A safety risk monitoring method and system for crane operation scenarios
By detecting and analyzing the environmental and load parameters of crane operation scenarios, using sensor technology and data algorithms to monitor and warn in real time, the problem of slow response speed of traditional safety monitoring methods is solved, and efficient, accurate and real-time safety risks of crane operation are achieved. manage.
Patent Information
- Application Number
- CN202410788341.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-19
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-06-19
AI Technical Summary
The traditional crane safety monitoring method relies on manual inspection and post-event analysis, with slow response speed and poor prevention effect, making it difficult to meet the needs of modern industry for efficient, accurate and real-time safety monitoring, especially in large-scale engineering projects, high-altitude operations and heavy objects. In high-risk links such as lifting, there is a huge risk of casualties and property losses.
By detecting environmental parameters and load parameters of crane operation scenarios, obtaining environmental and load parameter information, setting thresholds, performing super-value screening and influencing analysis, configuring pre-detection and tracking monitoring parameters, and real-time monitoring using sensor technology and data analysis algorithms Key parameters to realize safety risk assessment and early warning of crane operations, including adjusting operation parameters, sending early warning information and cutting off control power.
Real-time safety risk assessment and early warning for crane operations is realized, the response speed and prevention effect of safety monitoring is improved, casualties and property losses are reduced, and the modern industry needs for efficient, accurate and real-time safety monitoring is met.
Smart Images

Figure CN118365143B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cranes, and in particular to a safety risk monitoring method and system for crane operation scenarios. Background Art
[0002] With the rapid development of modern industrial technology, crane operations play an indispensable role in many fields such as engineering construction, logistics and transportation, and equipment manufacturing. However, with the continuous expansion of the scale of crane operations and the increasing complexity of the operating environment, the safety risks of crane operations are also showing an increasing trend. Traditional crane safety monitoring methods often rely on manual inspections and post-analysis. This method has problems such as slow response speed and poor prevention effect, and it is difficult to meet the needs of modern industrial production for efficient, accurate, and real-time safety monitoring.
[0003] Especially in large-scale engineering projects, crane operations often involve high-risk links such as aerial operations and heavy lifting. Once a safety accident occurs, it will not only cause huge casualties and property losses, but also have a serious impact on the progress and quality of the project. Therefore, how to achieve real-time, efficient and accurate monitoring of the entire process of crane operations, and timely discover and warn potential safety risks has become an urgent problem to be solved in modern industrial production. Summary of the invention
[0004] The present application provides a safety risk monitoring method and system for crane operation scenarios, which are used to solve the technical problem that the existing technology is difficult to timely discover and warn of potential safety risks.
[0005] In view of the above problems, the present application provides a safety risk monitoring method and system for crane operation scenarios.
[0006] In a first aspect of the present application, a safety risk monitoring method for a crane operation scenario is provided, the method comprising:
[0007] Perform environmental parameter and load parameter detection on the crane operation scene to obtain environmental parameter information and load item parameter information; obtain environmental parameter thresholds and load parameter thresholds based on the crane equipment parameters and work records; use the environmental parameter thresholds and load parameter thresholds to perform over-value screening on the environmental parameter information and load item parameter information to obtain an environmental over-threshold range and a load over-threshold range, wherein the over-threshold range is used to characterize the data range in which the environmental parameter and the load parameter exceed the standard parameter threshold; perform influence analysis on the crane components according to the environmental over-threshold range and the load over-threshold range, and match the safety risk events according to the influence of each crane component; configure pre-detection parameters and tracking monitoring parameters according to the safety risk events and the corresponding crane risk components, wherein the crane is pre-operation risk detected and predicted and evaluated according to the pre-detection parameters, the crane is monitored during the operation according to the tracking monitoring parameters, and risk prediction is performed according to the risk monitoring information during the operation and the pre-operation risk detection information is integrated; based on the risk monitoring information during the operation and the risk prediction results, adaptive control is performed according to a preset adaptive list, and the adaptive control includes adjusting the operation parameters, sending early warning information, and cutting off the control power supply.
[0008] A second aspect of the present application provides a safety risk monitoring system for crane operation scenarios, the system comprising:
[0009] a parameter collection unit, wherein the parameter collection unit detects the environmental parameters and load parameters of the crane operation scene to obtain environmental parameter information and load item parameter information; a parameter threshold acquisition unit, wherein the parameter threshold acquisition unit obtains the environmental parameter threshold and the load parameter threshold based on the crane equipment parameters and the work record; an over-value screening unit, wherein the over-value screening unit uses the environmental parameter threshold and the load parameter threshold to perform over-value screening on the environmental parameter information and the load item parameter information to obtain an environmental over-threshold range and a load over-threshold range, wherein the over-threshold range is used to characterize the data range in which the environmental parameters and the load parameters exceed the standard parameter threshold; an impact analysis unit, wherein the impact analysis unit performs a crane impact analysis based on the environmental over-threshold range and the load over-threshold range. An impact analysis of components is performed to match safety risk events according to the impact of each crane component; a risk prediction unit is configured with pre-detection parameters and tracking and monitoring parameters according to the safety risk events and the corresponding crane risk components, wherein risk detection and prediction evaluation are performed on the crane before operation according to the pre-detection parameters, the operation process of the crane is monitored according to the tracking and monitoring parameters, and risk prediction is performed based on the risk monitoring information during operation and the pre-operation risk detection information; an adaptive control unit is performed according to a preset adaptive list based on the risk monitoring information during operation and the risk prediction results, and the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power.
[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0011] The present application detects environmental parameters and load parameters of crane operation scenarios to obtain environmental parameter information and load item parameter information; obtains environmental parameter thresholds and load parameter thresholds based on crane equipment parameters and work records; uses environmental parameter thresholds and load parameter thresholds to perform over-value screening on environmental parameter information and load item parameter information to obtain environmental over-threshold ranges and load over-threshold ranges, wherein the over-threshold ranges are used to characterize the data ranges in which environmental parameters and load parameters exceed standard parameter thresholds; performs influence analysis on crane components based on environmental over-threshold ranges and load over-threshold ranges, and matches safety risk events according to the influence of each crane component; configures pre-detection parameters and tracking monitoring parameters based on safety risk events and corresponding crane risk components, wherein pre-operation risk detection and predictive evaluation are performed on the crane based on pre-detection parameters, operation process monitoring is performed on the crane based on tracking monitoring parameters, and risk prediction is performed based on risk monitoring information during operation and integrated with pre-operation risk detection information; based on risk monitoring information during operation and risk prediction results, adaptive control is performed according to a preset adaptive list, and the adaptive control includes adjusting operation parameters, sending early warning information, and cutting off control power. The present invention solves the technical problem that the prior art is difficult to detect and warn of potential safety risks in a timely manner. By integrating sensor technology and data analysis algorithms, the key parameters of the crane operation process are monitored in real time, thereby achieving the technical effect of real-time assessment and warning of crane operation safety risks. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0013] Figure 1 A schematic flow chart of a safety risk monitoring method for crane operation scenarios provided in an embodiment of the present application;
[0014] Figure 2 A schematic diagram of the structure of a safety risk monitoring system for crane operation scenarios provided in an embodiment of the present application.
