 3 shown, the present application provides a system for safety risk assessment of special equipment driven by data analysis. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes: A detection point parsing module 11, which is used to analyze the safety operation requirements of the target special equipment to obtain the equipment safety operation factors, and parse the detection points of the target special equipment according to the equipment safety operation factors to obtain a set of equipment factor detection points.

[0070] A sensor group arrangement module 12, which is used to determine factor detection sensors according to the equipment safety operation factors, and arrange a sensor group for the set of equipment factor detection points according to the factor detection sensors to obtain a special equipment sensing module.

[0071] An associated sampling module 13, which is used to collect and obtain a special equipment fault data set, and perform associated sampling based on the target special equipment and the special equipment fault data set to obtain a target equipment fault data set.

[0072] The safety risk assessment tree construction module 14 is configured to extract fault features and perform safety risk assessment on the target device fault data set to obtain a device safety risk data set, and perform cascaded fusion on the device safety risk data set to generate a special equipment safety risk assessment tree.

[0073] The safety risk assessment module 15 is configured to monitor and collect multi-point operation data streams of special equipment through the special equipment perception module, and perform feature analysis and risk assessment on the multi-point operation data streams of special equipment by using the special equipment safety risk assessment tree to obtain a special equipment safety risk assessment coefficient.

[0074] Furthermore, the detection point parsing module 11 is further configured to perform the following steps: Obtain the structural distribution information of the target special equipment, perform three-dimensional modeling based on the structural distribution information to generate a special equipment spatial structure model; perform finite element mesh division on the special equipment spatial structure model to obtain an equipment spatial finite element mesh model, and perform regional structure marking on the equipment spatial finite element mesh model; perform associated structure mapping on the equipment spatial finite element mesh model with regional structure marking according to the equipment safe operation factors respectively to obtain an associated factor equipment structure set; perform key detection point analysis on the associated factor equipment structure set respectively to obtain the equipment factor detection point set.

[0075] Furthermore, the detection point parsing module 11 is further configured to perform the following steps: Perform uniform marking of detection points on the associated factor equipment structure set respectively to obtain an equipment factor structure optional detection point set; design test parameters and perform orthogonal arrangement of parameters respectively according to the equipment safe operation factors to obtain an equipment safe operation test scenario parameter table; perform test recording on the equipment factor structure optional detection point set based on the equipment safe operation test scenario parameter table to obtain an optional detection point test parameter set, where the optional detection point test parameter set includes detection sensitivity and detection accuracy; perform detection point optimization on the equipment factor structure optional detection point set according to the optional detection point test parameter set to obtain the equipment factor detection point set.

[0076] Furthermore, the associated sampling module 13 is further configured to perform the following steps: Classify the target special equipment according to its specification attributes and scenario attributes to obtain equipment specification attribute information and equipment application scenario attribute information; perform feature correlation matching between the equipment specification attribute information and the equipment application scenario attribute information and the special equipment failure data set to obtain a primary failure data set; traverse the primary failure data set to collect similar feature data in the special equipment failure data set to obtain a secondary failure data set; perform P-level similar data collection in the special equipment failure data set based on the secondary failure data set to obtain a P-level failure data set, where 2 ≤ P ≤ 5; hierarchically integrate the primary failure data set, the secondary failure data set, up to the P-level failure data set to obtain the target equipment failure data set.

[0077] Further, the safety risk assessment tree construction module 14 is further configured to perform the following steps: Extract failure features from the target equipment failure data set to obtain an equipment-associated failure feature set, where the equipment-associated failure feature set includes failure types, generation causes, and failure levels; perform associated operation feature extraction on the target equipment failure data set based on the equipment-associated failure feature set to obtain an equipment-associated multi-point operation feature set; perform safety risk assessment on the equipment-associated failure feature set according to the special equipment safety risk assessment standard to obtain an equipment safety risk assessment coefficient set; map and associate the equipment-associated failure feature set, the equipment-associated multi-point operation feature set, and the equipment safety risk assessment coefficient set to obtain the equipment safety risk data set.

