Intelligent safety analysis and early warning system for crane

Abstract

The invention relates to the technical field of data analysis, and discloses a crane intelligent safety analysis and early warning system which comprises a behavior pattern capturing module, an operation abnormity analysis module, a load monitoring module, a dynamic early warning adjustment module, a risk assessment module and a real-time early warning transmitting module. According to the invention, by analyzing the operation data and operation behaviors of the crane in real time, the accuracy and response speed of the safety early warning system are effectively enhanced, the strategy of dynamically adjusting the operation limitation and speed allows the system to adapt to the changes of different working environments, and the safety threshold is adjusted in time to cope with the instant operation conditions and environmental factors; furthermore, through comparison with historical accident data, behavior modes similar to historical accidents are accurately recognized, and possible risks are warned in advance, so that safety accidents caused by misoperation or crane faults can be remarkably reduced, the safety of construction site personnel is guaranteed, and meanwhile possible property loss is also avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an intelligent safety analysis and early warning system for cranes. Background Art

[0002] Data analysis involves processing data using algorithms, statistical models, and computer software to extract useful information and insights from the data. The key is to transform large amounts of raw data into useful information to support the decision-making process. The applications of data analysis are very wide, including business intelligence, financial forecasting, health information management, logistics and supply chain optimization, etc. With the development of machine learning and artificial intelligence technology, the methods and tools of data analysis are also evolving, making it possible to process large-scale and complex data sets more accurately and efficiently.

[0003] Among them, the theme of the crane intelligent safety analysis and early warning system is to use data analysis technology to monitor and analyze the operation data of the crane in real time to identify possible safety risks and issue early warnings. The main purpose is to enhance the safety of crane operation and prevent accidents. By integrating data collected by sensors (such as position, load, operating speed, etc.), it is possible to evaluate the current status of the equipment and potential safety threats, and send alerts to operators or maintenance teams in a timely manner, which is crucial to ensuring the safety of construction sites, especially in high-risk heavy industrial environments.

[0004] Although existing technologies can process large amounts of data, they often show limitations in terms of real-time response and environmental adaptability. For example, in traditional analysis models, they usually rely on fixed analysis cycles and preset models, which often cannot meet the needs of real-time monitoring and immediate response in rapidly changing industrial environments. The lack of flexibility leads to major omissions when responding to emergencies, and it is impossible to capture subtle anomalies in crane operations in a timely manner, increasing the risk of accidents. In addition, existing technologies fail to make full use of historical data for risk prediction and early warning, and fail to effectively match operating behaviors with accident patterns, which weakens the pertinence and foresight of preventive measures and affects overall safety performance. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an intelligent safety analysis and early warning system for cranes.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A crane intelligent safety analysis and early warning system comprises: The behavior pattern capture module tracks the operator's operation sequence through the crane operation interface, counts the time point and duration of each movement of the joystick to a new position, continuously updates the operator's behavior data, and outputs the operation behavior feature set; The operation abnormality analysis module receives the operation behavior feature set, analyzes the operator's behavior pattern, compares the operator's current operation data with the crane standard operation data, calculates the difference, identifies and marks it as a potential risk point, and obtains an abnormal behavior analysis result; The load monitoring module monitors the load condition of the crane in real time through sensors, records the vibration frequency and amplitude generated by the load, and continuously tracks and analyzes the recorded data in real time to detect abnormal vibration conditions beyond the normal range, assess the risk of load instability of the crane, and generate a load status analysis report; The dynamic warning adjustment module evaluates the current environmental conditions and crane operation mode in real time according to the load status analysis report, dynamically adjusts the crane operation speed according to the real-time data, matches the differentiated working conditions, synchronously calculates the new load limit, and outputs the adjusted safety threshold; The risk assessment module combines the adjusted safety threshold and the abnormal behavior analysis result to match the current operation data of the crane with the crane accident database, identify similar operation behaviors, synchronously calculate the risk value of the current operation, divide the risk level, and comprehensively output the risk assessment result; The real-time warning signaling module determines the corresponding warning level according to the risk assessment results and the risk level, sends the warning information to the operator's control interface and the ground monitoring center, receives instant warning feedback from all relevant personnel, and executes emergency operations corresponding to the warning level in the safety manual, and outputs the warning execution record.

[0007] As a further solution of the present invention, the operation behavior feature set includes operation sequence data, time point records, duration records, operation force data and operation frequency data; the abnormal behavior analysis results include behavior pattern deviation records and risk point marking results; the load status analysis report includes load vibration frequency, load amplitude, abnormal vibration detection results and load stability assessment results; the adjusted safety threshold includes an operation speed adjustment value and a new load limit parameter; the risk assessment results include an operation risk value, a risk level division result and an accident pattern matching result; the early warning execution record includes an early warning level, an early warning information transmission record, an emergency operation execution status and an early warning feedback reception record.

[0008] As a further solution of the present invention, the behavior pattern capture module includes an operation data collection submodule, a behavior feature extraction submodule, and an operation feature integration submodule; The operation data acquisition submodule obtains the operator's operation sequence based on the crane operation interface, records the time point and duration of the joystick moving to a new position, and counts the change process and time span of each operation in turn to generate the operator's operation behavior data set; The behavior feature extraction submodule extracts the joystick movement time point and duration data based on the operator operation behavior data set, separates the action features and classifies and splits them according to the data type, and establishes an operation behavior feature set; The operation feature integration submodule integrates the data based on the operation behavior feature set and the separated joystick feature data, and merges all the data into a complete operation feature structure by uniformly classifying feature items and supplementing missing information to generate an operation behavior feature set.