[0015] Explanation of the reference numerals: parameter collection unit 11 , parameter threshold acquisition unit 12 , overvalue screening unit 13 , influence analysis unit 14 , risk prediction unit 15 , adaptive control unit 16 . DETAILED DESCRIPTION
[0016] This application provides a safety risk monitoring method and system for crane operation scenarios, aiming to solve the technical problem that the existing technology is difficult to timely detect and warn of potential safety risks. By integrating sensor technology and data analysis algorithms, key parameters in the crane operation process are monitored in real time, thereby achieving the technical effect of real-time assessment and warning of crane operation safety risks.
[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0018] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.
[0019] Embodiment 1
[0020] like Figure 1 As shown, the present application provides a safety risk monitoring method for crane operation scenarios, the method comprising:
[0021] Step S100: Detect environmental parameters and load parameters of the crane operation scene to obtain environmental parameter information and load item parameter information;
[0022] In the embodiment of the present application, when detecting environmental parameters and load parameters of the crane operation scene, an anemometer is used to measure the wind speed and direction of the operation site. A temperature and humidity sensor is used to monitor the temperature and humidity of the operation environment. A weight sensor, such as a load sensor, is used to measure the weight of the load. A measuring tool, such as a laser rangefinder, is used to determine the size and shape of the load.
[0023] Through the above process, environmental parameter information and load parameter information are obtained. Environmental parameter information includes wind speed, wind direction, temperature, humidity, etc. Load parameter information includes weight, size, shape and stability of the load.
[0024] Step S200: obtaining environmental parameter thresholds and load parameter thresholds based on the lifting equipment parameters and work records;
[0025] In an embodiment of the present application, the crane equipment parameters are obtained by querying the technical manual according to the crane model, and performance data directly related to environmental conditions, such as the operating temperature range, the maximum allowable wind speed, etc., are obtained from the crane equipment parameters. Then, based on the historical work records of the crane, operational problems or accidents caused by environmental factors, such as strong winds, extreme temperatures, etc., are obtained, and the environmental parameter values where the accidents occurred are extracted. Next, based on the equipment parameters and work records, the environmental parameter thresholds are set. For example, when the maximum wind speed allowed in the crane equipment parameters is 15m / s, and the work records indicate that an accident occurs when the wind speed exceeds 13.5m / s, the wind speed of 13.5m / s is set as the parameter threshold.
[0026] According to the model of the crane, check the technical manual to determine the crane's rated lifting capacity, maximum lifting height and other key parameters. Next, obtain the load parameter values when operating problems or accidents caused by overloading based on the work records. Set the load parameter threshold based on the equipment parameters and work records. When setting the load parameter threshold, set a safety margin below the rated lifting capacity based on historical data to prevent overloading. For example, set the maximum allowable load of the crane to a certain percentage of its rated lifting capacity, such as 90%. For a crane with a rated lifting capacity of 10t, the maximum allowable load is 9t.
[0027] Step S300: Using the environmental parameter threshold and the load parameter threshold to perform over-value screening on the environmental parameter information and the load item parameter information, and obtain an environmental over-threshold range and a load over-threshold range, wherein the over-threshold range is used to characterize the data range in which the environmental parameter and the load parameter exceed the standard parameter threshold;
[0028] In an embodiment of the present application, first, the environmental parameter information obtained in real time is compared with the set environmental parameter threshold. If the real-time wind speed exceeds the set wind speed threshold, it is determined that the wind speed is in the over-threshold range. The wind speed threshold is subtracted from the real-time wind speed to obtain the wind speed over-threshold range. Compare whether the real-time temperature is between the set minimum and maximum temperature thresholds. If the real-time temperature is lower than the minimum threshold or higher than the maximum threshold, it is determined that the temperature is in the over-threshold range. The absolute value after subtracting the temperature threshold from the real-time temperature is taken as the temperature over-threshold range.
[0029] The real-time acquired load parameter information, such as load weight, is compared with the set load parameter threshold. For example, when the real-time load weight exceeds the set maximum allowable load, it is determined that the load weight is in the over-threshold range. And through subtraction calculation, the weight over-threshold range is obtained.
[0030] Through the above process, the environmental threshold exceeding range and the load threshold exceeding range are obtained. The environmental threshold exceeding range includes the wind speed threshold exceeding range, the temperature threshold exceeding range, etc. The load threshold exceeding range includes the weight threshold exceeding range, etc.
[0031] Step S400: performing an influence analysis of crane components according to the environment exceeding threshold range and the load exceeding threshold range, and matching safety risk events according to the influence of each crane component;
[0032] In the embodiment of the present application, the influence analysis of crane components is performed according to the environmental threshold range. For example, when the wind speed is too high, the crane boom, tower, wire rope, etc. are affected, resulting in the crane overturning, boom breaking, wire rope breaking, etc. When the wind speed exceeds the threshold, the crane boom and tower may overturn or break due to uneven force; at the same time, the wire rope may break due to the swing and stretching under the action of wind.
[0033] The impact analysis of crane components is carried out according to the load exceeding threshold range. For example, when overloaded, the crane hook, wire rope, pulley block, motor, etc. are affected. This may lead to hook breakage, wire rope breakage, pulley block damage, motor overload, etc. When overloaded, the crane components will be subjected to loads exceeding the design limit, which will lead to serious consequences such as hook breakage and wire rope breakage; at the same time, the motor will be damaged due to overload, and the pulley block will be damaged due to long-term excessive load.
[0034] Based on the above impact analysis, the impact of different over-threshold ranges on crane components is clarified, and the corresponding safety risk events are matched.
[0035] Step S500: According to the safety risk event and the corresponding crane risk element, pre-detection parameters and tracking monitoring parameters are configured, wherein the crane is subjected to pre-operation risk detection and prediction evaluation according to the pre-detection parameters, the crane is subjected to operation process monitoring according to the tracking monitoring parameters, and risk prediction is performed according to the risk monitoring information during the operation and the pre-operation risk detection information;
[0036] In the embodiment of the present application, pre-detection parameters and tracking monitoring parameters are configured according to the safety risk events and the corresponding crane risk elements.
[0037] Configuring pre-detection parameters includes configuring environmental detection parameters, load detection parameters, and equipment component detection parameters. Configuring environmental detection parameters includes setting the wind speed threshold not to exceed the wind speed threshold, for example, not to exceed 30m / s. Setting the minimum and maximum temperature thresholds, such as -20℃ to 50℃. Setting the humidity threshold, such as not to exceed 85%RH. Configuring load detection parameters includes setting the rated load according to the crane model, such as 10t or 20t. Setting the safe load rate to 90% of the rated load, for example, a 10t rated load exceeding 9t is considered high risk. Configuring equipment component detection parameters includes detecting the degree of wear of the hook, if the wear exceeds 10%, it needs to be replaced. Detecting the number of broken wires in the wire rope, if the number of broken wires exceeds 10%, it needs to be replaced.