[0078] Further, the safety risk assessment tree construction module 14 is further configured to perform the following steps: Perform failure level classification and associated topology analysis on the equipment-associated failure feature set to obtain an equipment failure cascade feature set; perform logical mapping association between the equipment-associated multi-point operation feature set and the equipment failure cascade feature set to obtain a failure judgment logic feature set; generate feature nodes based on the equipment failure cascade feature set and the failure judgment logic feature set to obtain an equipment failure feature recognition tree; perform risk assessment assignment on the equipment failure feature recognition tree based on the equipment safety risk assessment coefficient set to generate the special equipment safety risk assessment tree.

[0079] Further, the system further includes: Device leaf node feature information acquisition module, which is used to obtain device leaf node feature information according to the special equipment safety risk assessment tree; node influence degree analysis module, which is used to sequentially analyze the influence degree of the upper-level node on the device leaf node feature information to obtain device leaf node influence degree information; leaf node pruning instruction generation module, which is used to generate a leaf node pruning instruction if the device leaf node influence degree information does not reach the preset influence degree threshold; evaluation tree pruning and optimization module, which is used to prune and optimize the special equipment safety risk assessment tree based on the leaf node pruning instruction.

[0080] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0082] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A data analysis driven special equipment safety risk assessment method, characterized in that: The method comprises: Conducting a safety operation demand analysis on the target special equipment to obtain the equipment safety operation factors, and analyzing the detection points of the target special equipment according to the equipment safety operation factors to obtain a set of equipment factor detection points; Determine the factor detection sensor according to the equipment safe operation factor, and arrange the sensor group on the equipment factor detection point set according to the factor detection sensor to obtain the special equipment perception module; Acquire a special equipment fault data set, and perform correlation sampling based on the target special equipment and the special equipment fault data set to obtain a target equipment fault data set; Performing fault feature extraction and safety risk assessment on the target equipment fault data set to obtain an equipment safety risk data set, and performing cascade fusion on the equipment safety risk data set to generate a special equipment safety risk assessment tree; The special equipment sensing module is used to monitor and collect the multi-point operation data stream of special equipment, and the special equipment safety risk assessment tree is used to perform feature analysis and risk assessment on the multi-point operation data stream of special equipment to obtain the special equipment safety risk assessment coefficient.

2. A data analysis driven special equipment safety risk assessment method as claimed in claim 1, characterized in that: The obtaining of the equipment factor detection point set includes: Acquiring structural distribution information of the target special equipment, performing three-dimensional modeling based on the structural distribution information, and generating a spatial structural model of the special equipment; Performing finite element mesh division on the special equipment space structural model to obtain an equipment space finite element mesh model, and performing regional structure marking on the equipment space finite element mesh model; According to the equipment safety operation factors, the equipment space finite element mesh model marked with regional structures is respectively associated with structural mapping to obtain an associated factor equipment structure set; The key detection point analysis is performed on the associated factor equipment structure set respectively to obtain the equipment factor detection point set.

3. A data analysis driven special equipment safety risk assessment method as claimed in claim 2, characterized in that: The obtaining of the device factor detection point set includes: Uniformly marking the detection points of the associated factor equipment structure set respectively to obtain an optional detection point set of the equipment factor structure; According to the equipment safety operation factors, test parameter design and parameter orthogonal arrangement are performed respectively to obtain a parameter table of equipment safety operation test scenarios; Based on the equipment safety operation test scenario parameter table, the optional detection point set of the equipment factors is constructed to test and record, and an optional detection point test parameter set is obtained, wherein the optional detection point test parameter set includes detection sensitivity and detection accuracy; According to the optional detection point test parameter set, the optional detection point set of the equipment factor is constructed to perform detection point optimization to obtain the equipment factor detection point set.