[0009] As a further solution of the present invention, the operation abnormality analysis module includes a behavior pattern analysis submodule, a difference calculation submodule, and a risk point marking submodule; The behavior pattern analysis submodule extracts the operator's current behavior characteristics based on the operation behavior feature set, decomposes the behavior feature data, analyzes the regularity and change trend in the action parameters and operation sequence, matches the data pattern matching the operation standard in the behavior characteristics, and generates the current behavior pattern analysis result; The difference calculation submodule compares the operator's current behavior feature data with the crane standard operation data based on the current behavior pattern analysis result, detects and records the data deviation that does not meet the standard by comparing the difference values ​​in the action parameters one by one, and generates a difference data result; The risk point marking submodule identifies the risk deviation points in the operator's behavior pattern based on the differential data results, and generates abnormal behavior analysis results by marking the data items in the deviation values ​​that exceed the allowable range, dividing the risk level according to the deviation intensity.

[0010] As a further solution of the present invention, the load monitoring module in the load monitoring module includes a load data acquisition submodule, a vibration analysis and calculation submodule, and a risk assessment generation submodule; The load data acquisition submodule uses sensors to monitor the load of the crane in real time. It collects the vibration frequency and amplitude data of the sensor, records the vibration change value corresponding to the load point by point, extracts the vibration time series data in sections, and generates load vibration monitoring data in combination with the load parameters. The vibration analysis and calculation submodule calculates the vibration frequency and amplitude data point by point based on the load vibration monitoring data, determines the frequency change trend by grouping the time series data of the vibration parameters and comparing the amplitude difference values, extracts the time period range of the abnormal values, and generates abnormal vibration characteristic data; The risk assessment generation submodule integrates the distribution of all abnormal points based on the abnormal vibration characteristic data, analyzes the impact of the abnormal vibration data on load stability point by point, and generates a load status analysis report in combination with the corresponding time period range.

[0011] As a further solution of the present invention, the dynamic warning adjustment module in the dynamic warning adjustment module includes an environmental condition assessment submodule, an operation dynamic adjustment submodule, and a safety threshold calculation submodule; The environmental condition assessment submodule extracts temperature and humidity, wind speed and ground stability parameters from the environmental data based on the load status analysis report, obtains the operating speed and load range parameters of the crane operation mode item by item, and analyzes the time variation trend of each parameter to generate environmental operation condition data; The operation dynamic adjustment submodule compares the current load range with the environmental restriction conditions based on the environmental operation condition data, reallocates the operation parameters according to the environmental conditions, adjusts the operation speed, operation radius and lifting rhythm of the crane item by item, and generates operation dynamic adjustment data by matching the differentiated conditions with the real-time update adjustment results; The safety threshold calculation submodule dynamically adjusts the operation data based on the operation, extracts the adjusted operating parameters and load pressure values, re-analyzes the maximum load parameter range in the environmental constraints, integrates the load limit value with the dynamic adjustment data, calculates the adjusted safety load limit value, and outputs the adjusted safety threshold.

[0012] As a further solution of the present invention, the adjusted safe load limit value is according to the formula: ; Calculate, where Represents the adjusted safe load limit value, Represents the load pressure value after dynamic adjustment, Represents the adjusted operating parameter value, Represents the benchmark operating parameter value under environmental constraints, Represents the maximum load parameter range limited by the environment.

[0013] As a further solution of the present invention, the risk assessment module includes a data matching analysis submodule, a risk value calculation submodule, and a risk level classification submodule; The data matching analysis submodule extracts dynamic parameters in the current operation data of the crane based on the adjusted safety threshold and the abnormal behavior analysis result, identifies similar operation data and corresponding behavior features by comparing key behavior patterns in the operation data with historical operation behaviors stored in the crane accident database, and generates similar operation behavior data; The risk value calculation submodule extracts accident parameters matching the current operation in the historical operation behavior based on the similar operation behavior data, calculates the risk value corresponding to the current operation behavior, evaluates the potential risk factors in the current operation behavior one by one, and generates operation risk value data; The risk level classification submodule is based on the operational risk value data and classifies the risk value of the current operational data according to the range of risk parameters, and simultaneously associates and matches the risk level with the operational data to comprehensively output the risk assessment result.

[0014] As a further solution of the present invention, the risk value corresponding to the current operation behavior is calculated according to the formula: ; Calculate, where Represents the risk value of the current operation behavior, Represents the specific value of the historical accident parameter, Represents the corresponding parameter value of the current operation behavior, Represents the standard deviation of potential risk factors in historical data, Represents the time parameter of the current operation behavior. Represents the mean of the time parameter in historical data, Represents the parameter value, Represents the number of risk factors.