[0038] At the same time, configure the tracking and monitoring parameters, which include the operating process environmental parameters, operating process load parameters and equipment component operating status. The operating process environmental parameters include real-time monitoring of changes in environmental parameters such as wind speed, temperature, and humidity. Set abnormal change thresholds, such as a sudden increase in wind speed exceeding 5m / s. The operating process load parameters include real-time monitoring of load weight, load rate and other parameters. Set the alarm threshold when the load rate exceeds 90%. The operating status of equipment components includes real-time monitoring of key components' temperature, vibration, sound and other operating parameters. Set thresholds for abnormal operating parameters, such as reducer temperature exceeding 80°C.
[0039] When performing risk detection on cranes before operation based on pre-detection parameters, the real-time environmental parameters are compared with the set thresholds to determine whether the environment has an impact on crane operations. When the threshold is exceeded, it is determined that there is an impact on crane operations. When performing load risk assessment, determine whether the load of the upcoming operation exceeds the safe load rate. When performing risk assessment on equipment components, the integrity and reliability of the equipment components are evaluated based on the pre-detection parameters, that is, whether the threshold of the equipment original component detection parameters is exceeded.
[0040] The crane operation process is monitored according to the tracking monitoring parameters, and wind speed change monitoring, load change monitoring and equipment failure monitoring are carried out. When risk prediction is carried out based on the risk monitoring information during the operation and combined with the risk detection information before the operation, the real-time monitoring data during the operation is processed to identify abnormal situations and potential risks. The current data is compared with the historical data to find out the risk occurrence patterns and trends under similar situations.
[0041] Based on historical data and current data, a risk prediction model is constructed. The risk prediction model is trained based on the convolutional neural network using the historical accident data of cranes. The historical accident data of cranes contains detailed information such as the cause of the accident and the type of accident. When training the risk prediction model, the historical accident data of cranes is divided into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the model parameters and prevent overfitting, and the test set is used to evaluate the generalization ability of the model. In supervised learning, each training sample has a known output label. In this case, the output label is the probability of an accident or the risk level. For the historical accident data of cranes, the labels are binary, such as an accident or no accident, or multi-classified, such as different accident types or risk levels. Labels are usually manually annotated by domain experts based on the accident data. Before starting training, initialize the parameters of the model, such as weights and bias terms. These parameters are randomly initialized.
[0042] Input the input data in the training set into the model, and obtain the predicted value through the calculation of the model, which is the forward propagation process. In this case, the input data is the risk monitoring information in the current operation of the crane, and the output is the predicted probability of accident occurrence or risk level. Compare the predicted value with the true label and calculate the loss function, such as the value of cross entropy loss or mean square error loss. The gradient of the loss function to the model parameters is calculated by the back propagation algorithm, and the parameters of the model are updated according to the gradient descent algorithm. During the training process, the validation set is used to monitor the performance of the model, and the parameters or structure of the model are adjusted according to the validation results. When the model training is completed, the performance of the model is evaluated using the test set. Common evaluation indicators include accuracy, recall rate, F1 score, etc. The construction of the risk prediction model is completed through the above process.
[0043] Risk prediction is carried out by using the constructed risk prediction model and combining it with the risk monitoring information in the current operation.
[0044] Step S600: Based on the risk monitoring information and risk prediction results in the operation, adaptive control is performed according to a preset adaptive list, and the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power.
[0045] In the embodiment of the present application, the risk prediction result is compared with the preset adaptive list. The adaptive list contains a series of preset risk levels, control measures and response actions. According to the comparison result, the corresponding control measure is selected for execution.
[0046] When potential risks are predicted, the operating parameters are automatically adjusted to reduce the risks, for example, reducing the lifting speed of the crane, limiting the rotation angle or adjusting the load distribution.
[0047] When the risk level reaches a certain level, an early warning message is automatically sent to the operator or relevant personnel. The early warning message is sent through sound and light alarms, display screens, or push notifications on mobile devices. The early warning message contains risk type, risk level, etc.
[0048] When the risk level is extremely high or an emergency occurs, the control power supply of the crane is automatically cut off.
[0049] Furthermore, step S100 in the method provided in the application embodiment also includes:
[0050] Acquire abnormal crane events, perform correlation impact fitting of environmental impact parameters, load impact parameters and abnormal events according to the abnormal crane events, and determine environmental impact indicators and load impact indicators;
[0051] According to the environmental impact index and the load impact index, detection equipment is set up, and the environmental parameters and load parameters in the crane operation scene are respectively collected by the detection equipment to collect the environmental impact index and the load impact index data, so as to obtain the environmental collection data and the load collection data;
[0052] Preprocessing the collected environmental data and load data, including denoising, abnormal data screening, and missing data supplementation;
[0053] The environmental parameter information and the load item parameter information are obtained according to the pre-processed environmental collection data and the load item collection data.
[0054] In the embodiment of the present application, abnormal crane events are obtained from the crane historical accident database, including abnormal events such as over-temperature, over-speed, and excessive vibration.
[0055] When fitting the correlation effects of environmental impact parameters, load impact parameters and abnormal events based on abnormal events of cranes, statistical analysis methods such as correlation analysis and regression analysis are used to compare abnormal event data with environmental parameters and load parameters of the same period to explore the potential correlation between these parameters. Use correlation analysis to determine which environmental parameters have a significant correlation with abnormal events. Set a correlation threshold, such as 0.7, and parameters exceeding this threshold are considered environmental impact parameters that have a significant impact on abnormal events. Use a similar correlation analysis method to determine which load parameters have a significant correlation with abnormal events. Set the same threshold to determine the load impact parameters that have a significant impact on abnormal events. Based on the correlation analysis, determine the environmental impact indicators and load impact indicators.
[0056] Next, detection equipment is set up according to the environmental impact indicators and load impact indicators. The detection equipment includes wind speed and direction sensors, temperature and humidity sensors, air quality monitors, load sensors, etc. Data is collected through the set detection equipment to obtain environmental collection data and load collection data.
[0057] When preprocessing the collected environmental data and load data, digital filtering techniques such as low-pass filters and band-pass filters are used to denoise the collected raw data. Statistical methods such as box plots and Z-score methods are used to identify and eliminate outliers. For missing data that may appear during data collection, interpolation methods such as linear interpolation and polynomial interpolation are used to supplement them.
[0058] The preprocessed data set will be used to extract environmental parameter information and load parameter information, which include real-time environmental data such as wind speed, temperature, humidity, and load data such as load weight and lifting speed.
[0059] Furthermore, the application embodiment also includes:
[0060] The environmental impact indicators include temperature, humidity, interfering electromagnetic waves, air particles, wind speed intensity, and road surface flatness; the load impact indicators include weight, volume, and length.