4. A data analysis driven special equipment safety risk assessment method as claimed in claim 1, characterized in that: The step of obtaining a target device fault data set includes: Classifying the target special equipment by specification attributes and scene attributes to obtain equipment specification attribute information and equipment application scene attribute information; Performing feature correlation matching with the special equipment fault data set according to the equipment specification attribute information and the equipment application scenario attribute information to obtain a primary fault data set; Traversing the primary fault data set to collect similar feature data in the special equipment fault data set to obtain a secondary fault data set; Based on the secondary fault data set, P-level similar data collection is performed in the special equipment fault data set to obtain a P-level fault data set, where 2≤P≤5; The primary fault data set, the secondary fault data set, and even the P-level fault data set are hierarchically integrated to obtain the target device fault data set.

5. The data analysis driven special equipment safety risk assessment method according to claim 1, characterized in that: The obtaining of the equipment security risk data set includes: Extracting fault features from the target device fault data set to obtain a device-associated fault feature set, wherein the device-associated fault feature set includes a fault type, a generating cause, and a fault level; Based on the device-associated fault feature set, associated operation feature extraction is performed on the target device fault data set to obtain a device-associated multi-point operation feature set; Performing a safety risk assessment on the equipment-related fault feature set according to the special equipment safety risk assessment standard to obtain an equipment safety risk assessment coefficient set; The equipment-associated fault feature set, the equipment-associated multi-point operation feature set, and the equipment safety risk assessment coefficient set are mapped and associated to obtain the equipment safety risk data set.

6. A data analysis driven special equipment safety risk assessment method as claimed in claim 5, characterized in that: The generating of the special equipment safety risk assessment tree comprises: Performing fault level classification and associated topology analysis on the device-associated fault feature set to obtain a device fault cascade feature set; Logically mapping and associating the equipment-associated multi-point operation feature set and the equipment fault cascade feature set to obtain a fault judgment logic feature set; Generate feature nodes based on the equipment fault cascade feature set and the fault judgment logic feature set to obtain an equipment fault feature identification tree; Based on the equipment safety risk assessment coefficient set, risk assessment is assigned to the equipment fault feature identification tree to generate the special equipment safety risk assessment tree.

7. A data analysis driven special equipment safety risk assessment method as claimed in claim 6, characterized in that: The method comprises: According to the special equipment safety risk assessment tree, obtaining equipment leaf node feature information; Performing upper level node influence degree analysis on the device leaf node feature information in turn to obtain device leaf node influence degree information; If the influence information of the device leaf node does not reach the preset influence threshold, generating a leaf node pruning instruction; Based on the leaf node pruning instructions, the special equipment safety risk assessment tree is pruned and optimized.

8. A data analysis driven special equipment safety risk assessment system, characterized in that: The system comprises: A detection point analysis module, which is used to analyze the safety operation requirements of the target special equipment, obtain the equipment safety operation factors, analyze the detection points of the target special equipment according to the equipment safety operation factors, and obtain a set of equipment factor detection points; A sensor group deployment module, the sensor group deployment module is used to determine the factor detection sensor according to the safety operation factor of the equipment, and deploy the sensor group for the equipment factor detection point set according to the factor detection sensor to obtain the special equipment perception module; An associated sampling module, the associated sampling module is used to collect and obtain a special equipment fault data set, and perform associated sampling based on the target special equipment and the special equipment fault data set to obtain a target equipment fault data set; A safety risk assessment tree construction module, wherein the safety risk assessment tree construction module is used to extract fault features and conduct safety risk assessment on the target equipment fault data set, obtain an equipment safety risk data set, cascade-fuse the equipment safety risk data set, and generate a special equipment safety risk assessment tree; A safety risk assessment module is used to monitor and collect the multi-point operation data stream of special equipment through the special equipment perception module, use the special equipment safety risk assessment tree to perform feature analysis and risk assessment on the multi-point operation data stream of special equipment, and obtain the special equipment safety risk assessment coefficient.

Images