[0015] As a further solution of the present invention, the real-time warning signaling module includes a warning level determination submodule, a warning information sending submodule, and an emergency operation execution submodule; The warning level determination submodule, based on the risk assessment result, calls the data of the current operation status and the risk level matching rules in the safety manual, determines the warning level corresponding to the risk of the current operation, and matches the emergency operation process and execution steps in the safety manual according to the warning level to generate warning level information; The warning information sending submodule extracts key information from the warning content based on the warning level information, sends the warning information item by item to the operator control panel and the monitoring center interface through wireless communication, receives feedback signals from the ground monitoring center and the operator, records the feedback content and response confirmation status item by item, and generates a warning sending record; The emergency operation execution submodule extracts the emergency operation content confirmed by feedback based on the warning sending record, calls the operation interface of the crane equipment, gradually executes the emergency operation instructions corresponding to the warning level in the safety manual, records the time and feedback status of the operation completion, and generates a warning execution record.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by real-time analysis of the operating data and operating behavior of the crane, the accuracy and response speed of the safety warning system are effectively enhanced. The strategy of dynamically adjusting the operating restrictions and speed allows the system to adapt to changes in different working environments, and timely adjust the safety thresholds to cope with immediate operating conditions and environmental factors. Further, by comparison with historical accident data, behavioral patterns similar to historical accidents can be accurately identified, and possible risks can be warned in advance, which can significantly reduce safety accidents caused by operating errors or crane failures, ensure the safety of construction site personnel, and avoid possible property losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a system flow chart of the present invention; Figure 2 It is a system module diagram of the present invention; Figure 3 It is a flow chart of the behavior pattern capturing module of the present invention; Figure 4 This is a flow chart of the abnormal operation analysis module of the present invention; Figure 5 This is a flow chart of the load monitoring module of the present invention; Figure 6 This is a flow chart of the dynamic early warning adjustment module of the present invention; Figure 7 This is a flow chart of the risk assessment module of the present invention; Figure 8 This is a flow chart of the real-time warning signaling module of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0020] See also Figure 1 , a crane intelligent safety analysis and early warning system includes: The behavior pattern capture module tracks the operator's operation sequence through the crane operation interface, counts the time point and duration of each movement of the joystick to a new position, continuously updates the operator's behavior data, and outputs the operation behavior feature set; The operation abnormality analysis module receives the operation behavior feature set, analyzes the operator's behavior pattern, compares the operator's current operation data with the crane standard operation data, calculates the difference, identifies and marks it as a potential risk point, and obtains the abnormal behavior analysis result; The load monitoring module monitors the load condition of the crane in real time through sensors, records the vibration frequency and amplitude generated by the load, and continuously tracks and analyzes the recorded data in real time to detect abnormal vibration conditions beyond the normal range, assess the risk of load instability of the crane, and generate a load status analysis report; The dynamic warning adjustment module evaluates the current environmental conditions and crane operation mode in real time according to the load status analysis report, dynamically adjusts the crane operation speed according to the real-time data, matches the differentiated working conditions, synchronously calculates the new load limit, and outputs the adjusted safety threshold; The risk assessment module combines the adjusted safety threshold and abnormal behavior analysis results to match the crane's current operation data with the crane accident database, identify similar operation behaviors, synchronously calculate the risk value of the current operation, divide the risk level, and comprehensively output the risk assessment results; The real-time warning signaling module determines the corresponding warning level according to the risk assessment results and the risk level, sends the warning information to the operator's control interface and ground monitoring center, receives immediate warning feedback from all relevant personnel, and executes emergency operations corresponding to the warning level in the safety manual, and outputs the warning execution record.

[0021] The operation behavior feature set includes operation sequence data, time point records, duration records, operation force data and operation frequency data; the abnormal behavior analysis results include behavior pattern deviation records and risk point marking results; the load status analysis report includes load vibration frequency, load amplitude, abnormal vibration detection results and load stability assessment results; the adjusted safety threshold includes the operation speed adjustment value and the new load limit parameter; the risk assessment results include operation risk value, risk level division results and accident pattern matching results; the early warning execution record includes the early warning level, early warning information transmission record, emergency operation execution status and early warning feedback reception record.

[0022] See also Figure 2 and Figure 3 ,The behavior pattern capturing module includes the operation data collection submodule, the ,behavior feature extraction submodule, and the operation feature integration submodule; The operation data acquisition submodule obtains the operator's operation sequence based on the crane operation interface, records the time point and duration of the joystick moving to a new position, and counts the change process and time span of each operation in turn to generate the operator's operation behavior data set; The operator's operation sequence is acquired based on the crane operation interface. During the acquisition process, the movement trajectory of the joystick is recorded through sensors and control modules, including the starting position, target position, movement time point and duration of each movement of the joystick. The noise data is eliminated by using a filtering algorithm, and abnormal values ​​are filtered and replaced by setting upper and lower limits. At the same time, all recorded data are segmented and sorted according to the time axis, and the operator's complete operation behavior data set is generated in the time order of the operations, providing standardized input data for subsequent analysis.

[0023] The behavior feature extraction submodule extracts the joystick movement time point and duration data based on the operator's operation behavior data set, separates the action features, and classifies and splits them according to the data type to establish an operation behavior feature set; Based on the operator's operation behavior dataset, the joystick movement time point and duration data are extracted, all data are segmented according to time series, the key time nodes of joystick movement and the corresponding duration are screened, and the change rules of different force characteristics are analyzed using distribution fitting. The frequency characteristics are combined with the force characteristics to generate a multidimensional feature matrix that conforms to the description of the operation behavior characteristics. At the same time, the data is split according to the joystick feature dimensions to ensure the integrity and separability of all data at specific time points and dimensions, and finally a set of operation behavior characteristics classified by category is formed.

[0024] The operation feature integration submodule integrates the data based on the operation behavior feature set and the separated joystick feature data, and merges all the data into a complete operation feature structure by uniformly classifying feature items and supplementing missing information to generate an operation behavior feature set; Based on the operation behavior feature set, the joystick feature data is integrated and processed through the time series feature analysis method. First, the joystick movement time points are synchronized using the time axis. The interpolation algorithm is used to make up for the missing time series data generated after the alignment. Further, the feature values ​​of different dimensions are mapped to a unified numerical range through normalization processing to facilitate subsequent analysis and feature processing. A complete operation feature set is formed by merging the duration and frequency characteristics of the joystick. Finally, a standardized operation behavior feature set is constructed to analyze the patterns and characteristics of the complete operation behavior.