[0061] In the embodiment of the present application, in the crane operation environment, environmental impact indicators and load impact indicators are key factors to ensure safe operation. Environmental impact indicators include temperature, humidity, interference electromagnetic waves, air particles, wind speed intensity, and road surface flatness. Load impact indicators include weight, volume, and length.
[0062] Furthermore, the influence of crane components is analyzed according to the environmental over-threshold range and the load over-threshold range, and the safety risk events are matched according to the influence of each crane component. The application embodiment also includes:
[0063] According to the abnormal event of the crane, the abnormal event is regarded as the top event;
[0064] Starting from the top event, using the principle of the accident tree analysis algorithm, the top event is decomposed based on the abnormal event of the crane to determine the intermediate event, where the intermediate event is the cause event that causes the top event and is used to characterize the component failure existing in the crane;
[0065] According to the abnormal event of the crane, the intermediate event is decomposed to obtain abnormal factors, where the abnormal factors are parameter indicators that cause the intermediate event, including environmental parameters and load parameters, and the influence relationship between the abnormal factors and the intermediate event is fitted using the sample data of the abnormal event of the crane to obtain an influence function relationship;
[0066] Based on the influence relationship among the top events, intermediate events and abnormal factors, a logic gate relationship is constructed, and the influence function relationship is added to construct an influence analysis module;
[0067] The impact analysis module is used to perform an intermediate event impact analysis on the environmental over-threshold range and the load over-threshold range, and a top event probability analysis is performed based on the intermediate event impact to obtain the abnormal impact relationship of the crane components and the corresponding safety risk events.
[0068] In the embodiment of the present application, the abnormal event of the crane is the overturning of the crane, etc. The overturning of the crane is regarded as the top event.
[0069] Using the causal analysis method, starting from the crane capsizing event, all possible causes that may have led to the capsizing were analyzed. These causes were further confirmed through expert interviews, and the causes that can be analyzed independently, such as outrigger instability, overloading, and excessive wind speed, were identified as intermediate events.
[0070] For each intermediate event, FMEA is used to analyze and find out the specific parameters or conditions that cause it, such as insufficient soil bearing capacity of the outriggers, load exceeding the design limit, wind speed exceeding the safety threshold, etc. These specific parameters or conditions are regarded as abnormal factors.
[0071] When fitting the influencing function relationship, collect historical data related to abnormal factors and intermediate events, including fault records, environmental monitoring data, load data, etc. Statistical analysis methods are used to calculate the correlation coefficient between abnormal factors and intermediate events through correlation analysis to evaluate the degree of correlation between them. Use statistical software such as SPSS to perform Pearson correlation analysis to obtain the correlation coefficient and significance level.
[0072] When performing regression analysis, select an appropriate regression model, such as linear regression, polynomial regression, etc., to fit the relationship between abnormal factors and intermediate events based on historical data. Use methods such as the least squares method to estimate the parameters in the regression model.
[0073] According to the characteristics of the data and the requirements of the problem, select an appropriate function form to fit the relationship between the abnormal factor and the intermediate event. For example, for the relationship between the soil bearing capacity of the outrigger and the instability of the outrigger, select a linear function or a logarithmic function for fitting. Using the results of the regression analysis, estimate the parameters in the selected function, and use statistical software such as Excel, R, Python, etc. for parameter estimation and model fitting. Specifically, for the relationship between the soil bearing capacity of the outrigger and the instability of the outrigger, assume that 10 sets of historical data on the soil bearing capacity of the outrigger and the probability of outrigger instability are collected, and a linear regression analysis is performed on these data, and the intercept term is 0.2 and the slope term is -0.02, and a linear regression model is obtained, in which the probability of outrigger instability is equal to 0.2 plus the product of -0.02 and the soil bearing capacity of the outrigger.
[0074] According to the logical relationship between the intermediate events and the abnormal factors, the corresponding logic gates are added to the accident tree, such as AND gates, OR gates, etc. The fitted influence function is integrated into the accident tree to ensure the association between the logic gate and the influence function. Finally, a computable analysis module is constructed, which calculates the probability of occurrence of intermediate events and top events according to the input abnormal factor value.
[0075] When using the impact analysis module to analyze the impact of environmental threshold exceeding ranges and load threshold exceeding ranges on intermediate events, first identify the environmental parameters that affect the operation of the crane, such as temperature, humidity, wind speed, etc. When these parameters exceed the set thresholds, they are considered abnormal. Next, analyze how these environmental parameter threshold exceeding ranges affect the various systems of the crane. For example, high temperature causes electrical components to overheat, which in turn causes electrical system failures. Use the impact analysis module to quantitatively evaluate the impact of environmental threshold exceeding ranges on intermediate events. For example, for every 10°C increase in temperature, the probability of electrical system failure increases by 2%.
[0076] Similarly, identify the load parameters that affect the crane, such as weight, size, etc. When these parameters exceed the design load capacity of the crane, it is considered to be a load overload. Load overload may cause mechanical system overload, such as damage to components such as hooks and wire ropes. Through the impact analysis module, evaluate the impact of load overload on intermediate events such as mechanical system overload. For example, for every 10% overweight of the load, the probability of mechanical system overload may increase by 3%.
[0077] Use logic gates to connect intermediate events with top events. For example, electrical system failure and control system failure may be in an AND gate relationship, while mechanical system failure and structural system deformation may be in an OR gate relationship. Based on the probability of intermediate events and the logic gate relationship, the probability of occurrence of top events is calculated using probability theory and mathematical statistics methods. Assume that the probability of electrical system failure is P1, the probability of control system failure is P2, the probability of mechanical system failure is P3, and the probability of structural system deformation is P4. Then the probability of top events is calculated based on the logic gate relationship.
[0078] Through the above analysis, the abnormal influence relationship between crane components and environmental parameters and load parameters is obtained. Based on the abnormal influence relationship, the corresponding safety risk events are identified. For example, overheating of electrical components in a high temperature environment may cause a fire, and damage to mechanical components under overload may cause the hanging object to fall.
[0079] Furthermore, based on the pre-detection parameters, the crane is subjected to risk detection and prediction assessment before operation, and the application embodiment also includes:
[0080] When the pre-detection parameter is a metal structure parameter, ultrasonic detection of the target element is performed by ultrasonic wave to obtain a real-time ultrasonic detection data set, wherein the real-time ultrasonic detection data set includes ultrasonic detection of different target elements;
[0081] Extract the waveform of real-time ultrasonic detection data, perform reflection echo feature analysis on the ultrasonic waveform, and obtain real-time waveform anomaly analysis results;
[0082] When the real-time waveform abnormality analysis result reaches a preset threshold, a reminder message is sent;
[0083] When the real-time waveform abnormality analysis result does not reach a preset threshold, extracting historical ultrasonic detection data based on the target element;
[0084] Classify the target components, align the real-time waveform abnormality analysis results of each component with the historical ultrasonic detection data in time series, fit the real-time-historical waveform relationship, and obtain the abnormal waveform change and abnormal signal reception time;
[0085] According to the real-time waveform abnormality analysis results, abnormal waveform changes and abnormal signal reception time, abnormal defect identification and abnormal trend prediction are performed to obtain the pre-operation risk detection information.