[0025] See also Figure 2 and Figure 4 ,The operation abnormality analysis module includes a behavior pattern analysis submodule, a difference calculation submodule, and a risk point marking submodule; The behavior pattern analysis submodule extracts the operator's current behavior characteristics based on the operation behavior feature set, decomposes the behavior feature data, analyzes the regularity and change trend in the action parameters and operation sequence, matches the data pattern in the behavior characteristics that matches the operation standard, and generates the current behavior pattern analysis results; Based on the specific data content of the operation behavior feature set, all operation behaviors are first grouped according to the joystick movement parameters, and the joystick-related feature data including the time point of movement, duration and direction of movement are extracted in sequence. Then, the change trend of each feature value is analyzed frame by frame in time sequence. In the specific execution process, each movement of the joystick is taken as the basic unit, its start time and end time are calculated, and the complete process of the movement is recorded. By unifying these data, a basic data set of behavior patterns including joystick movement changes is formed, which provides key behavioral feature basic support for subsequent analysis.

[0026] The difference calculation submodule compares the operator's current behavior feature data with the crane's standard operation data based on the current behavior pattern analysis results. By comparing the difference values ​​in the action parameters one by one, it detects and records the data deviations that do not meet the standards and generates difference data results. On the basis of obtaining the current operator behavior pattern, each of its behavior parameters is compared with the set standard operation parameters one by one. By comparing the movement time point, duration and direction data of the joystick, it is calculated whether there is a difference in each operation parameter that exceeds the preset standard value range; for example, by calculating the difference between the start time and the end time of the joystick one by one, and comparing it with the time range in the standard operation parameters, the deviation value is marked. Finally, all the difference data obtained from the analysis are classified and sorted, including which parameters have deviations and the specific values ​​of each deviation value, to form a comprehensive difference analysis data set, which provides direct data support for marking and evaluating behavioral characteristics that do not meet the standards.

[0027] The risk point marking submodule identifies risk deviation points in the operator's behavior pattern based on the differential data results, and generates abnormal behavior analysis results by marking the data items that exceed the allowable range in the deviation value and dividing the risk level according to the deviation intensity; Based on the differential data results in the operator's behavior, a detailed risk assessment is performed for each deviation data item. First, the deviation points that exceed the allowable range are extracted one by one, and their position in the set risk level is calculated according to the size of the deviation value. For example, for the deviation of the joystick movement parameter, the numerical difference that exceeds the time range is first recorded, and compared with the preset grading standard. Deviations close to the standard range are marked as low-risk points, and deviations that exceed the allowable range by a large amount are marked as high-risk points. After all risk points are integrated, specific deviation values ​​and corresponding data items are listed according to risk level classification, such as the specific difference value and data characteristics of each high-risk point. All risk point data are refined into standardized risk grading results to form the final abnormal behavior analysis results, marking the key risk points and deviation characteristics in the operator's behavior pattern, providing clear goals for subsequent improvements and optimizations.

[0028] See also Figure 2 and Figure 5 ,The load monitoring module includes a load data acquisition submodule, a vibration analysis and calculation submodule, and a risk assessment generation submodule; The load data acquisition submodule uses sensors to monitor the load of the crane in real time. It collects the vibration frequency and amplitude data of the sensor, records the vibration change value corresponding to the load point by point, extracts the vibration time series data in sections, and generates load vibration monitoring data in combination with the load parameters. Sensors are used to monitor the load status of the crane in real time. Specifically, vibration monitoring sensors are installed at key parts of the crane. The sensors record the vibration parameter data corresponding to the load during operation in real time, including the numerical changes in vibration frequency and vibration amplitude. During the collection process, the vibration data is sampled point by point at fixed intervals in chronological order, and the vibration characteristic value of each time point is recorded. At the same time, based on the collected vibration frequency and amplitude data, combined with load parameters such as the load weight and load position of the crane, the data is organized into a complete time series file. The time series data is divided into multiple sub-time periods, and the vibration change values ​​of each time period are extracted and organized in segments. The above method generates detailed load vibration monitoring data, which is used to describe the vibration characteristics during load changes and provide basic data support for subsequent analysis.

[0029] The vibration analysis and calculation submodule calculates the vibration frequency and amplitude data point by point based on the load vibration monitoring data. By grouping the time series data of the vibration parameters and comparing the amplitude difference values, the frequency change trend is determined, the time period range of the abnormal values ​​is extracted, and the abnormal vibration characteristic data is generated. Based on the load vibration monitoring data, the recorded vibration frequency and amplitude changes are analyzed point by point. During the execution process, the vibration time series data is sliced ​​and the data of each time period is classified into independent groups for calculation. The vibration amplitude change difference of each time period is calculated, and the maximum, minimum and average values ​​in the change difference are extracted; then, the vibration frequency in each time period is trend analyzed, and the frequency value of each time point is compared with the frequency change of its adjacent time points point by point to determine whether the vibration frequency shows abnormal fluctuations; for the points whose amplitude change values ​​exceed the standard range, outliers are screened, and their specific time period range and amplitude characteristics are recorded. Finally, the time periods and corresponding vibration parameter data of all outliers are sorted out, and abnormal vibration characteristic data describing the abnormal vibration law is generated to provide a basic basis for subsequent risk analysis.

[0030] The risk assessment generation submodule integrates the distribution of all abnormal points based on the abnormal vibration characteristic data, analyzes the impact of abnormal vibration data on load stability point by point, and generates a load status analysis report based on the corresponding time period range; Based on the abnormal vibration characteristic data, the distribution position of each abnormal point and its corresponding vibration characteristics are integrated in detail, and the impact of abnormal vibration on the load stability of the crane is analyzed point by point. In the specific implementation process, the vibration amplitude and frequency value corresponding to each abnormal point are first counted, and the time period range and corresponding load parameter data of the point are recorded. The distribution ranges of multiple abnormal points are compared and sorted to determine whether the abnormal points have concentrated characteristics or random distribution characteristics; then, the impact of all abnormal vibration points on load stability is graded and analyzed according to the vibration frequency and amplitude characteristics. For example, the degree of damage to the stability of the load center of gravity is evaluated according to the proportion of vibration amplitude exceeding the normal range, and the instability of the load state is determined according to the frequency fluctuation exceeding the standard; finally, combined with the statistical results of all abnormal points, a detailed load state analysis report is generated according to the time period range and load parameters. The report content includes the distribution law of abnormal points, vibration parameter characteristics and a comprehensive evaluation of load stability.