[0086] In an embodiment of the present application, when the pre-detection parameter is a metal structure parameter, an ultrasonic device is used to scan the target element to obtain a real-time ultrasonic detection data set. This data set contains ultrasonic detection data of different target elements. Using digital signal processing technology, the waveform signal of the ultrasonic wave is extracted from the real-time ultrasonic detection data set. Feature extraction and pattern recognition are performed on the extracted ultrasonic waveform, and by comparing the characteristic parameters of the waveform signal, such as amplitude, frequency, phase, etc., with the reference waveform in a normal or defective state, it is determined whether there is an abnormal waveform. Defects in the metal structure, such as cracks, inclusions, etc., are identified by analyzing the characteristics of the reflected echo. One or more thresholds are set by technical experts based on historical data to determine whether the real-time waveform abnormality analysis results reach a preset warning level. When the real-time waveform abnormality analysis results reach a preset threshold, it indicates that there are obvious defects or abnormalities in the target element. At this time, a reminder message is sent to the operator or maintenance personnel through sound and light alarms, SMS notifications, etc.
[0087] When the real-time waveform anomaly analysis result does not reach the preset threshold, the historical ultrasonic inspection data of the target component is retrieved from the database. According to the timestamp or inspection order, the real-time waveform anomaly analysis result is aligned with the historical ultrasonic inspection data in time series. The real-time data and historical data are fitted using mathematical statistical methods, such as time series analysis, to establish a real-time-historical waveform relationship model. By analyzing the fitted real-time-historical waveform relationship, the abnormal waveform changes and the reception time of the abnormal signal are identified. Abnormal waveform changes are manifested as sudden changes in parameters such as amplitude, frequency, and phase, or fluctuations that do not conform to normal patterns. By comparing the real-time waveform and the historical waveform, the time point when these abnormal changes occur, that is, the reception time of the abnormal signal, is determined.
[0088] During the abnormal defect identification process, the real-time waveform is compared with a library of known defect waveform patterns, and pattern recognition algorithms such as template matching and dynamic time warping are used to identify whether known defect types exist. Next, key information such as peaks, troughs, and frequency components are extracted from the real-time waveform through digital signal processing technology. These features are classified using machine learning algorithms such as support vector machines to determine whether there are abnormal defects. The machine learning model is pre-trained and trained using historical waveform data related to the task, which contains normal waveforms and abnormal waveforms. The training enables the model to judge the abnormal state of the waveform based on the features. Once the waveform anomaly is identified, the specific features of the waveform are further analyzed, such as the location and intensity of the reflected wave. These features are used to locate the position of the defect in the metal structure.
[0089] When predicting abnormal trends, time series analysis methods such as ARIMA model and exponential smoothing are used to model historical data to predict future waveform changes.
[0090] Finally, the abnormal defect identification results and abnormal trend prediction results are integrated to obtain pre-operation risk detection information.
[0091] Further, risk prediction is performed based on the risk monitoring information during the operation and the risk detection information before the operation. The application embodiment also includes:
[0092] Acquire abnormal defect identification information and abnormal trend prediction information based on the pre-operation risk detection information;
[0093] Performing an impact analysis using the risk monitoring information during the operation and the abnormal defect identification information to obtain an abnormal defect impact coefficient;
[0094] The abnormal trend prediction information is adjusted according to the abnormal defect impact coefficient to obtain the risk prediction result, which includes: performing time series decomposition according to the abnormal defect identification information and the abnormal trend prediction information, constructing an abnormal analysis time series chain, using the abnormal defect impact coefficient as a time series compensation coefficient, performing abnormal cumulative prediction in the order of the time series chain, and obtaining the prediction information of each time series as the risk prediction result.
[0095] In the embodiment of the present application, before starting risk prediction, firstly, abnormal defect identification information and abnormal trend prediction information are extracted from the pre-operation risk detection information. The abnormal defect identification information includes the type, location, severity, etc. of the identified abnormal defect. The abnormal trend prediction information includes the probability of abnormal occurrence, time range, etc.
[0096] Collect and analyze risk monitoring data in operation in real time, such as equipment status, environmental conditions, etc. Statistical analysis is used to combine abnormal defect identification information and risk monitoring information in operation to calculate the influence coefficient of abnormal defects on risk prediction results. When using statistical analysis to calculate the influence coefficient of abnormal defects, a prediction model is established through regression analysis, variance analysis, etc., which can describe the relationship between abnormal defects and risk prediction results. The abnormal defect identification information is used as the independent variable, and the risk prediction result is used as the dependent variable. Next, historical data is used to fit the statistical model through an iterative optimization algorithm, such as the gradient descent method. From the parameters of the statistical model, the influence coefficient of abnormal defects on the risk prediction results is extracted. For example, in the regression model, the regression coefficient corresponding to the severity of a certain abnormal defect is regarded as the abnormal defect influence coefficient of the abnormal defect on the risk prediction result. The abnormal defect influence coefficient reflects the degree and method of the influence of the abnormal defect on the risk prediction result, and the size and direction of its value determine the adjustment direction and amplitude of the prediction result.
[0097] Decompose the abnormal defect identification information and abnormal trend prediction information in chronological order to construct an abnormal analysis time series chain. Each node of the time series chain represents a time series point, which contains the prediction information and abnormal defect information of the time series point. According to the order of the time series chain, the prediction information of each time series point is accumulated and predicted. In the accumulation process, the abnormal defect impact coefficient is used as the time series compensation coefficient to compensate and adjust the prediction information.
[0098] Finally, the results of the cumulative prediction of the time series are summarized to generate the prediction information of each time series point. The prediction information includes the probability of risk occurrence, time range, severity, etc. The prediction information of each time series is used as the risk prediction result.
[0099] Further, based on the risk monitoring information and risk prediction results in the operation, adaptive control is performed according to a preset adaptive list, and the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power. The application embodiment also includes:
[0100] According to the accident consequences and response time of the abnormal event of the crane, configure multi-level safety risk events;
[0101] According to the multi-level security risk events, an adaptive list is set, which includes security risk events, predicted probabilities, detection / monitoring data, and adaptive controls;
[0102] The risk monitoring information and risk prediction results in the operation are matched with the detection / monitoring data, safety risk events and their predicted probabilities respectively to obtain matching adaptive control, wherein the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power supply;
[0103] When the adaptive control is a warning message or a control power supply is cut off, an execution message is generated for executing the sending of the warning message or the cutting off of the control power supply;
[0104] When the adaptive control is to adjust the operating parameters, the control parameter safety adjustment target analysis is performed according to the detection / monitoring data and risk prediction results, the parameter compensation target is obtained, and the adjustment control is performed based on the parameter compensation target.
[0105] In an embodiment of the present application, multi-level safety risk events are defined and configured according to the accident consequences and response time of abnormal events of the crane. These events can be graded based on severity, urgency, and possible consequences. For example, they are divided into level one safety risk events, level two safety risk events, and level three safety risk events. Level one safety risk events are abnormal situations that cause serious casualties or major damage to equipment and require immediate response, such as wire rope breakage, failure of major load-bearing components, etc. Level two safety risk events are abnormal situations that cause moderate losses or injuries to personnel, but do not require immediate cessation of operations, such as excessive wind speed, electrical system abnormalities, and reduced performance of the braking system. Level three safety risk events are abnormal situations that cause minor losses or do not affect normal operations, but still require attention and processing, such as lubrication system warnings, sensor failures, etc.
[0106] Next, set up an adaptive list for each level of security risk events. This list contains security risk events, predicted probabilities, detection / monitoring data, and adaptive controls. Security risk events clearly describe the type of abnormal event. The predicted probability is based on historical data and real-time data to predict the probability of the abnormal event. Detection / monitoring data is used to monitor and detect data sources for abnormal events, such as sensor readings, video surveillance, etc. Adaptive control is the adaptive control measures taken according to abnormal situations, such as adjusting operating parameters, sending warning information, and cutting off control power.
[0107] The risk monitoring information and risk prediction results in the operation are used to match the detection / monitoring data, safety risk events and their predicted probabilities in the adaptive list. Once the match is successful, the corresponding adaptive control is triggered.
[0108] When adaptive control sends warning information, it generates a warning containing information such as abnormal event type, risk level, and recommended response measures, and notifies relevant personnel through appropriate means such as SMS, email, system pop-up window, etc. For serious level 1 safety risk events, the control power supply of the crane is immediately cut off to prevent the accident from expanding.
[0109] When the adaptive control is to adjust the operating parameters, the control parameter safety adjustment target analysis is performed based on the detection / monitoring data and risk prediction results. When performing the control parameter safety adjustment target analysis, a large amount of historical data is first collected, including the crane operating parameters and performance under different wind speeds, loads, temperatures and other conditions. The collected historical data is preprocessed, including data cleaning and standardization. Continuous variables such as wind speed and load are fuzzy processed and divided into different fuzzy sets. For example, the threshold of wind speed is set to 0-30m / s, and divided into three fuzzy sets of low wind speed, medium wind speed and high wind speed. Low wind speed is 0-10m / s, medium wind speed is 10-20m / s, and high wind speed is 20-30m / s.
[0110] Next, based on historical data and expert knowledge, technical experts establish fuzzy rules. Fuzzy rules describe how to adjust control parameters under different fuzzy sets, such as reducing speed, adjusting working range, etc.
[0111] Finally, the real-time monitored data is fuzzified and matched with the fuzzy set in the fuzzy control strategy table. According to the matching results, the corresponding control parameter adjustment strategy is selected from the fuzzy control strategy table, that is, the parameter compensation target is obtained, and the control is adjusted through the parameter compensation target.
[0112] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:
[0113] The present application detects environmental parameters and load parameters of crane operation scenarios to obtain environmental parameter information and load item parameter information; obtains environmental parameter thresholds and load parameter thresholds based on crane equipment parameters and work records; uses environmental parameter thresholds and load parameter thresholds to perform over-value screening on environmental parameter information and load item parameter information to obtain environmental over-threshold ranges and load over-threshold ranges, wherein the over-threshold ranges are used to characterize the data ranges in which environmental parameters and load parameters exceed standard parameter thresholds; performs influence analysis on crane components based on environmental over-threshold ranges and load over-threshold ranges, and matches safety risk events according to the influence of each crane component; configures pre-detection parameters and tracking monitoring parameters based on safety risk events and corresponding crane risk components, wherein pre-operation risk detection and predictive evaluation are performed on the crane based on pre-detection parameters, operation process monitoring is performed on the crane based on tracking monitoring parameters, and risk prediction is performed based on risk monitoring information during operation and integrated with pre-operation risk detection information; based on risk monitoring information during operation and risk prediction results, adaptive control is performed according to a preset adaptive list, and the adaptive control includes adjusting operation parameters, sending early warning information, and cutting off control power. The present invention solves the technical problem that the prior art is difficult to detect and warn of potential safety risks in a timely manner. By integrating sensor technology and data analysis algorithms, the key parameters of the crane operation process are monitored in real time, thereby achieving the technical effect of real-time assessment and warning of crane operation safety risks.
[0114] Embodiment 2
[0115] Based on the same inventive concept as the safety risk monitoring method for crane operation scenarios in the aforementioned embodiment, Figure 2 As shown, the present application provides a safety risk monitoring system for crane operation scenarios, and the system and method embodiments in the present application embodiments are based on the same inventive concept. The system includes:
[0116] A parameter collection unit 11, wherein the parameter collection unit 11 detects environmental parameters and load parameters of the crane operation scene to obtain environmental parameter information and load item parameter information;
[0117] A parameter threshold value acquisition unit 12, wherein the parameter threshold value acquisition unit 12 acquires an environmental parameter threshold value and a load parameter threshold value based on the lifting device parameters and the working record;
[0118] An over-value screening unit 13, wherein the over-value screening unit 13 uses the environmental parameter threshold and the load parameter threshold to perform over-value screening on the environmental parameter information and the load item parameter information to obtain an over-threshold range of the environment and the load, wherein the over-threshold range is used to characterize a data range in which the environmental parameter and the load parameter exceed the standard parameter threshold;
[0119] An influence analysis unit 14, wherein the influence analysis unit 14 performs influence analysis on crane components according to the environmental over-threshold range and the load over-threshold range, and matches safety risk events according to the influence of each crane component;
[0120] A risk prediction unit 15, wherein the risk prediction unit 15 configures pre-detection parameters and tracking monitoring parameters according to the safety risk event and the corresponding crane risk element, wherein the crane is subjected to pre-operation risk detection and prediction evaluation according to the pre-detection parameters, the crane is subjected to operation process monitoring according to the tracking monitoring parameters, and risk prediction is performed according to the risk monitoring information during the operation and the pre-operation risk detection information;
[0121] The adaptive control unit 16 performs adaptive control according to a preset adaptive list based on the risk monitoring information and risk prediction results in the operation. The adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power.
[0122] Furthermore, the system is also used to implement the following functions:
[0123] Acquire abnormal crane events, perform correlation impact fitting of environmental impact parameters, load impact parameters and abnormal events according to the abnormal crane events, and determine environmental impact indicators and load impact indicators;
[0124] According to the environmental impact index and the load impact index, detection equipment is set up, and the environmental parameters and load parameters in the crane operation scene are respectively collected by the detection equipment to collect the environmental impact index and the load impact index data, so as to obtain the environmental collection data and the load collection data;
[0125] Preprocessing the collected environmental data and load data, including denoising, abnormal data screening, and missing data supplementation;
[0126] The environmental parameter information and the load item parameter information are obtained according to the pre-processed environmental collection data and the load item collection data.