[0031] See also Figure 2 and Figure 6 ,The dynamic warning adjustment module includes an environmental condition assessment submodule, an ,operation dynamic adjustment submodule, and a safety threshold calculation submodule; The environmental condition assessment submodule extracts the temperature, humidity, wind speed and ground stability parameters from the environmental data based on the load status analysis report, obtains the operating speed and load range parameters of the crane operation mode item by item, and analyzes the time variation trend of each parameter to generate environmental operation condition data; Based on the load status analysis report, key data parameters related to the environment are extracted one by one, including environmental data such as temperature, humidity, wind speed and ground stability. The time series values ​​of the above data are obtained through sensors and monitoring equipment, and they are integrated into a complete set of environmental data sets in chronological order. At the same time, parameters such as the operating speed and load range under the crane operation mode are extracted. These parameters are synchronously compared and analyzed with the environmental data to determine the changing trends of each parameter in different time periods. For example, the impact of the increase or decrease of wind speed over time on the operating speed of the crane, the impact of changes in ground stability on load parameters, etc. The correlation and change law between each parameter are obtained through analysis, and finally the environmental operating condition data describing the relationship between the environment and operating conditions are generated to provide a basis for dynamically adjusting the operating parameters.

[0032] The operation dynamic adjustment submodule compares the current load range with the environmental constraints based on the environmental operating condition data, reallocates the operation parameters according to the environmental conditions, adjusts the crane's operating speed, operating radius and lifting rhythm item by item, and generates operation dynamic adjustment data by matching the differentiated conditions with the real-time update adjustment results. Based on the environmental operating condition data, the current load range parameters are compared with the environmental restrictions one by one. The adaptability of the operating conditions is judged by calculating whether the load range parameters exceed the restrictions defined in the environmental data. Then the operating parameters are carefully adjusted. For example, by analyzing the relationship between the wind speed parameters and the crane operating speed, the operating speed is appropriately reduced to match the current wind speed conditions; for the operating radius, the crane's lifting range is adjusted in combination with the ground stability data; in terms of lifting rhythm, the interval time of each lifting is re-planned according to the changes in ambient temperature and humidity to avoid equipment stability problems caused by too fast operation. By adjusting the operating parameters item by item, all adjustment results are updated in real time to ensure that each operation matches the environmental conditions. Finally, complete dynamic adjustment data for operations is generated to provide real-time support for safety and efficiency.

[0033] The safety threshold calculation submodule extracts the adjusted operating parameters and load pressure values ​​based on the dynamic adjustment data of the operation, re-analyzes the maximum load parameter range in the environmental constraints, integrates the load limit value with the dynamic adjustment data, calculates the adjusted safe load limit value, and outputs the adjusted safety threshold; The adjusted safe load limit value is according to the formula: ; Calculate, where Represents the adjusted safe load limit value, which is used to evaluate the maximum load that the system can safely withstand in a dynamic environment. Represents the load pressure value after dynamic adjustment, Represents the adjusted operating parameter value, which is combined with the dynamic adjustment data to optimize the system operating conditions. Represents the benchmark operating parameter value under environmental constraints, which serves as a reference value for comparison and adjustment. The maximum load parameter range representing environmental restrictions is the upper limit of the permissible load extracted from the current environmental conditions.

[0034] parameter :The dynamically adjusted load pressure value is obtained by monitoring the load operation data of the real-time monitoring system. Taking the load pressure data recorded during the operation of a certain device as an example, the load values ​​of the device within one minute are 1000 N, 1050 N, 1100 N, 1070 N, 1150 N and 1120 N respectively. The dynamically adjusted load pressure value is obtained by calculating the average value of these load values. The calculation process is as follows: ; Bring in data: ; parameter :The adjusted operating parameter value is a set of dynamic optimization values ​​of actual operating data obtained through operating status monitoring. For example, during the operation of the system, the monitored operating parameters include key factors such as equipment speed, temperature, and vibration amplitude. These factors are quantified into a single value through the weighted average method: the speed is 3000 revolutions per minute, the temperature is 75 degrees Celsius, and the vibration amplitude is 0.8 mm, which are weighted as 0.5, 0.3, and 0.2 respectively. According to the weighted average formula: Bring in data: parameter :The benchmark operating parameter value is the design standard value of the equipment operation, which is usually obtained directly from the equipment manual or design specification. For example, the design operating parameters of the equipment are 3200 rpm, 70 degrees Celsius, and 0.5 mm vibration amplitude. According to the same weighted average calculation: Bring in data: parameter :The maximum load parameter range limited by the environment is calculated by the allowable load data of the system operating environment. Assume that the maximum allowable load range of the environment where the equipment is operating is 5000 Newtons. The actual measured temperature fluctuation range, humidity range and vibration frequency of the equipment environment have an impact on the maximum allowable load range of 5%, 3% and 2% respectively. The maximum load parameter range calculation formula is: Bring in data: Substitute the above parameter calculation results into the formula: The calculation results show that the safe load limit value is 20.6. This shows that under the current dynamic load pressure, adjusted operating parameters and environmental restrictions, the maximum safe load limit of the equipment operation is 20.6 units, which can be used to evaluate the safety range of the equipment in actual operation and avoid operating failures caused by excessive load.