[0127] Furthermore, the system is also used to implement the following functions:
[0128] The environmental impact indicators include temperature, humidity, interfering electromagnetic waves, air particles, wind speed intensity, and road surface flatness; the load impact indicators include weight, volume, and length.
[0129] Furthermore, the system is also used to implement the following functions:
[0130] According to the abnormal event of the crane, the abnormal event is regarded as the top event;
[0131] Starting from the top event, using the principle of the accident tree analysis algorithm, the top event is decomposed based on the abnormal event of the crane to determine the intermediate event, where the intermediate event is the cause event that causes the top event and is used to characterize the component failure existing in the crane;
[0132] According to the abnormal event of the crane, the intermediate event is decomposed to obtain abnormal factors, where the abnormal factors are parameter indicators that cause the intermediate event, including environmental parameters and load parameters, and the influence relationship between the abnormal factors and the intermediate event is fitted using the sample data of the abnormal event of the crane to obtain an influence function relationship;
[0133] Based on the influence relationship among the top events, intermediate events and abnormal factors, a logic gate relationship is constructed, and the influence function relationship is added to construct an influence analysis module;
[0134] The impact analysis module is used to perform an intermediate event impact analysis on the environmental over-threshold range and the load over-threshold range, and a top event probability analysis is performed based on the intermediate event impact to obtain the abnormal impact relationship of the crane components and the corresponding safety risk events.
[0135] Furthermore, the system is also used to implement the following functions:
[0136] When the pre-detection parameter is a metal structure parameter, ultrasonic detection of the target element is performed by ultrasonic wave to obtain a real-time ultrasonic detection data set, wherein the real-time ultrasonic detection data set includes ultrasonic detection of different target elements;
[0137] Extract the waveform of real-time ultrasonic detection data, perform reflection echo feature analysis on the ultrasonic waveform, and obtain real-time waveform anomaly analysis results;
[0138] When the real-time waveform abnormality analysis result reaches a preset threshold, a reminder message is sent;
[0139] When the real-time waveform abnormality analysis result does not reach a preset threshold, extracting historical ultrasonic detection data based on the target element;
[0140] Classify the target components, align the real-time waveform abnormality analysis results of each component with the historical ultrasonic detection data in time series, fit the real-time-historical waveform relationship, and obtain the abnormal waveform change and abnormal signal reception time;
[0141] According to the real-time waveform abnormality analysis results, abnormal waveform changes and abnormal signal reception time, abnormal defect identification and abnormal trend prediction are performed to obtain the pre-operation risk detection information.
[0142] Furthermore, the system is also used to implement the following functions:
[0143] Acquire abnormal defect identification information and abnormal trend prediction information based on the pre-operation risk detection information;
[0144] Performing an impact analysis using the risk monitoring information during the operation and the abnormal defect identification information to obtain an abnormal defect impact coefficient;
[0145] The abnormal trend prediction information is adjusted according to the abnormal defect impact coefficient to obtain the risk prediction result, which includes: performing time series decomposition according to the abnormal defect identification information and the abnormal trend prediction information, constructing an abnormal analysis time series chain, using the abnormal defect impact coefficient as a time series compensation coefficient, performing abnormal cumulative prediction in the order of the time series chain, and obtaining the prediction information of each time series as the risk prediction result.
[0146] Furthermore, the system is also used to implement the following functions:
[0147] According to the accident consequences and response time of the abnormal event of the crane, configure multi-level safety risk events;
[0148] According to the multi-level security risk events, an adaptive list is set, which includes security risk events, predicted probabilities, detection / monitoring data, and adaptive controls;
[0149] The risk monitoring information and risk prediction results in the operation are matched with the detection / monitoring data, safety risk events and their predicted probabilities respectively to obtain matching adaptive control, wherein the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power supply;
[0150] When the adaptive control is a warning message or a control power supply is cut off, an execution message is generated for executing the sending of the warning message or the cutting off of the control power supply;
[0151] When the adaptive control is to adjust the operating parameters, the control parameter safety adjustment target analysis is performed according to the detection / monitoring data and risk prediction results, the parameter compensation target is obtained, and the adjustment control is performed based on the parameter compensation target.
[0152] It should be noted that the above-mentioned sequence 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-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0153] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
[0154] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations 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 equivalents, the present application intends to include these modifications and variations.
Claims
1. A safety risk monitoring method for crane operation scenarios, characterized in that: The method comprises: Detect environmental parameters and load parameters of crane operation scenes to obtain environmental parameter information and load parameter information; Based on the lifting equipment parameters and work records, obtain the environmental parameter thresholds and load parameter thresholds; Using the environmental parameter threshold and the load parameter threshold to perform over-value screening on the environmental parameter information and the load item parameter information, to obtain an environmental over-threshold range and a load over-threshold range, wherein the over-threshold range is used to characterize the data range where the environmental parameter and the load parameter exceed the standard parameter threshold; Perform an impact analysis of crane components according to the environmental over-threshold range and the load over-threshold range, and match safety risk events according to the impact of each crane component; According to the safety risk events and the corresponding crane risk elements, pre-detection parameters and tracking monitoring parameters are configured, wherein the pre-operation risk detection and prediction evaluation of the crane is performed according to the pre-detection parameters, the operation process of the crane is monitored according to the tracking monitoring parameters, and the risk prediction is performed according to the risk monitoring information during the operation and the pre-operation risk detection information; Based on the risk monitoring information and risk prediction results in the operation, adaptive control is performed according to a preset adaptive list, wherein the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power supply; Wherein, the pre-operation risk detection and prediction assessment of the crane is performed according to the pre-detection parameters, including: When the pre-detection parameter is a metal structure parameter, ultrasonic detection of the target element is performed by ultrasonic wave to obtain a real-time ultrasonic detection data set, wherein the real-time ultrasonic detection data set includes ultrasonic detection of different target elements; Extract the waveform of real-time ultrasonic detection data, perform reflection echo feature analysis on the ultrasonic waveform, and obtain real-time waveform anomaly analysis results; When the real-time waveform abnormality analysis result reaches a preset threshold, a reminder message is sent; When the real-time waveform abnormality analysis result does not reach a preset threshold, extracting historical ultrasonic detection data based on the target element; Classify the target components, align the real-time waveform abnormality analysis results of each component with the historical ultrasonic detection data in time series, fit the real-time-historical waveform relationship, and obtain the abnormal waveform change and abnormal signal reception time; According to the real-time waveform abnormality analysis results, abnormal waveform changes and abnormal signal reception time, abnormal defect identification and abnormal trend prediction are performed to obtain the pre-operation risk detection information; Risk prediction is performed based on the risk monitoring information during the operation and the risk detection information before the operation, including: Acquire abnormal defect identification information and abnormal trend prediction information based on the pre-operation risk detection information; Performing an impact analysis using the risk monitoring information during the operation and the abnormal defect identification information to obtain an abnormal defect impact coefficient; The abnormal trend prediction information is adjusted according to the abnormal defect impact coefficient to obtain the risk prediction result, which includes: performing time series decomposition according to the abnormal defect identification information and the abnormal trend prediction information, constructing an abnormal analysis time series chain, using the abnormal defect impact coefficient as a time series compensation coefficient, performing abnormal cumulative prediction in the order of the time series chain, and obtaining the prediction information of each time series as the risk prediction result.