[0035] See also Figure 2 and Figure 7 ,The risk assessment module includes a data matching analysis submodule, a risk value calculation submodule, and a risk level classification submodule; The data matching analysis submodule extracts dynamic parameters from the crane's current operation data based on the adjusted safety threshold and abnormal behavior analysis results, and identifies similar operation data and corresponding behavior features by comparing key behavior patterns in the operation data with historical operation behaviors stored in the crane accident database, thereby generating similar operation behavior data. Based on the adjusted safety thresholds and abnormal behavior analysis results, dynamic parameters are extracted from the current operation data of the crane, including key indicators such as operating speed, operating radius, load weight and lifting time. These dynamic parameters are compared one by one, and the current operation behavior pattern is matched with the historical operation behavior recorded in the crane accident database. During the matching process, by comparing key behavior parameters, such as whether there are similarities between the operating speed change trend and the accident trend in the historical data, and whether the load weight distribution is related to the historical abnormal data, by comparing parameter values ​​and behavior characteristics point by point, historical data similar to the current operation behavior and its corresponding behavior characteristics are identified, and finally a set of similar operation behavior data is generated to provide a historical reference basis for further risk assessment.

[0036] The risk value calculation submodule extracts accident parameters matching the current operation in historical operation behaviors based on similar operation behavior data, calculates the risk value corresponding to the current operation behavior, evaluates the potential risk factors in the current operation behavior one by one, and generates operation risk value data; The risk value corresponding to the current operation behavior is based on the formula: ; Calculate, where Represents the risk value of the current operation behavior, Represents the specific values ​​of historical accident parameters, which are used as reference data for assessing the risks that may be caused by current operating behaviors. Represents the corresponding parameter value of the current operation behavior, indicating the actual measured data value in the current operation behavior. Represents the standard deviation of the potential risk factor in historical data and is used to measure the volatility of the risk factor. Represents the time parameter of the current operation behavior, indicating the time range in which the current operation behavior occurs. Represents the mean of the time parameters in historical data, which is used to compare with the current time parameters to correct potential risks. Represents the parameter value, Represents the number of risk factors.

[0037] : The specific value of the historical accident parameter represents the accident characteristic parameter corresponding to the current operation behavior extracted from the historical operation data. It is extracted by normalizing the historical operation behavior data. The specific value of the historical accident parameter comes from the recorded industrial equipment operation log, such as the temperature limit value and pressure fluctuation value of the equipment. Assume that the parameter value obtained from the monitoring data is: , , .

[0038] : The corresponding parameter value of the current operation behavior, which indicates the parameter value extracted from the current real-time monitoring device operation behavior. It is obtained through the real-time data acquisition module in the monitoring system. The parameter value monitored in the current operation behavior is: , , .

[0039] : The standard deviation of potential risk factors in historical data indicates the fluctuation range of a risk factor in historical accidents. It is obtained by calculating the standard deviation of the parameters of similar accidents in historical data. The standard deviation values ​​of the three risk factors calculated through historical data are: , , .

[0040] : The time parameter of the current operation behavior, indicating the time range of the current operation. For example, the monitoring system records that the current device operation time is 2:00 p.m., which means the time is quantified as 14 (hours).

[0041] : The mean of the time parameter in the historical data, indicating the time distribution center of the historical operation behavior. The time mean is extracted by analyzing the time when the corresponding operation behavior occurred in all historical data. For example, the mean operation time in the historical data is 12 (hours).

[0042] Substituting the above parameters into the formula step by step for calculation, it can be divided into the following steps: Calculate the sum of the absolute value differences between historical accident parameters and current operating behavior parameters: Calculate the square root of the sum of squared standard deviations of the underlying risk factors in the historical data: Compute the square root of the difference of the time parameters: Substitute all the calculated results into the formula: The final risk value calculation result is 2.78. The results show that the risk level of the current operation behavior is in the upper-middle range compared with the historical accident parameters. The calculation process takes into account the historical accident parameters, current operation behavior parameters, potential risk standard deviation and time parameters to achieve a comprehensive assessment of the risk value. The numerical value can be used as a basis for further analysis of potential risk sources and formulation of countermeasures, providing support for the optimization of operation behavior and risk avoidance.

[0043] The risk level classification submodule is based on the operational risk value data, classifies the risk value of the current operational data according to the range of risk parameters, and simultaneously associates and matches the risk level with the operational data to comprehensively output the risk assessment results; Based on the operational risk value data, the risk value of the current operational data is graded according to the preset risk parameter range. For example, the risk value is divided into three levels: low risk, medium risk and high risk. The risk level of each operational parameter is clearly marked through the division rules of the risk value range. At the same time, the risk level is associated with the corresponding operational data to ensure that each risk value and its corresponding dynamic parameter can be matched one by one. For example, the high-risk mark of the operating speed is bound to the specific time point and operational data to facilitate subsequent evaluation and adjustment. The final comprehensive output includes a complete risk assessment result including the risk level division and the corresponding operational parameters, which is used to guide the safe operation of the crane and optimize the operating behavior.

[0044] See also Figure 2 and Figure 8 ,The real-time warning sending module includes a warning level determination submodule, a warning information sending submodule, and an emergency operation execution submodule; The warning level determination submodule, based on the risk assessment results, calls the data of the current operation status and the risk level matching rules in the safety manual to determine the warning level corresponding to the risk of the current operation, and matches the emergency operation process and execution steps in the safety manual according to the warning level to generate warning level information; Based on the risk assessment results, the current operating status data is compared with the risk level matching rules in the safety manual one by one. By identifying the risk level of each operating parameter, it is determined whether the current operation is within different risk ranges such as low, medium, and high. The corresponding warning level is determined according to the risk assessment results. For example, operating parameters with a lower risk level are matched as low-level warnings, while operations with a higher risk level and parameters exceeding the safety threshold range are matched as high-level warnings. At the same time, the corresponding emergency operation procedures in the safety manual are matched in combination with the warning level, including specific steps such as clarifying emergency stop, reducing operating speed or reducing load. Finally, warning level information including warning level and emergency measures is generated to guide subsequent operation processing.

[0045] The warning information sending submodule extracts key information from the warning content based on the warning level information, sends the warning information item by item to the operator control panel and the monitoring center interface through wireless communication, receives feedback signals from the ground monitoring center and the operator, records the feedback content and response confirmation status item by item, and generates a warning sending record; Based on the warning level information, key information in the warning content is extracted one by one, such as risk level, abnormal range of operating parameters and recommended emergency operation procedures, and sent to the operator control panel and ground monitoring center interface one by one through the wireless communication module. The accuracy and completeness of each warning message are ensured during the information transmission process. At the same time, whether there is any information delay or loss during the transmission process is monitored. The warning information includes recommended emergency treatment measures and operating instructions, and receives feedback signals from operators and monitoring centers in real time. By recording the content of the feedback signal and the status of confirmation whether it has been received, the warning sending records are generated one by one, including the time of warning sending, feedback reception status and operation response confirmation status, to ensure that all warning information has been correctly transmitted and recorded.

[0046] The emergency operation execution submodule extracts the emergency operation content confirmed by feedback based on the warning sending record, calls the operation interface of the crane equipment, gradually executes the emergency operation instructions corresponding to the warning level in the safety manual, records the time and feedback status of the operation completion, and generates a warning execution record; Based on the early warning sending records, the confirmed emergency operation content is extracted from the feedback of the operator and the monitoring center, including the recommended operation steps and execution requirements. The control interface of the crane equipment is called to step by step execute the corresponding emergency operation instructions, such as reducing the operating speed, reducing the hoisting load, shortening the operation radius and other steps. During the execution process, the time point of completion of each operation and the response status of the equipment are recorded in real time to ensure that each instruction is executed in sequence and obtains correct feedback. At the same time, the real-time data collected during the operation execution is organized into an operation record file, such as recording the time when the emergency operation is started, the time when the execution is completed, and the status change of the equipment. Finally, a complete early warning execution record is generated for subsequent analysis and operation log archiving.

[0047] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent safety analysis and early warning system for cranes, characterized in that: The system comprises: The behavior pattern capture module tracks the operator's operation sequence through the crane operation interface, counts the time point and duration of each movement of the joystick to a new position, continuously updates the operator's behavior data, and outputs the operation behavior feature set; The operation abnormality analysis module receives the operation behavior feature set, analyzes the operator's behavior pattern, compares the operator's current operation data with the crane standard operation data, calculates the difference, identifies and marks it as a potential risk point, and obtains an abnormal behavior analysis result; The load monitoring module monitors the load condition of the crane in real time through sensors, records the vibration frequency and amplitude generated by the load, and continuously tracks and analyzes the recorded data in real time to detect abnormal vibration conditions beyond the normal range, assess the risk of load instability of the crane, and generate a load status analysis report; The dynamic warning adjustment module evaluates the current environmental conditions and crane operation mode in real time according to the load status analysis report, dynamically adjusts the crane operation speed according to the real-time data, matches the differentiated working conditions, synchronously calculates the new load limit, and outputs the adjusted safety threshold; The risk assessment module combines the adjusted safety threshold and the abnormal behavior analysis result to match the current operation data of the crane with the crane accident database, identify similar operation behaviors, synchronously calculate the risk value of the current operation, divide the risk level, and comprehensively output the risk assessment result; The real-time warning signaling module determines the corresponding warning level according to the risk assessment results and the risk level, sends the warning information to the operator's control interface and the ground monitoring center, receives instant warning feedback from all relevant personnel, and executes emergency operations corresponding to the warning level in the safety manual, and outputs the warning execution record.

2. The intelligent safety analysis and early warning system for cranes according to claim 1 is characterized in that: The operation behavior feature set includes operation sequence data, time point records, duration records, operation force data and operation frequency data; the abnormal behavior analysis results include behavior pattern deviation records and risk point marking results; the load state analysis report includes load vibration frequency, load amplitude, abnormal vibration detection results and load stability assessment results; the adjusted safety threshold includes operation speed adjustment value and new load limit parameter; the risk assessment results include operation risk value, risk level classification result and accident pattern matching result; The warning execution record includes the warning level, warning information transmission record, emergency operation execution status and warning feedback reception record.

3. The intelligent safety analysis and early warning system for cranes according to claim 1 is characterized in that: The behavior pattern capture module includes an operation data collection submodule, a behavior feature extraction submodule, and an operation feature integration submodule; The operation data acquisition submodule obtains the operator's operation sequence based on the crane operation interface, records the time point and duration of the joystick moving to a new position, and counts the change process and time span of each operation in turn to generate the operator's operation behavior data set; The behavior feature extraction submodule extracts the joystick movement time point and duration data based on the operator operation behavior data set, separates the action features and classifies and splits them according to the data type, and establishes an operation behavior feature set; The operation feature integration submodule integrates the data based on the operation behavior feature set and the separated joystick feature data, and merges all the data into a complete operation feature structure by uniformly classifying feature items and supplementing missing information to generate an operation behavior feature set.