2. The method according to claim 1, characterized in that Perform environmental parameter and load parameter detection on the crane operation scene to obtain environmental parameter information and load item parameter information, including: Acquire abnormal crane events, perform correlation impact fitting of environmental impact parameters, load impact parameters and abnormal events according to the abnormal crane events, and determine environmental impact indicators and load impact indicators; According to the environmental impact index and the load impact index, detection equipment is set up, and the environmental parameters and load parameters in the crane operation scene are respectively collected by the detection equipment to collect the environmental impact index and the load impact index data, so as to obtain the environmental collection data and the load collection data; Preprocessing the collected environmental data and load data, including denoising, abnormal data screening, and missing data supplementation; The environmental parameter information and the load item parameter information are obtained according to the pre-processed environmental collection data and the load item collection data.
3. The method according to claim 2, characterized in that The environmental impact indicators include temperature, humidity, interfering electromagnetic waves, air particles, wind speed intensity, and road surface flatness; the load impact indicators include weight, volume, and length.
4. The method according to claim 3, characterized in that According to the above-mentioned environmental threshold range and load threshold range, the influence of crane components is analyzed, and safety risk events are matched according to the influence of each crane component, including: According to the abnormal event of the crane, the abnormal event is regarded as the top event; Starting from the top event, using the principle of the accident tree analysis algorithm, the top event is decomposed based on the abnormal event of the crane to determine the intermediate event, where the intermediate event is the cause event that causes the top event and is used to characterize the component failure existing in the crane; According to the abnormal event of the crane, the intermediate event is decomposed to obtain abnormal factors, where the abnormal factors are parameter indicators that cause the intermediate event, including environmental parameters and load parameters, and the influence relationship between the abnormal factors and the intermediate event is fitted using the sample data of the abnormal event of the crane to obtain an influence function relationship; Based on the influence relationship among the top events, intermediate events and abnormal factors, a logic gate relationship is constructed, and the influence function relationship is added to construct an influence analysis module; The impact analysis module is used to perform an intermediate event impact analysis on the environmental over-threshold range and the load over-threshold range, and a top event probability analysis is performed based on the intermediate event impact to obtain the abnormal impact relationship of the crane components and the corresponding safety risk events.
5. The method according to claim 4, characterized in that Based on the risk monitoring information and risk prediction results in the operation, adaptive control is performed according to a preset adaptive list, and the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power supply, including: According to the accident consequences and response time of the abnormal event of the crane, configure multi-level safety risk events; According to the multi-level security risk events, an adaptive list is set, which includes security risk events, predicted probabilities, detection / monitoring data, and adaptive controls; The risk monitoring information and risk prediction results in the operation are matched with the detection / monitoring data, safety risk events and their predicted probabilities respectively to obtain matching adaptive control, wherein the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power supply; When the adaptive control is a warning message or a control power supply is cut off, an execution message is generated for executing the sending of the warning message or the cutting off of the control power supply; When the adaptive control is to adjust the operating parameters, the control parameter safety adjustment target analysis is performed according to the detection / monitoring data and risk prediction results, the parameter compensation target is obtained, and the adjustment control is performed based on the parameter compensation target.
6. A safety risk monitoring system for crane operation scenarios, characterized in that: The system comprises: A parameter collection unit, wherein the parameter collection unit detects environmental parameters and load parameters of the crane operation scene to obtain environmental parameter information and load item parameter information; A parameter threshold value acquisition unit, wherein the parameter threshold value acquisition unit acquires an environmental parameter threshold value and a load parameter threshold value based on the lifting device parameters and the working record; an over-value screening unit, wherein the over-value screening unit uses the environmental parameter threshold and the load parameter threshold to perform over-value screening on the environmental parameter information and the load item parameter information to obtain an over-threshold range of the environment and the load, wherein the over-threshold range is used to characterize a data range in which the environmental parameter and the load parameter exceed the standard parameter threshold; An impact analysis unit, wherein the impact analysis unit performs an impact analysis of crane components according to the environmental over-threshold range and the load over-threshold range, and matches safety risk events according to the impact of each crane component; A risk prediction unit, wherein the risk prediction unit configures pre-detection parameters and tracking monitoring parameters according to the safety risk event and the corresponding crane risk element, wherein the pre-operation risk detection and prediction evaluation of the crane is performed according to the pre-detection parameters, the operation process of the crane is monitored according to the tracking monitoring parameters, and the risk prediction is performed according to the risk monitoring information during the operation and the pre-operation risk detection information; An adaptive control unit, wherein the adaptive control unit performs adaptive control according to a preset adaptive list based on the risk monitoring information and risk prediction results in the operation, wherein the adaptive control includes adjusting operation parameters, sending warning information, and cutting off control power; The risk prediction unit is also used to implement the following steps: When the pre-detection parameter is a metal structure parameter, ultrasonic detection of the target element is performed by ultrasonic wave to obtain a real-time ultrasonic detection data set, wherein the real-time ultrasonic detection data set includes ultrasonic detection of different target elements; Extract the waveform of real-time ultrasonic detection data, perform reflection echo feature analysis on the ultrasonic waveform, and obtain real-time waveform anomaly analysis results; When the real-time waveform abnormality analysis result reaches a preset threshold, a reminder message is sent; When the real-time waveform abnormality analysis result does not reach a preset threshold, extracting historical ultrasonic detection data based on the target element; Classify the target components, align the real-time waveform abnormality analysis results of each component with the historical ultrasonic detection data in time series, fit the real-time-historical waveform relationship, and obtain the abnormal waveform change and abnormal signal reception time; According to the real-time waveform abnormality analysis results, abnormal waveform changes and abnormal signal reception time, abnormal defect identification and abnormal trend prediction are performed to obtain the pre-operation risk detection information; Risk prediction is performed based on the risk monitoring information during the operation and the risk detection information before the operation, including: Acquire abnormal defect identification information and abnormal trend prediction information based on the pre-operation risk detection information; Performing an impact analysis using the risk monitoring information during the operation and the abnormal defect identification information to obtain an abnormal defect impact coefficient; The abnormal trend prediction information is adjusted according to the abnormal defect impact coefficient to obtain the risk prediction result, which includes: performing time series decomposition according to the abnormal defect identification information and the abnormal trend prediction information, constructing an abnormal analysis time series chain, using the abnormal defect impact coefficient as a time series compensation coefficient, performing abnormal cumulative prediction in the order of the time series chain, and obtaining the prediction information of each time series as the risk prediction result.