4. The intelligent safety analysis and early warning system for cranes according to claim 1 is characterized in that: The operation abnormality analysis module includes a behavior pattern analysis submodule, a difference calculation submodule, and a risk point marking submodule; The behavior pattern analysis submodule extracts the operator's current behavior characteristics based on the operation behavior feature set, decomposes the behavior feature data, analyzes the regularity and change trend in the action parameters and operation sequence, matches the data pattern matching the operation standard in the behavior characteristics, and generates the current behavior pattern analysis result; The difference calculation submodule compares the operator's current behavior feature data with the crane standard operation data based on the current behavior pattern analysis result, detects and records the data deviation that does not meet the standard by comparing the difference values ​​in the action parameters one by one, and generates a difference data result; The risk point marking submodule identifies the risk deviation points in the operator's behavior pattern based on the differential data results, and generates abnormal behavior analysis results by marking the data items in the deviation values ​​that exceed the allowable range, dividing the risk level according to the deviation intensity.

5. The intelligent safety analysis and early warning system for cranes according to claim 1 is characterized in that: The load monitoring module includes a load data acquisition submodule, a vibration analysis and calculation submodule, and a risk assessment generation submodule; The load data acquisition submodule uses sensors to monitor the load of the crane in real time. It collects the vibration frequency and amplitude data of the sensor, records the vibration change value corresponding to the load point by point, extracts the vibration time series data in sections, and generates load vibration monitoring data in combination with the load parameters. The vibration analysis and calculation submodule calculates the vibration frequency and amplitude data point by point based on the load vibration monitoring data, determines the frequency change trend by grouping the time series data of the vibration parameters and comparing the amplitude difference values, extracts the time period range of the abnormal values, and generates abnormal vibration characteristic data; The risk assessment generation submodule integrates the distribution of all abnormal points based on the abnormal vibration characteristic data, analyzes the impact of the abnormal vibration data on load stability point by point, and generates a load status analysis report in combination with the corresponding time period range.

6. The intelligent safety analysis and early warning system for cranes according to claim 1 is characterized in that: The dynamic warning adjustment module includes an environmental condition assessment submodule, an operation dynamic adjustment submodule, and a safety threshold calculation submodule; The environmental condition assessment submodule extracts temperature and humidity, wind speed and ground stability parameters from the environmental data based on the load status analysis report, obtains the operating speed and load range parameters of the crane operation mode item by item, and analyzes the time variation trend of each parameter to generate environmental operation condition data; The operation dynamic adjustment submodule compares the current load range with the environmental restriction conditions based on the environmental operation condition data, reallocates the operation parameters according to the environmental conditions, adjusts the operation speed, operation radius and lifting rhythm of the crane item by item, and generates operation dynamic adjustment data by matching the differentiated conditions with the real-time update adjustment results; The safety threshold calculation submodule dynamically adjusts the operation data based on the operation, extracts the adjusted operating parameters and load pressure values, re-analyzes the maximum load parameter range in the environmental constraints, integrates the load limit value with the dynamic adjustment data, calculates the adjusted safety load limit value, and outputs the adjusted safety threshold.

7. The intelligent safety analysis and early warning system for cranes according to claim 6 is characterized in that: The adjusted safe load limit value is according to the formula: ； Calculate, where Represents the adjusted safe load limit value, Represents the load pressure value after dynamic adjustment, Represents the adjusted operating parameter value, Represents the benchmark operating parameter value under environmental constraints, Represents the maximum load parameter range limited by the environment.

8. The intelligent safety analysis and early warning system for cranes according to claim 1 is characterized in that: The risk assessment module includes a data matching analysis submodule, a risk value calculation submodule, and a risk level classification submodule; The data matching analysis submodule extracts dynamic parameters in the current operation data of the crane based on the adjusted safety threshold and the abnormal behavior analysis result, identifies similar operation data and corresponding behavior features by comparing key behavior patterns in the operation data with historical operation behaviors stored in the crane accident database, and generates similar operation behavior data; The risk value calculation submodule extracts accident parameters matching the current operation in the historical operation behavior based on the similar operation behavior data, calculates the risk value corresponding to the current operation behavior, evaluates the potential risk factors in the current operation behavior one by one, and generates operation risk value data; The risk level classification submodule is based on the operational risk value data and classifies the risk value of the current operational data according to the range of risk parameters, and simultaneously associates and matches the risk level with the operational data to comprehensively output the risk assessment result.

9. The intelligent safety analysis and early warning system for cranes according to claim 8 is characterized in that: The risk value corresponding to the current operation behavior is calculated according to the formula: ； Calculate, where Represents the risk value of the current operation behavior, Represents the specific value of the historical accident parameter, Represents the corresponding parameter value of the current operation behavior, Represents the standard deviation of potential risk factors in historical data, Represents the time parameter of the current operation behavior. Represents the mean of the time parameter in historical data, Represents the parameter value, Represents the number of risk factors.

10. The intelligent safety analysis and early warning system for cranes according to claim 1 is characterized in that: The real-time warning signaling module includes a warning level determination submodule, a warning information sending submodule, and an emergency operation execution submodule; The warning level determination submodule, based on the risk assessment result, calls the data of the current operation status and the risk level matching rules in the safety manual, determines the warning level corresponding to the risk of the current operation, and matches the emergency operation process and execution steps in the safety manual according to the warning level to generate warning level information; The warning information sending submodule extracts key information from the warning content based on the warning level information, sends the warning information item by item to the operator control panel and the monitoring center interface through wireless communication, receives feedback signals from the ground monitoring center and the operator, records the feedback content and response confirmation status item by item, and generates a warning sending record; The emergency operation execution submodule extracts the emergency operation content confirmed by feedback based on the warning sending record, calls the operation interface of the crane equipment, gradually executes the emergency operation instructions corresponding to the warning level in the safety manual, records the time and feedback status of the operation completion, and generates a warning execution record.

Images